From 2184890cdfd11dabbd259dbb0ae9e87886485465 Mon Sep 17 00:00:00 2001
From: Danny Auble <da@llnl.gov>
Date: Wed, 2 Dec 2009 00:01:45 +0000
Subject: [PATCH] whitespaces removed from man pages
---
doc/man/Makefile.am | 2 +-
doc/man/Makefile.in | 2 +-
doc/man/man1/sacct.1 | 784 +++++------
doc/man/man1/sacctmgr.1 | 158 +--
doc/man/man1/salloc.1 | 204 +--
doc/man/man1/sattach.1 | 22 +-
doc/man/man1/sbatch.1 | 182 +--
doc/man/man1/sbcast.1 | 38 +-
doc/man/man1/scancel.1 | 44 +-
doc/man/man1/scontrol.1 | 372 +++---
doc/man/man1/sinfo.1 | 160 +--
doc/man/man1/slurm.1 | 22 +-
doc/man/man1/smap.1 | 160 +--
doc/man/man1/squeue.1 | 170 +--
doc/man/man1/sreport.1 | 40 +-
doc/man/man1/srun.1 | 396 +++---
doc/man/man1/srun_cr.1 | 18 +-
doc/man/man1/sshare.1 | 2 +-
doc/man/man1/sstat.1 | 52 +-
doc/man/man1/strigger.1 | 80 +-
doc/man/man1/sview.1 | 38 +-
doc/man/man3/slurm_allocate_resources.3 | 330 ++---
doc/man/man3/slurm_checkpoint_error.3 | 50 +-
doc/man/man3/slurm_complete_job.3 | 36 +-
doc/man/man3/slurm_free_ctl_conf.3 | 78 +-
doc/man/man3/slurm_free_job_info_msg.3 | 202 +--
.../slurm_free_job_step_info_response_msg.3 | 110 +-
doc/man/man3/slurm_free_node_info.3 | 130 +-
doc/man/man3/slurm_free_partition_info.3 | 112 +-
doc/man/man3/slurm_get_errno.3 | 70 +-
doc/man/man3/slurm_hostlist_create.3 | 40 +-
doc/man/man3/slurm_job_step_create.3 | 48 +-
doc/man/man3/slurm_kill_job.3 | 78 +-
doc/man/man3/slurm_load_reservations.3 | 116 +-
doc/man/man3/slurm_reconfigure.3 | 388 +++---
doc/man/man3/slurm_resume.3 | 18 +-
doc/man/man3/slurm_slurmd_status.3 | 14 +-
doc/man/man3/slurm_step_ctx_create.3 | 92 +-
doc/man/man3/slurm_step_launch.3 | 56 +-
doc/man/man5/bluegene.conf.5 | 80 +-
doc/man/man5/slurm.conf.5 | 1164 ++++++++---------
doc/man/man5/slurmdbd.conf.5 | 142 +-
doc/man/man5/topology.conf.5 | 16 +-
doc/man/man5/wiki.conf.5 | 70 +-
doc/man/man8/slurmctld.8 | 18 +-
doc/man/man8/slurmd.8 | 6 +-
doc/man/man8/slurmdbd.8 | 2 +-
doc/man/man8/slurmstepd.8 | 8 +-
doc/man/man8/spank.8 | 96 +-
49 files changed, 3258 insertions(+), 3258 deletions(-)
diff --git a/doc/man/Makefile.am b/doc/man/Makefile.am
index 3ee8ff79659..e33fbe2b389 100644
--- a/doc/man/Makefile.am
+++ b/doc/man/Makefile.am
@@ -1,5 +1,5 @@
-EXTRA_DIST = man1 man3 man5 man8
+EXTRA_DIST = man1 man3 man5 man8
man1_MANS = \
man1/sacct.1 \
diff --git a/doc/man/Makefile.in b/doc/man/Makefile.in
index 0184288c2b1..c4f6507a0e9 100644
--- a/doc/man/Makefile.in
+++ b/doc/man/Makefile.in
@@ -292,7 +292,7 @@ target_vendor = @target_vendor@
top_build_prefix = @top_build_prefix@
top_builddir = @top_builddir@
top_srcdir = @top_srcdir@
-EXTRA_DIST = man1 man3 man5 man8
+EXTRA_DIST = man1 man3 man5 man8
man1_MANS = \
man1/sacct.1 \
man1/sacctmgr.1 \
diff --git a/doc/man/man1/sacct.1 b/doc/man/man1/sacct.1
index 149ba08ccaf..f2904adacb0 100644
--- a/doc/man/man1/sacct.1
+++ b/doc/man/man1/sacct.1
@@ -12,33 +12,33 @@ SLURM job accounting log or SLURM database
Accounting information for jobs invoked with SLURM are either logged
in the job accounting log file or saved to the SLURM database.
.PP
-The
+The
.BR "sacct "
-command displays job accounting data stored in the job accounting log
+command displays job accounting data stored in the job accounting log
file or SLURM database in a variety of forms for your analysis.
-The
+The
.BR "sacct "
-command displays information on jobs, job steps, status, and exitcodes by
+command displays information on jobs, job steps, status, and exitcodes by
default.
-You can tailor the output with the use of the
-\f3\-\-fields=\fP
+You can tailor the output with the use of the
+\f3\-\-fields=\fP
option to specify the fields to be shown.
.PP
-For the root user, the
+For the root user, the
.BR "sacct "
-command displays job accounting data for all users, although there are
-options to filter the output to report only the jobs from a specified
+command displays job accounting data for all users, although there are
+options to filter the output to report only the jobs from a specified
user or group.
.PP
-For the non\-root user, the
+For the non\-root user, the
.BR "sacct "
-command limits the display of job accounting data to jobs that were
+command limits the display of job accounting data to jobs that were
launched with their own user identifier (UID) by default.
-Data for other users can be displayed with the
+Data for other users can be displayed with the
\f3\-\-all\fP,
\f3\-\-user\fP,
-or
-\f3\-\-uid\fP
+or
+\f3\-\-uid\fP
options.
.TP "10"
\f3Note: \fP\c
@@ -50,7 +50,7 @@ gather and report incomplete information for these calls;
actually available on your system.
.IP
If \-\-dump is specified, the field selection options (\-\-brief,
-\-\-format, ...) have no effect.
+\-\-format, ...) have no effect.
.IP
Elapsed time fields are presented as 2 fields, integral seconds and integral microseconds
.IP
@@ -65,35 +65,35 @@ parameter in slurm.conf.
.TP "10"
\f3\-a \fP\f3,\fP \f3\-\-allusers\fP
Displays the current user's jobs. Displays all users jobs when run by root.
-.IP
+.IP
.TP
\f3\-A \fP\f2account_list\fP \fP\f3,\fP \f3\-\-accounts\fP\f3=\fP\f2account_list\fP
Displays jobs when a comma separated list of accounts are given as the
argument.
-.IP
+.IP
-.TP
+.TP
\f3\-b \fP\f3,\fP \f3\-\-brief\fP
Displays a brief listing, which includes the following data:
-.RS
+.RS
.TP "3"
\(bu
-\f3jobid\fP
+\f3jobid\fP
.TP "3"
\(bu
-\f3status\fP
+\f3status\fP
.TP "3"
\(bu
-\f3exitcode\fP
-.RE
-.IP
-This option has no effect when the
-\f3\-\-\-dump\fP
+\f3exitcode\fP
+.RE
+.IP
+This option has no effect when the
+\f3\-\-\-dump\fP
option is also specified.
-.TP
+.TP
\f3\-C \fP\f2cluster_list\fP\f3,\fP \f3\-\-cluster\fP\f3=\fP\f2cluster_list\fP
Displays the statistics only for the jobs started on the clusters specified by
the \f2cluster_list\fP operand, which is a comma\-separated list of clusters.
@@ -104,25 +104,25 @@ command on\&.
.TP
\f3\-c \fP\f3,\fP \f3\-\-completion\fP
Use job completion instead of job accounting.
-.IP
+.IP
-.TP
+.TP
\f3\-d \fP\f3,\fP \f3\-\-dump\fP
Dumps the raw data records.
-.IP
+.IP
-The section titled "INTERPRETING THE \-\-dump OPTION OUTPUT" describes the
+The section titled "INTERPRETING THE \-\-dump OPTION OUTPUT" describes the
data output when this option is used.
-.TP
+.TP
\f3\-\-duplicates\fP
If SLURM job ids are reset, but the job accounting log file isn't
reset at the same time (with \-e, for example), some job numbers will
probably appear more than once in the accounting log file to refer to
different jobs; such jobs can be distinguished by the "submit" time
stamp in the data records.
-.IP
+.IP
When data for specific jobs are requested with the \-\-jobs option, we
assume that the user wants to see only the most recent job with that
number. This behavior can be overridden by specifying \-\-duplicates, in
@@ -133,31 +133,31 @@ which case all records that match the selection criteria will be returned.
.IP
Print a list of fields that can be specified with the \f3\-\-format\fP option.
.IP
-.RS
+.RS
.PP
-.nf
+.nf
.ft 3
Fields available:
-AllocCPUS Account AssocID AveCPU
-AvePages AveRSS AveVMSize BlockID
-Cluster CPUTime CPUTimeRAW Elapsed
-Eligible End ExitCode GID
-Group JobID JobName Layout
-MaxPages MaxPagesNode MaxPagesTask MaxRSS
+AllocCPUS Account AssocID AveCPU
+AvePages AveRSS AveVMSize BlockID
+Cluster CPUTime CPUTimeRAW Elapsed
+Eligible End ExitCode GID
+Group JobID JobName Layout
+MaxPages MaxPagesNode MaxPagesTask MaxRSS
MaxRSSNode MaxRSSTask MaxVMSize MaxVMSizeNode
-MaxVMSizeTask MinCPU MinCPUNode MinCPUTask
-NCPUS NNodes NodeList NTasks
-Priority Partition QOS QOSRAW
-ReqCPUS Reserved ResvCPU ResvCPURAW
-Start State Submit Suspended
-SystemCPU Timelimit TotalCPU UID
-User UserCPU WCKey WCKeyID
+MaxVMSizeTask MinCPU MinCPUNode MinCPUTask
+NCPUS NNodes NodeList NTasks
+Priority Partition QOS QOSRAW
+ReqCPUS Reserved ResvCPU ResvCPURAW
+Start State Submit Suspended
+SystemCPU Timelimit TotalCPU UID
+User UserCPU WCKey WCKeyID
.ft 1
-.fi
-.RE
-.IP
+.fi
+.RE
+.IP
The section titled "Job Accounting Fields" describes these fields.
.TP
@@ -169,89 +169,89 @@ option return jobs in this state before this period.
Valid time formats are...
HH:MM[:SS] [AM|PM]
MMDD[YY] or MM/DD[/YY] or MM.DD[.YY]
-MM/DD[/YY]-HH:MM[:SS]
+MM/DD[/YY]-HH:MM[:SS]
YYYY-MM-DD[THH:MM[:SS]]
.IP
-.TP
+.TP
\f3\-f \fP\f2file\fP\f3,\fP \f3\-\-file\fP\f3=\fP\f2file\fP
-Causes the
+Causes the
.BR "sacct "
-command to read job accounting data from the named
-\f2file\fP
+command to read job accounting data from the named
+\f2file\fP
instead of the current SLURM job accounting log file. Only applicable
when running the filetxt plugin.
-.TP
+.TP
\f3\-g \fP\f2gid_list\fP\f3,\fP \f3\-\-gid\fP\f3=\fP\f2gid_list\fP \f3\-\-group\fP\f3=\fP\f2group_list\fP
Displays the statistics only for the jobs started with the GID
or the GROUP specified by the \f2gid_list\fP or the\f2group_list\fP operand, which is a comma\-separated
-list. Space characters are not allowed.
-Default is no restrictions.\&.
+list. Space characters are not allowed.
+Default is no restrictions.\&.
-.TP
+.TP
\f3\-h \fP\f3,\fP \f3\-\-help\fP
Displays a general help message.
-.TP
+.TP
-.TP
+.TP
\f3\-j \fP\f2job(.step)\fP \f3,\fP \f3\-\-jobs\fP\f3=\fP\f2job(.step)\fP
Displays information about the specified job(.step) or list of job(.step)s.
-.IP
-The
-\f2job(.step)\fP
+.IP
+The
+\f2job(.step)\fP
parameter is a comma\-separated list of jobs.
Space characters are not permitted in this list.
-.IP
+.IP
The default is to display information on all jobs.
-.TP
+.TP
\f3\-l\fP\f3,\fP \f3\-\-long\fP
Equivalent to specifying:
.IP
.na
-\'\-\-fields=jobid,jobname,partition,maxvsize,maxvsizenode,maxvsizetask,avevsize,maxrss,maxrssnode,maxrsstask,averss,maxpages,maxpagesnode,maxpagestask,avepages,mincpu,mincpunode,mincputask,avecpu,ntasks,alloccpus,elapsed,state,exitcode\'
+\'\-\-fields=jobid,jobname,partition,maxvsize,maxvsizenode,maxvsizetask,avevsize,maxrss,maxrssnode,maxrsstask,averss,maxpages,maxpagesnode,maxpagestask,avepages,mincpu,mincpunode,mincputask,avecpu,ntasks,alloccpus,elapsed,state,exitcode\'
.ad
-.TP
+.TP
\f3\-L\fP\f3,\fP \f3\-\-allclusters\fP
Display jobs ran on all clusters. By default, only jobs ran on the
cluster from where sacct is called are displayed.
-.TP
+.TP
\f3\-n\fP\f3,\fP \f3\-\-noheader\fP
No heading will be added to the output. The default action is to
display a header.
-.IP
-This option has no effect when used with the
-\f3\-\-dump\fP
+.IP
+This option has no effect when used with the
+\f3\-\-dump\fP
option.
-.TP
+.TP
\f3\-N\fP\f3,\fP \f3\-\-nodelist\fP
Display jobs that ran on any of these nodes, can be one or more using
a ranged string.
.IP
-.TP
+.TP
\f3\-o \fP\f3,\fP \f3\-\-format\fP
Comma seperated list of fields. (use "\-\-helpformat" for a list of
-available fields).
+available fields).
NOTE: When using the format option for listing various fields you can put a
%NUMBER afterwards to specify how many characters should be printed.
i.e. format=name%30 will print 30 characters of field name right
-justified. A \-30 will print 30 characters left justified.
-.IP
+justified. A \-30 will print 30 characters left justified.
+.IP
-.TP
+.TP
\f3\-O \fP\f3,\fP \f3\-\-formatted_dump\fP
Dumps accounting records in an easy\-to\-read format.
-.IP
+.IP
This option is provided for debugging.
.TP
@@ -268,49 +268,49 @@ output will be '|' delimited without a '|' at the end
Comma seperated list of partitions to select jobs and job steps
from. The default is all partitions.
-.TP
+.TP
\f3\-s \fP\f2state_list\fP \f3,\fP \f3\-\-state\fP\f3=\fP\f2state_list\fP
Selects jobs based on their current state or the state they were in
-during the time period given, which can be designated with
+during the time period given, which can be designated with
the following state designators:
-.RS
+.RS
.TP "10"
-\f3r\fP
+\f3r\fP
running
.TP
\f3s\fP
suspended
-.TP
-\f3ca\fP
+.TP
+\f3ca\fP
cancelled
-.TP
-\f3cd\fP
+.TP
+\f3cd\fP
completed
-.TP
-\f3pd\fP
+.TP
+\f3pd\fP
pending
-.TP
-\f3f\fP
+.TP
+\f3f\fP
failed
-.TP
-\f3to\fP
+.TP
+\f3to\fP
timed out
-.TP
-\f3nf\fP
+.TP
+\f3nf\fP
node_fail
-.RE
-.IP
-The
-\f2state_list\fP
+.RE
+.IP
+The
+\f2state_list\fP
operand is a comma\-separated list of these state designators.
-Space characters are not allowed in the
+Space characters are not allowed in the
\f2state_list\fP\c
NOTE: When specifying states and no start time is given the default
starttime is 'now'.
\&.
-.TP
+.TP
\f3\-S \fP\f3,\fP \f3\-\-starttime\fP
Select jobs eligible after the specified time. Default is midnight of
current day. If states are given with the \-s option then return jobs
@@ -319,32 +319,32 @@ in this state at this time, 'now' is also used as the default time.
Valid time formats are...
HH:MM[:SS] [AM|PM]
MMDD[YY] or MM/DD[/YY] or MM.DD[.YY]
-MM/DD[/YY]-HH:MM[:SS]
+MM/DD[/YY]-HH:MM[:SS]
YYYY-MM-DD[THH:MM[:SS]]
-.TP
+.TP
\f3\-T \fP\f3,\fP \f3\-\-truncate\fP
Truncate time. So if a job started before \-\-starttime the start time
would be truncated to \-\-starttime. The same for end time and \-\-endtime.
-.TP
+.TP
\f3\-u \fP\f2uid_list\fP\f3,\fP \f3\-\-uid\fP\f3=\fP\f2uid_list\fP \f3\-\-user\fP\f3=\fP\f2user_list\fP
Use this comma seperated list of uids or user names to select jobs to display. By default, the running
user's uid is used.
-.TP
+.TP
\f3\-\-usage\fP
Displays a help message.
-.TP
+.TP
\f3\-v \fP\f3,\fP \f3\-\-verbose\fP
Primarily for debug use reports the state of certain variables during processing.
-.TP
+.TP
\f3\-V \fP\f3,\fP \f3\-\-version\fP
Print version.
-.TP
+.TP
\f3\-W \fP\f2wckey_list\fP\f3,\fP \f3\-\-wckeys\fP\f3=\fP\f2wckey_list\fP
Displays the statistics only for the jobs started on the wckeys specified by
the \f2wckey_list\fP operand, which is a comma\-separated list of
@@ -352,13 +352,13 @@ wckey names.
Space characters are not allowed in the \f2wckey_list\fP. Default is
all wckeys\&.
-.TP
+.TP
\f3\-X \fP\f3,\fP \f3\-\-allocations\fP
Only show cumulative statistics for each job, not the intermediate steps.
.SS "Job Accounting Fields"
The following describes each job accounting field:
-.RS
+.RS
.TP "10"
\f3alloccpus\fP
Count of allocated processors.
@@ -392,48 +392,48 @@ Average Virtual Memory size of a process.
Block ID, applicable to BlueGene computers only.
.TP
-\f3cluster\fP
+\f3cluster\fP
Cluster name.
.TP
\f3cputime\fP
-Formatted number of cpu seconds a process was allocated.
+Formatted number of cpu seconds a process was allocated.
.TP
\f3cputimeraw\fP
How much cpu time process was allocated in second format, not formatted
like above.
-.TP
-\f3elapsed\fP
+.TP
+\f3elapsed\fP
The jobs elapsed time.
-.IP
+.IP
The format of this fields output is as follows:
-.RS
+.RS
.PD "0"
-.HP
-\f2[DD\-[hh:]]mm:ss\fP
-.PD
-.RE
-.IP
+.HP
+\f2[DD\-[hh:]]mm:ss\fP
+.PD
+.RE
+.IP
as defined by the following:
-.RS
+.RS
.TP "10"
-\f2DD\fP
+\f2DD\fP
days
-.TP
-\f2hh\fP
+.TP
+\f2hh\fP
hours
-.TP
-\f2mm\fP
+.TP
+\f2mm\fP
minutes
-.TP
-\f2ss\fP
+.TP
+\f2ss\fP
seconds
-.RE
+.RE
-.TP
-\f3eligible\fP
+.TP
+\f3eligible\fP
When the job became eligible to run.
.TP
@@ -465,22 +465,22 @@ minutes
seconds
.RE
-.TP
-\f3exitcode\fP
+.TP
+\f3exitcode\fP
The first non\-zero error code returned by any job step.
-.TP
-\f3gid\fP
+.TP
+\f3gid\fP
The group identifier of the user who ran the job.
.TP
\f3group\fP
The group name of the user who ran the job.
-.TP
-\f3jobid\fP
+.TP
+\f3jobid\fP
The number of the job or job step.
-It is in the form:
+It is in the form:
\f2job.jobstep\fP\c
\&.
@@ -488,7 +488,7 @@ It is in the form:
\f3jobname\fP
The name of the job or job step.
-.TP
+.TP
\f3layout\fP
What the layout of a step was when it was running. This can be used
to give you an idea of which node ran which rank in your job.
@@ -541,8 +541,8 @@ The node where the mincpu occured.
\f3mincputask\fP
The task on mincpunode where the mincpu occured.
-.TP
-\f3ncpus\fP
+.TP
+\f3ncpus\fP
Total number of CPUs allocated to the job.
.TP
@@ -553,15 +553,15 @@ List of nodes in job/step.
\f3nnodes\fP
Number of nodes in a job or step.
-.TP
-\f3ntasks\fP
+.TP
+\f3ntasks\fP
Total number of tasks in a job or step.
.TP
\f3priority\fP
Slurm priority.
-.TP
+.TP
\f3partition\fP
Identifies the partition on which the job ran.
@@ -570,15 +570,15 @@ Identifies the partition on which the job ran.
Name of Quality of Service.
.TP
-\f3qosraw\fP
+\f3qosraw\fP
Id of Quality of Service.
-.TP
-\f3reqcpus\fP
+.TP
+\f3reqcpus\fP
Required CPUs.
-.TP
-\f3reserved\fP
+.TP
+\f3reserved\fP
How much wall clock time was used as reserved time for this job. This is
derived from how long a job was waiting from eligible time to when it
actually started.
@@ -587,8 +587,8 @@ actually started.
\f3resvcpu\fP
Formatted time for how long (cpu secs) a job was reserved for.
-.TP
-\f3resvcpuraw\fP
+.TP
+\f3resvcpuraw\fP
Reserved CPUs in second format, not formatted.
.TP
@@ -600,7 +600,7 @@ Initiation time of the job in the same format as \f3end\fP.
Displays the job status, or state.
Output can be RUNNING, SUSPENDED, COMPLETED, CANCELLED, FAILED,
-TIMEOUT, or NODE_FAIL.
+TIMEOUT, or NODE_FAIL.
.TP
\f3submit\fP
@@ -616,8 +616,8 @@ How long the job was suspended for.
The amount of system CPU time. (If job was running on multiple cpus this
is a combination of all the times so this number could be much larger
than the elapsed time.)
-The format of the output is identical to that of the
-\f3elapsed\fP
+The format of the output is identical to that of the
+\f3elapsed\fP
field.
.TP
@@ -655,38 +655,38 @@ Workload Characterization Key. Arbitrary string for grouping orthogonal acc
\f3wckeyid\fP
Reference to the wckey.
-.RE
+.RE
.SH "INTERPRETING THE \-DUMP OPTION OUTPUT"
-The
+The
.BR "sacct "
-commands
-\f3\-\-dump\fP
-option displays data in a horizontal list of fields depending on the
+commands
+\f3\-\-dump\fP
+option displays data in a horizontal list of fields depending on the
record type;
-there are three record types:
+there are three record types:
\f3JOB_START\fP\c
-\&,
+\&,
\f3JOB_STEP\fP\c
-\&, and
+\&, and
\f3JOB_TERMINATED\fP\c
\&.
There is a subsection that describes the output for each record type.
.PP
-When the data output is a job accounting field, as described in the
-section titled "Job Accounting Fields", only the name of the job
+When the data output is a job accounting field, as described in the
+section titled "Job Accounting Fields", only the name of the job
accounting field is listed.
Otherwise, additional information is provided.
.TP "10"
\f3Note: \fP\c
-The output for the
-\f3JOB_STEP\fP
-and
-\f3JOB_TERMINATED\fP
+The output for the
+\f3JOB_STEP\fP
+and
+\f3JOB_TERMINATED\fP
record types present a pair of fields for the following data:
Total CPU time, Total User CPU time, and Total System CPU time.
-The first field of each pair is the time in seconds expressed as an
+The first field of each pair is the time in seconds expressed as an
integer.
-The second field of each pair is the fractional number of seconds
+The second field of each pair is the fractional number of seconds
multiplied by one million.
Thus, a pair of fields output as "\c
\f31 024315\fP\c
@@ -694,386 +694,386 @@ Thus, a pair of fields output as "\c
The least significant digits in the second field are truncated in
formatted displays.
.SS "Output for the JOB_START Record Type"
-The following describes the horizontal fields output by the
+The following describes the horizontal fields output by the
.BR "sacct "
-\f3\-\-dump\fP
-option for the
-\f3JOB_START\fP
+\f3\-\-dump\fP
+option for the
+\f3JOB_START\fP
record type.
-.RS
+.RS
.TP "10"
Field #
Field
-.TP
+.TP
1
-\f3job\fP
-.TP
+\f3job\fP
+.TP
2
-\f3partition\fP
-.TP
+\f3partition\fP
+.TP
3
-\f3submitted\fP
-.TP
+\f3submitted\fP
+.TP
4
The jobs start time;
-this value is the number of non\-leap seconds since the Epoch (00:00:00
+this value is the number of non\-leap seconds since the Epoch (00:00:00
UTC, January 1, 1970)
-.TP
+.TP
5
\f3uid.gid\fP
-.TP
+.TP
6
(Reserved)
-.TP
+.TP
7
\f3JOB_START\fP (literal string)
-.TP
+.TP
8
Job Record Version (1)
-.TP
+.TP
9
The number of fields in the record (16)
-.TP
+.TP
10
-\f3uid\fP
-.TP
+\f3uid\fP
+.TP
11
-\f3gid\fP
-.TP
+\f3gid\fP
+.TP
12
The job name
-.TP
+.TP
13
Batch Flag (0=no batch)
-.TP
+.TP
14
Relative SLURM priority
-.TP
+.TP
15
-\f3ncpus\fP
-.TP
+\f3ncpus\fP
+.TP
16
-\f3nodes\fP
-.RE
+\f3nodes\fP
+.RE
.SS "Output for the JOB_STEP Record Type"
-The following describes the horizontal fields output by the
+The following describes the horizontal fields output by the
.BR "sacct "
-\f3\-\-dump\fP
-option for the
-\f3JOB_STEP\fP
+\f3\-\-dump\fP
+option for the
+\f3JOB_STEP\fP
record type.
-.RS
+.RS
.TP "10"
Field #
Field
-.TP
+.TP
1
-\f3job\fP
-.TP
+\f3job\fP
+.TP
2
-\f3partition\fP
-.TP
+\f3partition\fP
+.TP
3
-\f3submitted\fP
-.TP
+\f3submitted\fP
+.TP
4
The jobs start time;
-this value is the number of non\-leap seconds since the Epoch (00:00:00
+this value is the number of non\-leap seconds since the Epoch (00:00:00
UTC, January 1, 1970)
-.TP
+.TP
5
\f3uid.gid\fP
-.TP
+.TP
6
(Reserved)
-.TP
+.TP
7
\f3JOB_STEP\fP (literal string)
-.TP
+.TP
8
Job Record Version (1)
-.TP
+.TP
9
The number of fields in the record (38)
-.TP
+.TP
10
-\f3jobid\fP
-.TP
+\f3jobid\fP
+.TP
11
-\f3end\fP
-.TP
+\f3end\fP
+.TP
12
Completion Status;
the mnemonics, which may appear in uppercase or lowercase, are as follows:
-.RS
+.RS
.TP "10"
-\f3CA\fP
+\f3CA\fP
Cancelled
.TP "10"
-\f3CD\fP
+\f3CD\fP
Completed successfully
-.TP
-\f3F\fP
+.TP
+\f3F\fP
Failed
-.TP
-\f3NF\fP
+.TP
+\f3NF\fP
Job terminated from node failure
-.TP
-\f3R\fP
+.TP
+\f3R\fP
Running
.TP
\f3S\fP
Suspended
-.TP
-\f3TO\fP
+.TP
+\f3TO\fP
Timed out
-.RE
-.TP
+.RE
+.TP
13
-\f3exitcode\fP
-.TP
+\f3exitcode\fP
+.TP
14
-\f3ntasks\fP
-.TP
+\f3ntasks\fP
+.TP
15
-\f3ncpus\fP
-.TP
+\f3ncpus\fP
+.TP
16
-\f3elapsed\fP
+\f3elapsed\fP
time in seconds expressed as an integer
-.TP
+.TP
17
Integer portion of the Total CPU time in seconds for all processes
-.TP
+.TP
18
Fractional portion of the Total CPU time for all processes expressed in microseconds
-.TP
+.TP
19
Integer portion of the Total User CPU time in seconds for all processes
-.TP
+.TP
20
-Fractional portion of the Total User CPU time for all processes
+Fractional portion of the Total User CPU time for all processes
expressed in microseconds
-.TP
+.TP
21
Integer portion of the Total System CPU time in seconds for all processes
-.TP
+.TP
22
-Fractional portion of the Total System CPU time for all processes
+Fractional portion of the Total System CPU time for all processes
expressed in microseconds
-.TP
+.TP
23
-\f3rss\fP
-.TP
+\f3rss\fP
+.TP
24
-\f3ixrss\fP
-.TP
+\f3ixrss\fP
+.TP
25
-\f3idrss\fP
-.TP
+\f3idrss\fP
+.TP
26
-\f3isrss\fP
-.TP
+\f3isrss\fP
+.TP
27
-\f3minflt\fP
-.TP
+\f3minflt\fP
+.TP
28
-\f3majflt\fP
-.TP
+\f3majflt\fP
+.TP
29
-\f3nswap\fP
-.TP
+\f3nswap\fP
+.TP
30
-\f3inblocks\fP
-.TP
+\f3inblocks\fP
+.TP
31
-\f3outblocks\fP
-.TP
+\f3outblocks\fP
+.TP
32
-\f3msgsnd\fP
-.TP
+\f3msgsnd\fP
+.TP
33
-\f3msgrcv\fP
-.TP
+\f3msgrcv\fP
+.TP
34
-\f3nsignals\fP
-.TP
+\f3nsignals\fP
+.TP
35
-\f3nvcsw\fP
-.TP
+\f3nvcsw\fP
+.TP
36
-\f3nivcsw\fP
-.TP
+\f3nivcsw\fP
+.TP
37
-\f3vsize\fP
-.TP
-.RE
+\f3vsize\fP
+.TP
+.RE
.SS "Output for the JOB_TERMINATED Record Type"
-The following describes the horizontal fields output by the
+The following describes the horizontal fields output by the
.BR "sacct "
-\f3\-\-dump\fP
-option for the
+\f3\-\-dump\fP
+option for the
\f3JOB_TERMINATED\fP (literal string)
record type.
-.RS
+.RS
.TP "10"
Field #
Field
-.TP
+.TP
1
-\f3job\fP
-.TP
+\f3job\fP
+.TP
2
-\f3partition\fP
-.TP
+\f3partition\fP
+.TP
3
-\f3submitted\fP
-.TP
+\f3submitted\fP
+.TP
4
The jobs start time;
-this value is the number of non\-leap seconds since the Epoch (00:00:00
+this value is the number of non\-leap seconds since the Epoch (00:00:00
UTC, January 1, 1970)
-.TP
+.TP
5
\f3uid.gid\fP
-.TP
+.TP
6
(Reserved)
-.TP
+.TP
7
\f3JOB_TERMINATED\fP (literal string)
-.TP
+.TP
8
Job Record Version (1)
-.TP
+.TP
9
The number of fields in the record (38)
-.IP
-Although thirty\-eight fields are displayed by the
+.IP
+Although thirty\-eight fields are displayed by the
.BR "sacct "
-command for the
-\f3JOB_TERMINATED\fP
+command for the
+\f3JOB_TERMINATED\fP
record, only fields 1 through 12 are recorded in the actual data file;
-the
+the
.BR "sacct "
command aggregates the remainder.
-.TP
+.TP
10
The total elapsed time in seconds for the job.
-.TP
+.TP
11
-\f3end\fP
-.TP
+\f3end\fP
+.TP
12
Completion Status;
the mnemonics, which may appear in uppercase or lowercase, are as follows:
-.RS
+.RS
.TP "10"
-\f3CA\fP
+\f3CA\fP
Cancelled
-.TP
-\f3CD\fP
+.TP
+\f3CD\fP
Completed successfully
-.TP
-\f3F\fP
+.TP
+\f3F\fP
Failed
-.TP
-\f3NF\fP
+.TP
+\f3NF\fP
Job terminated from node failure
-.TP
-\f3R\fP
+.TP
+\f3R\fP
Running
-.TP
-\f3TO\fP
+.TP
+\f3TO\fP
Timed out
-.RE
-.TP
+.RE
+.TP
13
-\f3exitcode\fP
-.TP
+\f3exitcode\fP
+.TP
14
-\f3ntasks\fP
-.TP
+\f3ntasks\fP
+.TP
15
-\f3ncpus\fP
-.TP
+\f3ncpus\fP
+.TP
16
-\f3elapsed\fP
+\f3elapsed\fP
time in seconds expressed as an integer
-.TP
+.TP
17
Integer portion of the Total CPU time in seconds for all processes
-.TP
+.TP
18
Fractional portion of the Total CPU time for all processes expressed in microseconds
-.TP
+.TP
19
Integer portion of the Total User CPU time in seconds for all processes
-.TP
+.TP
20
-Fractional portion of the Total User CPU time for all processes
+Fractional portion of the Total User CPU time for all processes
expressed in microseconds
-.TP
+.TP
21
Integer portion of the Total System CPU time in seconds for all processes
-.TP
+.TP
22
-Fractional portion of the Total System CPU time for all processes
+Fractional portion of the Total System CPU time for all processes
expressed in microseconds
-.TP
+.TP
23
-\f3rss\fP
-.TP
+\f3rss\fP
+.TP
24
-\f3ixrss\fP
-.TP
+\f3ixrss\fP
+.TP
25
-\f3idrss\fP
-.TP
+\f3idrss\fP
+.TP
26
-\f3isrss\fP
-.TP
+\f3isrss\fP
+.TP
27
-\f3minflt\fP
-.TP
+\f3minflt\fP
+.TP
28
-\f3majflt\fP
-.TP
+\f3majflt\fP
+.TP
29
-\f3nswap\fP
-.TP
+\f3nswap\fP
+.TP
30
-\f3inblocks\fP
-.TP
+\f3inblocks\fP
+.TP
31
-\f3outblocks\fP
-.TP
+\f3outblocks\fP
+.TP
32
-\f3msgsnd\fP
-.TP
+\f3msgsnd\fP
+.TP
33
-\f3msgrcv\fP
-.TP
+\f3msgrcv\fP
+.TP
34
-\f3nsignals\fP
-.TP
+\f3nsignals\fP
+.TP
35
-\f3nvcsw\fP
-.TP
+\f3nvcsw\fP
+.TP
36
-\f3nivcsw\fP
-.TP
+\f3nivcsw\fP
+.TP
37
-\f3vsize\fP
+\f3vsize\fP
.RE
.SH "EXAMPLES"
-This example illustrates the default invocation of the
+This example illustrates the default invocation of the
.BR "sacct "
command:
-.RS
+.RS
.PP
-.nf
+.nf
.ft 3
# sacct
Jobid Jobname Partition Account AllocCPUS State ExitCode
@@ -1084,15 +1084,15 @@ Jobid Jobname Partition Account AllocCPUS State ExitCode
4.0 srun acct1 1 COMPLETED 0
.ft 1
-.fi
-.RE
+.fi
+.RE
.PP
-This example shows the same job accounting information with the
-\f3brief\fP
+This example shows the same job accounting information with the
+\f3brief\fP
option.
-.RS
+.RS
.PP
-.nf
+.nf
.ft 3
# sacct \-\-brief
Jobid Status Exitcode
@@ -1102,12 +1102,12 @@ Jobid Status Exitcode
4 RUNNING 0
4.0 COMPLETED 0
.ft 1
-.fi
-.RE
+.fi
+.RE
.PP
-.RS
+.RS
.PP
-.nf
+.nf
.ft 3
# sacct \-\-allocations
Jobid Jobname Partition Account AllocCPUS State Exitcode
@@ -1122,16 +1122,16 @@ Jobid Jobname Partition Account AllocCPUS State Exitcode
10 endscript andy acct1 186 COMPLETED 0
.ft 1
-.fi
-.RE
+.fi
+.RE
.PP
-This example demonstrates the ability to customize the output of the
+This example demonstrates the ability to customize the output of the
.BR "sacct "
command.
The fields are displayed in the order designated on the command line.
-.RS
+.RS
.PP
-.nf
+.nf
.ft 3
# sacct \-\-fields=jobid,ncpus,ntasks,nsignals,status
Jobid Elapsed Ncpus Ntasks Status
@@ -1144,8 +1144,8 @@ Jobid Elapsed Ncpus Ntasks Status
5.0 00:01:31 2 1 COMPLETED
.ft 1
-.fi
-.RE
+.fi
+.RE
.SH "COPYING"
Copyright (C) 2005\-2007 Copyright Hewlett\-Packard Development Company L.P.
@@ -1167,8 +1167,8 @@ FOR A PARTICULAR PURPOSE. See the GNU General Public License for more
details.
.SH "FILES"
.TP "10"
-\f3/etc/slurm.conf\fP
-Entries to this file enable job accounting and
+\f3/etc/slurm.conf\fP
+Entries to this file enable job accounting and
designate the job accounting log file that collects system job accounting.
.TP
\f3/var/log/slurm_accounting.log\fP
diff --git a/doc/man/man1/sacctmgr.1 b/doc/man/man1/sacctmgr.1
index fdf4044402a..158e514e39c 100644
--- a/doc/man/man1/sacctmgr.1
+++ b/doc/man/man1/sacctmgr.1
@@ -8,20 +8,20 @@ sacctmgr \- Used to view and modify Slurm account information.
.SH "DESCRIPTION"
\fBsacctmgr\fR is used to view or modify Slurm account information.
-The account information is maintained within a database with the interface
+The account information is maintained within a database with the interface
being provided by \fBslurmdbd\fR (Slurm Database daemon).
-This database can serve as a central storehouse of user and
+This database can serve as a central storehouse of user and
computer information for multiple computers at a single site.
Slurm account information is recorded based upon four parameters
-that form what is referred to as an \fIassociation\fR.
-These parameters are \fIuser\fR, \fIcluster\fR, \fIpartition\fR, and
+that form what is referred to as an \fIassociation\fR.
+These parameters are \fIuser\fR, \fIcluster\fR, \fIpartition\fR, and
\fIaccount\fR. \fIuser\fR is the login name.
-\fIcluster\fR is the name of a Slurm managed cluster as specified by
-the \fIClusterName\fR parameter in the \fIslurm.conf\fR configuration file.
+\fIcluster\fR is the name of a Slurm managed cluster as specified by
+the \fIClusterName\fR parameter in the \fIslurm.conf\fR configuration file.
\fIpartition\fR is the name of a Slurm partition on that cluster.
\fIaccount\fR is the bank account for a job.
-The intended mode of operation is to initiate the \fBsacctmgr\fR command,
-add, delete, modify, and/or list \fIassociation\fR records then
+The intended mode of operation is to initiate the \fBsacctmgr\fR command,
+add, delete, modify, and/or list \fIassociation\fR records then
commit the changes and exit.
.SH "OPTIONS"
@@ -68,7 +68,7 @@ This is equivalent to the \fBassociations\fR command.
.TP
\fB\-v\fR, \fB\-\-verbose\fR
-Enable detailed logging.
+Enable detailed logging.
This is equivalent to the \fBverbose\fR command.
.TP
@@ -146,7 +146,7 @@ Identical to the \fBlist\fR command.
.TP
\fBverbose\fP
-Enable detailed logging.
+Enable detailed logging.
This includes time\-stamps on data structures, record counts, etc.
This is an independent command with no options meant for use in interactive mode.
@@ -162,11 +162,11 @@ Repeat the last command.
.TP
\fIaccount\fP
-A bank account, typically specified at job submit time using the
+A bank account, typically specified at job submit time using the
\fI\-\-account=\fR option.
These may be arranged in a hierarchical fashion, for example
accounts \fIchemistry\fR and \fIphysics\fR may be children of
-the account \fIscience\fR.
+the account \fIscience\fR.
The hierarchy may have an arbitrary depth.
.TP
@@ -177,12 +177,12 @@ The entity used to group information consisting of four parameters:
.TP
\fIcluster\fP
The \fIClusterName\fR parameter in the \fIslurm.conf\fR configuration
-file, used to differentiate accounts from on different machines.
+file, used to differentiate accounts from on different machines.
.TP
\fIconfiguration\fP
Used only with the \fIlist\fR or \fIshow\fR command to report current
-system configuration.
+system configuration.
.TP
\fIcoordinator\fR
@@ -190,7 +190,7 @@ A special privileged user usually an account manager or such that can
add users or sub accounts to the account they are coordinator over.
This should be a trusted person since they can change limits on
account and user associations inside their realm.
-
+
.TP
\fIqos\fR
Quality of Service.
@@ -215,14 +215,14 @@ Number used in conjunction with other accounts to determine job priority.
To clear a previously set value use the modify command with a new value of \-1.
.TP
-\fIGrpCPUMins\fP=<max cpu minutes>
-Maximum number of CPU minutes running jobs are able to be allocated in
+\fIGrpCPUMins\fP=<max cpu minutes>
+Maximum number of CPU minutes running jobs are able to be allocated in
aggregate for this association and all association which are children
of this association.
To clear a previously set value use the modify command with a new
value of \-1. (NOTE: This limit is not enforced if set on the root
association of a cluster. So even though it may appear in sacctmgr
-output it will not be enforced.
+output it will not be enforced.
NOTE: This limit only applys when using the Priority Multifactor
plugin. The time is decayed using the value of PriorityDecayHalfLife
or PriorityUsageResetPeriod as set in the slurm.conf. Currently when
@@ -232,7 +232,7 @@ this will change in future versions of SLURM.)
.TP
\fIGrpCPUs\fP=<max cpus>
-Maximum number of CPUs running jobs are able to be allocated in aggregate for
+Maximum number of CPUs running jobs are able to be allocated in aggregate for
this association and all association which are children of this association.
To clear a previously set value use the modify command with a new
value of \-1. (NOTE: This limit is not currently enforced in SLURM.
@@ -241,31 +241,31 @@ before it is enforced.)
.TP
\fIGrpJobs\fP=<max jobs>
-Maximum number of running jobs in aggregate for
+Maximum number of running jobs in aggregate for
this association and all association which are children of this association.
To clear a previously set value use the modify command with a new value of \-1.
.TP
\fIGrpNodes\fP=<max nodes>
-Maximum number of nodes running jobs are able to be allocated in aggregate for
+Maximum number of nodes running jobs are able to be allocated in aggregate for
this association and all association which are children of this association.
To clear a previously set value use the modify command with a new value of \-1.
.TP
\fIGrpSubmitJobs\fP=<max jobs>
-Maximum number of jobs which can be in a pending or running state at any time
-in aggregate for this association and all association which are children of
+Maximum number of jobs which can be in a pending or running state at any time
+in aggregate for this association and all association which are children of
this association.
To clear a previously set value use the modify command with a new value of \-1.
.TP
\fIGrpWall\fP=<max wall>
-Maximum wall clock time running jobs are able to be allocated in aggregate for
+Maximum wall clock time running jobs are able to be allocated in aggregate for
this association and all association which are children of this association.
To clear a previously set value use the modify command with a new value of \-1.
(NOTE: This limit is not enforced if set on the root
association of a cluster. So even though it may appear in sacctmgr
-output it will not be enforced.
+output it will not be enforced.
NOTE: This limit only applys when using the Priority Multifactor
plugin. The time is decayed using the value of PriorityDecayHalfLife
or PriorityUsageResetPeriod as set in the slurm.conf. Currently when
@@ -274,17 +274,17 @@ inside the limit. No jobs will be killed if this limit is reached,
this will change in future versions of SLURM.)
.TP
-\fIMaxCPUMins\fP=<max cpu minutes>
+\fIMaxCPUMins\fP=<max cpu minutes>
Maximum number of CPU minutes each job is able to use in this account.
-This is overridden if set directly on a user.
+This is overridden if set directly on a user.
Default is the cluster's limit.
To clear a previously set value use the modify command with a new
-value of \-1.
+value of \-1.
.TP
\fIMaxCPUs\fP=<max cpus>
Maximum number of CPUs each job is able to use in this account.
-This is overridden if set directly on a user.
+This is overridden if set directly on a user.
Default is the cluster's limit.
To clear a previously set value use the modify command with a new
value of \-1. (NOTE: This limit is not currently enforced in SLURM.
@@ -294,14 +294,14 @@ before it is enforced.)
.TP
\fIMaxJobs\fP=<max jobs>
Maximum number of jobs each user is allowed to run at one time in this account.
-This is overridden if set directly on a user.
+This is overridden if set directly on a user.
Default is the cluster's limit.
To clear a previously set value use the modify command with a new value of \-1.
.TP
\fIMaxNodes\fP=<max nodes>
Maximum number of nodes each job is able to use in this account.
-This is overridden if set directly on a user.
+This is overridden if set directly on a user.
Default is the cluster's limit.
To clear a previously set value use the modify command with a new value of \-1.
This is a c\-node limit on BlueGene systems.
@@ -316,9 +316,9 @@ To clear a previously set value use the modify command with a new value of \-1.
.TP
\fIMaxWall\fP=<max wall>
Maximum wall clock time each job is able to use in this account.
-This is overridden if set directly on a user.
+This is overridden if set directly on a user.
Default is the cluster's limit.
-<max wall> format is <min> or <min>:<sec> or <hr>:<min>:<sec> or
+<max wall> format is <min> or <min>:<sec> or <hr>:<min>:<sec> or
<days>\-<hr>:<min>:<sec> or <days>\-<hr>.
The value is recorded in minutes with rounding as needed.
To clear a previously set value use the modify command with a new value of \-1.
@@ -326,7 +326,7 @@ To clear a previously set value use the modify command with a new value of \-1.
.TP
\fIQosLevel\fP<operator><comma separated list of qos names>
Specify the default Quality of Service's that jobs are able to run at
-for this account. To get a list of valid QOS's use 'sacctmgr list qos'.
+for this account. To get a list of valid QOS's use 'sacctmgr list qos'.
This value will override it's parents value and push down to it's
children as the new default. Setting a QosLevel to '' (two single
quotes with nothing between them) restores it's default setting. You
@@ -442,7 +442,7 @@ Display information with previously deleted data.
Display information with subaccounts. Only really valuable when used
with the account= option. This will display all the subaccount
associations along with the accounts listed in the option.
-
+
.TP
\fIWOLimits\fP
Display information without limit information. This is for a smaller
@@ -452,7 +452,7 @@ default format of Cluster,Account,User,Partition
\fIWOPInfo\fP
Display information without parent information. (i.e. parent id, and
parent account name.) This option also invokes WOPLIMITS.
-
+
.TP
\fIWOPLimits\fP
Display information without hierarchical parent limits. (i.e. will
@@ -478,34 +478,34 @@ Number used in conjunction with other accounts to determine job priority.
.TP
\fIGrpCPUMins\fP
-Maximum number of CPU minutes running jobs are able to be allocated in
+Maximum number of CPU minutes running jobs are able to be allocated in
aggregate for this association and all association which are children
of this association.
.TP
\fIGrpCPUs\fP
-Maximum number of CPUs running jobs are able to be allocated in aggregate for
+Maximum number of CPUs running jobs are able to be allocated in aggregate for
this association and all association which are children of this association.
.TP
\fIGrpJobs\fP
-Maximum number of running jobs in aggregate for
+Maximum number of running jobs in aggregate for
this association and all association which are children of this association.
.TP
\fIGrpNodes\fP
-Maximum number of nodes running jobs are able to be allocated in aggregate for
+Maximum number of nodes running jobs are able to be allocated in aggregate for
this association and all association which are children of this association.
.TP
\fIGrpSubmitJobs\fP
-Maximum number of jobs which can be in a pending or running state at any time
-in aggregate for this association and all association which are children of
+Maximum number of jobs which can be in a pending or running state at any time
+in aggregate for this association and all association which are children of
this association.
.TP
\fIGrpWall\fP
-Maximum wall clock time running jobs are able to be allocated in aggregate for
+Maximum wall clock time running jobs are able to be allocated in aggregate for
this association and all association which are children of this association.
.TP
@@ -520,7 +520,7 @@ associations with a LFT inside this LFT and before the RGT are
childern of this association.
.TP
-\fIMaxCPUMins\fP
+\fIMaxCPUMins\fP
Maximum number of CPU minutes each job is able to use.
.TP
@@ -581,8 +581,8 @@ The name of a user in the association.
.TP
\fIName\fP=<name>
The name of a cluster.
-This should be equal to the \fIClusterName\fR parameter in the \fIslurm.conf\fR
-configuration file for some Slurm\-managed cluster.
+This should be equal to the \fIClusterName\fR parameter in the \fIslurm.conf\fR
+configuration file for some Slurm\-managed cluster.
.TP
\fIWOLimits\fP
@@ -653,12 +653,12 @@ account or list user.
.TP
\fIGrpCPUMins\fP
-Maximum number of CPU minutes running jobs are able to be allocated in
+Maximum number of CPU minutes running jobs are able to be allocated in
aggregate for this QOS.
.TP
\fIGrpCPUs\fP
-Maximum number of CPUs running jobs are able to be allocated in aggregate for
+Maximum number of CPUs running jobs are able to be allocated in aggregate for
this QOS.
.TP
@@ -667,17 +667,17 @@ Maximum number of running jobs in aggregate for this QOS.
.TP
\fIGrpNodes\fP
-Maximum number of nodes running jobs are able to be allocated in aggregate for
+Maximum number of nodes running jobs are able to be allocated in aggregate for
this QOS.
.TP
\fIGrpSubmitJobs\fP
-Maximum number of jobs which can be in a pending or running state at any time
+Maximum number of jobs which can be in a pending or running state at any time
in aggregate for this QOS.
.TP
\fIGrpWall\fP
-Maximum wall clock time running jobs are able to be allocated in aggregate for
+Maximum wall clock time running jobs are able to be allocated in aggregate for
this QOS.
.TP
@@ -685,7 +685,7 @@ this QOS.
The id of the QOS.
.TP
-\fIMaxCPUMins\fP
+\fIMaxCPUMins\fP
Maximum number of CPU minutes each job is able to use.
.TP
@@ -734,10 +734,10 @@ An arbitrary string describing a QOS.
.TP
\fIGrpCPUMins\fP
-Maximum number of CPU minutes running jobs are able to be allocated in
+Maximum number of CPU minutes running jobs are able to be allocated in
aggregate for this QOS.
To clear a previously set value use the modify command with a new
-value of \-1.
+value of \-1.
NOTE: This limit only applys when using the Priority Multifactor
plugin. The time is decayed using the value of PriorityDecayHalfLife
or PriorityUsageResetPeriod as set in the slurm.conf. Currently when
@@ -747,7 +747,7 @@ this will change in future versions of SLURM.)
.TP
\fIGrpCPUs\fP
-Maximum number of CPUs running jobs are able to be allocated in aggregate for
+Maximum number of CPUs running jobs are able to be allocated in aggregate for
this QOS.
To clear a previously set value use the modify command with a new
value of \-1. (NOTE: This limit is not currently enforced in SLURM.
@@ -761,19 +761,19 @@ To clear a previously set value use the modify command with a new value of \-1.
.TP
\fIGrpNodes\fP
-Maximum number of nodes running jobs are able to be allocated in aggregate for
+Maximum number of nodes running jobs are able to be allocated in aggregate for
this QOS.
To clear a previously set value use the modify command with a new value of \-1.
.TP
\fIGrpSubmitJobs\fP
-Maximum number of jobs which can be in a pending or running state at any time
+Maximum number of jobs which can be in a pending or running state at any time
in aggregate for this QOS.
To clear a previously set value use the modify command with a new value of \-1.
.TP
\fIGrpWall\fP
-Maximum wall clock time running jobs are able to be allocated in aggregate for
+Maximum wall clock time running jobs are able to be allocated in aggregate for
this QOS.
To clear a previously set value use the modify command with a new value of \-1.
NOTE: This limit only applys when using the Priority Multifactor
@@ -784,10 +784,10 @@ inside the limit. No jobs will be killed if this limit is reached,
this will change in future versions of SLURM.)
.TP
-\fIMaxCPUMins\fP
+\fIMaxCPUMins\fP
Maximum number of CPU minutes each job is able to use.
To clear a previously set value use the modify command with a new
-value of \-1.
+value of \-1.
.TP
\fIMaxCPUs\fP
@@ -815,7 +815,7 @@ To clear a previously set value use the modify command with a new value of \-1.
.TP
\fIMaxWall\fP
Maximum wall clock time each job is able to use.
-<max wall> format is <min> or <min>:<sec> or <hr>:<min>:<sec> or
+<max wall> format is <min> or <min>:<sec> or <hr>:<min>:<sec> or
<days>\-<hr>:<min>:<sec> or <days>\-<hr>.
The value is recorded in minutes with rounding as needed.
To clear a previously set value use the modify command with a new value of \-1.
@@ -899,7 +899,7 @@ Get information about which associations were affected by the transactions.
.SH ""
NOTE: If using the WithAssoc option you can also view the information
about the various associations the transaction effected. The
-Association format fields are described
+Association format fields are described
in the \fILIST/SHOW ASSOCIATION FORMAT OPTIONS\fP section.
.RE
@@ -919,7 +919,7 @@ Specific cluster to add user to the account on. Default is all in system.
.TP
\fIDefaultAccount\fP=<account>
-Identify the default bank account name to be used for a job if none is
+Identify the default bank account name to be used for a job if none is
specified at submission time.
.TP
@@ -951,7 +951,7 @@ ASSOCIATION BASED ENTITIES\fP section.
.TP
\fIAdminLevel\fP
-Admin level of user.
+Admin level of user.
.TP
\fIDefaultAccount\fP
@@ -977,7 +977,7 @@ in the \fILIST/SHOW ASSOCIATION FORMAT OPTIONS\fP section.
.TP
\fIWCKey\fP
-Workload Characterization Key.
+Workload Characterization Key.
.TP
\fICluster\fP
@@ -999,7 +999,7 @@ When using the format option for listing various fields you can put a
%NUMBER afterwards to specify how many characters should be printed.
i.e. format=name%30 will print 30 characters of field name right
-justified. A \-30 will print 30 characters left justified.
+justified. A \-30 will print 30 characters left justified.
.SH "FLAT FILE DUMP AND LOAD"
sacctmgr has the capability to load and dump SLURM association data to and
@@ -1071,12 +1071,12 @@ are children of this association.
\fIGrpSubmitJobs=\fP
Maximum number of jobs which can be in a pending or
running state at any time in aggregate for this association and all
-association which are children of this association.
+association which are children of this association.
.TP
\fIGrpWall=\fP
Maximum wall clock time running jobs are able to be
allocated in aggregate for this association and all association which
-are children of this association.
+are children of this association.
.TP
\fIFairShare=\fP
Number used in conjunction with other associations to determine job priority.
@@ -1111,7 +1111,7 @@ Followed by Accounts you want in this fashion...
.TP
Any of the options after a ':' can be left out and they can be in any order.
-If you want to add any sub accounts just list the Parent THAT HAS ALREADY
+If you want to add any sub accounts just list the Parent THAT HAS ALREADY
BEEN CREATED before the account line in this fashion...
.TP
All account options are
@@ -1145,12 +1145,12 @@ are children of this association.
\fIGrpSubmitJobs=\fP
Maximum number of jobs which can be in a pending or
running state at any time in aggregate for this association and all
-association which are children of this association.
+association which are children of this association.
.TP
\fIGrpWall=\fP
Maximum wall clock time running jobs are able to be
allocated in aggregate for this association and all association which
-are children of this association.
+are children of this association.
.TP
\fIFairShare=\fP
Number used in conjunction with other associations to determine job priority.
@@ -1167,7 +1167,7 @@ Maximum cpu seconds children of this accounts jobs can run.
\fIMaxWallDurationPerJob=\fP
Maximum time (not related to job size) children of this accounts jobs can run.
.TP
-\fIOrganization=
+\fIOrganization=
Name of organization that owns this account.
.TP
\fI\fIQOS(=,+=,\-=)\fP
@@ -1224,9 +1224,9 @@ Sacctmgr has the capability to archive to a flatfile and or load that
data if needed later. The archiving is usually done by the slurmdbd
and it is highly recommended you only do it through sacctmgr if you
completely understand what you are doing. For slurmdbd options see
-"man slurmdbd" for more information.
+"man slurmdbd" for more information.
Loading data into the database can be done from these files to either
-view old data or regenerate rolled up data.
+view old data or regenerate rolled up data.
These are the options for both dump and load of archive information.
@@ -1266,14 +1266,14 @@ all step data removed will be lost permanently.
\fISuspend\fP
Archive Suspend Data. If not specified and PurgeSuspendMonths is set
all suspend data removed will be lost permanently.
-.RE
-
+.RE
+
archive load
.TP
\fIFile=\fP
File to load into database.
.TP
-\fIInsert=\fP
+\fIInsert=\fP
SQL to insert directly into the database. This should be used very
cautiously since this is writing your sql into the database.
.RE
@@ -1322,13 +1322,13 @@ wrong> sacctmgr modify user name=adam set fairshare=10 cluster=tux
.br
This will produce an error as the above line reads modify user adam
-set fairshare=10 and cluster=tux.
+set fairshare=10 and cluster=tux.
.br
.br
right> sacctmgr modify user name=adam cluster=tux set fairshare=10
.br
-right> sacctmgr modify user name=adam set fairshare=10 where cluster=tux
+right> sacctmgr modify user name=adam set fairshare=10 where cluster=tux
.br
.br
diff --git a/doc/man/man1/salloc.1 b/doc/man/man1/salloc.1
index 4fd4cea3266..345fe67411e 100644
--- a/doc/man/man1/salloc.1
+++ b/doc/man/man1/salloc.1
@@ -1,24 +1,24 @@
.TH "salloc" "1" "SLURM 2.1" "September 2009" "SLURM Commands"
.SH "NAME"
-salloc \- Obtain a SLURM job allocation (a set of nodes), execute a command,
+salloc \- Obtain a SLURM job allocation (a set of nodes), execute a command,
and then release the allocation when the command is finished.
.SH "SYNOPSIS"
salloc [\fIoptions\fP] [<\fIcommand\fP> [\fIcommand args\fR]]
.SH "DESCRIPTION"
-salloc is used to allocate a SLURM job allocation, which is a set of resources
-(nodes), possibly with some set of constraints (e.g. number of processors per
-node). When salloc successfully obtains the requested allocation, it then runs
-the command specified by the user. Finally, when the user specified command is
+salloc is used to allocate a SLURM job allocation, which is a set of resources
+(nodes), possibly with some set of constraints (e.g. number of processors per
+node). When salloc successfully obtains the requested allocation, it then runs
+the command specified by the user. Finally, when the user specified command is
complete, salloc relinquishes the job allocation.
-The command may be any program the user wishes. Some typical commands are
-xterm, a shell script containing srun commands, and srun (see the EXAMPLES
-section). If no command is specified, then the value of
-\fBSallocDefaultCommand\fR in slurm.conf is used. If
-\fBSallocDefaultCommand\fR is not set, then \fBsalloc\fR runs the
+The command may be any program the user wishes. Some typical commands are
+xterm, a shell script containing srun commands, and srun (see the EXAMPLES
+section). If no command is specified, then the value of
+\fBSallocDefaultCommand\fR in slurm.conf is used. If
+\fBSallocDefaultCommand\fR is not set, then \fBsalloc\fR runs the
user's default shell.
.SH "OPTIONS"
@@ -60,12 +60,12 @@ options if desired:
When the task/affinity plugin is enabled,
specifying an allocation in this manner also instructs SLURM to use
a CPU affinity mask to guarantee the request is filled as specified.
-NOTE: Support for these options are configuration dependent.
+NOTE: Support for these options are configuration dependent.
The task/affinity plugin must be configured.
-In addition either select/linear or select/cons_res plugin must be
+In addition either select/linear or select/cons_res plugin must be
configured.
-If select/cons_res is configured, it must have a parameter of CR_Core,
-CR_Core_Memory, CR_Socket, or CR_Socket_Memory.
+If select/cons_res is configured, it must have a parameter of CR_Core,
+CR_Core_Memory, CR_Socket, or CR_Socket_Memory.
.TP
\fB\-\-begin\fR=<\fItime\fR>
@@ -125,30 +125,30 @@ An arbitrary comment.
.TP
\fB\-C\fR, \fB\-\-constraint\fR=<\fIlist\fR>
-Specify a list of constraints.
-The constraints are features that have been assigned to the nodes by
-the slurm administrator.
-The \fIlist\fR of constraints may include multiple features separated
+Specify a list of constraints.
+The constraints are features that have been assigned to the nodes by
+the slurm administrator.
+The \fIlist\fR of constraints may include multiple features separated
by ampersand (AND) and/or vertical bar (OR) operators.
-For example: \fB\-\-constraint="opteron&video"\fR or
+For example: \fB\-\-constraint="opteron&video"\fR or
\fB\-\-constraint="fast|faster"\fR.
In the first example, only nodes having both the feature "opteron" AND
the feature "video" will be used.
There is no mechanism to specify that you want one node with feature
"opteron" and another node with feature "video" in that case that no
node has both features.
-If only one of a set of possible options should be used for all allocated
-nodes, then use the OR operator and enclose the options within square brackets.
-For example: "\fB\-\-constraint=[rack1|rack2|rack3|rack4]"\fR might
-be used to specify that all nodes must be allocated on a single rack of
+If only one of a set of possible options should be used for all allocated
+nodes, then use the OR operator and enclose the options within square brackets.
+For example: "\fB\-\-constraint=[rack1|rack2|rack3|rack4]"\fR might
+be used to specify that all nodes must be allocated on a single rack of
the cluster, but any of those four racks can be used.
A request can also specify the number of nodes needed with some feature
-by appending an asterisk and count after the feature name.
-For example "\fBsalloc \-\-nodes=16 \-\-constraint=graphics*4 ..."\fR
+by appending an asterisk and count after the feature name.
+For example "\fBsalloc \-\-nodes=16 \-\-constraint=graphics*4 ..."\fR
indicates that the job requires 16 nodes at that at least four of those
nodes must have the feature "graphics."
Constraints with node counts may only be combined with AND operators.
-If no nodes have the requested features, then the job will be rejected
+If no nodes have the requested features, then the job will be rejected
by the slurm job manager.
.TP
@@ -263,7 +263,7 @@ Show this help message
.TP
\fB\-c\fR, \fB\-\-cpus\-per\-task\fR=<\fIncpus\fR>
-Advise the SLURM controller that ensuing job steps will require \fIncpus\fR
+Advise the SLURM controller that ensuing job steps will require \fIncpus\fR
number of processors per task. Without this option, the controller will
just try to allocate one processor per task.
@@ -279,7 +279,7 @@ of 4 nodes, one for each of the 4 tasks.
\fB\-d\fR, \fB\-\-dependency\fR=<\fIdependency_list\fR>
Defer the start of this job until the specified dependencies have been
satisfied completed.
-<\fIdependency_list\fR> is of the form
+<\fIdependency_list\fR> is of the form
<\fItype:job_id[:job_id][,type:job_id[:job_id]]\fR>.
Many jobs can share the same dependency and these jobs may even belong to
different users. The value may be changed after job submission using the
@@ -350,8 +350,8 @@ This option was originally created for use by Moab.
.TP
\fB\-\-gid\fR=<\fIgroup\fR>
-If \fBsalloc\fR is run as root, and the \fB\-\-gid\fR option is used,
-submit the job with \fIgroup\fR's group access permissions. \fIgroup\fR
+If \fBsalloc\fR is run as root, and the \fB\-\-gid\fR option is used,
+submit the job with \fIgroup\fR's group access permissions. \fIgroup\fR
may be the group name or the numerical group ID.
.TP
@@ -381,8 +381,8 @@ show this help message
.TP
\fB\-I\fR, \fB\-\-immediate\fR[=<\fIseconds\fR>]
-exit if resources are not available within the
-time period specified.
+exit if resources are not available within the
+time period specified.
If no argument is given, resources must be available immediately
for the request to succeed.
By default, \fB\-\-immediate\fR is off, and the command
@@ -424,9 +424,9 @@ range of allocated nodes.
.TP
\fB\-L\fR, \fB\-\-licenses\fR=<\fBlicense\fR>
-Specification of licenses (or other resources available on all
+Specification of licenses (or other resources available on all
nodes of the cluster) which must be allocated to this job.
-License names can be followed by an asterisk and count
+License names can be followed by an asterisk and count
(the default count is one).
Multiple license names should be comma separated (e.g.
"\-\-licenses=foo*4,bar").
@@ -441,13 +441,13 @@ subsequent srun requests.
.TP
.B block
The block method of distribution will allocate processes in\-order to
-the cpus on a node. If the number of processes exceeds the number of
-cpus on all of the nodes in the allocation then all nodes will be
-utilized. For example, consider an allocation of three nodes each with
-two cpus. A four\-process block distribution request will distribute
-those processes to the nodes with processes one and two on the first
-node, process three on the second node, and process four on the third node.
-Block distribution is the default behavior if the number of tasks
+the cpus on a node. If the number of processes exceeds the number of
+cpus on all of the nodes in the allocation then all nodes will be
+utilized. For example, consider an allocation of three nodes each with
+two cpus. A four\-process block distribution request will distribute
+those processes to the nodes with processes one and two on the first
+node, process three on the second node, and process four on the third node.
+Block distribution is the default behavior if the number of tasks
exceeds the number of nodes requested.
.TP
.B cyclic
@@ -459,7 +459,7 @@ if the number of tasks is no larger than the number of nodes requested.
.B plane
The tasks are distributed in blocks of a specified size.
The options include a number representing the size of the task block.
-This is followed by an optional specification of the task distribution
+This is followed by an optional specification of the task distribution
scheme within a block of tasks and between the blocks of tasks.
For more details (including examples and diagrams), please see
.br
@@ -470,9 +470,9 @@ and
https://computing.llnl.gov/linux/slurm/dist_plane.html.
.TP
.B arbitrary
-The arbitrary method of distribution will allocate processes in\-order as
+The arbitrary method of distribution will allocate processes in\-order as
listed in file designated by the environment variable SLURM_HOSTFILE. If
-this variable is listed it will over ride any other method specified.
+this variable is listed it will over ride any other method specified.
If not set the method will default to block. Inside the hostfile must
contain at minimum the number of hosts requested. If requesting tasks
(\-n) your tasks will be laid out on the nodes in the order of the file.
@@ -480,13 +480,13 @@ contain at minimum the number of hosts requested. If requesting tasks
.TP
\fB\-\-mail\-type\fR=<\fItype\fR>
-Notify user by email when certain event types occur.
-Valid \fItype\fR values are BEGIN, END, FAIL, ALL (any state change).
-The user to be notified is indicated with \fB\-\-mail\-user\fR.
+Notify user by email when certain event types occur.
+Valid \fItype\fR values are BEGIN, END, FAIL, ALL (any state change).
+The user to be notified is indicated with \fB\-\-mail\-user\fR.
.TP
\fB\-\-mail\-user\fR=<\fIuser\fR>
-User to receive email notification of state changes as defined by
+User to receive email notification of state changes as defined by
\fB\-\-mail\-type\fR.
The default value is the submitting user.
@@ -505,7 +505,7 @@ Also see \fB\-\-mem\-per\-cpu\fR.
\fB\-\-mem\-per\-cpu\fR=<\fIMB\fR>
Mimimum memory required per allocated CPU in MegaBytes.
Default value is \fBDefMemPerCPU\fR and the maximum value is
-\fBMaxMemPerCPU\fR. If configured, both of parameters can be
+\fBMaxMemPerCPU\fR. If configured, both of parameters can be
seen using the \fBscontrol show config\fR command.
This parameter would generally be used of individual processors
are allocated to jobs (\fBSelectType=select/cons_res\fR).
@@ -514,16 +514,16 @@ Also see \fB\-\-mem\fR.
.TP
\fB\-\-mem_bind\fR=[{\fIquiet,verbose\fR},]\fItype\fR
-Bind tasks to memory. Used only when the task/affinity plugin is enabled
+Bind tasks to memory. Used only when the task/affinity plugin is enabled
and the NUMA memory functions are available.
-\fBNote that the resolution of CPU and memory binding
-may differ on some architectures.\fR For example, CPU binding may be performed
-at the level of the cores within a processor while memory binding will
-be performed at the level of nodes, where the definition of "nodes"
-may differ from system to system. \fBThe use of any type other than
+\fBNote that the resolution of CPU and memory binding
+may differ on some architectures.\fR For example, CPU binding may be performed
+at the level of the cores within a processor while memory binding will
+be performed at the level of nodes, where the definition of "nodes"
+may differ from system to system. \fBThe use of any type other than
"none" or "local" is not recommended.\fR
-If you want greater control, try running a simple test code with the
-options "\-\-cpu_bind=verbose,none \-\-mem_bind=verbose,none" to determine
+If you want greater control, try running a simple test code with the
+options "\-\-cpu_bind=verbose,none \-\-mem_bind=verbose,none" to determine
the specific configuration.
NOTE: To have SLURM always report on the selected memory binding for
@@ -602,16 +602,16 @@ A limit on the maximum node count may be specified with \fImaxnodes\fR
(e.g. "\-\-nodes=2\-4"). The minimum and maximum node count may be the
same to specify a specific number of nodes (e.g. "\-\-nodes=2\-2" will ask
for two and ONLY two nodes).
-The partition's node limits supersede those of the job.
-If a job's node limits are outside of the range permitted for its
-associated partition, the job will be left in a PENDING state.
-This permits possible execution at a later time, when the partition
+The partition's node limits supersede those of the job.
+If a job's node limits are outside of the range permitted for its
+associated partition, the job will be left in a PENDING state.
+This permits possible execution at a later time, when the partition
limit is changed.
-If a job node limit exceeds the number of nodes configured in the
+If a job node limit exceeds the number of nodes configured in the
partition, the job will be rejected.
-Note that the environment
-variable \fBSLURM_NNODES\fR will be set to the count of nodes actually
-allocated to the job. See the \fBENVIRONMENT VARIABLES \fR section
+Note that the environment
+variable \fBSLURM_NNODES\fR will be set to the count of nodes actually
+allocated to the job. See the \fBENVIRONMENT VARIABLES \fR section
for more information. If \fB\-N\fR is not specified, the default
behavior is to allocate enough nodes to satisfy the requirements of
the \fB\-n\fR and \fB\-c\fR options.
@@ -620,28 +620,28 @@ and without delaying the initiation of the job.
.TP
\fB\-n\fR, \fB\-\-ntasks\fR=<\fInumber\fR>
-salloc does not launch tasks, it requests an allocation of resources and
-executed some command. This option advises the SLURM controller that job
+salloc does not launch tasks, it requests an allocation of resources and
+executed some command. This option advises the SLURM controller that job
steps run within this allocation will launch a maximum of \fInumber\fR
-tasks and sufficient resources are allocated to accomplish this.
-The default is one task per socket or core (depending upon the value
-of the \fISelectTypeParameters\fR parameter in slurm.conf), but note
+tasks and sufficient resources are allocated to accomplish this.
+The default is one task per socket or core (depending upon the value
+of the \fISelectTypeParameters\fR parameter in slurm.conf), but note
that the \fB\-\-cpus\-per\-task\fR option will change this default.
.TP
\fB\-\-network\fR=<\fItype\fR>
-Specify the communication protocol to be used.
+Specify the communication protocol to be used.
This option is supported on AIX systems.
-Since POE is used to launch tasks, this option is not normally used or
+Since POE is used to launch tasks, this option is not normally used or
is specified using the \fBSLURM_NETWORK\fR environment variable.
The interpretation of \fItype\fR is system dependent.
-For systems with an IBM Federation switch, the following
+For systems with an IBM Federation switch, the following
comma\-separated and case insensitive types are recognized:
-\fBIP\fR (the default is user\-space), \fBSN_ALL\fR, \fBSN_SINGLE\fR,
-\fBBULK_XFER\fR and adapter names (e.g. \fBSNI0\fR and \fBSNI1\fR).
+\fBIP\fR (the default is user\-space), \fBSN_ALL\fR, \fBSN_SINGLE\fR,
+\fBBULK_XFER\fR and adapter names (e.g. \fBSNI0\fR and \fBSNI1\fR).
For more information, on IBM systems see \fIpoe\fR documentation on
the environment variables \fBMP_EUIDEVICE\fR and \fBMP_USE_BULK_XFER\fR.
-Note that only four jobs steps may be active at once on a node with the
+Note that only four jobs steps may be active at once on a node with the
\fBBULK_XFER\fR option due to limitations in the Federation switch driver.
.TP
@@ -651,7 +651,7 @@ With no adjustment value the scheduling priority is decreased
by 100. The adjustment range is from \-10000 (highest priority)
to 10000 (lowest priority). Only privileged users can specify
a negative adjustment. NOTE: This option is presently
-ignored if \fISchedulerType=sched/wiki\fR or
+ignored if \fISchedulerType=sched/wiki\fR or
\fISchedulerType=sched/wiki2\fR.
.TP
@@ -738,14 +738,14 @@ performance will likely suffer due to competition for resources within a node.
.TP
\fB\-\-signal\fR=<\fIsig_num\fR>[@<\fIsig_time\fR>]
-When a job is within \fIsig_time\fR seconds of its end time,
-send it the signal \fIsig_num\fR.
-Due to the resolution of event handling by SLURM, the signal may
+When a job is within \fIsig_time\fR seconds of its end time,
+send it the signal \fIsig_num\fR.
+Due to the resolution of event handling by SLURM, the signal may
be sent up to 60 seconds earlier than specified.
Both \fIsig_time\fR and \fIsig_num\fR must have integer values
between zero and 65535.
-By default, no signal is sent before the job's end time.
-If a \fIsig_num\fR is specified without any \fIsig_time\fR,
+By default, no signal is sent before the job's end time.
+If a \fIsig_num\fR is specified without any \fIsig_time\fR,
the default time will be 60 seconds.
.TP
@@ -826,8 +826,8 @@ Default from \fIblugene.conf\fR if not set.
.TP
\fB\-\-conn\-type\fR=<\fItype\fR>
-Require the partition connection type to be of a certain type.
-On Blue Gene the acceptable of \fItype\fR are MESH, TORUS and NAV.
+Require the partition connection type to be of a certain type.
+On Blue Gene the acceptable of \fItype\fR are MESH, TORUS and NAV.
If NAV, or if not set, then SLURM will try to fit a TORUS else MESH.
You should not normally set this option.
SLURM will normally allocate a TORUS if possible for a given geometry.
@@ -837,10 +837,10 @@ for virtual node mode, and HTC_L for Linux mode.
.TP
\fB\-g\fR, \fB\-\-geometry\fR=<\fIXxYxZ\fR>
-Specify the geometry requirements for the job. The three numbers
-represent the required geometry giving dimensions in the X, Y and
-Z directions. For example "\-\-geometry=2x3x4", specifies a block
-of nodes having 2 x 3 x 4 = 24 nodes (actually base partitions on
+Specify the geometry requirements for the job. The three numbers
+represent the required geometry giving dimensions in the X, Y and
+Z directions. For example "\-\-geometry=2x3x4", specifies a block
+of nodes having 2 x 3 x 4 = 24 nodes (actually base partitions on
Blue Gene).
.TP
@@ -860,7 +860,7 @@ Default from \fIblugene.conf\fR if not set.
.TP
\fB\-R\fR, \fB\-\-no\-rotate\fR
-Disables rotation of the job's requested geometry in order to fit an
+Disables rotation of the job's requested geometry in order to fit an
appropriate partition.
By default the specified geometry can rotate in three dimensions.
@@ -902,15 +902,15 @@ Same as \fB\-v, \-\-verbose\fR
Same as \fB\-\-exclusive\fR
.TP
\fBSLURM_EXIT_ERROR\fR
-Specifies the exit code generated when a SLURM error occurs
+Specifies the exit code generated when a SLURM error occurs
(e.g. invalid options).
This can be used by a script to distinguish application exit codes from
various SLURM error conditions.
Also see \fBSLURM_EXIT_IMMEDIATE\fR.
.TP
\fBSLURM_EXIT_IMMEDIATE\fR
-Specifies the exit code generated when the \fB\-\-immediate\fR option
-is used and resources are not currently available.
+Specifies the exit code generated when the \fB\-\-immediate\fR option
+is used and resources are not currently available.
This can be used by a script to distinguish application exit codes from
various SLURM error conditions.
Also see \fBSLURM_EXIT_ERROR\fR.
@@ -1007,26 +1007,26 @@ Do not free a block on Blue Gene systems only.
The block name on Blue Gene systems only.
.SH "SIGNALS"
-.LP
+.LP
While salloc is waiting for a PENDING job allocation, most signals will cause salloc to revoke the allocation request and exit.
-However, if the allocation has been granted and salloc has already started the command
+However, if the allocation has been granted and salloc has already started the command
specified in its command line parameters salloc will ignore most signals. salloc will not exit or release the allocation until the command exits. The notable exception is SIGHUP; a HUP signal will cause salloc to release the allocation and exit without waiting for the command to finish.
.SH "EXAMPLES"
-.LP
+.LP
To get an allocation, and open a new xterm in which srun commands may be typed interactively:
-.IP
+.IP
$ salloc \-N16 xterm
-.br
+.br
salloc: Granted job allocation 65537
-.br
+.br
(at this point the xterm appears, and salloc waits for xterm to exit)
-.br
+.br
salloc: Relinquishing job allocation 65537
-.LP
+.LP
To grab an allocation of nodes and launch a parallel application on one command line (See the \fBsalloc\fR man page for more examples):
-.IP
+.IP
salloc \-N5 srun \-n10 myprogram
.SH "COPYING"
@@ -1049,5 +1049,5 @@ FOR A PARTICULAR PURPOSE. See the GNU General Public License for more
details.
.SH "SEE ALSO"
-.LP
+.LP
sinfo(1), sattach(1), sbatch(1), squeue(1), scancel(1), scontrol(1), slurm.conf(5), sched_setaffinity(2), numa(3)
diff --git a/doc/man/man1/sattach.1 b/doc/man/man1/sattach.1
index f50b7200f0d..47b15628836 100644
--- a/doc/man/man1/sattach.1
+++ b/doc/man/man1/sattach.1
@@ -1,30 +1,30 @@
.TH "sattach" "1" "SLURM 2.1" "October 2009" "SLURM Commands"
.SH "NAME"
-.LP
+.LP
sattach \- Attach to a SLURM job step.
.SH "SYNOPSIS"
-.LP
+.LP
sattach [\fIoptions\fP] <jobid.stepid>
.SH "DESCRIPTION"
-.LP
+.LP
sattach attaches to a running SLURM job step. By attaching, it makes available
the IO streams of all of the tasks of a running SLURM job step. It also
suitable for use with a parallel debugger like TotalView.
.SH "OPTIONS"
-.LP
+.LP
-.TP
+.TP
\fB\-h\fR, \fB\-\-help\fR
Display help information and exit.
-.TP
+.TP
\fB\-\-input\-filter\fR[=]<\fItask number\fR>
.PD 0
.TP
\fB\-\-output\-filter\fR[=]<\fItask number\fR>
.PD 0
-.TP
+.TP
\fB\-\-error\-filter\fR[=]<\fItask number\fR>
.PD
Only transmit standard input to a single task, or print the standard output
@@ -50,7 +50,7 @@ Suppress informational messages from sattach. Errors will still be displayed.
\fB\-u\fR, \fB\-\-usage\fR
Display brief usage message and exit.
-.TP
+.TP
\fB\-V\fR, \fB\-\-version\fR
Display SLURM version number and exit.
@@ -67,14 +67,14 @@ variables settings.
.TP 22
\fBSLURM_EXIT_ERROR\fR
-Specifies the exit code generated when a SLURM error occurs
+Specifies the exit code generated when a SLURM error occurs
(e.g. invalid options).
This can be used by a script to distinguish application exit codes from
various SLURM error conditions.
.SH "EXAMPLES"
-.LP
+.LP
sattach 15.0
sattach \-\-output\-filter 5 65386.15
@@ -99,5 +99,5 @@ FOR A PARTICULAR PURPOSE. See the GNU General Public License for more
details.
.SH "SEE ALSO"
-.LP
+.LP
sinfo(1), salloc(1), sbatch(1), squeue(1), scancel(1), scontrol(1), slurm.conf(5), sched_setaffinity(2), numa(3)
diff --git a/doc/man/man1/sbatch.1 b/doc/man/man1/sbatch.1
index 5bc3d216912..88266b3a372 100644
--- a/doc/man/man1/sbatch.1
+++ b/doc/man/man1/sbatch.1
@@ -59,12 +59,12 @@ options if desired:
When the task/affinity plugin is enabled,
specifying an allocation in this manner also instructs SLURM to use
a CPU affinity mask to guarantee the request is filled as specified.
-NOTE: Support for these options are configuration dependent.
+NOTE: Support for these options are configuration dependent.
The task/affinity plugin must be configured.
-In addition either select/linear or select/cons_res plugin must be
+In addition either select/linear or select/cons_res plugin must be
configured.
-If select/cons_res is configured, it must have a parameter of CR_Core,
-CR_Core_Memory, CR_Socket, or CR_Socket_Memory.
+If select/cons_res is configured, it must have a parameter of CR_Core,
+CR_Core_Memory, CR_Socket, or CR_Socket_Memory.
.TP
\fB\-\-begin\fR=<\fItime\fR>
@@ -113,15 +113,15 @@ already passed for that year, in which case the next year is used.
.TP
\fB\-\-checkpoint\fR=<\fItime\fR>
-Specifies the interval between creating checkpoints of the job step.
+Specifies the interval between creating checkpoints of the job step.
By default, the job step will no checkpoints created.
-Acceptable time formats include "minutes", "minutes:seconds",
-"hours:minutes:seconds", "days\-hours", "days\-hours:minutes" and
+Acceptable time formats include "minutes", "minutes:seconds",
+"hours:minutes:seconds", "days\-hours", "days\-hours:minutes" and
"days\-hours:minutes:seconds".
.TP
\fB\-\-checkpoint\-dir\fR=<\fIdirectory\fR>
-Specifies the directory into which the job or job step's checkpoint should
+Specifies the directory into which the job or job step's checkpoint should
be written (used by the checkpoint/blcrm and checkpoint/xlch plugins only).
The default value is the current working directory.
Checkpoint files will be of the form "<job_id>.ckpt" for jobs
@@ -133,30 +133,30 @@ An arbitrary comment.
.TP
\fB\-C\fR, \fB\-\-constraint\fR=<\fIlist\fR>
-Specify a list of constraints.
-The constraints are features that have been assigned to the nodes by
-the slurm administrator.
-The \fIlist\fR of constraints may include multiple features separated
+Specify a list of constraints.
+The constraints are features that have been assigned to the nodes by
+the slurm administrator.
+The \fIlist\fR of constraints may include multiple features separated
by ampersand (AND) and/or vertical bar (OR) operators.
-For example: \fB\-\-constraint="opteron&video"\fR or
+For example: \fB\-\-constraint="opteron&video"\fR or
\fB\-\-constraint="fast|faster"\fR.
In the first example, only nodes having both the feature "opteron" AND
the feature "video" will be used.
There is no mechanism to specify that you want one node with feature
"opteron" and another node with feature "video" in that case that no
node has both features.
-If only one of a set of possible options should be used for all allocated
-nodes, then use the OR operator and enclose the options within square brackets.
-For example: "\fB\-\-constraint=[rack1|rack2|rack3|rack4]"\fR might
-be used to specify that all nodes must be allocated on a single rack of
+If only one of a set of possible options should be used for all allocated
+nodes, then use the OR operator and enclose the options within square brackets.
+For example: "\fB\-\-constraint=[rack1|rack2|rack3|rack4]"\fR might
+be used to specify that all nodes must be allocated on a single rack of
the cluster, but any of those four racks can be used.
A request can also specify the number of nodes needed with some feature
-by appending an asterisk and count after the feature name.
-For example "\fBsbatch \-\-nodes=16 \-\-constraint=graphics*4 ..."\fR
+by appending an asterisk and count after the feature name.
+For example "\fBsbatch \-\-nodes=16 \-\-constraint=graphics*4 ..."\fR
indicates that the job requires 16 nodes at that at least four of those
nodes must have the feature "graphics."
Constraints with node counts may only be combined with AND operators.
-If no nodes have the requested features, then the job will be rejected
+If no nodes have the requested features, then the job will be rejected
by the slurm job manager.
.TP
@@ -271,7 +271,7 @@ Show this help message
.TP
\fB\-c\fR, \fB\-\-cpus\-per\-task\fR=<\fIncpus\fR>
-Advise the SLURM controller that ensuing job steps will require \fIncpus\fR
+Advise the SLURM controller that ensuing job steps will require \fIncpus\fR
number of processors per task. Without this option, the controller will
just try to allocate one processor per task.
@@ -287,7 +287,7 @@ of 4 nodes, one for each of the 4 tasks.
\fB\-d\fR, \fB\-\-dependency\fR=<\fIdependency_list\fR>
Defer the start of this job until the specified dependencies have been
satisfied completed.
-<\fIdependency_list\fR> is of the form
+<\fIdependency_list\fR> is of the form
<\fItype:job_id[:job_id][,type:job_id[:job_id]]\fR>.
Many jobs can share the same dependency and these jobs may even belong to
different users. The value may be changed after job submission using the
@@ -322,7 +322,7 @@ it it executed.
.TP
\fB\-e\fR, \fB\-\-error\fR=<\fIfilename pattern\fR>
-Instruct SLURM to connect the batch script's standard error directly to the
+Instruct SLURM to connect the batch script's standard error directly to the
file name specified in the "\fIfilename pattern\fR".
See the \fB\-\-input\fR option for filename specification options.
@@ -366,8 +366,8 @@ This option was originally created for use by Moab.
.TP
\fB\-\-gid\fR=<\fIgroup\fR>
-If \fBsbatch\fR is run as root, and the \fB\-\-gid\fR option is used,
-submit the job with \fIgroup\fR's group access permissions. \fIgroup\fR
+If \fBsbatch\fR is run as root, and the \fB\-\-gid\fR option is used,
+submit the job with \fIgroup\fR's group access permissions. \fIgroup\fR
may be the group name or the numerical group ID.
.TP
@@ -454,9 +454,9 @@ range of allocated nodes.
.TP
\fB\-L\fR, \fB\-\-licenses\fR=<\fBlicense\fR>
-Specification of licenses (or other resources available on all
+Specification of licenses (or other resources available on all
nodes of the cluster) which must be allocated to this job.
-License names can be followed by an asterisk and count
+License names can be followed by an asterisk and count
(the default count is one).
Multiple license names should be comma separated (e.g.
"\-\-licenses=foo*4,bar").
@@ -471,13 +471,13 @@ subsequent srun requests.
.TP
.B block
The block method of distribution will allocate processes in\-order to
-the cpus on a node. If the number of processes exceeds the number of
-cpus on all of the nodes in the allocation then all nodes will be
-utilized. For example, consider an allocation of three nodes each with
-two cpus. A four\-process block distribution request will distribute
-those processes to the nodes with processes one and two on the first
-node, process three on the second node, and process four on the third node.
-Block distribution is the default behavior if the number of tasks
+the cpus on a node. If the number of processes exceeds the number of
+cpus on all of the nodes in the allocation then all nodes will be
+utilized. For example, consider an allocation of three nodes each with
+two cpus. A four\-process block distribution request will distribute
+those processes to the nodes with processes one and two on the first
+node, process three on the second node, and process four on the third node.
+Block distribution is the default behavior if the number of tasks
exceeds the number of nodes requested.
.TP
.B cyclic
@@ -489,7 +489,7 @@ if the number of tasks is no larger than the number of nodes requested.
.B plane
The tasks are distributed in blocks of a specified size.
The options include a number representing the size of the task block.
-This is followed by an optional specification of the task distribution
+This is followed by an optional specification of the task distribution
scheme within a block of tasks and between the blocks of tasks.
For more details (including examples and diagrams), please see
.br
@@ -500,9 +500,9 @@ and
https://computing.llnl.gov/linux/slurm/dist_plane.html.
.TP
.B arbitrary
-The arbitrary method of distribution will allocate processes in\-order as
+The arbitrary method of distribution will allocate processes in\-order as
listed in file designated by the environment variable SLURM_HOSTFILE. If
-this variable is listed it will over ride any other method specified.
+this variable is listed it will over ride any other method specified.
If not set the method will default to block. Inside the hostfile must
contain at minimum the number of hosts requested. If requesting tasks
(\-n) your tasks will be laid out on the nodes in the order of the file.
@@ -510,13 +510,13 @@ contain at minimum the number of hosts requested. If requesting tasks
.TP
\fB\-\-mail\-type\fR=<\fItype\fR>
-Notify user by email when certain event types occur.
-Valid \fItype\fR values are BEGIN, END, FAIL, ALL (any state change).
-The user to be notified is indicated with \fB\-\-mail\-user\fR.
+Notify user by email when certain event types occur.
+Valid \fItype\fR values are BEGIN, END, FAIL, ALL (any state change).
+The user to be notified is indicated with \fB\-\-mail\-user\fR.
.TP
\fB\-\-mail\-user\fR=<\fIuser\fR>
-User to receive email notification of state changes as defined by
+User to receive email notification of state changes as defined by
\fB\-\-mail\-type\fR.
The default value is the submitting user.
@@ -535,7 +535,7 @@ Also see \fB\-\-mem\-per\-cpu\fR.
\fB\-\-mem\-per\-cpu\fR=<\fIMB\fR>
Mimimum memory required per allocated CPU in MegaBytes.
Default value is \fBDefMemPerCPU\fR and the maximum value is
-\fBMaxMemPerCPU\fR. If configured, both of parameters can be
+\fBMaxMemPerCPU\fR. If configured, both of parameters can be
seen using the \fBscontrol show config\fR command.
This parameter would generally be used of individual processors
are allocated to jobs (\fBSelectType=select/cons_res\fR).
@@ -544,16 +544,16 @@ Also see \fB\-\-mem\fR.
.TP
\fB\-\-mem_bind\fR=[{\fIquiet,verbose\fR},]\fItype\fR
-Bind tasks to memory. Used only when the task/affinity plugin is enabled
+Bind tasks to memory. Used only when the task/affinity plugin is enabled
and the NUMA memory functions are available.
-\fBNote that the resolution of CPU and memory binding
-may differ on some architectures.\fR For example, CPU binding may be performed
-at the level of the cores within a processor while memory binding will
-be performed at the level of nodes, where the definition of "nodes"
-may differ from system to system. \fBThe use of any type other than
+\fBNote that the resolution of CPU and memory binding
+may differ on some architectures.\fR For example, CPU binding may be performed
+at the level of the cores within a processor while memory binding will
+be performed at the level of nodes, where the definition of "nodes"
+may differ from system to system. \fBThe use of any type other than
"none" or "local" is not recommended.\fR
-If you want greater control, try running a simple test code with the
-options "\-\-cpu_bind=verbose,none \-\-mem_bind=verbose,none" to determine
+If you want greater control, try running a simple test code with the
+options "\-\-cpu_bind=verbose,none \-\-mem_bind=verbose,none" to determine
the specific configuration.
NOTE: To have SLURM always report on the selected memory binding for
@@ -632,16 +632,16 @@ A limit on the maximum node count may be specified with \fImaxnodes\fR
(e.g. "\-\-nodes=2\-4"). The minimum and maximum node count may be the
same to specify a specific number of nodes (e.g. "\-\-nodes=2\-2" will ask
for two and ONLY two nodes).
-The partition's node limits supersede those of the job.
-If a job's node limits are outside of the range permitted for its
-associated partition, the job will be left in a PENDING state.
-This permits possible execution at a later time, when the partition
+The partition's node limits supersede those of the job.
+If a job's node limits are outside of the range permitted for its
+associated partition, the job will be left in a PENDING state.
+This permits possible execution at a later time, when the partition
limit is changed.
-If a job node limit exceeds the number of nodes configured in the
+If a job node limit exceeds the number of nodes configured in the
partition, the job will be rejected.
-Note that the environment
-variable \fBSLURM_NNODES\fR will be set to the count of nodes actually
-allocated to the job. See the \fBENVIRONMENT VARIABLES \fR section
+Note that the environment
+variable \fBSLURM_NNODES\fR will be set to the count of nodes actually
+allocated to the job. See the \fBENVIRONMENT VARIABLES \fR section
for more information. If \fB\-N\fR is not specified, the default
behavior is to allocate enough nodes to satisfy the requirements of
the \fB\-n\fR and \fB\-c\fR options.
@@ -650,28 +650,28 @@ and without delaying the initiation of the job.
.TP
\fB\-n\fR, \fB\-\-ntasks\fR=<\fInumber\fR>
-sbatch does not launch tasks, it requests an allocation of resources and
-submits a batch script. This option advises the SLURM controller that job
+sbatch does not launch tasks, it requests an allocation of resources and
+submits a batch script. This option advises the SLURM controller that job
steps run within this allocation will launch a maximum of \fInumber\fR
-tasks and sufficient resources are allocated to accomplish this.
-The default is one task per socket or core (depending upon the value
-of the \fISelectTypeParameters\fR parameter in slurm.conf), but note
+tasks and sufficient resources are allocated to accomplish this.
+The default is one task per socket or core (depending upon the value
+of the \fISelectTypeParameters\fR parameter in slurm.conf), but note
that the \fB\-\-cpus\-per\-task\fR option will change this default.
.TP
\fB\-\-network\fR=<\fItype\fR>
-Specify the communication protocol to be used.
+Specify the communication protocol to be used.
This option is supported on AIX systems.
-Since POE is used to launch tasks, this option is not normally used or
+Since POE is used to launch tasks, this option is not normally used or
is specified using the \fBSLURM_NETWORK\fR environment variable.
The interpretation of \fItype\fR is system dependent.
-For systems with an IBM Federation switch, the following
+For systems with an IBM Federation switch, the following
comma\-separated and case insensitive types are recognized:
-\fBIP\fR (the default is user\-space), \fBSN_ALL\fR, \fBSN_SINGLE\fR,
-\fBBULK_XFER\fR and adapter names (e.g. \fBSNI0\fR and \fBSNI1\fR).
+\fBIP\fR (the default is user\-space), \fBSN_ALL\fR, \fBSN_SINGLE\fR,
+\fBBULK_XFER\fR and adapter names (e.g. \fBSNI0\fR and \fBSNI1\fR).
For more information, on IBM systems see \fIpoe\fR documentation on
the environment variables \fBMP_EUIDEVICE\fR and \fBMP_USE_BULK_XFER\fR.
-Note that only four jobs steps may be active at once on a node with the
+Note that only four jobs steps may be active at once on a node with the
\fBBULK_XFER\fR option due to limitations in the Federation switch driver.
.TP
@@ -681,17 +681,17 @@ With no adjustment value the scheduling priority is decreased
by 100. The adjustment range is from \-10000 (highest priority)
to 10000 (lowest priority). Only privileged users can specify
a negative adjustment. NOTE: This option is presently
-ignored if \fISchedulerType=sched/wiki\fR or
+ignored if \fISchedulerType=sched/wiki\fR or
\fISchedulerType=sched/wiki2\fR.
.TP
\fB\-\-no\-requeue\fR
Specifies that the batch job should not be requeued after node failure.
-Setting this option will prevent system administrators from being able
+Setting this option will prevent system administrators from being able
to restart the job (for example, after a scheduled downtime).
When a job is requeued, the batch script is initiated from its beginning.
Also see the \fB\-\-requeue\fR option.
-The \fIJobRequeue\fR configuration parameter controls the default
+The \fIJobRequeue\fR configuration parameter controls the default
behavior on the cluster.
.TP
@@ -739,7 +739,7 @@ allowing more than one task per processor. However no more than
.TP
\fB\-o\fR, \fB\-\-output\fR=<\fIfilename pattern\fR>
-Instruct SLURM to connect the batch script's standard output directly to the
+Instruct SLURM to connect the batch script's standard output directly to the
file name specified in the "\fIfilename pattern\fR".
See the \fB\-\-input\fR option for filename specification options.
@@ -816,7 +816,7 @@ the SLURM configuration parameter, AccountingStorageEnforce, includes
Specifies that the batch job should be requeued after node failure.
When a job is requeued, the batch script is initiated from its beginning.
Also see the \fB\-\-no\-requeue\fR option.
-The \fIJobRequeue\fR configuration parameter controls the default
+The \fIJobRequeue\fR configuration parameter controls the default
behavior on the cluster.
.TP
@@ -833,14 +833,14 @@ performance will likely suffer due to competition for resources within a node.
.TP
\fB\-\-signal\fR=<\fIsig_num\fR>[@<\fIsig_time\fR>]
-When a job is within \fIsig_time\fR seconds of its end time,
-send it the signal \fIsig_num\fR.
-Due to the resolution of event handling by SLURM, the signal may
+When a job is within \fIsig_time\fR seconds of its end time,
+send it the signal \fIsig_num\fR.
+Due to the resolution of event handling by SLURM, the signal may
be sent up to 60 seconds earlier than specified.
Both \fIsig_time\fR and \fIsig_num\fR must have integer values
between zero and 65535.
-By default, no signal is sent before the job's end time.
-If a \fIsig_num\fR is specified without any \fIsig_time\fR,
+By default, no signal is sent before the job's end time.
+If a \fIsig_num\fR is specified without any \fIsig_time\fR,
the default time will be 60 seconds.
.TP
@@ -929,8 +929,8 @@ Default from \fIblugene.conf\fR if not set.
.TP
\fB\-\-conn\-type\fR=<\fItype\fR>
-Require the partition connection type to be of a certain type.
-On Blue Gene the acceptable of \fItype\fR are MESH, TORUS and NAV.
+Require the partition connection type to be of a certain type.
+On Blue Gene the acceptable of \fItype\fR are MESH, TORUS and NAV.
If NAV, or if not set, then SLURM will try to fit a TORUS else MESH.
You should not normally set this option.
SLURM will normally allocate a TORUS if possible for a given geometry.
@@ -940,10 +940,10 @@ for virtual node mode, and HTC_L for Linux mode.
.TP
\fB\-g\fR, \fB\-\-geometry\fR=<\fIXxYxZ\fR>
-Specify the geometry requirements for the job. The three numbers
-represent the required geometry giving dimensions in the X, Y and
-Z directions. For example "\-\-geometry=2x3x4", specifies a block
-of nodes having 2 x 3 x 4 = 24 nodes (actually base partitions on
+Specify the geometry requirements for the job. The three numbers
+represent the required geometry giving dimensions in the X, Y and
+Z directions. For example "\-\-geometry=2x3x4", specifies a block
+of nodes having 2 x 3 x 4 = 24 nodes (actually base partitions on
Blue Gene).
.TP
@@ -963,7 +963,7 @@ Default from \fIblugene.conf\fR if not set.
.TP
\fB\-R\fR, \fB\-\-no\-rotate\fR
-Disables rotation of the job's requested geometry in order to fit an
+Disables rotation of the job's requested geometry in order to fit an
appropriate partition.
By default the specified geometry can rotate in three dimensions.
@@ -1012,7 +1012,7 @@ Same as \fB\-m, \-\-distribution\fR
Same as \fB\-\-exclusive\fR
.TP
\fBSLURM_EXIT_ERROR\fR
-Specifies the exit code generated when a SLURM error occurs
+Specifies the exit code generated when a SLURM error occurs
(e.g. invalid options).
This can be used by a script to distinguish application exit codes from
various SLURM error conditions.
@@ -1138,7 +1138,7 @@ The block name on Blue Gene systems only.
.LP
Specify a batch script by filename on the command line.
The batch script specifies a 1 minute time limit for the job.
-.IP
+.IP
$ cat myscript
.br
#!/bin/sh
@@ -1165,9 +1165,9 @@ host3
.br
host4
-.LP
+.LP
Pass a batch script to sbatch on standard input:
-.IP
+.IP
$ sbatch \-N4 <<EOF
.br
> #!/bin/sh
@@ -1210,5 +1210,5 @@ FOR A PARTICULAR PURPOSE. See the GNU General Public License for more
details.
.SH "SEE ALSO"
-.LP
+.LP
sinfo(1), sattach(1), salloc(1), squeue(1), scancel(1), scontrol(1), slurm.conf(5), sched_setaffinity(2), numa(3)
diff --git a/doc/man/man1/sbcast.1 b/doc/man/man1/sbcast.1
index 85215e0e36c..20d8bf0835f 100644
--- a/doc/man/man1/sbcast.1
+++ b/doc/man/man1/sbcast.1
@@ -4,20 +4,20 @@
sbcast \- transmit a file to the nodes allocated to a SLURM job.
.SH "SYNOPSIS"
-\fBsbcast\fR [\-CfpstvV] SOURCE DEST
+\fBsbcast\fR [\-CfpstvV] SOURCE DEST
.SH "DESCRIPTION"
-\fBsbcast\fR is used to transmit a file to all nodes allocated
+\fBsbcast\fR is used to transmit a file to all nodes allocated
to the currenly active SLURM job.
This command should only be executed from within a SLURM batch
-job or within the shell spawned after a SLURM job's resource
-allocation.
+job or within the shell spawned after a SLURM job's resource
+allocation.
\fBSOURCE\fR is the name of a file on the current node.
-\fBDEST\fR should be the fully qualified pathname for the
-file copy to be created on each node.
+\fBDEST\fR should be the fully qualified pathname for the
+file copy to be created on each node.
\fBDEST\fR should be on a file system local to that node.
-Note that parallel file systems \fImay\fR provide better performance
-than \fBsbcast\fR can provide, although performance will vary
+Note that parallel file systems \fImay\fR provide better performance
+than \fBsbcast\fR can provide, although performance will vary
by file size, degree of parallelism, and network type.
.SH "OPTIONS"
@@ -33,20 +33,20 @@ Specify the fanout of messages used for file transfer.
Maximum value is currently eight.
.TP
\fB\-p\fR, \fB\-\-preserve\fR
-Preserves modification times, access times, and modes from the
+Preserves modification times, access times, and modes from the
original file.
.TP
\fB\-s\fR \fIsize\fR, \fB\-\-size\fR=\fIsize\fR
Specify the block size used for file broadcast.
-The size can have a suffix of \fIk\fR or \fIm\fR for kilobytes
+The size can have a suffix of \fIk\fR or \fIm\fR for kilobytes
or megabytes respecitively (defaults to bytes).
-This size subject to rounding and range limits to maintain
-good performance. This value may need to be set on systems
+This size subject to rounding and range limits to maintain
+good performance. This value may need to be set on systems
with very limited memory.
.TP
\fB\-t\fB \fIseconds\fR, fB\-\-timeout\fR=\fIseconds\fR
Specify the message timeout in seconds.
-The default value is \fIMessageTimeout\fR as reported by
+The default value is \fIMessageTimeout\fR as reported by
"scontrol show config".
Setting a higher value may be necessitated by relatively slow
I/O performance on the compute node disks.
@@ -57,11 +57,11 @@ Provide detailed event logging through program execution.
\fB\-V\fR, \fB\-\-version\fR
Print version information and exit.
-.SH "ENVIRONMENT VARIABLES"
-.PP
-Some \fBsbcast\fR options may be set via environment variables.
-These environment variables, along with their corresponding options,
-are listed below. (Note: Command line options will always override
+.SH "ENVIRONMENT VARIABLES"
+.PP
+Some \fBsbcast\fR options may be set via environment variables.
+These environment variables, along with their corresponding options,
+are listed below. (Note: Command line options will always override
these settings.)
.TP 20
\fBSBCAST_COMPRESS\fR
@@ -84,7 +84,7 @@ these settings.)
.SH "EXAMPLE"
-Using a batch script, transmit local file \fBmy.prog\fR to
+Using a batch script, transmit local file \fBmy.prog\fR to
\fB/tmp/my.proc\fR on the local nodes and then execute it.
.nf
diff --git a/doc/man/man1/scancel.1 b/doc/man/man1/scancel.1
index e9fc04c0558..ce3e2b6cf30 100644
--- a/doc/man/man1/scancel.1
+++ b/doc/man/man1/scancel.1
@@ -7,12 +7,12 @@ scancel \- Used to signal jobs or job steps that are under the control of Slurm.
\fBscancel\fR [\fIOPTIONS\fR...] [\fIjob_id\fR[.\fIstep_id\fR]] [\fIjob_id\fR[.\fIstep_id\fR]...]
.SH "DESCRIPTION"
-\fBscancel\fR is used to signal or cancel jobs or job steps. An arbitrary number
+\fBscancel\fR is used to signal or cancel jobs or job steps. An arbitrary number
of jobs or job steps may be signaled using job specification filters or a
-space separated list of specific job and/or job step IDs. A job or job step
-can only be signaled by the owner of that job or user root. If an attempt is
-made by an unauthorized user to signal a job or job step, an error message will
-be printed and the job will not be signaled.
+space separated list of specific job and/or job step IDs. A job or job step
+can only be signaled by the owner of that job or user root. If an attempt is
+made by an unauthorized user to signal a job or job step, an error message will
+be printed and the job will not be signaled.
.SH "OPTIONS"
@@ -26,7 +26,7 @@ Signal the batch job shell and its child processes.
This is not applicable if \fIstep_id\fR is specified.
NOTE: The shell itself may exit upon receipt of many signals.
You may avoid this by explicitly trap signals within the shell
-script (e.g. "trap <arg> <signals>"). See the shell documentation
+script (e.g. "trap <arg> <signals>"). See the shell documentation
for details.
.TP
@@ -85,14 +85,14 @@ This option is incompatible with the \fB\-\-quiet\fR option.
.TP
\fB\-V\fR, \fB\-\-version\fR
-Print the version number of the scancel command.
+Print the version number of the scancel command.
.TP
\fB\-w\fR, \fB\-\-nodelist=\fIhost1,host2,...\fR
-Cancel any jobs using any of the given hosts. The list may be specified as
-a comma\-separated list of hosts, a range of hosts (host[1\-5,7,...] for
-example), or a filename. The host list will be assumed to be a filename only
-if it contains a "/" character.
+Cancel any jobs using any of the given hosts. The list may be specified as
+a comma\-separated list of hosts, a range of hosts (host[1\-5,7,...] for
+example), or a filename. The host list will be assumed to be a filename only
+if it contains a "/" character.
.TP
\fB\-\-wckey\fR=\fIwckey\fR
@@ -108,23 +108,23 @@ The Slurm job ID to be signaled.
.TP
\fIstep_id\fP
-The step ID of the job step to be signaled.
+The step ID of the job step to be signaled.
If not specified, the operation is performed at the level of a job.
-If neither \fB\-\-batch\fR nor \fB\-\-signal\fR are used,
+If neither \fB\-\-batch\fR nor \fB\-\-signal\fR are used,
the entire job will be terminated.
When \fB\-\-batch\fR is used, the batch shell processes will be signaled.
-The child processes of the shell will not be signalled by SLURM, but
+The child processes of the shell will not be signalled by SLURM, but
the shell may forward the signal.
-When \fB\-\-batch\fR is not used but \fB\-\-signal\fR is used,
-then all job steps will be signalled, but the batch script itself
+When \fB\-\-batch\fR is not used but \fB\-\-signal\fR is used,
+then all job steps will be signalled, but the batch script itself
will not be signalled.
.SH "ENVIRONMENT VARIABLES"
.PP
-Some \fBscancel\fR options may be set via environment variables. These
+Some \fBscancel\fR options may be set via environment variables. These
environment variables, along with their corresponding options, are listed below.
(Note: commandline options will always override these settings)
.TP 20
@@ -166,15 +166,15 @@ The location of the SLURM configuration file.
.SH "NOTES"
.LP
-If multiple filters are supplied (e.g. \fB\-\-partition\fR and \fB\-\-name\fR)
+If multiple filters are supplied (e.g. \fB\-\-partition\fR and \fB\-\-name\fR)
only the jobs satisfying all of the filtering options will be signaled.
.LP
-If a signal value of "KILL" (the default value) is to be sent to an entire
-job, this will result in the job's termination and its resource allocation
+If a signal value of "KILL" (the default value) is to be sent to an entire
+job, this will result in the job's termination and its resource allocation
being released.
.LP
-Cancelling a job step will not result in a job being terminated.
-The job must be cancelled to release a resource allocation.
+Cancelling a job step will not result in a job being terminated.
+The job must be cancelled to release a resource allocation.
.SH "EXAMPLES"
.TP
diff --git a/doc/man/man1/scontrol.1 b/doc/man/man1/scontrol.1
index 5540b5bd687..836d1cba1a6 100644
--- a/doc/man/man1/scontrol.1
+++ b/doc/man/man1/scontrol.1
@@ -7,26 +7,26 @@ scontrol \- Used view and modify Slurm configuration and state.
\fBscontrol\fR [\fIOPTIONS\fR...] [\fICOMMAND\fR...]
.SH "DESCRIPTION"
-\fBscontrol\fR is used to view or modify Slurm configuration including: job,
-job step, node, partition, reservation, and overall system configuration. Most
-of the commands can only be executed by user root. If an attempt to view or modify
-configuration information is made by an unauthorized user, an error message
-will be printed and the requested action will not occur. If no command is
-entered on the execute line, \fBscontrol\fR will operate in an interactive
-mode and prompt for input. It will continue prompting for input and executing
-commands until explicitly terminated. If a command is entered on the execute
-line, \fBscontrol\fR will execute that command and terminate. All commands
-and options are case\-insensitive, although node names, partition names, and
-reservation names are case\-sensitive (node names "LX" and "lx" are distinct).
-All commands and options can be abbreviated to the extent that the
+\fBscontrol\fR is used to view or modify Slurm configuration including: job,
+job step, node, partition, reservation, and overall system configuration. Most
+of the commands can only be executed by user root. If an attempt to view or modify
+configuration information is made by an unauthorized user, an error message
+will be printed and the requested action will not occur. If no command is
+entered on the execute line, \fBscontrol\fR will operate in an interactive
+mode and prompt for input. It will continue prompting for input and executing
+commands until explicitly terminated. If a command is entered on the execute
+line, \fBscontrol\fR will execute that command and terminate. All commands
+and options are case\-insensitive, although node names, partition names, and
+reservation names are case\-sensitive (node names "LX" and "lx" are distinct).
+All commands and options can be abbreviated to the extent that the
specification is unique.
.SH "OPTIONS"
.TP
\fB\-a\fR, \fB\-\-all\fR
-When the \fIshow\fR command is used, then display all partitions, their jobs
-and jobs steps. This causes information to be displayed about partitions
-that are configured as hidden and partitions that are unavailable to user's
+When the \fIshow\fR command is used, then display all partitions, their jobs
+and jobs steps. This causes information to be displayed about partitions
+that are configured as hidden and partitions that are unavailable to user's
group.
.TP
\fB\-d\fR, \fB\-\-detail\fR
@@ -36,8 +36,8 @@ Causes the \fBshow\fR command to provide additional details where available.
Print a help message describing the usage of scontrol.
.TP
\fB\-\-hide\fR
-Do not display information about hidden partitions, their jobs and job steps.
-By default, neither partitions that are configured as hidden nor those partitions
+Do not display information about hidden partitions, their jobs and job steps.
+By default, neither partitions that are configured as hidden nor those partitions
unavailable to user's group will be displayed (i.e. this is the default behavior).
.TP
\fB\-o\fR, \fB\-\-oneliner\fR
@@ -47,7 +47,7 @@ Print information one line per record.
Print no warning or informational messages, only fatal error messages.
.TP
\fB\-v\fR, \fB\-\-verbose\fR
-Print detailed event logging. Multiple \fB\-v\fR's will further increase
+Print detailed event logging. Multiple \fB\-v\fR's will further increase
the verbosity of logging. By default only errors will be displayed.
.TP
@@ -58,7 +58,7 @@ Print version information and exit.
.TP
\fBall\fP
-Show all partitions, their jobs and jobs steps. This causes information to be
+Show all partitions, their jobs and jobs steps. This causes information to be
displayed about partitions that are configured as hidden and partitions that
are unavailable to user's group.
@@ -76,22 +76,22 @@ Acceptable values for \fICKPT_OP\fP include:
.RS
.TP
\fIdisable\fP (disable future checkpoints)
-.TP
+.TP
\fIenable\fP (enable future checkpoints)
.TP
\fIable\fP (test if presently not disabled, report start time if checkpoint in progress)
.TP
\fIcreate\fP (create a checkpoint and continue the job step)
.TP
-\fIvacate\fP (create a checkpoint and terminate the job step)
+\fIvacate\fP (create a checkpoint and terminate the job step)
.TP
-\fIerror\fP (report the result for the last checkpoint request, error code and message)
+\fIerror\fP (report the result for the last checkpoint request, error code and message)
.TP
\fIrestart\fP (restart execution of the previously checkpointed job steps)
.TP
Acceptable values for \fICKPT_OP\fP include:
.TP
-\fIMaxWait=<seconds>\fP maximum time for checkpoint to be written.
+\fIMaxWait=<seconds>\fP maximum time for checkpoint to be written.
Default value is 10 seconds.
Valid with \fIcreate\fP and \fIvacate\fP options only.
.TP
@@ -106,13 +106,13 @@ Valid with the \fIrestart\fP option only.
.TP
\fBcreate\fP \fISPECIFICATION\fP
-Create a new partition or reservation. See the full list of parameters
+Create a new partition or reservation. See the full list of parameters
below. Include the tag "res" to create a reservation without specifying
a reservation name.
.TP
\fBcompleting\fP
-Display all jobs in a COMPLETING state along with associated nodes in either a
+Display all jobs in a COMPLETING state along with associated nodes in either a
COMPLETING or DOWN state.
.TP
@@ -125,14 +125,14 @@ The two \fISPECIFICATION\fP choices are \fIPartitionName=<name>\fP and
.TP
\fBdetail\fP
Causes the \fIshow\fP command to provide additional details where available,
-namely the specific CPUs and NUMA memory allocated on each node.
+namely the specific CPUs and NUMA memory allocated on each node.
Note that on computers with hyperthreading enabled and SLURM configured to
allocate cores, each listed CPU represents one physical core.
Each hyperthread on that core can be allocated a separate task, so a job's
CPU count and task count may differ.
See the \fB\-\-cpu_bind\fR and \fB\-\-mem_bind\fR option descriptions in
srun man pages for more information.
-The \fBdetail\fP option is currently only supported for the \fIshow job\fP
+The \fBdetail\fP option is currently only supported for the \fIshow job\fP
command.
.TP
@@ -146,13 +146,13 @@ Display a description of scontrol options and commands.
.TP
\fBhide\fP
-Do not display partition, job or jobs step information for partitions that are
-configured as hidden or partitions that are unavailable to the user's group.
+Do not display partition, job or jobs step information for partitions that are
+configured as hidden or partitions that are unavailable to the user's group.
This is the default behavior.
.TP
\fBnotify\fP \fIjob_id\fP \fImessage\fP
-Send a message to standard error of the srun command associated with the
+Send a message to standard error of the srun command associated with the
specified \fIjob_id\fP.
.TP
@@ -161,7 +161,7 @@ Print information one line per record.
.TP
\fBpidinfo\fP \fIproc_id\fP
-Print the Slurm job id and scheduled termination time corresponding to the
+Print the Slurm job id and scheduled termination time corresponding to the
supplied process id, \fIproc_id\fP, on the current node. This will work only
with processes on node on which scontrol is run, and only for those processes
spawned by SLURM and their descendants.
@@ -170,11 +170,11 @@ spawned by SLURM and their descendants.
\fBlistpids\fP [\fIjob_id\fP[.\fIstep_id\fP]] [\fINodeName\fP]
Print a listing of the process IDs in a job step (if JOBID.STEPID is provided),
or all of the job steps in a job (if \fIjob_id\fP is provided), or all of the job
-steps in all of the jobs on the local node (if \fIjob_id\fP is not provided
-or \fIjob_id\fP is "*"). This will work only with processes on the node on
+steps in all of the jobs on the local node (if \fIjob_id\fP is not provided
+or \fIjob_id\fP is "*"). This will work only with processes on the node on
which scontrol is run, and only for those processes spawned by SLURM and
their descendants. Note that some SLURM configurations
-(\fIProctrackType\fP value of \fIpgid\fP or \fIaix\fP)
+(\fIProctrackType\fP value of \fIpgid\fP or \fIaix\fP)
are unable to identify all processes associated with a job or job step.
Note that the NodeName option is only really useful when you have multiple
@@ -183,7 +183,7 @@ one host are, in general, only used by SLURM developers.
.TP
\fBping\fP
-Ping the primary and secondary slurmctld daemon and report if
+Ping the primary and secondary slurmctld daemon and report if
they are responding.
.TP
@@ -196,18 +196,18 @@ Terminate the execution of scontrol.
.TP
\fBreconfigure\fP
-Instruct all Slurm daemons to re\-read the configuration file.
+Instruct all Slurm daemons to re\-read the configuration file.
This command does not restart the daemons.
-This mechanism would be used to modify configuration parameters (Epilog,
-Prolog, SlurmctldLogFile, SlurmdLogFile, etc.) register the physical
-addition or removal of nodes from the cluster or recognize the change
-of a node's configuration, such as the addition of memory or processors.
-The Slurm controller (slurmctld) forwards the request all other daemons
+This mechanism would be used to modify configuration parameters (Epilog,
+Prolog, SlurmctldLogFile, SlurmdLogFile, etc.) register the physical
+addition or removal of nodes from the cluster or recognize the change
+of a node's configuration, such as the addition of memory or processors.
+The Slurm controller (slurmctld) forwards the request all other daemons
(slurmd daemon on each compute node). Running jobs continue execution.
-Most configuration parameters can be changed by just running this command,
-however, SLURM daemons should be shutdown and restarted if any of these
-parameters are to be changed: AuthType, BackupAddr, BackupController,
-ControlAddr, ControlMach, PluginDir, StateSaveLocation, SlurmctldPort
+Most configuration parameters can be changed by just running this command,
+however, SLURM daemons should be shutdown and restarted if any of these
+parameters are to be changed: AuthType, BackupAddr, BackupController,
+ControlAddr, ControlMach, PluginDir, StateSaveLocation, SlurmctldPort
or SlurmdPort.
.TP
@@ -221,93 +221,93 @@ Requeue a running or pending SLURM batch job.
.TP
\fBsetdebug\fP \fILEVEL\fP
Change the debug level of the slurmctld daemon.
-\fILEVEL\fP may be an integer value between zero and nine (using the
-same values as \fISlurmctldDebug\fP in the \fIslurm.conf\fP file) or
-the name of the most detailed message type to be printed:
-"quiet", "fatal", "error", "info", "verbose", "debug", "debug2", "debug3",
+\fILEVEL\fP may be an integer value between zero and nine (using the
+same values as \fISlurmctldDebug\fP in the \fIslurm.conf\fP file) or
+the name of the most detailed message type to be printed:
+"quiet", "fatal", "error", "info", "verbose", "debug", "debug2", "debug3",
"debug4", or "debug5".
-This value is temporary and will be overwritten whenever the slurmctld
-daemon reads the slurm.conf configuration file (e.g. when the daemon
+This value is temporary and will be overwritten whenever the slurmctld
+daemon reads the slurm.conf configuration file (e.g. when the daemon
is restarted or \fBscontrol reconfigure\fR is executed).
.TP
\fBshow\fP \fIENTITY\fP \fIID\fP
Display the state of the specified entity with the specified identification.
-\fIENTITY\fP may be \fIconfig\fP, \fIdaemons\fP, \fIjob\fP, \fInode\fP,
+\fIENTITY\fP may be \fIconfig\fP, \fIdaemons\fP, \fIjob\fP, \fInode\fP,
\fIpartition\fP, \fIreservation\fP, \fIslurmd\fP, \fIstep\fP, \fItopology\fP,
-\fIhostlist\fP or \fIhostnames\fP
+\fIhostlist\fP or \fIhostnames\fP
(also \fIblock\fP or \fIsubbp\fP on BlueGene systems).
-\fIID\fP can be used to identify a specific element of the identified
-entity: the configuration parameter name, job ID, node name, partition name,
-reservation name, or job step ID for \fIconfig\fP, \fIjob\fP, \fInode\fP,
-\fIpartition\fP, or \fIstep\fP respectively.
+\fIID\fP can be used to identify a specific element of the identified
+entity: the configuration parameter name, job ID, node name, partition name,
+reservation name, or job step ID for \fIconfig\fP, \fIjob\fP, \fInode\fP,
+\fIpartition\fP, or \fIstep\fP respectively.
For an \fIENTITY\fP of \fItopology\fP, the \fIID\fP may be a node or switch name.
-If one node name is specified, all switches connected to that node (and
+If one node name is specified, all switches connected to that node (and
their parent switches) will be shown.
-If more than one node name is specified, only switches that connect to all
+If more than one node name is specified, only switches that connect to all
named nodes will be shown.
-\fIhostnames\fP takes an optional hostlist expression as input and
-writes a list of individual host names to standard output (one per
-line). If no hostlist expression is supplied, the contents of the
-SLURM_NODELIST environment variable is used. For example "tux[1\-3]"
+\fIhostnames\fP takes an optional hostlist expression as input and
+writes a list of individual host names to standard output (one per
+line). If no hostlist expression is supplied, the contents of the
+SLURM_NODELIST environment variable is used. For example "tux[1\-3]"
is mapped to "tux1","tux2" and "tux3" (one hostname per line).
-\fIhostlist\fP takes a list of host names and prints the hostlist
-expression for them (the inverse of \fIhostnames\fP).
-\fIhostlist\fP can also take the absolute pathname of a file
+\fIhostlist\fP takes a list of host names and prints the hostlist
+expression for them (the inverse of \fIhostnames\fP).
+\fIhostlist\fP can also take the absolute pathname of a file
(beginning with the character '/') containing a list of hostnames.
-Multiple node names may be specified using simple node range expressions
-(e.g. "lx[10\-20]"). All other \fIID\fP values must identify a single
+Multiple node names may be specified using simple node range expressions
+(e.g. "lx[10\-20]"). All other \fIID\fP values must identify a single
element. The job step ID is of the form "job_id.step_id", (e.g. "1234.1").
-\fIslurmd\fP reports the current status of the slurmd daemon executing
-on the same node from which the scontrol command is executed (the
+\fIslurmd\fP reports the current status of the slurmd daemon executing
+on the same node from which the scontrol command is executed (the
local host). It can be useful to diagnose problems.
By default, all elements of the entity type specified are printed.
.TP
\fBshutdown\fP \fIOPTION\fP
Instruct Slurm daemons to save current state and terminate.
-By default, the Slurm controller (slurmctld) forwards the request all
-other daemons (slurmd daemon on each compute node).
-An \fIOPTION\fP of \fIslurmctld\fP or \fIcontroller\fP results in
-only the slurmctld daemon being shutdown and the slurmd daemons
+By default, the Slurm controller (slurmctld) forwards the request all
+other daemons (slurmd daemon on each compute node).
+An \fIOPTION\fP of \fIslurmctld\fP or \fIcontroller\fP results in
+only the slurmctld daemon being shutdown and the slurmd daemons
remaining active.
.TP
\fBsuspend\fP \fIjob_id\fP
Suspend a running job.
Use the \fIresume\fP command to resume its execution.
-User processes must stop on receipt of SIGSTOP signal and resume
+User processes must stop on receipt of SIGSTOP signal and resume
upon receipt of SIGCONT for this operation to be effective.
Not all architectures and configurations support job suspension.
.TP
\fBtakeover\fP
Instruct SLURM's backup controller (slurmctld) to take over system control.
-SLURM's backup controller requests control from the primary and waits for
+SLURM's backup controller requests control from the primary and waits for
its termination. After that, it switches from backup mode to controller
-mode. If primary controller can not be contacted, it directly switches to
-controller mode. This can be used to speed up the SLURM controller
+mode. If primary controller can not be contacted, it directly switches to
+controller mode. This can be used to speed up the SLURM controller
fail\-over mechanism when the primary node is down.
This can be used to minimize disruption if the computer executing the
primary SLURM controller is scheduled down.
(Note: SLURM's primary controller will take the control back at startup.)
.TP
-\fBupdate\fP \fISPECIFICATION\fP
-Update job, node, partition, or reservation configuration per the supplied
-specification. \fISPECIFICATION\fP is in the same format as the Slurm
+\fBupdate\fP \fISPECIFICATION\fP
+Update job, node, partition, or reservation configuration per the supplied
+specification. \fISPECIFICATION\fP is in the same format as the Slurm
configuration file and the output of the \fIshow\fP command described above. It
-may be desirable to execute the \fIshow\fP command (described above) on the
-specific entity you which to update, then use cut\-and\-paste tools to enter
-updated configuration values to the \fIupdate\fP. Note that while most
-configuration values can be changed using this command, not all can be changed
-using this mechanism. In particular, the hardware configuration of a node or
-the physical addition or removal of nodes from the cluster may only be
+may be desirable to execute the \fIshow\fP command (described above) on the
+specific entity you which to update, then use cut\-and\-paste tools to enter
+updated configuration values to the \fIupdate\fP. Note that while most
+configuration values can be changed using this command, not all can be changed
+using this mechanism. In particular, the hardware configuration of a node or
+the physical addition or removal of nodes from the cluster may only be
accomplished through editing the Slurm configuration file and executing the \fIreconfigure\fP command (described above).
.TP
\fBverbose\fP
-Print detailed event logging.
+Print detailed event logging.
This includes time\-stamps on data structures, record counts, etc.
.TP
@@ -327,11 +327,11 @@ Value may be cleared with blank data value, "Account=".
.TP
\fIConnection\fP=<type>
Reset the node connection type.
-Possible values on Blue Gene are "MESH", "TORUS" and "NAV"
+Possible values on Blue Gene are "MESH", "TORUS" and "NAV"
(mesh else torus).
.TP
\fIContiguous\fP=<yes|no>
-Set the job's requirement for contiguous (consecutive) nodes to be allocated.
+Set the job's requirement for contiguous (consecutive) nodes to be allocated.
Possible values are "YES" and "NO".
.TP
\fIDependency\fP=<job_id>
@@ -339,8 +339,8 @@ Defer job's initiation until specified job_id completes.
Cancel dependency with job_id value of "0", "Dependency=0".
.TP
\fIExcNodeList\fP=<nodes>
-Set the job's list of excluded node. Multiple node names may be
-specified using simple node range expressions (e.g. "lx[10\-20]").
+Set the job's list of excluded node. Multiple node names may be
+specified using simple node range expressions (e.g. "lx[10\-20]").
Value may be cleared with blank data value, "ExcNodeList=".
.TP
\fIExitCode\fP=<exit>:<sig>
@@ -350,15 +350,15 @@ The second number of the signal that caused the process to terminate if
it was terminated by a signal.
.TP
\fIFeatures\fP=<features>
-Set the job's required node features. Multiple values
-may be comma separated if all features are required (AND operation) or
+Set the job's required node features. Multiple values
+may be comma separated if all features are required (AND operation) or
separated by "|" if any of the specified features are required (OR operation).
Value may be cleared with blank data value, "Features=".
.TP
\fIGeometry\fP=<geo>
Reset the required job geometry.
-On Blue Gene the value should be three digits separated by
-"x" or ",". The digits represent the allocation size in
+On Blue Gene the value should be three digits separated by
+"x" or ",". The digits represent the allocation size in
X, Y and Z dimensions (e.g. "2x3x4").
.TP
\fIRotate\fP=<yes|no>
@@ -369,7 +369,7 @@ Possible values are "YES" and "NO".
Identify the job to be updated. This specification is required.
.TP
\fIMinMemoryCPU\fP=<megabytes>
-Set the job's minimum real memory required per allocated CPU to the specified
+Set the job's minimum real memory required per allocated CPU to the specified
value.
Either \fIMinMemoryCPU\fP or \fIMinMemoryNode\fP may be set, but not both.
.TP
@@ -389,7 +389,7 @@ Set the job's name to the specified value.
\fINice\fP[=delta]
Adjust job's priority by the specified value. Default value is 100.
The adjustment range is from \-10000 (highest priority)
-to 10000 (lowest priority).
+to 10000 (lowest priority).
Nice value changes are not additive, but overwrite any prior nice
value and are applied to the job's base priority.
Only privileged users can specify a negative adjustment.
@@ -414,8 +414,8 @@ Explicitly setting a job's priority clears any previously set nice value.
Set the job's count of minimum cores per socket to the specified value.
.TP
\fIReqNodeList\fP=<nodes>
-Set the job's list of required node. Multiple node names may be specified using
-simple node range expressions (e.g. "lx[10\-20]").
+Set the job's list of required node. Multiple node names may be specified using
+simple node range expressions (e.g. "lx[10\-20]").
Value may be cleared with blank data value, "ReqNodeList=".
.TP
\fIReqSockets\fP=<count>
@@ -437,7 +437,7 @@ You may also specify \fImidnight\fR, \fInoon\fR, or
\fIteatime\fR (4pm) and you can have a time\-of\-day suffixed
with \fIAM\fR or \fIPM\fR for running in the morning or the evening.
You can also say what day the job will be run, by specifying
-a date of the form \fIMMDDYY\fR or \fIMM/DD/YY\fR or \fIMM.DD.YY\fR,
+a date of the form \fIMMDDYY\fR or \fIMM/DD/YY\fR or \fIMM.DD.YY\fR,
or a date and time as \fIYYYY\-MM\-DD[THH:MM[:SS]]\fR. You can also
give times like \fInow + count time\-units\fR, where the time\-units
can be \fIminutes\fR, \fIhours\fR, \fIdays\fR, or \fIweeks\fR
@@ -462,10 +462,10 @@ already passed for that year, in which case the next year is used.
\fITimeLimit\fP=<time>
The job's time limit.
Output format is [days\-]hours:minutes:seconds or "UNLIMITED".
-Input format (for \fBupdate\fR command) set is minutes, minutes:seconds,
-hours:minutes:seconds, days\-hours, days\-hours:minutes or
+Input format (for \fBupdate\fR command) set is minutes, minutes:seconds,
+hours:minutes:seconds, days\-hours, days\-hours:minutes or
days\-hours:minutes:seconds.
-Time resolution is one minute and second values are rounded up to
+Time resolution is one minute and second values are rounded up to
the next minute.
.TP
@@ -509,7 +509,7 @@ The user and group under which the job was submitted.
\fBSPECIFICATIONS FOR UPDATE COMMAND, NODES\fR
.TP
\fINodeName\fP=<name>
-Identify the node(s) to be updated. Multiple node names may be specified using
+Identify the node(s) to be updated. Multiple node names may be specified using
simple node range expressions (e.g. "lx[10\-20]"). This specification is required.
.TP
\fIFeatures\fP=<features>
@@ -522,37 +522,37 @@ slurm.conf with any changes meant to be persistent.
.TP
\fIReason\fP=<reason>
-Identify the reason the node is in a "DOWN" or "DRAINED", "DRAINING",
+Identify the reason the node is in a "DOWN" or "DRAINED", "DRAINING",
"FAILING" or "FAIL" state.
Use quotes to enclose a reason having more than one word.
.TP
\fIState\fP=<state>
-Identify the state to be assigned to the node. Possible values are "NoResp",
+Identify the state to be assigned to the node. Possible values are "NoResp",
"ALLOC", "ALLOCATED", "DOWN", "DRAIN", "FAIL", "FAILING", "IDLE", "MAINT",
-"POWER_DOWN", "POWER_UP", or "RESUME".
-If you want to remove a node from service, you typically want to set
-it's state to "DRAIN".
-"FAILING" is similar to "DRAIN" except that some applications will
+"POWER_DOWN", "POWER_UP", or "RESUME".
+If you want to remove a node from service, you typically want to set
+it's state to "DRAIN".
+"FAILING" is similar to "DRAIN" except that some applications will
seek to relinquish those nodes before the job completes.
-"RESUME" is not an actual node state, but will return a "DRAINED", "DRAINING",
+"RESUME" is not an actual node state, but will return a "DRAINED", "DRAINING",
or "DOWN" node to service, either "IDLE" or "ALLOCATED" state as appropriate.
Setting a node "DOWN" will cause all running and suspended jobs on that
node to be terminated.
"POWER_DOWN" and "POWER_UP" will use the configured \fISuspendProg\fR and
-\fIResumeProg\fR programs to explicitly place a node in or out of a power
+\fIResumeProg\fR programs to explicitly place a node in or out of a power
saving mode.
The "NoResp" state will only set the "NoResp" flag for a node without
changing its underlying state.
While all of the above states are valid, some of them are not valid new
-node states given their prior state.
+node states given their prior state.
Generally only "DRAIN", "FAIL" and "RESUME" should be used.
.TP
\fIWeight\fP=<weight>
-Identify weight to be associated with specified nodes. This allows
-dynamic changes to weight associated with nodes, which will be used
-for the subsequent node allocation decisions.
+Identify weight to be associated with specified nodes. This allows
+dynamic changes to weight associated with nodes, which will be used
+for the subsequent node allocation decisions.
Any previously identified weight will be overwritten with the new value.\fBNOTE:\fR The \fIWeight\fP associated with nodes will be reset to
the values specified in slurm.conf (if any) upon slurmctld restart
or reconfiguration.
@@ -562,27 +562,27 @@ Update slurm.conf with any changes meant to be persistent.
\fBSPECIFICATIONS FOR CREATE, UPDATE, AND DELETE COMMANDS, PARTITIONS\fR
.TP
\fIAllowGroups\fP=<name>
-Identify the user groups which may use this partition.
-Multiple groups may be specified in a comma separated list.
+Identify the user groups which may use this partition.
+Multiple groups may be specified in a comma separated list.
To permit all groups to use the partition specify "AllowGroups=ALL".
.TP
\fIDefault\fP=<yes|no>
-Specify if this partition is to be used by jobs which do not explicitly
-identify a partition to use.
+Specify if this partition is to be used by jobs which do not explicitly
+identify a partition to use.
Possible output values are "YES" and "NO".
-In order to change the default partition of a running system,
+In order to change the default partition of a running system,
use the scontrol update command and set Default=yes for the partition
that you want to become the new default.
.TP
\fIHidden\fP=<yes|no>
-Specify if the partition and its jobs should be hidden from view.
-Hidden partitions will by default not be reported by SLURM APIs
-or commands.
+Specify if the partition and its jobs should be hidden from view.
+Hidden partitions will by default not be reported by SLURM APIs
+or commands.
Possible values are "YES" and "NO".
.TP
\fIMaxNodes\fP=<count>
-Set the maximum number of nodes which will be allocated to any single job
+Set the maximum number of nodes which will be allocated to any single job
in the partition. Specify a number, "INFINITE" or "UNLIMITED". (On a
Bluegene type system this represents a c\-node count.)
@@ -590,21 +590,21 @@ Bluegene type system this represents a c\-node count.)
\fIMaxTime\fP=<time>
The maximum run time for jobs.
Output format is [days\-]hours:minutes:seconds or "UNLIMITED".
-Input format (for \fBupdate\fR command) is minutes, minutes:seconds,
-hours:minutes:seconds, days\-hours, days\-hours:minutes or
+Input format (for \fBupdate\fR command) is minutes, minutes:seconds,
+hours:minutes:seconds, days\-hours, days\-hours:minutes or
days\-hours:minutes:seconds.
-Time resolution is one minute and second values are rounded up to
+Time resolution is one minute and second values are rounded up to
the next minute.
.TP
\fIMinNodes\fP=<count>
-Set the minimum number of nodes which will be allocated to any single job
+Set the minimum number of nodes which will be allocated to any single job
in the partition. (On a Bluegene type system this represents a c\-node count.)
.TP
\fINodes\fP=<name>
-Identify the node(s) to be associated with this partition. Multiple node names
-may be specified using simple node range expressions (e.g. "lx[10\-20]").
+Identify the node(s) to be associated with this partition. Multiple node names
+may be specified using simple node range expressions (e.g. "lx[10\-20]").
Note that jobs may only be associated with one partition at any time.
Specify a blank data value to remove all nodes from a partition: "Nodes=".
@@ -614,23 +614,23 @@ Identify the partition to be updated. This specification is required.
.TP
\fIRootOnly\fP=<yes|no>
-Specify if only allocation requests initiated by user root will be satisfied.
-This can be used to restrict control of the partition to some meta\-scheduler.
+Specify if only allocation requests initiated by user root will be satisfied.
+This can be used to restrict control of the partition to some meta\-scheduler.
Possible values are "YES" and "NO".
.TP
\fIShared\fP=<yes|no|exclusive|force>[:<job_count>]
-Specify if nodes in this partition can be shared by multiple jobs.
+Specify if nodes in this partition can be shared by multiple jobs.
Possible values are "YES", "NO", "EXCLUSIVE" and "FORCE".
An optional job count specifies how many jobs can be allocated to use
each resource.
.TP
\fIState\fP=<up|down>
-Specify if jobs can be allocated nodes in this partition.
+Specify if jobs can be allocated nodes in this partition.
Possible values are"UP" and "DOWN".
-If a partition allocated nodes to running jobs, those jobs will continue
-execution even after the partition's state is set to "DOWN". The jobs
+If a partition allocated nodes to running jobs, those jobs will continue
+execution even after the partition's state is set to "DOWN". The jobs
must be explicitly canceled to force their termination.
.TP
@@ -639,16 +639,16 @@ must be explicitly canceled to force their termination.
.TP
\fIReservation\fP=<name>
-Identify the name of the reservation to be created, updated, or deleted.
-This parameter is required for update and is the only parameter for delete.
-For create, if you do not want to give a reservation name, use
+Identify the name of the reservation to be created, updated, or deleted.
+This parameter is required for update and is the only parameter for delete.
+For create, if you do not want to give a reservation name, use
"scontrol create res ..." and a name will be created automatically.
.TP
\fILicenses\fP=<license>
-Specification of licenses (or other resources available on all
+Specification of licenses (or other resources available on all
nodes of the cluster) which are to be reserved.
-License names can be followed by an asterisk and count
+License names can be followed by an asterisk and count
(the default count is one).
Multiple license names should be comma separated (e.g.
"Licenses=foo*4,bar").
@@ -660,14 +660,14 @@ NodeCnt or Nodes.
.TP
\fINodes\fP=<name>
-Identify the node(s) to be reserved. Multiple node names
-may be specified using simple node range expressions (e.g. "Nodes=lx[10\-20]").
+Identify the node(s) to be reserved. Multiple node names
+may be specified using simple node range expressions (e.g. "Nodes=lx[10\-20]").
Specify a blank data value to remove all nodes from a reservation: "Nodes=".
A new reservation must specify either NodeCnt or Nodes.
.TP
\fIStartTime\fP=<time_spec>
-The start time for the reservation. A new reservation must specify a start
+The start time for the reservation. A new reservation must specify a start
time. It accepts times of the form \fIHH:MM:SS\fR for
a specific time of day (seconds are optional).
(If that time is already past, the next day is assumed.)
@@ -675,7 +675,7 @@ You may also specify \fImidnight\fR, \fInoon\fR, or
\fIteatime\fR (4pm) and you can have a time\-of\-day suffixed
with \fIAM\fR or \fIPM\fR for running in the morning or the evening.
You can also say what day the job will be run, by specifying
-a date of the form \fIMMDDYY\fR or \fIMM/DD/YY\fR or \fIMM.DD.YY\fR,
+a date of the form \fIMMDDYY\fR or \fIMM/DD/YY\fR or \fIMM.DD.YY\fR,
or a date and time as \fIYYYY\-MM\-DD[THH:MM[:SS]]\fR. You can also
give times like \fInow + count time\-units\fR, where the time\-units
can be \fIminutes\fR, \fIhours\fR, \fIdays\fR, or \fIweeks\fR
@@ -685,15 +685,15 @@ and you can tell SLURM to run the job today with the keyword
.TP
\fIEndTime\fP=<time_spec>
-The end time for the reservation. A new reservation must specify an end
+The end time for the reservation. A new reservation must specify an end
time or a duration. Valid formats are the same as for StartTime.
.TP
\fIDuration\fP=<time>
-The length of a reservation. A new reservation must specify an end
-time or a duration. Valid formats are minutes, minutes:seconds,
-hours:minutes:seconds, days\-hours, days\-hours:minutes,
-days\-hours:minutes:seconds, or UNLIMITED. Time resolution is one minute and
+The length of a reservation. A new reservation must specify an end
+time or a duration. Valid formats are minutes, minutes:seconds,
+hours:minutes:seconds, days\-hours, days\-hours:minutes,
+days\-hours:minutes:seconds, or UNLIMITED. Time resolution is one minute and
second values are rounded up to the next minute.
.TP
@@ -702,25 +702,25 @@ Identify the partition to be reserved.
.TP
\fIFlags\fP=<flags>
-Flags associated with the reservation.
-In order to remove a flag with the update option, preceed the name with
-a minus sign. For example: Flags=\-DAILY (NOTE: this option is not supported
+Flags associated with the reservation.
+In order to remove a flag with the update option, preceed the name with
+a minus sign. For example: Flags=\-DAILY (NOTE: this option is not supported
for all flags).
Currently supported flags include:
.RS
.TP 12
\fIMAINT\fR
Maintenance mode, receives special accounting treatment.
-This partition is permitted to use resources that are already in another
+This partition is permitted to use resources that are already in another
reservation.
.TP
\fIOVERLAP\fR
-This reservation can be allocated resources that are already in another
+This reservation can be allocated resources that are already in another
reservation.
.TP
\fIIGNORE_JOBS\fR
Ignore currently running jobs when creating the reservation.
-This can be especially useful when reserving all nodes in the system
+This can be especially useful when reserving all nodes in the system
for maintenance.
.TP
\fIDAILY\fR
@@ -735,20 +735,20 @@ Reservation is for specific nodes (output only)
.TP
\fIFeatures\fP=<features>
-Set the reservation's required node features. Multiple values
-may be "&" separated if all features are required (AND operation) or
+Set the reservation's required node features. Multiple values
+may be "&" separated if all features are required (AND operation) or
separated by "|" if any of the specified features are required (OR operation).
Value may be cleared with blank data value, "Features=".
.TP
\fIUsers\fP=<user list>
-List of users permitted to use the reserved nodes.
+List of users permitted to use the reserved nodes.
E.g. Users=jones1,smith2.
A new reservation must specify Users and/or Accounts.
.TP
\fIAccounts\fP=<account list>
-List of accounts permitted to use the reserved nodes.
+List of accounts permitted to use the reserved nodes.
E.g. Accounts=physcode1,physcode2. A user in any of the accounts
may use the reserved nodes.
A new reservation must specify Users and/or Accounts.
@@ -756,13 +756,13 @@ A new reservation must specify Users and/or Accounts.
.TP
\fBSPECIFICATIONS FOR UPDATE, BLOCK \fR
.TP
-Bluegene systems only!
+Bluegene systems only!
.TP
\fIBlockName\fP=<name>
Identify the bluegene block to be updated. This specification is required.
.TP
\fIState\fP=<free|error|remove>
-This will update the state of a bluegene block to either FREE or ERROR.
+This will update the state of a bluegene block to either FREE or ERROR.
(i.e. update BlockName=RMP0 STATE=ERROR) State error will not allow jobs
to run on the block. \fBWARNING!!!!\fR This will cancel any
running job on the block! On dynamically laid out systems REMOVE will
@@ -774,8 +774,8 @@ Identify the bluegene ionodes to be updated (i.e. bg000[0\-3]). This
specification is required.
.TP
-.SH "ENVIRONMENT VARIABLES"
-.PP
+.SH "ENVIRONMENT VARIABLES"
+.PP
Some \fBscontrol\fR options may
be set via environment variables. These environment variables,
along with their corresponding options, are listed below. (Note:
@@ -789,37 +789,37 @@ The location of the SLURM configuration file.
.SH "EXAMPLES"
.eo
-.br
+.br
# scontrol
-.br
+.br
scontrol: show part class
-.br
+.br
PartitionName=class TotalNodes=10 TotalCPUs=20 RootOnly=NO
-.br
+.br
Default=NO Shared=NO State=UP MaxTime=0:30:00 Hidden=NO
.br
MinNodes=1 MaxNodes=2 AllowGroups=students
.br
Nodes=lx[0031-0040] NodeIndices=31,40,-1
-.br
+.br
scontrol: update PartitionName=class MaxTime=60:00 MaxNodes=4
-.br
+.br
scontrol: show job 65539
-.br
+.br
JobId=65539 UserId=1500 JobState=PENDING TimeLimit=0:20:00
-.br
- Priority=100 Partition=batch Name=job01 NodeList=(null)
-.br
+.br
+ Priority=100 Partition=batch Name=job01 NodeList=(null)
+.br
StartTime=0 EndTime=0 Shared=0 ReqProcs=1000
.br
ReqNodes=400 Contiguous=1 MinCPUs=4 MinMemoryNode=1024
-.br
- MinTmpDisk=2034 ReqNodeList=lx[3000-3003]
.br
- Features=(null) JobScript=/bin/hostname
-.br
+ MinTmpDisk=2034 ReqNodeList=lx[3000-3003]
+.br
+ Features=(null) JobScript=/bin/hostname
+.br
scontrol: update JobId=65539 TimeLimit=30:00 Priority=500
-.br
+.br
scontrol: show hostnames tux[1-3]
.br
tux1
@@ -860,16 +860,16 @@ details.
.LP
/etc/slurm.conf
.SH "SEE ALSO"
-\fBscancel\fR(1), \fBsinfo\fR(1), \fBsqueue\fR(1),
+\fBscancel\fR(1), \fBsinfo\fR(1), \fBsqueue\fR(1),
\fBslurm_checkpoint\fR(3),
\fBslurm_create_partition\fR(3),
\fBslurm_delete_partition\fR(3),
-\fBslurm_load_ctl_conf\fR(3),
-\fBslurm_load_jobs\fR(3), \fBslurm_load_node\fR(3),
-\fBslurm_load_partitions\fR(3),
+\fBslurm_load_ctl_conf\fR(3),
+\fBslurm_load_jobs\fR(3), \fBslurm_load_node\fR(3),
+\fBslurm_load_partitions\fR(3),
\fBslurm_reconfigure\fR(3), \fBslurm_requeue\fR(3), \fBslurm_resume\fR(3),
\fBslurm_shutdown\fR(3), \fBslurm_suspend\fR(3),
\fBslurm_takeover\fR(3),
-\fBslurm_update_job\fR(3), \fBslurm_update_node\fR(3),
+\fBslurm_update_job\fR(3), \fBslurm_update_node\fR(3),
\fBslurm_update_partition\fR(3),
\fBslurm.conf\fR(5)
diff --git a/doc/man/man1/sinfo.1 b/doc/man/man1/sinfo.1
index a3dab17322b..0b876f96995 100644
--- a/doc/man/man1/sinfo.1
+++ b/doc/man/man1/sinfo.1
@@ -4,16 +4,16 @@
sinfo \- view information about SLURM nodes and partitions.
.SH "SYNOPSIS"
-\fBsinfo\fR [\fIOPTIONS\fR...]
+\fBsinfo\fR [\fIOPTIONS\fR...]
.SH "DESCRIPTION"
-\fBsinfo\fR is used to view partition and node information for a
-system running SLURM.
+\fBsinfo\fR is used to view partition and node information for a
+system running SLURM.
.SH "OPTIONS"
.TP
\fB\-a\fR, \fB\-\-all\fR
-Display information about all partions. This causes information to be
+Display information about all partions. This causes information to be
displayed about partitions that are configured as hidden and partitions that
are unavailable to user's group.
@@ -43,26 +43,26 @@ Print a message describing all \fBsinfo\fR options.
.TP
\fB\-\-hide\fR
-Do not display information about hidden partitions. By default, partitions
-that are configured as hidden or are not available to the user's group
+Do not display information about hidden partitions. By default, partitions
+that are configured as hidden or are not available to the user's group
will not be displayed (i.e. this is the default behavior).
.TP
\fB\-i <seconds>\fR, \fB\-\-iterate=<seconds>\fR
-Print the state on a periodic basis.
+Print the state on a periodic basis.
Sleep for the indicated number of seconds between reports.
By default, prints a time stamp with the header.
.TP
\fB\-l\fR, \fB\-\-long\fR
-Print more detailed information.
+Print more detailed information.
This is ignored if the \fB\-\-format\fR option is specified.
.TP
\fB\-n <nodes>\fR, \fB\-\-nodes=<nodes>\fR
-Print information only about the specified node(s).
-Multiple nodes may be comma separated or expressed using a
-node range expression. For example "linux[00\-07]" would
+Print information only about the specified node(s).
+Multiple nodes may be comma separated or expressed using a
+node range expression. For example "linux[00\-07]" would
indicate eight nodes, "linux00" through "linux07."
.TP
@@ -80,10 +80,10 @@ when running with various options are
.TP 15
.I "default"
"%9P %5a %.10l %.5D %6t %N"
-.TP
+.TP
.I "\-\-summarize"
"%9P %5a %.10l %15F %N"
-.TP
+.TP
.I "\-\-long"
"%9P %5a %.10l %.8s %4r %5h %10g %.5D %11T %N"
.TP
@@ -104,18 +104,18 @@ when running with various options are
In the above format strings the use of "#" represents the
maximum length of an node list to be printed.
.IP
-The field specifications available include:
+The field specifications available include:
.RS
.TP 4
-\fB%a\fR
+\fB%a\fR
State/availability of a partition
.TP
-\fB%A\fR
+\fB%A\fR
Number of nodes by state in the format "allocated/idle".
Do not use this with a node state option ("%t" or "%T") or
the different node states will be placed on separate lines.
.TP
-\fB%c\fR
+\fB%c\fR
Number of CPUs per node
.TP
\fB%C\fR
@@ -124,91 +124,91 @@ Number of CPUs by state in the format
state option ("%t" or "%T") or the different node states will
be placed on separate lines.
.TP
-\fB%d\fR
+\fB%d\fR
Size of temporary disk space per node in megabytes
.TP
-\fB%D\fR
+\fB%D\fR
Number of nodes
.TP
\fB%E\fR
The reason a node is unavailable (down, drained, or draining states).
-This is the same as \fB%R\fR except the entries will be sorted by
+This is the same as \fB%R\fR except the entries will be sorted by
time rather than the reason string.
.TP
-\fB%f\fR
+\fB%f\fR
Features associated with the nodes
.TP
-\fB%F\fR
+\fB%F\fR
Number of nodes by state in the format
"allocated/idle/other/total". Do not use this with a node
state option ("%t" or "%T") or the different node states will
be placed on separate lines.
.TP
-\fB%g\fR
+\fB%g\fR
Groups which may use the nodes
.TP
-\fB%h\fR
+\fB%h\fR
Jobs may share nodes, "yes", "no", or "force"
.TP
-\fB%l\fR
+\fB%l\fR
Maximum time for any job in the format "days\-hours:minutes:seconds"
.TP
\fB%L\fR
Default time for any job in the format "days\-hours:minutes:seconds"
.TP
-\fB%m\fR
+\fB%m\fR
Size of memory per node in megabytes
.TP
-\fB%N\fR
+\fB%N\fR
List of node names
.TP
-\fB%P\fR
+\fB%P\fR
Partition name
.TP
-\fB%r\fR
+\fB%r\fR
Only user root may initiate jobs, "yes" or "no"
.TP
-\fB%R\fR
-The reason a node is unavailable (down, drained, draining,
+\fB%R\fR
+The reason a node is unavailable (down, drained, draining,
fail or failing states)
.TP
-\fB%s\fR
+\fB%s\fR
Maximum job size in nodes
.TP
-\fB%S\fR
+\fB%S\fR
Allowed allocating nodes
.TP
-\fB%t\fR
+\fB%t\fR
State of nodes, compact form
.TP
-\fB%T\fR
+\fB%T\fR
State of nodes, extended form
.TP
-\fB%w\fR
+\fB%w\fR
Scheduling weight of the nodes
.TP
-\fB%X\fR
+\fB%X\fR
Number of sockets per node
.TP
-\fB%Y\fR
+\fB%Y\fR
Number of cores per socket
.TP
-\fB%Z\fR
+\fB%Z\fR
Number of threads per core
.TP
-\fB%z\fR
+\fB%z\fR
Extended processor information: number of sockets, cores, threads (S:C:T) per node
.TP
-\fB%.<*>\fR
+\fB%.<*>\fR
right justification of the field
.TP
-\fB%<Number><*>\fR
+\fB%<Number><*>\fR
size of field
.RE
.TP
\fB\-p <partition>\fR, \fB\-\-partition=<partition>\fR
-Print information only about the specified partition.
+Print information only about the specified partition.
.TP
\fB\-r\fR, \fB\-\-responding\fR
@@ -216,16 +216,16 @@ If set only report state information for responding nodes.
.TP
\fB\-R\fR, \fB\-\-list\-reasons\fR
-List reasons nodes are in the down, drained, fail or failing state.
-When nodes are in these states SLURM supports optional inclusion
-of a "reason" string by an administrator.
-This option will display the first 35 characters of the reason
-field and list of nodes with that reason for all nodes that are,
-by default, down, drained, draining or failing.
-This option may be used with other node filtering options
+List reasons nodes are in the down, drained, fail or failing state.
+When nodes are in these states SLURM supports optional inclusion
+of a "reason" string by an administrator.
+This option will display the first 35 characters of the reason
+field and list of nodes with that reason for all nodes that are,
+by default, down, drained, draining or failing.
+This option may be used with other node filtering options
(e.g. \fB\-r\fR, \fB\-d\fR, \fB\-t\fR, \fB\-n\fR),
-however, combinations of these options that result in a
-list of nodes that are not down or drained or failing will
+however, combinations of these options that result in a
+list of nodes that are not down or drained or failing will
not produce any output.
When used with \fB\-l\fR the output additionally includes
the current node state.
@@ -258,11 +258,11 @@ List nodes only having the given state(s). Multiple states
may be comma separated and the comparison is case insensitive.
Possible values include (case insensitive): ALLOC, ALLOCATED,
COMP, COMPLETING, DOWN, DRAIN (for node in DRAINING or DRAINED
-states), DRAINED, DRAINING, FAIL, FAILING, IDLE, MAINT, NO_RESPOND,
-POWER_SAVE, UNK, and UNKNOWN.
-By default nodes in the specified state are reported whether
-they are responding or not.
-The \fB\-\-dead\fR and \fB\-\-responding\fR options may be
+states), DRAINED, DRAINING, FAIL, FAILING, IDLE, MAINT, NO_RESPOND,
+POWER_SAVE, UNK, and UNKNOWN.
+By default nodes in the specified state are reported whether
+they are responding or not.
+The \fB\-\-dead\fR and \fB\-\-responding\fR options may be
used to filtering nodes by the responding flag.
.TP
@@ -340,22 +340,22 @@ restricted to user root, \fByes\fR or \fBno\fR.
.TP
\fBSHARE\fR
Will jobs allocated resources in this partition share those
-resources.
+resources.
\fBno\fR indicates resources are never shared.
\fBexclusive\fR indicates whole nodes are dedicated to jobs
-(equivalent to srun \-\-exclusive option, may be used even
+(equivalent to srun \-\-exclusive option, may be used even
with shared/cons_res managing individual processors).
-\fBforce\fR indicates resources are always available to be shared.
+\fBforce\fR indicates resources are always available to be shared.
\fByes\fR indicates resource may be shared or not
per job's resource allocation.
.TP
\fBSTATE\fR
-State of the nodes.
-Possible states include: allocated, completing, down,
+State of the nodes.
+Possible states include: allocated, completing, down,
drained, draining, fail, failing, idle, and unknown plus
-their abbreviated forms: alloc, comp, donw, drain, drng,
+their abbreviated forms: alloc, comp, donw, drain, drng,
fail, failg, idle, and unk respectively.
-Note that the suffix "*" identifies nodes that are presently
+Note that the suffix "*" identifies nodes that are presently
not responding.
.TP
\fBTMP_DISK\fR
@@ -385,7 +385,7 @@ The node is allocated to one or more active jobs plus
one or more jobs are in the process of COMPLETING.
.TP
\fBCOMPLETING\fR
-All jobs associated with this node are in the process of
+All jobs associated with this node are in the process of
COMPLETING. This node state will be removed when
all of the job's processes have terminated and the SLURM
epilog program (if any) has terminated. See the \fBEpilog\fR
@@ -416,15 +416,15 @@ node\fR command in the \fBscontrol\fR(1) man page or the
\fBslurm.conf\fR(5) man page for more information.
.TP
\fBFAIL\fR
-The node is expected to fail soon and is unavailable for
-use per system administrator request.
-See the \fBupdate node\fR command in the \fBscontrol\fR(1)
+The node is expected to fail soon and is unavailable for
+use per system administrator request.
+See the \fBupdate node\fR command in the \fBscontrol\fR(1)
man page or the \fBslurm.conf\fR(5) man page for more information.
.TP
\fBFAILING\fR
-The node is currently executing a job, but is expected to fail
-soon and is unavailable for use per system administrator request.
-See the \fBupdate node\fR command in the \fBscontrol\fR(1)
+The node is currently executing a job, but is expected to fail
+soon and is unavailable for use per system administrator request.
+See the \fBupdate node\fR command in the \fBscontrol\fR(1)
man page or the \fBslurm.conf\fR(5) man page for more information.
.TP
\fBIDLE\fR
@@ -437,8 +437,8 @@ The node is currently in a reservation with a flag value of "maintainence".
The SLURM controller has just started and the node's state
has not yet been determined.
-.SH "ENVIRONMENT VARIABLES"
-.PP
+.SH "ENVIRONMENT VARIABLES"
+.PP
Some \fBsinfo\fR options may
be set via environment variables. These environment variables,
along with their corresponding options, are listed below. (Note:
@@ -472,7 +472,7 @@ batch up infinite 6 idle adev[10-15]
debug* up 30:00 8 idle adev[0-7]
.fi
-
+
Report partition summary information:
.nf
@@ -482,7 +482,7 @@ batch up infinite 2/6/0/8 adev[8-15]
debug* up 30:00 0/8/0/8 adev[0-7]
.fi
-
+
Report more complete information about the partition debug:
.nf
@@ -544,10 +544,10 @@ FOR A PARTICULAR PURPOSE. See the GNU General Public License for more
details.
.SH "SEE ALSO"
-\fBscontrol\fR(1), \fBsmap\fR(1), \fBsqueue\fR(1),
-\fBslurm_load_ctl_conf\fR(3), \fBslurm_load_jobs\fR(3), \fBslurm_load_node\fR(3),
-\fBslurm_load_partitions\fR(3),
-\fBslurm_reconfigure\fR(3), \fBslurm_shutdown\fR(3),
-\fBslurm_update_job\fR(3), \fBslurm_update_node\fR(3),
+\fBscontrol\fR(1), \fBsmap\fR(1), \fBsqueue\fR(1),
+\fBslurm_load_ctl_conf\fR(3), \fBslurm_load_jobs\fR(3), \fBslurm_load_node\fR(3),
+\fBslurm_load_partitions\fR(3),
+\fBslurm_reconfigure\fR(3), \fBslurm_shutdown\fR(3),
+\fBslurm_update_job\fR(3), \fBslurm_update_node\fR(3),
\fBslurm_update_partition\fR(3),
\fBslurm.conf\fR(5)
diff --git a/doc/man/man1/slurm.1 b/doc/man/man1/slurm.1
index 20ab95650a6..c23c3d98729 100644
--- a/doc/man/man1/slurm.1
+++ b/doc/man/man1/slurm.1
@@ -20,21 +20,21 @@ resource limits by user or bank account,
and sophisticated multifactor job prioritization algorithms.
SLURM has a centralized manager, \fBslurmctld\fR, to monitor resources and
-work. There may also be a backup manager to assume those responsibilities in the
+work. There may also be a backup manager to assume those responsibilities in the
event of failure. Each compute server (node) has a \fBslurmd\fR daemon, which
-can be compared to a remote shell: it waits for work, executes that work, returns
+can be compared to a remote shell: it waits for work, executes that work, returns
status, and waits for more work. An optional \fBslurmDBD\fR (SLURM DataBase Daemon)
can be used for accounting purposes and to maintain resource limit information.
-Basic user tools include \fBsrun\fR to initiate jobs,
-\fBscancel\fR to terminate queued or running jobs, \fBsinfo\fR to report system
+Basic user tools include \fBsrun\fR to initiate jobs,
+\fBscancel\fR to terminate queued or running jobs, \fBsinfo\fR to report system
status, and \fBsqueue\fR to report the status of jobs. There is also an administrative
tool \fBscontrol\fR available to monitor and/or modify configuration and state
information. APIs are available for all functions.
SLURM configuration is maintained in the \fBslurm.conf\fR file.
-Man pages are available for all SLURM commands, daemons, APIs, plus the
+Man pages are available for all SLURM commands, daemons, APIs, plus the
\fBslurm.conf\fR file.
Extensive documenation is also available on the internet at
\fB<https://computing.llnl.gov/linux/slurm/>\fR.
@@ -59,13 +59,13 @@ FOR A PARTICULAR PURPOSE. See the GNU General Public License for more
details.
.SH "SEE ALSO"
-\fBsacct\fR(1), \fBsacctmgr\fR(1), \fBsalloc\fR(1), \fBsattach\fR(1),
-\fBsbatch\fR(1), \fBsbcast\fR(1), \fBscancel\fR(1), \fBscontrol\fR(1),
-\fBsinfo\fR(1), \fBsmap\fR(1), \fBsqueue\fR(1), \fBsreport\fR(1),
+\fBsacct\fR(1), \fBsacctmgr\fR(1), \fBsalloc\fR(1), \fBsattach\fR(1),
+\fBsbatch\fR(1), \fBsbcast\fR(1), \fBscancel\fR(1), \fBscontrol\fR(1),
+\fBsinfo\fR(1), \fBsmap\fR(1), \fBsqueue\fR(1), \fBsreport\fR(1),
\fBsrun\fR(1),\fBsshare\fR(1), \fBsstate\fR(1), \fBstrigger\fR(1),
-\fBsview\fR(1),
-\fBbluegene.conf\fR(5), \fBslurm.conf\fR(5), \fBslurmdbd.conf\fR(5),
+\fBsview\fR(1),
+\fBbluegene.conf\fR(5), \fBslurm.conf\fR(5), \fBslurmdbd.conf\fR(5),
\fBwiki.conf\fR(5),
-\fBslurmctld\fR(8), \fBslurmd\fR(8), \fBslurmdbd\fR(8), \fBslurmstepd\fR(8),
+\fBslurmctld\fR(8), \fBslurmd\fR(8), \fBslurmdbd\fR(8), \fBslurmstepd\fR(8),
\fBspank\fR(8)
diff --git a/doc/man/man1/smap.1 b/doc/man/man1/smap.1
index 225eb548d7b..282d583de45 100644
--- a/doc/man/man1/smap.1
+++ b/doc/man/man1/smap.1
@@ -1,18 +1,18 @@
.TH SMAP "1" "June 2009" "smap 2.1" "Slurm components"
.SH "NAME"
-smap \- graphically view information about SLURM jobs, partitions, and set
+smap \- graphically view information about SLURM jobs, partitions, and set
configurations parameters.
.SH "SYNOPSIS"
-\fBsmap\fR [\fIOPTIONS\fR...]
+\fBsmap\fR [\fIOPTIONS\fR...]
.SH "DESCRIPTION"
-\fBsmap\fR is used to graphically view job, partition and node information
-for a system running SLURM.
-Note that information about nodes and partitions to which a user lacks
+\fBsmap\fR is used to graphically view job, partition and node information
+for a system running SLURM.
+Note that information about nodes and partitions to which a user lacks
access will always be displayed to avoid obvious gaps in the output.
-This is equivalent to the \fB\-\-all\fR option of the \fBsinfo\fR and
-\fBsqueue\fR commands.
+This is equivalent to the \fB\-\-all\fR option of the \fBsinfo\fR and
+\fBsqueue\fR commands.
.SH "OPTIONS"
.TP
@@ -21,12 +21,12 @@ Print output to the commandline, no curses.
.TP
\fB\-D <option>\fR, \fB\-\-display=<option>\fR
-sets the display mode for smap. Showing revelant information about specific
-views and displaying a corresponding node chart. While in any
+sets the display mode for smap. Showing revelant information about specific
+views and displaying a corresponding node chart. While in any
display a user can switch by typing a different view letter. This is true in
-all modes except for 'configure mode' user can type 'quit' to exit just
+all modes except for 'configure mode' user can type 'quit' to exit just
configure mode. Typing 'exit' will end the configuration mode and exit smap.
-Note that unallocated nodes are indicated by a '.' and nodes in the
+Note that unallocated nodes are indicated by a '.' and nodes in the
DOWN, DRAINED or FAIL state by a '#'.
.RS
.TP 15
@@ -40,10 +40,10 @@ Displays current BlueGene node states and allows users to configure the system.
Displays information about jobs running on system.
.TP
.I "r"
-Display information about advanced reservations.
-While all current and future reservations will be listed,
+Display information about advanced reservations.
+While all current and future reservations will be listed,
only currently active reservations will appear on the node map.
-.TP
+.TP
.I "s"
Displays information about slurm partitions on the system
.RE
@@ -58,10 +58,10 @@ Print a message describing all \fBsmap\fR options.
.TP
\fB\-i <seconds>\fR , \fB\-\-iterate=<seconds>\fR
-Print the state on a periodic basis.
+Print the state on a periodic basis.
Sleep for the indicated number of seconds between reports.
User can exit at anytime by typing 'q' or hitting the return key.
-If user is in configure mode type 'exit' to exit program, 'quit'
+If user is in configure mode type 'exit' to exit program, 'quit'
to exit configure mode.
.TP
@@ -69,7 +69,7 @@ to exit configure mode.
Only show objects with these ionodes this support is only for
bluegene systems. This should be used inconjuction with the '\-n'
option. Only specify the ionode number range here. Specify the node
-name with the '\-n' option.
+name with the '\-n' option.
.TP
\fB\-n\fR, \fB\-\-nodes\fR
@@ -83,10 +83,10 @@ Avoid printing error messages.
.TP
\fB\-R <RACK_MIDPLANE_ID/XYZ>\fR, \fB\-\-resolve=<RACK_MIDPLANE_ID/XYZ>\fR
Returns the XYZ coords for a Rack/Midplane id or vice\-versa.
-
+
To get the XYZ coord for a Rack/Midplane id input \-R R101 where 10 is the rack
and 1 is the midplane.
-
+
To get the Rack/Midplane id from a XYZ coord input \-R 101 where X=1 Y=1 Z=1 with
no leading 'R'.
@@ -100,8 +100,8 @@ Print version information and exit.
.SH "INTERACTIVE OPTIONS"
When using smap in curses mode you can scroll through the different windows
-using the arrow keys. The \fBup\fR and \fBdown\fR arrow keys scroll
-the window containing the grid, and the \fBleft\fR and \fBright\fR arrow keys
+using the arrow keys. The \fBup\fR and \fBdown\fR arrow keys scroll
+the window containing the grid, and the \fBleft\fR and \fBright\fR arrow keys
scroll the window containing the text information.
.SH "OUTPUT FIELD DESCRIPTIONS"
@@ -133,7 +133,7 @@ Mode Type: \fBCOPROCESS\fR or \fBVIRTUAL\fR.
Name of the job or advanced reservation.
.TP
\fBNODELIST\fR or \fBBP_LIST\fR
-Names of nodes or base partitions associated with this configuration,
+Names of nodes or base partitions associated with this configuration,
partition or reservation.
.TP
\fBNODES\fR
@@ -145,21 +145,21 @@ default partition.
.TP
\fBST\fR
State of a job in compact form. Possible states include:
-PD (pending), R (running), S (suspended),
-CD (completed), CF (configuring), CG (completing),
-F (failed), TO (timeout), and NF (node failure). See
+PD (pending), R (running), S (suspended),
+CD (completed), CF (configuring), CG (completing),
+F (failed), TO (timeout), and NF (node failure). See
\fBJOB STATE CODES\fR section below for more information.
.TP
\fBSTART_TIME\fR
The time when an advanced reservation started.
.TP
\fBSTATE\fR
-State of the nodes.
-Possible states include: allocated, completing, down,
+State of the nodes.
+Possible states include: allocated, completing, down,
drained, draining, fail, failing, idle, and unknown plus
-their abbreviated forms: alloc, comp, donw, drain, drng,
+their abbreviated forms: alloc, comp, donw, drain, drng,
fail, failg, idle, and unk respectively.
-Note that the suffix "*" identifies nodes that are presently
+Note that the suffix "*" identifies nodes that are presently
not responding.
See \fBNODE STATE CODES\fR section below for more information.
.TP
@@ -171,19 +171,19 @@ jobs or partitions without a job time limit.
.SH "TOPOGRAPHY INFORMATION"
.PP
-The node chart is designed to indicate relative locations of
-the nodes.
-On most Linux clusters this will represent a one\-dimensional
-array of nodes. Larger clusters will utilize multiple as needed
-with right side of one line being logically followed by the
+The node chart is designed to indicate relative locations of
+the nodes.
+On most Linux clusters this will represent a one\-dimensional
+array of nodes. Larger clusters will utilize multiple as needed
+with right side of one line being logically followed by the
left side of the next line.
.PP
.nf
-On BlueGene systems, the node chart will indicate the three
+On BlueGene systems, the node chart will indicate the three
dimensional topography of the system.
The X dimension will increase from left to right on a given line.
The Y dimension will increase in planes from bottom to top.
-The Z dimension will increase within a plane from the back
+The Z dimension will increase within a plane from the back
line to the front line of a plane.
Note the example below:
@@ -218,9 +218,9 @@ e 12378 debug RMP4 joseph asx4 R 0:34 2k bgl[612x713]
.SH "CONFIGURATION INSTRUCTIONS"
.PP
-For Admin use. From this screen one can create a configuration
+For Admin use. From this screen one can create a configuration
file that is used to partition and wire the system into usable
-blocks.
+blocks.
.TP
\fBOUTPUT\fR
@@ -248,45 +248,45 @@ Mode Type: \fBCOPROCESS\fR or \fBVIRTUAL\fR.
Returns the XYZ coords for a Rack/Midplane id or vice\-versa.
To get the XYZ coord for a Rack/Midplane id input \-R R101 where 10 is the rack
-and 1 is the midplane.
+and 1 is the midplane.
To get the Rack/Midplane id from a XYZ coord input \-R 101 where X=1 Y=1 Z=1 with
-no leading 'R'.
+no leading 'R'.
.TP
\fBload <bluegene.conf file>\fR
Load an already exsistant bluegene.conf file. This will varify and mapout a
-bluegene.conf file. After loaded the configuration may be edited and
+bluegene.conf file. After loaded the configuration may be edited and
saved as a new file.
-.TP
+.TP
\fBcreate <size> <options>\fR
-Submit request for partition creation. The size may be specified either
-as a count of base partitions or specific dimensions in the X, Y and Z
-directions separated by "x", for example "2x3x4". A variety of options
+Submit request for partition creation. The size may be specified either
+as a count of base partitions or specific dimensions in the X, Y and Z
+directions separated by "x", for example "2x3x4". A variety of options
may be specified. Valid options are listed below. Note that the option
and their values are case insensitive (e.g. "MESH" and "mesh" are equivalent).
.TP
\fBStart = XxYxZ\fR
-Identify where to start the partition. This is primarily for testing
+Identify where to start the partition. This is primarily for testing
purposes. For convenience one can only put the X coord or XxY will also work.
The default value is 0x0x0.
.TP
\fBConnection = MESH | TORUS | SMALL\fR
-Identify how the nodes should be connected in network.
+Identify how the nodes should be connected in network.
The default value is TORUS.
.RS
.TP
\fBSmall\fR
Equivalent to "Connection=Small".
-If a small connection is specified the base partition chosen will create
-smaller partitions based on options \fB32CNBlocks\fR and
-\fB128CNBlocks\fR respectively for a Bluegene L system.
+If a small connection is specified the base partition chosen will create
+smaller partitions based on options \fB32CNBlocks\fR and
+\fB128CNBlocks\fR respectively for a Bluegene L system.
\fB16CNBlocks\fR, \fB64CNBlocks\fR, and \fB256CNBlocks\fR are also
-available for Bluegene P systems. Keep in mind you
+available for Bluegene P systems. Keep in mind you
must have enough ionodes to make all these configurations possible.
- These number will be altered to take up the
-entire base partition. Size does not need to be specified with a small
+ These number will be altered to take up the
+entire base partition. Size does not need to be specified with a small
request, we will always default to 1 base partition for allocation.
.TP
\fBMesh\fR
@@ -298,7 +298,7 @@ Equivalent to "Connection=Torus".
.TP
\fBRotation = TRUE | FALSE\fR
-Specifies that the geometry specified in the size parameter may
+Specifies that the geometry specified in the size parameter may
be rotated in space (e.g. the Y and Z dimensions may be switched).
The default value is FALSE.
.TP
@@ -306,10 +306,10 @@ The default value is FALSE.
Equivalent to "Rotation=true".
.TP
\fBElongation = TRUE | FALSE\fR
-If TRUE, permit the geometry specified in the size parameter to be altered as
-needed to fit available resources.
-For example, an allocation of "4x2x1" might be used to satisfy a size specification
-of "2x2x2".
+If TRUE, permit the geometry specified in the size parameter to be altered as
+needed to fit available resources.
+For example, an allocation of "4x2x1" might be used to satisfy a size specification
+of "2x2x2".
The default value is FALSE.
.TP
\fBElongate\fR
@@ -317,23 +317,23 @@ Equivalent to "Elongation=true".
.TP
\fBcopy <id> <count>\fR
-Submit request for partition to be copied.
-You may copy a specific partition by specifying its id, by default the
-last configured partition is copied.
-You may also specify a number of copies to be made.
+Submit request for partition to be copied.
+You may copy a specific partition by specifying its id, by default the
+last configured partition is copied.
+You may also specify a number of copies to be made.
By default, one copy is made.
.TP
\fBdelete <id>\fR
-Delete the specified block.
+Delete the specified block.
.TP
\fBdown <node_range>\fR
-Down a specific node or range of nodes.
+Down a specific node or range of nodes.
i.e. 000, 000\-111 [000x111]
.TP
\fBup <node_range>\fR
-Bring a specific node or range of nodes up.
+Bring a specific node or range of nodes up.
i.e. 000, 000\-111 [000x111]
.TP
\fBalldown\fR
@@ -344,8 +344,8 @@ Set all nodes to up state.
.TP
\fBsave <file_name>\fR
-Save the current configuration to a file.
-If no file_name is specified, the configuration is written to a
+Save the current configuration to a file.
+If no file_name is specified, the configuration is written to a
file named "bluegene.conf" in the current working directory.
.TP
@@ -377,7 +377,7 @@ The node is allocated to one or more active jobs plus
one or more jobs are in the process of COMPLETING.
.TP
\fBCOMPLETING\fR
-All jobs associated with this node are in the process of
+All jobs associated with this node are in the process of
COMPLETING. This node state will be removed when
all of the job's processes have terminated and the SLURM
epilog program (if any) has terminated. See the \fBEpilog\fR
@@ -408,15 +408,15 @@ node\fR command in the \fBscontrol\fR(1) man page or the
\fBslurm.conf\fR(5) man page for more information.
.TP
\fBFAIL\fR
-The node is expected to fail soon and is unavailable for
-use per system administrator request.
-See the \fBupdate node\fR command in the \fBscontrol\fR(1)
+The node is expected to fail soon and is unavailable for
+use per system administrator request.
+See the \fBupdate node\fR command in the \fBscontrol\fR(1)
man page or the \fBslurm.conf\fR(5) man page for more information.
.TP
\fBFAILING\fR
-The node is currently executing a job, but is expected to fail
-soon and is unavailable for use per system administrator request.
-See the \fBupdate node\fR command in the \fBscontrol\fR(1)
+The node is currently executing a job, but is expected to fail
+soon and is unavailable for use per system administrator request.
+See the \fBupdate node\fR command in the \fBscontrol\fR(1)
man page or the \fBslurm.conf\fR(5) man page for more information.
.TP
\fBIDLE\fR
@@ -432,7 +432,7 @@ has not yet been determined.
.SH "JOB STATE CODES"
Jobs typically pass through several states in the course of their
execution.
-The typical states are \fBPENDING\fR, \fBRUNNING\fR, \fBSUSPENDED\fR,
+The typical states are \fBPENDING\fR, \fBRUNNING\fR, \fBSUSPENDED\fR,
\fBCOMPLETING\fR, and \fBCOMPLETED\fR.
An explanation of each state follows.
.TP 20
@@ -495,10 +495,10 @@ FOR A PARTICULAR PURPOSE. See the GNU General Public License for more
details.
.SH "SEE ALSO"
-\fBscontrol\fR(1), \fBsinfo\fR(1), \fBsqueue\fR(1),
-\fBslurm_load_ctl_conf\fR(3), \fBslurm_load_jobs\fR(3), \fBslurm_load_node\fR(3),
-\fBslurm_load_partitions\fR(3),
-\fBslurm_reconfigure\fR(3), \fBslurm_shutdown\fR(3),
-\fBslurm_update_job\fR(3), \fBslurm_update_node\fR(3),
+\fBscontrol\fR(1), \fBsinfo\fR(1), \fBsqueue\fR(1),
+\fBslurm_load_ctl_conf\fR(3), \fBslurm_load_jobs\fR(3), \fBslurm_load_node\fR(3),
+\fBslurm_load_partitions\fR(3),
+\fBslurm_reconfigure\fR(3), \fBslurm_shutdown\fR(3),
+\fBslurm_update_job\fR(3), \fBslurm_update_node\fR(3),
\fBslurm_update_partition\fR(3),
\fBslurm.conf\fR(5)
diff --git a/doc/man/man1/squeue.1 b/doc/man/man1/squeue.1
index 3634ed73b38..5bfb4a3e997 100644
--- a/doc/man/man1/squeue.1
+++ b/doc/man/man1/squeue.1
@@ -4,11 +4,11 @@
squeue \- view information about jobs located in the SLURM scheduling queue.
.SH "SYNOPSIS"
-\fBsqueue\fR [\fIOPTIONS\fR...]
+\fBsqueue\fR [\fIOPTIONS\fR...]
.SH "DESCRIPTION"
-\fBsqueue\fR is used to view job and job step information for jobs managed by
-SLURM.
+\fBsqueue\fR is used to view job and job step information for jobs managed by
+SLURM.
.SH "OPTIONS"
@@ -19,8 +19,8 @@ list of account names. This has no effect when listing job steps.
.TP
\fB\-a\fR, \fB\-\-all\fR
-Display information about jobs and job steps in all partions.
-This causes information to be displayed about partitions that are configured as
+Display information about jobs and job steps in all partions.
+This causes information to be displayed about partitions that are configured as
hidden and partitions that are unavailable to user's group.
.TP
@@ -33,8 +33,8 @@ Print a help message describing all options \fBsqueue\fR.
.TP
\fB\-\-hide\fR
-Do not display information about jobs and job steps in all partions. By default,
-information about partitions that are configured as hidden or are not available
+Do not display information about jobs and job steps in all partions. By default,
+information about partitions that are configured as hidden or are not available
to the user's group will not be displayed (i.e. this is the default behavior).
.TP
@@ -51,7 +51,7 @@ The \fB\-\-jobs=<job_id_list>\fR option may be used in conjunction with the
.TP
\fB\-l\fR, \fB\-\-long\fR
-Report more of the available information for the selected jobs or job steps,
+Report more of the available information for the selected jobs or job steps,
subject to any constraints specified.
.TP
@@ -63,8 +63,8 @@ A node_name of \fBlocalhost\fR is mapped to the current host name.
.TP
\fB\-o <output_format>\fR, \fB\-\-format=<output_format>\fR
-Specify the information to be displayed, its size and position
-(right or left justified).
+Specify the information to be displayed, its size and position
+(right or left justified).
The default formats with various options are
.RS
@@ -83,7 +83,7 @@ The default formats with various options are
The format of each field is "%[.][size]type".
.RS
.TP 8
-\fIsize\fR
+\fIsize\fR
is the minimum field size.
If no size is specified, whatever is needed to print the information will be used.
.TP
@@ -93,9 +93,9 @@ By default, output is right justified.
.RE
.IP
-Note that many of these \fItype\fR specifications are valid
+Note that many of these \fItype\fR specifications are valid
only for jobs while others are valid only for job steps.
-Valid \fItype\fR specifications include:
+Valid \fItype\fR specifications include:
.RS
.TP 4
@@ -106,37 +106,37 @@ Account associated with the job.
Number of tasks created by a job step.
This reports the value of the \fBsrun \-\-ntasks\fR option.
.TP
-\fB%c\fR
+\fB%c\fR
Minimum number of CPUs (processors) per node requested by the job.
-This reports the value of the \fBsrun \-\-mincpus\fR option with a
+This reports the value of the \fBsrun \-\-mincpus\fR option with a
default value of zero.
.TP
-\fB%C\fR
-Number of CPUs (processors) requested by the job or allocated to
+\fB%C\fR
+Number of CPUs (processors) requested by the job or allocated to
it if already running.
.TP
-\fB%d\fR
+\fB%d\fR
Minimum size of temporary disk space (in MB) requested by the job.
.TP
-\fB%D\fR
-Number of nodes allocated to the job or the minimum number of nodes
-required by a pending job. The actual number of nodes allocated to a pending
-job may exceed this number if the job specified a node range count (e.g.
-minimum and maximum node counts) or the the job specifies a processor
-count instead of a node count and the cluster contains nodes with varying
+\fB%D\fR
+Number of nodes allocated to the job or the minimum number of nodes
+required by a pending job. The actual number of nodes allocated to a pending
+job may exceed this number if the job specified a node range count (e.g.
+minimum and maximum node counts) or the the job specifies a processor
+count instead of a node count and the cluster contains nodes with varying
processor counts.
.TP
-\fB%e\fR
+\fB%e\fR
Time at which the job ended or is expected to end (based upon its time limit)
.TP
\fB%E\fR
-Job dependency. This job will not begin execution until the dependent job
+Job dependency. This job will not begin execution until the dependent job
completes. A value of zero implies this job has no dependencies.
.TP
-\fB%f\fR
+\fB%f\fR
Features required by the job.
.TP
-\fB%g\fR
+\fB%g\fR
Group name of the job.
.TP
\fB%G\fR
@@ -145,33 +145,33 @@ Group ID of the job.
\fB%h\fR
Can the nodes allocated to the job be shared with other jobs.
.TP
-\fB%H\fR
+\fB%H\fR
Minimum number of sockets per node requested by the job.
This reports the value of the \fBsrun \-\-sockets\-per\-node\fR option.
.TP
\fB%i\fR
Job or job step id.
.TP
-\fB%I\fR
+\fB%I\fR
Minimum number of cores per socket requested by the job.
This reports the value of the \fBsrun \-\-cores\-per\-socket\fR option.
.TP
\fB%j\fR
Job or job step name.
.TP
-\fB%J\fR
+\fB%J\fR
Minimum number of threads per core requested by the job.
This reports the value of the \fBsrun \-\-threads\-per\-core\fR option.
.TP
\fB%k\fR
Comment associated with the job.
\fB%l\fR
-Time limit of the job or job step in days\-hours:minutes:seconds.
+Time limit of the job or job step in days\-hours:minutes:seconds.
The value may be "NOT_SET" if not yet established or "UNLIMITED" for no limit.
.TP
\fB%L\fR
-Time left for the job to execute in days\-hours:minutes:seconds.
-This value is calculated by subtracting the job's time used from its time
+Time left for the job to execute in days\-hours:minutes:seconds.
+This value is calculated by subtracting the job's time used from its time
limit.
The value may be "NOT_SET" if not yet established or "UNLIMITED" for no limit.
.TP
@@ -179,21 +179,21 @@ The value may be "NOT_SET" if not yet established or "UNLIMITED" for no limit.
Minimum size of memory (in MB) requested by the job
.TP
\fB%M\fR
-Time used by the job or job step in days\-hours:minutes:seconds.
+Time used by the job or job step in days\-hours:minutes:seconds.
The days and hours are printed only as needed.
-For job steps this field shows the elapsed time since execution began
+For job steps this field shows the elapsed time since execution began
and thus will be inaccurate for job steps which have been suspended.
Clock skew between nodes in the cluster will cause the time to be inaccurate.
If the time is obviously wrong (e.g. negative), it displays as "INVALID".
.TP
\fB%n\fR
-List of node names (or base partitions on BlueGene systems) explicitly
+List of node names (or base partitions on BlueGene systems) explicitly
requested by the job
.TP
\fB%N\fR
-List of nodes allocated to the job or job step. In the case of a
+List of nodes allocated to the job or job step. In the case of a
\fICOMPLETING\fR job, the list of nodes will comprise only those
-nodes that have not yet been returned to service. This may result
+nodes that have not yet been returned to service. This may result
in the node count being greater than the number of listed nodes.
.TP
\fB%O\fR
@@ -203,7 +203,7 @@ Are contiguous nodes requested by the job.
Priority of the job (converted to a floating point number between 0.0 and 1.0).
Also see \fB%Q\fR.
.TP
-\fB%P\fR
+\fB%P\fR
Partition of the job or job step.
.TP
\fB%q\fR
@@ -218,47 +218,47 @@ The reason a job is in its current state.
See the \fBJOB REASON CODES\fR section below for more information.
.TP
\fB%R\fR
-For pending jobs: the reason a job is waiting for execution
+For pending jobs: the reason a job is waiting for execution
is printed within parenthesis.
-For terminated jobs with failure: an explanation as to why the
+For terminated jobs with failure: an explanation as to why the
job failed is printed within parenthesis.
-For all other job states: the list of allocate nodes.
+For all other job states: the list of allocate nodes.
See the \fBJOB REASON CODES\fR section below for more information.
.TP
-\fB%s\fR
+\fB%s\fR
Node selection plugin specific data for a job. Possible data includes:
-Geometry requirement of resource allocation (X,Y,Z dimensions),
-Connection type (TORUS, MESH, or NAV == torus else mesh),
-Permit rotation of geometry (yes or no),
+Geometry requirement of resource allocation (X,Y,Z dimensions),
+Connection type (TORUS, MESH, or NAV == torus else mesh),
+Permit rotation of geometry (yes or no),
Node use (VIRTUAL or COPROCESSOR),
etc.
.TP
-\fB%S\fR
+\fB%S\fR
Actual or expected start time of the job or job step.
.TP
-\fB%t\fR
+\fB%t\fR
Job state, compact form:
-PD (pending), R (running), CA (cancelled), CF(configuring),
-CG (completing), CD (completed),
+PD (pending), R (running), CA (cancelled), CF(configuring),
+CG (completing), CD (completed),
F (failed), TO (timeout), and NF (node failure).
See the \fBJOB STATE CODES\fR section below for more information.
.TP
-\fB%T\fR
-Job state, extended form:
-PENDING, RUNNING, SUSPENDED, CANCELLED, COMPLETING, COMPLETED, CONFIGURING,
+\fB%T\fR
+Job state, extended form:
+PENDING, RUNNING, SUSPENDED, CANCELLED, COMPLETING, COMPLETED, CONFIGURING,
FAILED, TIMEOUT, and NODE_FAIL.
See the \fBJOB STATE CODES\fR section below for more information.
.TP
-\fB%u\fR
+\fB%u\fR
User name for a job or job step.
.TP
-\fB%U\fR
+\fB%U\fR
User ID for a job or job step.
.TP
-\fB%v\fR
+\fB%v\fR
Reservation for the job.
.TP
-\fB%x\fR
+\fB%x\fR
List of node names explicitly excluded by the job.
.TP
\fB%z\fR
@@ -268,7 +268,7 @@ the job.
.TP
\fB\-p <part_list>\fR, \fB\-\-partition=<part_list>\fR
-Specify the partitions of the jobs or steps to view. Accepts a comma separated
+Specify the partitions of the jobs or steps to view. Accepts a comma separated
list of partition names.
.TP
@@ -278,7 +278,7 @@ separated list of qos's.
.TP
\fB\-s\fR, \fB\-\-steps\fR
-Specify the job steps to view. This flag indicates that a comma separated list
+Specify the job steps to view. This flag indicates that a comma separated list
of job steps to view follows without an equal sign (see examples).
The job step format is "job_id.step_id". Defaults to all job steps.
@@ -286,21 +286,21 @@ The job step format is "job_id.step_id". Defaults to all job steps.
\fB\-S <sort_list>\fR, \fB\-\-sort=<sort_list>\fR
Specification of the order in which records should be reported.
This uses the same field specifciation as the <output_format>.
-Multiple sorts may be performed by listing multiple sort fields
+Multiple sorts may be performed by listing multiple sort fields
separated by commas.
-The field specifications may be preceeded by "+" or "\-" for
-ascending (default) and descending order respectively.
+The field specifications may be preceeded by "+" or "\-" for
+ascending (default) and descending order respectively.
For example, a sort value of "P,U" will sort the
-records by partition name then by user id.
-The default value of sort for jobs is "P,t,\-p" (increasing partition
-name then within a given partition by increasing node state and then
+records by partition name then by user id.
+The default value of sort for jobs is "P,t,\-p" (increasing partition
+name then within a given partition by increasing node state and then
decreasing priority).
-The default value of sort for job steps is "P,i" (increasing partition
+The default value of sort for job steps is "P,i" (increasing partition
name then within a given partition by increasing step id).
.TP
\fB\-\-start\fR
-Report the expected start time of pending jobs in order of increasing
+Report the expected start time of pending jobs in order of increasing
start time. This is equivalent to the following options:
\fB\-\-format="%.7i %.9P %.8j %.8u %.2t %.19S %.6D %R"\fR,
\fB\-\-sort=S\fR and \fB\-\-states=PENDING\fR.
@@ -313,10 +313,10 @@ SLURM is configured to use the backfill scheduling plugin.
.TP
\fB\-t <state_list>\fR, \fB\-\-states=<state_list>\fR
Specify the states of jobs to view. Accepts a comma separated list of
-state names or "all". If "all" is specified then jobs of all states will be
+state names or "all". If "all" is specified then jobs of all states will be
reported. If no state is specified then pending, running, and completing
jobs are reported. Valid states (in both extended and compact form) include:
-PENDING (PD), RUNNING (R), SUSPENDED (S),
+PENDING (PD), RUNNING (R), SUSPENDED (S),
COMPLETING (CG), COMPLETED (CD), CONFIGURING (CF), CANCELLED (CA),
FAILED (F), TIMEOUT (TO), and NODE_FAIL (NF). Note the \fB<state_list>\fR
supplied is case insensitve ("pd" and "PD" work the same).
@@ -340,8 +340,8 @@ Report details of squeues actions.
Print version information and exit.
.SH "JOB REASON CODES"
-These codes identify the reason that a job is waiting for execution.
-A job may be waiting for more than one reason, in which case only
+These codes identify the reason that a job is waiting for execution.
+A job may be waiting for more than one reason, in which case only
one of those reasons is displayed.
.TP 20
\fBDependency\fR
@@ -354,7 +354,7 @@ No reason is set for this job.
The partition required by this job is in a DOWN state.
.TP
\fBPartitionNodeLimit\fR
-The number of nodes required by this job is outside of it's
+The number of nodes required by this job is outside of it's
partitions current limits.
Can also indicate that required nodes are DOWN or DRAINED.
.TP
@@ -377,7 +377,7 @@ The job's constraints can not be satisfied.
Failure of the SLURM system, a file system, the network, etc.
.TP
\fBJobLaunchFailure\fR
-The job could not be launched.
+The job could not be launched.
This may be due to a file system problem, invalid program name, etc.
.TP
\fBNonZeroExitCode\fR
@@ -390,8 +390,8 @@ The job exhausted its time limit.
The job reached the system InactiveLimit.
.SH "JOB STATE CODES"
-Jobs typically pass through several states in the course of their
-execution.
+Jobs typically pass through several states in the course of their
+execution.
The typical states are PENDING, RUNNING, SUSPENDED, COMPLETING, and COMPLETED.
An explanation of each state follows.
.TP 20
@@ -429,8 +429,8 @@ Job terminated upon reaching its time limit.
.SH "ENVIRONMENT VARIABLES"
.PP
-Some \fBsqueue\fR options may be set via environment variables. These
-environment variables, along with their corresponding options, are listed
+Some \fBsqueue\fR options may be set via environment variables. These
+environment variables, along with their corresponding options, are listed
below. (Note: Commandline options will always override these settings.)
.TP 20
\fBSLURM_CONF\fR
@@ -462,19 +462,19 @@ The location of the SLURM configuration file.
.SH "EXAMPLES"
.eo
-Print the jobs scheduled in the debug partition and in the
-COMPLETED state in the format with six right justified digits for
+Print the jobs scheduled in the debug partition and in the
+COMPLETED state in the format with six right justified digits for
the job id followed by the priority with an arbitrary fields size:
.br
# squeue -p debug -t COMPLETED -o "%.6i %p"
.br
JOBID PRIORITY
.br
- 65543 99993
+ 65543 99993
.br
- 65544 99992
+ 65544 99992
.br
- 65545 99991
+ 65545 99991
.ec
.eo
@@ -534,8 +534,8 @@ WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
FOR A PARTICULAR PURPOSE. See the GNU General Public License for more
details.
.SH "SEE ALSO"
-\fBscancel\fR(1), \fBscontrol\fR(1), \fBsinfo\fR(1),
+\fBscancel\fR(1), \fBscontrol\fR(1), \fBsinfo\fR(1),
\fBsmap\fR(1), \fBsrun\fR(1),
\fBslurm_load_ctl_conf\fR(3), \fBslurm_load_jobs\fR(3),
-\fBslurm_load_node\fR(3),
+\fBslurm_load_node\fR(3),
\fBslurm_load_partitions\fR(3)
diff --git a/doc/man/man1/sreport.1 b/doc/man/man1/sreport.1
index 354a4ed56d3..3ec9547ed05 100644
--- a/doc/man/man1/sreport.1
+++ b/doc/man/man1/sreport.1
@@ -8,7 +8,7 @@ sreport \- Generate reports from the slurm accounting data.
.SH "DESCRIPTION"
\fBsreport\fR is used to generate certain reports. It provides a view into accounting data gathered from slurm via
-the account information maintained within a database with the interface
+the account information maintained within a database with the interface
being provided by the \fBslurmdbd\fR (Slurm Database daemon).
.SH "OPTIONS"
@@ -33,14 +33,14 @@ Output will be '|' delimited without a '|' at the end.
Print no warning or informational messages, only error messages.
.TP
\fB\-t <format>\fR
-Specify the output time format.
+Specify the output time format.
Time format options are case insensitive and may be abbreviated.
The default format is Minutes.
Supported time format options are listed in the \fBtime\fP command
section below.
.TP
\fB\-v\fR, \fB\-\-verbose\fR
-Print detailed event logging.
+Print detailed event logging.
.TP
\fB\-V\fR , \fB\-\-version\fR
Print version information and exit.
@@ -80,7 +80,7 @@ Identical to the \fBexit\fR command.
.TP
\fBtime <time_format>\fP
-Specify the output time format.
+Specify the output time format.
Time format options are case insensitive and may be abbreviated.
The default format is Minutes.
Supported time format options include:
@@ -110,7 +110,7 @@ Percentage of Total
.TP
\fBverbose\fP
-Enable detailed event logging.
+Enable detailed event logging.
.TP
\fBversion\fP
@@ -148,13 +148,13 @@ UserUtilizationByWckey, Utilization, WCKeyUtilizationByUser
REPORT DESCRIPTION
.RS
.TP
-.B cluster AccountUtilizationByUser
+.B cluster AccountUtilizationByUser
This report will display account utilization as it appears on the
hierarchical tree. Starting with the specified account or the
root account by default this report will list the underlying
usage with a sum on each level. Use the 'tree' option to span
the tree for better visibility.
-.TP
+.TP
.B cluster UserUtilizationByAccount
This report will display users by account in order of utilization without
grouping multiple accounts by user into one, but displaying them
@@ -174,7 +174,7 @@ the number should be grouped with idle time.
.TP
.B cluster WCKeyUtilizationByUser
This report will display wckey utilization sorted by WCKey name for
-each user on each cluster.
+each user on each cluster.
.TP
.B job SizesByAccount
@@ -187,7 +187,7 @@ accounts listed.
.TP
.B job SizesByWckey
This report will dispay the amount of time for each wckey for job ranges
-specified by the 'grouping=' option.
+specified by the 'grouping=' option.
.TP
.B reservation Utilization
@@ -197,7 +197,7 @@ This report will display total usage for reservations on the systems.
.B user TopUsage
Displays the top users on a cluster. Use the group option to group
accounts together. The default is to have a different line for each
-user account combination.
+user account combination.
.TP
Each report type has various options...
@@ -217,7 +217,7 @@ Period ending for report. Default is 23:59:59 of previous day.
Valid time formats are...
HH:MM[:SS] [AM|PM]
MMDD[YY] or MM/DD[/YY] or MM.DD[.YY]
-MM/DD[/YY]-HH:MM[:SS]
+MM/DD[/YY]-HH:MM[:SS]
YYYY-MM-DD[THH:MM[:SS]]
.TP
.B Format=<OPT>
@@ -227,7 +227,7 @@ When using the format option for listing various fields you can put a
%NUMBER afterwards to specify how many characters should be printed.
i.e. format=name%30 will print 30 characters of field name right
-justified. A \-30 will print 30 characters left justified.
+justified. A \-30 will print 30 characters left justified.
.TP
.B Start=<OPT>
@@ -235,7 +235,7 @@ Period start for report. Default is 00:00:00 of previous day.
Valid time formats are...
HH:MM[:SS] [AM|PM]
MMDD[YY] or MM/DD[/YY] or MM.DD[.YY]
-MM/DD[/YY]-HH:MM[:SS]
+MM/DD[/YY]-HH:MM[:SS]
YYYY-MM-DD[THH:MM[:SS]]
.RE
@@ -246,7 +246,7 @@ CLUSTER
.B Accounts=<OPT>
When used with the UserUtilizationByAccount, or
AccountUtilizationByUser, List of accounts to include in report.
-Default is all.
+Default is all.
.TP
.B Tree
When used with the AccountUtilizationByUser report will span the
@@ -258,11 +258,11 @@ include in report. Default is all.
.TP
.B Wckeys=<OPT>
When used with the UserUtilizationByWckey or WCKeyUtilizationByUser,
-List of wckeys to include in report. Default is all.
+List of wckeys to include in report. Default is all.
.RE
.TP
-JOB
+JOB
.RS
.TP
.B Accounts=<OPT>
@@ -295,7 +295,7 @@ List of partitions jobs ran on to include in report. Default is all.
.TP
.B PrintJobCount
When used with the Sizes report will print number of jobs ran instead
-of time used.
+of time used.
.TP
.B Users=<OPT>
List of users jobs to include in report. Default is all.
@@ -333,10 +333,10 @@ Default is 10.
.TP
.B Users=<OPT>
List of users jobs to include in report. Default is all.
-.RE
+.RE
.TP
-
+
.SH "Format Options for Each Report"
\fBCluster\fP
@@ -364,7 +364,7 @@ List of users jobs to include in report. Default is all.
\fBUser\fP
TopUsage
\- Account, Cluster, Login, Proper, Used
-
+
.TP
All commands and options are case-insensitive.
.TP
diff --git a/doc/man/man1/srun.1 b/doc/man/man1/srun.1
index 7b14b94655e..a637b6db963 100644
--- a/doc/man/man1/srun.1
+++ b/doc/man/man1/srun.1
@@ -49,12 +49,12 @@ options if desired:
When the task/affinity plugin is enabled,
specifying an allocation in this manner also instructs SLURM to use
a CPU affinity mask to guarantee the request is filled as specified.
-NOTE: Support for these options are configuration dependent.
+NOTE: Support for these options are configuration dependent.
The task/affinity plugin must be configured.
-In addition either select/linear or select/cons_res plugin must be
+In addition either select/linear or select/cons_res plugin must be
configured.
-If select/cons_res is configured, it must have a parameter of CR_Core,
-CR_Core_Memory, CR_Socket, or CR_Socket_Memory.
+If select/cons_res is configured, it must have a parameter of CR_Core,
+CR_Core_Memory, CR_Socket, or CR_Socket_Memory.
.TP
\fB\-\-begin\fR=<\fItime\fR>
@@ -101,15 +101,15 @@ already passed for that year, in which case the next year is used.
.TP
\fB\-\-checkpoint\fR=<\fItime\fR>
-Specifies the interval between creating checkpoints of the job step.
+Specifies the interval between creating checkpoints of the job step.
By default, the job step will no checkpoints created.
-Acceptable time formats include "minutes", "minutes:seconds",
-"hours:minutes:seconds", "days\-hours", "days\-hours:minutes" and
+Acceptable time formats include "minutes", "minutes:seconds",
+"hours:minutes:seconds", "days\-hours", "days\-hours:minutes" and
"days\-hours:minutes:seconds".
.TP
\fB\-\-checkpoint\-dir\fR=<\fIdirectory\fR>
-Specifies the directory into which the job or job step's checkpoint should
+Specifies the directory into which the job or job step's checkpoint should
be written (used by the checkpoint/blcr and checkpoint/xlch plugins only).
The default value is the current working directory.
Checkpoint files will be of the form "<job_id>.ckpt" for jobs
@@ -121,30 +121,30 @@ An arbitrary comment.
.TP
\fB\-C\fR, \fB\-\-constraint\fR=<\fIlist\fR>
-Specify a list of constraints.
-The constraints are features that have been assigned to the nodes by
-the slurm administrator.
-The \fIlist\fR of constraints may include multiple features separated
+Specify a list of constraints.
+The constraints are features that have been assigned to the nodes by
+the slurm administrator.
+The \fIlist\fR of constraints may include multiple features separated
by ampersand (AND) and/or vertical bar (OR) operators.
-For example: \fB\-\-constraint="opteron&video"\fR or
+For example: \fB\-\-constraint="opteron&video"\fR or
\fB\-\-constraint="fast|faster"\fR.
In the first example, only nodes having both the feature "opteron" AND
the feature "video" will be used.
There is no mechanism to specify that you want one node with feature
"opteron" and another node with feature "video" in that case that no
node has both features.
-If only one of a set of possible options should be used for all allocated
-nodes, then use the OR operator and enclose the options within square brackets.
-For example: "\fB\-\-constraint=[rack1|rack2|rack3|rack4]"\fR might
-be used to specify that all nodes must be allocated on a single rack of
+If only one of a set of possible options should be used for all allocated
+nodes, then use the OR operator and enclose the options within square brackets.
+For example: "\fB\-\-constraint=[rack1|rack2|rack3|rack4]"\fR might
+be used to specify that all nodes must be allocated on a single rack of
the cluster, but any of those four racks can be used.
A request can also specify the number of nodes needed with some feature
-by appending an asterisk and count after the feature name.
-For example "\fBsrun \-\-nodes=16 \-\-constraint=graphics*4 ..."\fR
+by appending an asterisk and count after the feature name.
+For example "\fBsrun \-\-nodes=16 \-\-constraint=graphics*4 ..."\fR
indicates that the job requires 16 nodes at that at least four of those
nodes must have the feature "graphics."
Constraints with node counts may only be combined with AND operators.
-If no nodes have the requested features, then the job will be rejected
+If no nodes have the requested features, then the job will be rejected
by the slurm job manager.
.TP
@@ -288,22 +288,22 @@ Show this help message
Request that \fIncpus\fR be allocated \fBper process\fR. This may be
useful if the job is multithreaded and requires more than one CPU
per task for optimal performance. The default is one CPU per process.
-If \fB\-c\fR is specified without \fB\-n\fR, as many
+If \fB\-c\fR is specified without \fB\-n\fR, as many
tasks will be allocated per node as possible while satisfying
the \fB\-c\fR restriction. For instance on a cluster with 8 CPUs
-per node, a job request for 4 nodes and 3 CPUs per task may be
-allocated 3 or 6 CPUs per node (1 or 2 tasks per node) depending
-upon resource consumption by other jobs. Such a job may be
-unable to execute more than a total of 4 tasks.
+per node, a job request for 4 nodes and 3 CPUs per task may be
+allocated 3 or 6 CPUs per node (1 or 2 tasks per node) depending
+upon resource consumption by other jobs. Such a job may be
+unable to execute more than a total of 4 tasks.
This option may also be useful to spawn tasks without allocating
-resources to the job step from the job's allocation when running
+resources to the job step from the job's allocation when running
multiple job steps with the \fB\-\-exclusive\fR option.
.TP
\fB\-d\fR, \fB\-\-dependency\fR=<\fIdependency_list\fR>
Defer the start of this job until the specified dependencies have been
satisfied completed.
-<\fIdependency_list\fR> is of the form
+<\fIdependency_list\fR> is of the form
<\fItype:job_id[:job_id][,type:job_id[:job_id]]\fR>.
Many jobs can share the same dependency and these jobs may even belong to
different users. The value may be changed after job submission using the
@@ -349,7 +349,7 @@ If the specified file already exists, it will be overwritten.
.TP
\fB\-E\fR, \fB\-\-preserve-env\fR
-Pass the current values of environment variables SLURM_NNODES and
+Pass the current values of environment variables SLURM_NNODES and
SLURM_NPROCS through to the \fIexecutable\fR, rather than computing them
from commandline parameters.
@@ -363,28 +363,28 @@ parameter in slurm.conf.
.TP
\fB\-\-exclusive\fR
-When used to initiate a job, the job allocation cannot share nodes with
-other running jobs. This is the oposite of \-\-share, whichever option
-is seen last on the command line will win. (The default shared/exclusive
+When used to initiate a job, the job allocation cannot share nodes with
+other running jobs. This is the oposite of \-\-share, whichever option
+is seen last on the command line will win. (The default shared/exclusive
behaviour depends on system configuration.)
-This option can also be used when initiating more than job step within
-an existing resource allocation and you want separate processors to
-be dedicated to each job step. If sufficient processors are not
-available to initiate the job step, it will be deferred. This can
+This option can also be used when initiating more than job step within
+an existing resource allocation and you want separate processors to
+be dedicated to each job step. If sufficient processors are not
+available to initiate the job step, it will be deferred. This can
be thought of as providing resource management for the job within
it's allocation. Note that all CPUs allocated to a job are available
to each job step unless the \fB\-\-exclusive\fR option is used plus
-task affinity is configured. Since resource management is provided by
-processor, the \fB\-\-ntasks\fR option must be specified, but the
-following options should NOT be specified \fB\-\-nodes\fR,
+task affinity is configured. Since resource management is provided by
+processor, the \fB\-\-ntasks\fR option must be specified, but the
+following options should NOT be specified \fB\-\-nodes\fR,
\fB\-\-relative\fR, \fB\-\-distribution\fR=\fIarbitrary\fR.
See \fBEXAMPLE\fR below.
.TP
\fB\-\-gid\fR=<\fIgroup\fR>
-If \fBsrun\fR is run as root, and the \fB\-\-gid\fR option is used,
-submit the job with \fIgroup\fR's group access permissions. \fIgroup\fR
+If \fBsrun\fR is run as root, and the \fB\-\-gid\fR option is used,
+submit the job with \fIgroup\fR's group access permissions. \fIgroup\fR
may be the group name or the numerical group ID.
.\".TP
@@ -420,8 +420,8 @@ show this help message
.TP
\fB\-I\fR, \fB\-\-immediate\fR[=<\fIseconds\fR>]
-exit if resources are not available within the
-time period specified.
+exit if resources are not available within the
+time period specified.
If no argument is given, resources must be available immediately
for the request to succeed.
By default, \fB\-\-immediate\fR is off, and the command
@@ -433,7 +433,7 @@ Specify how stdin is to redirected. By default,
.B srun
redirects stdin from the terminal all tasks. See \fBIO Redirection\fR
below for more options.
-For OS X, the poll() function does not support stdin, so input from
+For OS X, the poll() function does not support stdin, so input from
a terminal is not possible.
.TP
@@ -455,10 +455,10 @@ Terminate a job if any task exits with a non\-zero exit code.
.TP
\fB\-k\fR, \fB\-\-no\-kill\fR
Do not automatically terminate a job of one of the nodes it has been
-allocated fails. This option is only recognized on a job allocation,
-not for the submission of individual job steps.
-The job will assume all responsibilities for fault\-tolerance. The
-active job step (MPI job) will almost certainly suffer a fatal error,
+allocated fails. This option is only recognized on a job allocation,
+not for the submission of individual job steps.
+The job will assume all responsibilities for fault\-tolerance. The
+active job step (MPI job) will almost certainly suffer a fatal error,
but subsequent job steps may be run if this option is specified. The
default action is to terminate job upon node failure.
@@ -472,9 +472,9 @@ task id.
.TP
\fB\-L\fR, \fB\-\-licenses\fR=<\fBlicense\fR>
-Specification of licenses (or other resources available on all
+Specification of licenses (or other resources available on all
nodes of the cluster) which must be allocated to this job.
-License names can be followed by an asterisk and count
+License names can be followed by an asterisk and count
(the default count is one).
Multiple license names should be comma separated (e.g.
"\-\-licenses=foo*4,bar").
@@ -487,13 +487,13 @@ Specify an alternate distribution method for remote processes.
.TP
.B block
The block method of distribution will allocate processes in\-order to
-the cpus on a node. If the number of processes exceeds the number of
-cpus on all of the nodes in the allocation then all nodes will be
-utilized. For example, consider an allocation of three nodes each with
-two cpus. A four\-process block distribution request will distribute
-those processes to the nodes with processes one and two on the first
-node, process three on the second node, and process four on the third node.
-Block distribution is the default behavior if the number of tasks
+the cpus on a node. If the number of processes exceeds the number of
+cpus on all of the nodes in the allocation then all nodes will be
+utilized. For example, consider an allocation of three nodes each with
+two cpus. A four\-process block distribution request will distribute
+those processes to the nodes with processes one and two on the first
+node, process three on the second node, and process four on the third node.
+Block distribution is the default behavior if the number of tasks
exceeds the number of nodes requested.
.TP
.B cyclic
@@ -505,7 +505,7 @@ if the number of tasks is no larger than the number of nodes requested.
.B plane
The tasks are distributed in blocks of a specified size.
The options include a number representing the size of the task block.
-This is followed by an optional specification of the task distribution
+This is followed by an optional specification of the task distribution
scheme within a block of tasks and between the blocks of tasks.
For more details (including examples and diagrams), please see
.br
@@ -516,9 +516,9 @@ and
https://computing.llnl.gov/linux/slurm/dist_plane.html.
.TP
.B arbitrary
-The arbitrary method of distribution will allocate processes in\-order as
+The arbitrary method of distribution will allocate processes in\-order as
listed in file designated by the environment variable SLURM_HOSTFILE. If
-this variable is listed it will over ride any other method specified.
+this variable is listed it will over ride any other method specified.
If not set the method will default to block. Inside the hostfile must
contain at minimum the number of hosts requested. If requesting tasks
(\-n) your tasks will be laid out on the nodes in the order of the file.
@@ -526,13 +526,13 @@ contain at minimum the number of hosts requested. If requesting tasks
.TP
\fB\-\-mail\-type\fR=<\fItype\fR>
-Notify user by email when certain event types occur.
-Valid \fItype\fR values are BEGIN, END, FAIL, ALL (any state change).
-The user to be notified is indicated with \fB\-\-mail\-user\fR.
+Notify user by email when certain event types occur.
+Valid \fItype\fR values are BEGIN, END, FAIL, ALL (any state change).
+The user to be notified is indicated with \fB\-\-mail\-user\fR.
.TP
\fB\-\-mail\-user\fR=<\fIuser\fR>
-User to receive email notification of state changes as defined by
+User to receive email notification of state changes as defined by
\fB\-\-mail\-type\fR.
The default value is the submitting user.
@@ -551,7 +551,7 @@ Also see \fB\-\-mem\-per\-cpu\fR.
\fB\-\-mem\-per\-cpu\fR=<\fIMB\fR>
Mimimum memory required per allocated CPU in MegaBytes.
Default value is \fBDefMemPerCPU\fR and the maximum value is
-\fBMaxMemPerCPU\fR. If configured, both of parameters can be
+\fBMaxMemPerCPU\fR. If configured, both of parameters can be
seen using the \fBscontrol show config\fR command.
This parameter would generally be used of individual processors
are allocated to jobs (\fBSelectType=select/cons_res\fR).
@@ -560,16 +560,16 @@ Also see \fB\-\-mem\fR.
.TP
\fB\-\-mem_bind\fR=[{\fIquiet,verbose\fR},]\fItype\fR
-Bind tasks to memory. Used only when the task/affinity plugin is enabled
+Bind tasks to memory. Used only when the task/affinity plugin is enabled
and the NUMA memory functions are available.
-\fBNote that the resolution of CPU and memory binding
-may differ on some architectures.\fR For example, CPU binding may be performed
-at the level of the cores within a processor while memory binding will
-be performed at the level of nodes, where the definition of "nodes"
-may differ from system to system. \fBThe use of any type other than
+\fBNote that the resolution of CPU and memory binding
+may differ on some architectures.\fR For example, CPU binding may be performed
+at the level of the cores within a processor while memory binding will
+be performed at the level of nodes, where the definition of "nodes"
+may differ from system to system. \fBThe use of any type other than
"none" or "local" is not recommended.\fR
-If you want greater control, try running a simple test code with the
-options "\-\-cpu_bind=verbose,none \-\-mem_bind=verbose,none" to determine
+If you want greater control, try running a simple test code with the
+options "\-\-cpu_bind=verbose,none \-\-mem_bind=verbose,none" to determine
the specific configuration.
NOTE: To have SLURM always report on the selected memory binding for
@@ -643,12 +643,12 @@ Specify a minimum number of threads per core.
.TP
\fB\-\-msg\-timeout\fR=<\fIseconds\fR>
Modify the job launch message timeout.
-The default value is \fBMessageTimeout\fR in the SLURM configuration file slurm.conf.
+The default value is \fBMessageTimeout\fR in the SLURM configuration file slurm.conf.
Changes to this are typically not recommended, but could be useful to diagnose problems.
.TP
\fB\-\-mpi\fR=<\fImpi_type\fR>
-Identify the type of MPI to be used. May result in unique initiation
+Identify the type of MPI to be used. May result in unique initiation
procedures.
.RS
.TP
@@ -674,17 +674,17 @@ For use with Infiniband.
For use with OpenMPI.
.TP
.B none
-No special MPI processing. This is the default and works with
+No special MPI processing. This is the default and works with
many other versions of MPI.
.RE
.TP
\fB\-\-multi\-prog\fR
-Run a job with different programs and different arguments for
-each task. In this case, the executable program specified is
-actually a configuration file specifying the executable and
+Run a job with different programs and different arguments for
+each task. In this case, the executable program specified is
+actually a configuration file specifying the executable and
arguments for each task. See \fBMULTIPLE PROGRAM CONFIGURATION\fR
-below for details on the configuration file contents.
+below for details on the configuration file contents.
.TP
\fB\-N\fR, \fB\-\-nodes\fR=<\fIminnodes\fR[\-\fImaxnodes\fR]>
@@ -694,16 +694,16 @@ A limit on the maximum node count may be specified with \fImaxnodes\fR
(e.g. "\-\-nodes=2\-4"). The minimum and maximum node count may be the
same to specify a specific number of nodes (e.g. "\-\-nodes=2\-2" will ask
for two and ONLY two nodes).
-The partition's node limits supersede those of the job.
-If a job's node limits are outside of the range permitted for its
-associated partition, the job will be left in a PENDING state.
-This permits possible execution at a later time, when the partition
+The partition's node limits supersede those of the job.
+If a job's node limits are outside of the range permitted for its
+associated partition, the job will be left in a PENDING state.
+This permits possible execution at a later time, when the partition
limit is changed.
-If a job node limit exceeds the number of nodes configured in the
+If a job node limit exceeds the number of nodes configured in the
partition, the job will be rejected.
-Note that the environment
-variable \fBSLURM_NNODES\fR will be set to the count of nodes actually
-allocated to the job. See the \fBENVIRONMENT VARIABLES \fR section
+Note that the environment
+variable \fBSLURM_NNODES\fR will be set to the count of nodes actually
+allocated to the job. See the \fBENVIRONMENT VARIABLES \fR section
for more information. If \fB\-N\fR is not specified, the default
behavior is to allocate enough nodes to satisfy the requirements of
the \fB\-n\fR and \fB\-c\fR options.
@@ -713,25 +713,25 @@ and without delaying the initiation of the job.
.TP
\fB\-n\fR, \fB\-\-ntasks\fR=<\fInumber\fR>
Specify the number of tasks to run. Request that \fBsrun\fR
-allocate resources for \fIntasks\fR tasks.
-The default is one task per socket or core (depending upon the value
-of the \fISelectTypeParameters\fR parameter in slurm.conf), but note
+allocate resources for \fIntasks\fR tasks.
+The default is one task per socket or core (depending upon the value
+of the \fISelectTypeParameters\fR parameter in slurm.conf), but note
that the \fB\-\-cpus\-per\-task\fR option will change this default.
.TP
\fB\-\-network\fR=<\fItype\fR>
-Specify the communication protocol to be used.
+Specify the communication protocol to be used.
This option is supported on AIX systems.
-Since POE is used to launch tasks, this option is not normally used or
+Since POE is used to launch tasks, this option is not normally used or
is specified using the \fBSLURM_NETWORK\fR environment variable.
The interpretation of \fItype\fR is system dependent.
-For systems with an IBM Federation switch, the following
+For systems with an IBM Federation switch, the following
comma\-separated and case insensitive types are recognized:
-\fBIP\fR (the default is user\-space), \fBSN_ALL\fR, \fBSN_SINGLE\fR,
-\fBBULK_XFER\fR and adapter names (e.g. \fBSNI0\fR and \fBSNI1\fR).
+\fBIP\fR (the default is user\-space), \fBSN_ALL\fR, \fBSN_SINGLE\fR,
+\fBBULK_XFER\fR and adapter names (e.g. \fBSNI0\fR and \fBSNI1\fR).
For more information, on IBM systems see \fIpoe\fR documentation on
the environment variables \fBMP_EUIDEVICE\fR and \fBMP_USE_BULK_XFER\fR.
-Note that only four jobs steps may be active at once on a node with the
+Note that only four jobs steps may be active at once on a node with the
\fBBULK_XFER\fR option due to limitations in the Federation switch driver.
.TP
@@ -741,7 +741,7 @@ With no adjustment value the scheduling priority is decreased
by 100. The adjustment range is from \-10000 (highest priority)
to 10000 (lowest priority). Only privileged users can specify
a negative adjustment. NOTE: This option is presently
-ignored if \fISchedulerType=sched/wiki\fR or
+ignored if \fISchedulerType=sched/wiki\fR or
\fISchedulerType=sched/wiki2\fR.
.TP
@@ -793,7 +793,7 @@ Specify the mode for stdout redirection. By default in interactive mode,
.B srun
collects stdout from all tasks and line buffers this output to
the attached terminal. With \fB\-\-output\fR stdout may be redirected
-to a file, to one file per task, or to /dev/null. See section
+to a file, to one file per task, or to /dev/null. See section
\fBIO Redirection\fR below for the various forms of \fImode\fR.
If the specified file already exists, it will be overwritten.
.br
@@ -869,7 +869,7 @@ The maximum stack size
\fB\-\-pty\fR
Execute task zero in pseudo terminal.
Implicitly sets \fB\-\-unbuffered\fR.
-Implicitly sets \fB\-\-error\fR and \fB\-\-output\fR to /dev/null
+Implicitly sets \fB\-\-error\fR and \fB\-\-output\fR to /dev/null
for all tasks except task zero.
Not currently supported on AIX platforms.
@@ -880,9 +880,9 @@ Suppress informational messages from srun. Errors will still be displayed.
.TP
\fB\-q\fR, \fB\-\-quit\-on\-interrupt\fR
Quit immediately on single SIGINT (Ctrl\-C). Use of this option
-disables the status feature normally available when \fBsrun\fR receives
+disables the status feature normally available when \fBsrun\fR receives
a single Ctrl\-C and causes \fBsrun\fR to instead immediately terminate the
-running job.
+running job.
.TP
\fB\-\-qos\fR=<\fIqos\fR>
@@ -894,16 +894,16 @@ the SLURM configuration parameter, AccountingStorageEnforce, includes
.TP
\fB\-r\fR, \fB\-\-relative\fR=<\fIn\fR>
-Run a job step relative to node \fIn\fR of the current allocation.
+Run a job step relative to node \fIn\fR of the current allocation.
This option may be used to spread several job steps out among the
nodes of the current job. If \fB\-r\fR is used, the current job
step will begin at node \fIn\fR of the allocated nodelist, where
-the first node is considered node 0. The \fB\-r\fR option is not
+the first node is considered node 0. The \fB\-r\fR option is not
permitted along with \fB\-w\fR or \fB\-x\fR, and will be silently
ignored when not running within a prior allocation (i.e. when
-SLURM_JOB_ID is not set). The default for \fIn\fR is 0. If the
-value of \fB\-\-nodes\fR exceeds the number of nodes identified
-with the \fB\-\-relative\fR option, a warning message will be
+SLURM_JOB_ID is not set). The default for \fIn\fR is 0. If the
+value of \fB\-\-nodes\fR exceeds the number of nodes identified
+with the \fB\-\-relative\fR option, a warning message will be
printed and the \fB\-\-relative\fR option will take precedence.
.TP
@@ -917,24 +917,24 @@ Allocate resources for the job from the named reservation.
.TP
\fB\-\-restart\-dir\fR=<\fIdirectory\fR>
-Specifies the directory from which the job or job step's checkpoint should
+Specifies the directory from which the job or job step's checkpoint should
be read (used by the checkpoint/blcrm and checkpoint/xlch plugins only).
.TP
\fB\-s\fR, \fB\-\-share\fR
-The job can share nodes with other running jobs. This may result in faster job
+The job can share nodes with other running jobs. This may result in faster job
initiation and higher system utilization, but lower application performance.
.TP
\fB\-\-signal\fR=<\fIsig_num\fR>[@<\fIsig_time\fR>]
-When a job is within \fIsig_time\fR seconds of its end time,
-send it the signal \fIsig_num\fR.
-Due to the resolution of event handling by SLURM, the signal may
+When a job is within \fIsig_time\fR seconds of its end time,
+send it the signal \fIsig_num\fR.
+Due to the resolution of event handling by SLURM, the signal may
be sent up to 60 seconds earlier than specified.
Both \fIsig_time\fR and \fIsig_num\fR must have integer values
between zero and 65535.
-By default, no signal is sent before the job's end time.
-If a \fIsig_num\fR is specified without any \fIsig_time\fR,
+By default, no signal is sent before the job's end time.
+If a \fIsig_num\fR is specified without any \fIsig_time\fR,
the default time will be 60 seconds.
.TP
@@ -947,16 +947,16 @@ the job. By default only errors are displayed.
.TP
\fB\-T\fR, \fB\-\-threads\fR=<\fInthreads\fR>
Request that \fBsrun\fR
-use \fInthreads\fR to initiate and control the parallel job. The
+use \fInthreads\fR to initiate and control the parallel job. The
default value is the smaller of 60 or the number of nodes allocated.
-This should only be used to set a low thread count for testing on
+This should only be used to set a low thread count for testing on
very small memory computers.
.TP
\fB\-t\fR, \fB\-\-time\fR=<\fItime\fR>
Set a limit on the total run time of the job or job step. If the
-requested time limit for a job exceeds the partition's time limit,
-the job will be left in a PENDING state (possibly indefinitely).
+requested time limit for a job exceeds the partition's time limit,
+the job will be left in a PENDING state (possibly indefinitely).
If the requested time limit for a job step exceeds the partition's
time limit, the job step will not be initiated. The default time
limit is the partition's time limit. When the time limit is reached,
@@ -980,8 +980,8 @@ killed along with any descendant processes.
.TP
\fB\-\-task\-prolog\fR=<\fIexecutable\fR>
-The \fBslurmstepd\fR daemon will run \fIexecutable\fR just before launching
-each task. This will be executed after any TaskProlog parameter
+The \fBslurmstepd\fR daemon will run \fIexecutable\fR just before launching
+each task. This will be executed after any TaskProlog parameter
in slurm.conf is executed.
Besides the normal environment variables, this has SLURM_TASK_PID
available to identify the process ID of the task being started.
@@ -1076,8 +1076,8 @@ Default from \fIblugene.conf\fR if not set.
.TP
\fB\-\-conn\-type\fR=<\fItype\fR>
-Require the partition connection type to be of a certain type.
-On Blue Gene the acceptable of \fItype\fR are MESH, TORUS and NAV.
+Require the partition connection type to be of a certain type.
+On Blue Gene the acceptable of \fItype\fR are MESH, TORUS and NAV.
If NAV, or if not set, then SLURM will try to fit a TORUS else MESH.
You should not normally set this option.
SLURM will normally allocate a TORUS if possible for a given geometry.
@@ -1087,10 +1087,10 @@ for virtual node mode, and HTC_L for Linux mode.
.TP
\fB\-g\fR, \fB\-\-geometry\fR=<\fIXxYxZ\fR>
-Specify the geometry requirements for the job. The three numbers
-represent the required geometry giving dimensions in the X, Y and
-Z directions. For example "\-\-geometry=2x3x4", specifies a block
-of nodes having 2 x 3 x 4 = 24 nodes (actually base partitions on
+Specify the geometry requirements for the job. The three numbers
+represent the required geometry giving dimensions in the X, Y and
+Z directions. For example "\-\-geometry=2x3x4", specifies a block
+of nodes having 2 x 3 x 4 = 24 nodes (actually base partitions on
Blue Gene).
.TP
@@ -1110,7 +1110,7 @@ Default from \fIblugene.conf\fR if not set.
.TP
\fB\-R\fR, \fB\-\-no\-rotate\fR
-Disables rotation of the job's requested geometry in order to fit an
+Disables rotation of the job's requested geometry in order to fit an
appropriate partition.
By default the specified geometry can rotate in three dimensions.
@@ -1172,13 +1172,13 @@ will consider this an error, as 15 processes cannot run across 16 nodes.
.B "IO Redirection"
.PP
By default, stdout and stderr will be redirected from all tasks to the
-stdout and stderr of \fBsrun\fR, and stdin will be redirected from the
-standard input of \fBsrun\fR to all remote tasks.
-For OS X, the poll() function does not support stdin, so input from
+stdout and stderr of \fBsrun\fR, and stdin will be redirected from the
+standard input of \fBsrun\fR to all remote tasks.
+For OS X, the poll() function does not support stdin, so input from
a terminal is not possible.
-This behavior may be changed with the
-\fB\-\-output\fR, \fB\-\-error\fR, and \fB\-\-input\fR
-(\fB\-o\fR, \fB\-e\fR, \fB\-i\fR) options. Valid format specifications
+This behavior may be changed with the
+\fB\-\-output\fR, \fB\-\-error\fR, and \fB\-\-input\fR
+(\fB\-o\fR, \fB\-e\fR, \fB\-i\fR) options. Valid format specifications
for these options are
.TP 10
\fBall\fR
@@ -1187,7 +1187,7 @@ stdin is broadcast to all remote tasks.
(This is the default behavior)
.TP
\fBnone\fR
-stdout and stderr is not received from any task.
+stdout and stderr is not received from any task.
stdin is not sent to any task (stdin is closed).
.TP
\fItaskid\fR
@@ -1198,7 +1198,7 @@ stdin is redirected from the stdin of \fBsrun\fR to this same task.
This file will be written on the node executing the task.
.TP
\fIfilename\fR
-\fBsrun\fR will redirect stdout and/or stderr to the named file from
+\fBsrun\fR will redirect stdout and/or stderr to the named file from
all tasks.
stdin will be redirected from the named file and broadcast to all
tasks in the job. \fIfilename\fR refers to a path on the host
@@ -1207,22 +1207,22 @@ this may result in the output appearing in different places depending
on whether the job is run in batch mode.
.TP
format string
-\fBsrun\fR allows for a format string to be used to generate the
-named IO file
+\fBsrun\fR allows for a format string to be used to generate the
+named IO file
described above. The following list of format specifiers may be
used in the format string to generate a filename that will be
-unique to a given jobid, stepid, node, or task. In each case,
+unique to a given jobid, stepid, node, or task. In each case,
the appropriate number of files are opened and associated with
-the corresponding tasks. Note that any format string containing
-%t, %n, and/or %N will be written on the node executing the task
+the corresponding tasks. Note that any format string containing
+%t, %n, and/or %N will be written on the node executing the task
rather than the node where \fBsrun\fR executes.
.RS 10
.TP
%J
jobid.stepid of the running job. (e.g. "128.0")
.TP
-%j
-jobid of the running job.
+%j
+jobid of the running job.
.TP
%s
stepid of the running job.
@@ -1239,7 +1239,7 @@ task identifier (rank) relative to current job. This will create a
separate IO file per task.
.PP
A number placed between the percent character and format specifier may be
-used to zero\-pad the result in the IO filename. This number is ignored if
+used to zero\-pad the result in the IO filename. This number is ignored if
the format specifier corresponds to non\-numeric data (%N for example).
Some examples of how the format string may be used for a 4 task job step
@@ -1251,7 +1251,7 @@ job128.0.out
job%4j.out
job0128.out
.TP
-job%j\-%2t.out
+job%j\-%2t.out
job128\-00.out, job128\-01.out, ...
.PP
.RS -10
@@ -1259,8 +1259,8 @@ job128\-00.out, job128\-01.out, ...
.SH "INPUT ENVIRONMENT VARIABLES"
.PP
-Some srun options may be set via environment variables.
-These environment variables, along with their corresponding options,
+Some srun options may be set via environment variables.
+These environment variables, along with their corresponding options,
are listed below.
Note: Command line options will always override these settings.
.TP 22
@@ -1268,10 +1268,10 @@ Note: Command line options will always override these settings.
This is used exclusively with PMI (MPICH2 and MVAPICH2) and
controls the fanout of data communications. The srun command
sends messages to application programs (via the PMI library)
-and those applications may be called upon to forward that
+and those applications may be called upon to forward that
data to up to this number of additional tasks. Higher values
-offload work from the srun command to the applications and
-likely increase the vulnerability to failures.
+offload work from the srun command to the applications and
+likely increase the vulnerability to failures.
The default value is 32.
.TP
\fBPMI_FANOUT_OFF_HOST\fR
@@ -1279,23 +1279,23 @@ This is used exclusively with PMI (MPICH2 and MVAPICH2) and
controls the fanout of data communications. The srun command
sends messages to application programs (via the PMI library)
and those applications may be called upon to forward that
-data to additional tasks. By default, srun sends one message
-per host and one task on that host forwards the data to other
-tasks on that host up to \fBPMI_FANOUT\fR.
-If \fBPMI_FANOUT_OFF_HOST\fR is defined, the user task
+data to additional tasks. By default, srun sends one message
+per host and one task on that host forwards the data to other
+tasks on that host up to \fBPMI_FANOUT\fR.
+If \fBPMI_FANOUT_OFF_HOST\fR is defined, the user task
may be required to forward the data to tasks on other hosts.
-Setting \fBPMI_FANOUT_OFF_HOST\fR may increase performance.
+Setting \fBPMI_FANOUT_OFF_HOST\fR may increase performance.
Since more work is performed by the PMI library loaded by
-the user application, failures also can be more common and
+the user application, failures also can be more common and
more difficult to diagnose.
.TP
\fBPMI_TIME\fR
-This is used exclusively with PMI (MPICH2 and MVAPICH2) and
-controls how much the communications from the tasks to the
-srun are spread out in time in order to avoid overwhelming the
+This is used exclusively with PMI (MPICH2 and MVAPICH2) and
+controls how much the communications from the tasks to the
+srun are spread out in time in order to avoid overwhelming the
srun command with work. The default value is 500 (microseconds)
-per task. On relatively slow processors or systems with very
-large processor counts (and large PMI data sets), higher values
+per task. On relatively slow processors or systems with very
+large processor counts (and large PMI data sets), higher values
may be required.
.TP
\fBSLURM_CONF\fR
@@ -1350,15 +1350,15 @@ Same as \fB\-\-epilog\fR
Same as \fB\-\-exclusive\fR
.TP
\fBSLURM_EXIT_ERROR\fR
-Specifies the exit code generated when a SLURM error occurs
+Specifies the exit code generated when a SLURM error occurs
(e.g. invalid options).
This can be used by a script to distinguish application exit codes from
various SLURM error conditions.
Also see \fBSLURM_EXIT_IMMEDIATE\fR.
.TP
\fBSLURM_EXIT_IMMEDIATE\fR
-Specifies the exit code generated when the \fB\-\-immediate\fR option
-is used and resources are not currently available.
+Specifies the exit code generated when the \fB\-\-immediate\fR option
+is used and resources are not currently available.
This can be used by a script to distinguish application exit codes from
various SLURM error conditions.
Also see \fBSLURM_EXIT_ERROR\fR.
@@ -1457,8 +1457,8 @@ Same as \fB\-W, \-\-wckey\fR
.SH "OUTPUT ENVIRONMENT VARIABLES"
.PP
-srun will set some environment variables in the environment
-of the executing tasks on the remote compute nodes.
+srun will set some environment variables in the environment
+of the executing tasks on the remote compute nodes.
These environment variables are:
.TP 22
@@ -1483,10 +1483,10 @@ if specified on the execute line.
.TP
\fBSLURM_CPUS_ON_NODE\fR
Count of processors available to the job on this node.
-Note the select/linear plugin allocates entire nodes to
+Note the select/linear plugin allocates entire nodes to
jobs, so the value indicates the total count of CPUs on the node.
-The select/cons_res plugin allocates individual processors
-to jobs, so this number indicates the number of processors
+The select/cons_res plugin allocates individual processors
+to jobs, so this number indicates the number of processors
on this node allocated to the job.
.TP
@@ -1502,7 +1502,7 @@ Job id of the executing job
.TP
\fBSLURM_LAUNCH_NODE_IPADDR\fR
-IP address of the node from which the task launch was
+IP address of the node from which the task launch was
initiated (where the srun command ran from)
.TP
\fBSLURM_LOCALID\fR
@@ -1567,19 +1567,19 @@ Do not free a block on Blue Gene systems only.
The block name on Blue Gene systems only.
.SH "SIGNALS AND ESCAPE SEQUENCES"
-Signals sent to the \fBsrun\fR command are automatically forwarded to
+Signals sent to the \fBsrun\fR command are automatically forwarded to
the tasks it is controlling with a few exceptions. The escape sequence
-\fB<control\-c>\fR will report the state of all tasks associated with
-the \fBsrun\fR command. If \fB<control\-c>\fR is entered twice within
+\fB<control\-c>\fR will report the state of all tasks associated with
+the \fBsrun\fR command. If \fB<control\-c>\fR is entered twice within
one second, then the associated SIGINT signal will be sent to all tasks
-and a termination sequence will be entered sending SIGCONT, SIGTERM,
+and a termination sequence will be entered sending SIGCONT, SIGTERM,
and SIGKILL to all spawned tasks.
-If a third \fB<control\-c>\fR is received, the srun program will be
+If a third \fB<control\-c>\fR is received, the srun program will be
terminated without waiting for remote tasks to exit or their I/O to
complete.
-The escape sequence \fB<control\-z>\fR is presently ignored. Our intent
-is for this put the \fBsrun\fR command into a mode where various special
+The escape sequence \fB<control\-z>\fR is presently ignored. Our intent
+is for this put the \fBsrun\fR command into a mode where various special
actions may be invoked.
.SH "MPI SUPPORT"
@@ -1593,7 +1593,7 @@ and some MPICH1 modes). For example: "srun \-n16 a.out".
2. SLURM creates a resource allocation for the job and then
mpirun launches tasks using SLURM's infrastructure (OpenMPI,
-LAM/MPI, HP-MPI and some MPICH1 modes).
+LAM/MPI, HP-MPI and some MPICH1 modes).
3. SLURM creates a resource allocation for the job and then
mpirun launches tasks using some mechanism other than SLURM,
@@ -1602,8 +1602,8 @@ These tasks initiated outside of SLURM's monitoring
or control. SLURM's epilog should be configured to purge
these tasks when the job's allocation is relinquished.
-See \fIhttps://computing.llnl.gov/linux/slurm/mpi_guide.html\fR
-for more information on use of these various MPI implementation
+See \fIhttps://computing.llnl.gov/linux/slurm/mpi_guide.html\fR
+for more information on use of these various MPI implementation
with SLURM.
.SH "MULTIPLE PROGRAM CONFIGURATION"
@@ -1614,11 +1614,11 @@ space:
Task rank
One or more task ranks to use this configuration.
Multiple values may be comma separated.
-Ranges may be indicated with two numbers separated with a '\-' with
+Ranges may be indicated with two numbers separated with a '\-' with
the smaller number first (e.g. "0\-4" and not "4\-0").
-To indicate all tasks, specify a rank of '*' (in which case you probably
+To indicate all tasks, specify a rank of '*' (in which case you probably
should not be using this option).
-If an attempt is made to initiate a task for which no executable
+If an attempt is made to initiate a task for which no executable
program is defined, the following error message will be produced
"No executable program specified for this task".
.TP
@@ -1661,8 +1661,8 @@ For example:
.SH "EXAMPLES"
This simple example demonstrates the execution of the command \fBhostname\fR
-in eight tasks. At least eight processors will be allocated to the job
-(the same as the task count) on however many nodes are required to satisfy
+in eight tasks. At least eight processors will be allocated to the job
+(the same as the task count) on however many nodes are required to satisfy
the request. The output of each task will be proceeded with its task number.
(The machine "dev" in the example below has a total of two CPUs per node)
@@ -1705,8 +1705,8 @@ dev[7\-10]
.fi
.PP
-The follwing script runs two job steps in parallel
-within an allocated set of nodes.
+The follwing script runs two job steps in parallel
+within an allocated set of nodes.
.nf
@@ -1730,8 +1730,8 @@ STEPID PARTITION USER TIME NODELIST
.fi
.PP
This example demonstrates how one executes a simple MPICH job.
-We use \fBsrun\fR to build a list of machines (nodes) to be used by
-\fBmpirun\fR in its required format. A sample command line and
+We use \fBsrun\fR to build a list of machines (nodes) to be used by
+\fBmpirun\fR in its required format. A sample command line and
the script to be executed follow.
.nf
@@ -1752,11 +1752,11 @@ rm $MACHINEFILE
> salloc \-N2 \-n4 test.sh
-.fi
+.fi
.PP
-This simple example demonstrates the execution of different jobs on different
-nodes in the same srun. You can do this for any number of nodes or any
-number of jobs. The executables are placed on the nodes sited by the
+This simple example demonstrates the execution of different jobs on different
+nodes in the same srun. You can do this for any number of nodes or any
+number of jobs. The executables are placed on the nodes sited by the
SLURM_NODEID env var. Starting at 0 and going to the number specified on
the srun commandline.
@@ -1773,23 +1773,23 @@ esac
> srun \-N2 test.sh
dev0
is where I am running
-I am running on
+I am running on
dev1
.fi
.PP
-This example demonstrates use of multi\-core options to control layout
-of tasks.
-We request that four sockets per node and two cores per socket be
-dedicated to the job.
+This example demonstrates use of multi\-core options to control layout
+of tasks.
+We request that four sockets per node and two cores per socket be
+dedicated to the job.
.nf
> srun \-N2 \-B 4\-4:2\-2 a.out
.fi
.PP
-This example shows a script in which Slurm is used to provide resource
-management for a job by executing the various job steps as processors
+This example shows a script in which Slurm is used to provide resource
+management for a job by executing the various job steps as processors
become available for their dedicated use.
.nf
diff --git a/doc/man/man1/srun_cr.1 b/doc/man/man1/srun_cr.1
index ca7a320932a..11378aa7596 100644
--- a/doc/man/man1/srun_cr.1
+++ b/doc/man/man1/srun_cr.1
@@ -9,7 +9,7 @@ srun_cr \- run parallel jobs with checkpoint/restart support
.SH DESCRIPTION
The design of \fBsrun_cr\fR is inspired by \fBmpiexec_cr\fR from MVAPICH2 and
\fBcr_restart\fR form BLCR.
-It is a wrapper around the \fBsrun\fR command to enable batch job
+It is a wrapper around the \fBsrun\fR command to enable batch job
checkpoint/restart support when used with SLURM's \fBcheckpoint/blcr\fR plugin.
.SH "OPTIONS"
@@ -22,12 +22,12 @@ See "man srun" for details.
After initialization, \fBsrun_cr\fR registers a thread context callback
function.
Then it forks a process and executes "cr_run \-\-omit srun" with its arguments.
-\fBcr_run\fR is employed to exclude the \fBsrun\fR process from being dumped
+\fBcr_run\fR is employed to exclude the \fBsrun\fR process from being dumped
upon checkpoint.
-All catchable signals except SIGCHLD sent to \fBsrun_cr\fR will be forwarded
+All catchable signals except SIGCHLD sent to \fBsrun_cr\fR will be forwarded
to the child \fBsrun\fR process.
SIGCHLD will be captured to mimic the exit status of \fBsrun\fR when it exits.
-Then \fBsrun_cr\fR loops waiting for termination of tasks being launched
+Then \fBsrun_cr\fR loops waiting for termination of tasks being launched
from \fBsrun\fR.
The step launch logic of SLURM is augmented to check if \fBsrun\fR is running
@@ -39,16 +39,16 @@ After launching the tasks, \fBsrun\fR tires to connect to the socket and sends
the job ID, step ID and the nodes allocated to the step to \fBsrun_cr\fR.
Upon checkpoint, \fRsrun_cr\fR checks to see if the tasks have been launched.
-If not \fRsrun_cr\fR first forwards the checkpoint request to the tasks by
+If not \fRsrun_cr\fR first forwards the checkpoint request to the tasks by
calling the SLURM API \fBslurm_checkpoint_tasks()\fR before dumping its process
context.
-Upon restart, \fBsrun_cr\fR checks to see if the tasks have been previously
-launched and checkpointed.
+Upon restart, \fBsrun_cr\fR checks to see if the tasks have been previously
+launched and checkpointed.
If true, the environment variable \fRSLURM_RESTART_DIR\fR is set to the directory
of the checkpoint image files of the tasks.
-Then \fBsrun\fR is forked and executed again.
-The environment variable will be used by the \fBsrun\fR command to restart
+Then \fBsrun\fR is forked and executed again.
+The environment variable will be used by the \fBsrun\fR command to restart
execution of the tasks from the previous checkpoint.
.SH "COPYING"
diff --git a/doc/man/man1/sshare.1 b/doc/man/man1/sshare.1
index 2f8a890ba03..9d76c820d79 100644
--- a/doc/man/man1/sshare.1
+++ b/doc/man/man1/sshare.1
@@ -9,7 +9,7 @@ sshare \- Tool for listing the shares of associations to a cluster.
.SH "DESCRIPTION"
\fBsshare\fR is used to view SLURM share information. This command is
only viable when running with the priority/multifactor plugin.
-The sshare information is derived from a database with the interface
+The sshare information is derived from a database with the interface
being provided by \fBslurmdbd\fR (SLURM Database daemon) which is
read in from the slurmctld and used to process the shares available
to a given association. sshare provides SLURM share information of
diff --git a/doc/man/man1/sstat.1 b/doc/man/man1/sstat.1
index 27d30348fbd..3501dcdfe2c 100644
--- a/doc/man/man1/sstat.1
+++ b/doc/man/man1/sstat.1
@@ -5,103 +5,103 @@ sstat \- Display various status information
of a running job/step.
.SH "SYNOPSIS"
-.BR "sstat "
-[\fIOPTIONS\fR...]
+.BR "sstat "
+[\fIOPTIONS\fR...]
.SH "DESCRIPTION"
.PP
Status information for running jobs invoked with SLURM.
.PP
-The
+The
.BR "sstat "
command displays job status information for your analysis.
-The
+The
.BR "sstat "
command displays information pertaining to CPU, Task, Node, Resident
Set Size (RSS) and Virtual Memory (VM).
-You can tailor the output with the use of the
-\f3\-\-fields=\fP
+You can tailor the output with the use of the
+\f3\-\-fields=\fP
option to specify the fields to be shown.
.PP
-For the root user, the
+For the root user, the
.BR "sstat "
command displays job status data for any job running on the system.
.PP
-For the non\-root user, the
+For the non\-root user, the
.BR "sstat "
-command limits the display of job status data to jobs that were
+command limits the display of job status data to jobs that were
launched with their own user identifier (UID).
-.TP
+.TP
\f3\-a \fP\f3,\fP \f3\-\-allsteps\fP
Print all steps for the given job(s) when no step is specified.
-.TP
+.TP
\f3\-e \fP\f3,\fP \f3\-\-helpformat\fP
Print a list of fields that can be specified with the '\-\-format' option.
-.TP
+.TP
\f3\-h \fP\f3,\fP \f3\-\-help\fP
Displays a general help message.
-.TP
+.TP
\f3\-j \fP\f3,\fP \f3\-\-jobs\fP
Format is <job(.step)>. Stat this job step or comma-separated list of
job steps. This option is required. The step portion will default to
step 0 if not specified, unless the \-\-allsteps flag is set where not
specifing a step will result in all running steps to be displayed.
-.TP
+.TP
\f3\-n \fP\f3,\fP \f3\-\-noheader\fP
No header will be added to the beginning of output. The default is to print a header.
-.TP
+.TP
\f3\-o \fP\f3,\fP \f3\-\-format\fP,\fP \f3\-\-fields\fP
Comma seperated list of fields.
(use '\-\-helpformat' for a list of available fields).
-.TP
+.TP
\f3\-p \fP\f3,\fP \f3\-\-parsable\fP
output will be '|' delimited with a '|' at the end.
-.TP
+.TP
\f3\-P \fP\f3,\fP \f3\-\-parsable2\fP
output will be '|' delimited without a '|' at the end
-.TP
+.TP
\f3\-\-usage\fP
Display brief usage message.
-.TP
+.TP
\f3\-v\fP\f3,\fP \f3\-\-verbose\fP
Primarily for debugging purposes, report the state of various variables during processing.
-.TP
+.TP
\f3\-V \fP\f3,\fP \f3\-\-version\fP
Print version.
.SS "Job Status Fields"
The following are the field options:
-.RS
+.RS
.TP
\f3AveCPU\fP
-.TP
-\f3AvePages\fP
+.TP
+\f3AvePages\fP
.TP
-\f3AveRSS\fP
+\f3AveRSS\fP
.TP
\f3AveVMSize\fP
-.TP
-\f3JobID\fP
+.TP
+\f3JobID\fP
.TP
diff --git a/doc/man/man1/strigger.1 b/doc/man/man1/strigger.1
index a797e2399ad..46695b185aa 100644
--- a/doc/man/man1/strigger.1
+++ b/doc/man/man1/strigger.1
@@ -12,37 +12,37 @@ strigger \- Used set, get or clear Slurm trigger information.
.SH "DESCRIPTION"
\fBstrigger\fR is used to set, get or clear Slurm trigger information.
-Triggers include events such as a node failing, a job reaching its
+Triggers include events such as a node failing, a job reaching its
time limit or a job terminating.
-These events can cause actions such as the execution of an arbitrary
-script.
-Typical uses include notifying system administrators of node failures
+These events can cause actions such as the execution of an arbitrary
+script.
+Typical uses include notifying system administrators of node failures
and gracefully terminating a job when it's time limit is approaching.
-A hostlist expression for the nodelist or job ID is passed as an argument
+A hostlist expression for the nodelist or job ID is passed as an argument
to the program.
-Trigger events are not processed instantly, but a check is performed for
-trigger events on a periodic basis (currently every 15 seconds).
-Any trigger events which occur within that interval will be compared
-against the trigger programs set at the end of the time interval.
+Trigger events are not processed instantly, but a check is performed for
+trigger events on a periodic basis (currently every 15 seconds).
+Any trigger events which occur within that interval will be compared
+against the trigger programs set at the end of the time interval.
The trigger program will be executed once for any event occuring in
that interval.
The record of those events (e.g. nodes which went DOWN in the previous
15 seconds) will then be cleared.
-The trigger program must set a new trigger before the end of the next
+The trigger program must set a new trigger before the end of the next
interval to insure that no trigger events are missed.
If desired, multiple trigger programs can be set for the same event.
-\fBIMPORTANT NOTE:\fR This command can only set triggers if run by the
+\fBIMPORTANT NOTE:\fR This command can only set triggers if run by the
user \fISlurmUser\fR unless \fISlurmUser\fR is configured as user root.
This is required for the \fIslurmctld\fR daemon to set the appropriate
-user and group IDs for the executed program.
-Also note that the program is executed on the same node that the
+user and group IDs for the executed program.
+Also note that the program is executed on the same node that the
\fIslurmctld\fR daemon uses rather than some allocated compute node.
To check the value of \fISlurmUser\fR, run the command:
-\fIscontrol show config | grep SlurmUser\fR
-
+\fIscontrol show config | grep SlurmUser\fR
+
.SH "ARGUMENTS"
.TP
\fB\-\-block_err\fP
@@ -52,7 +52,7 @@ Trigger an event when a BlueGene block enters an ERROR state.
\fB\-\-clear\fP
Clear or delete a previously defined event trigger.
The \fB\-\-id\fR, \fB\-\-jobid\fR or \fB\-\-userid\fR
-option must be specified to identify the trigger(s) to
+option must be specified to identify the trigger(s) to
be cleared.
.TP
@@ -85,28 +85,28 @@ Trigger ID number.
\fB\-I\fR, \fB\-\-idle\fR
Trigger an event if the specified node remains in an IDLE state
for at least the time period specified by the \fB\-\-offset\fR
-option. This can be useful to hibernate a node that remains idle,
+option. This can be useful to hibernate a node that remains idle,
thus reducing power consumption.
.TP
\fB\-j\fR, \fB\-\-jobid\fR=\fIid\fR
Job ID of interest.
-\fBNOTE:\fR The \fB\-\-jobid\fR option can not be used in conjunction
-with the \fB\-\-node\fR option. When the \fB\-\-jobid\fR option is
-used in conjunction with the \fB\-\-up\fR or \fB\-\-down\fR option,
-all nodes allocated to that job will considered the nodes used as a
+\fBNOTE:\fR The \fB\-\-jobid\fR option can not be used in conjunction
+with the \fB\-\-node\fR option. When the \fB\-\-jobid\fR option is
+used in conjunction with the \fB\-\-up\fR or \fB\-\-down\fR option,
+all nodes allocated to that job will considered the nodes used as a
trigger event.
.TP
\fB\-n\fR, \fB\-\-node\fR[=\fIhost\fR]
-Host name(s) of interest.
-By default, all nodes associated with the job (if \fB\-\-jobid\fR
+Host name(s) of interest.
+By default, all nodes associated with the job (if \fB\-\-jobid\fR
is specified) or on the system are considered for event triggers.
-\fBNOTE:\fR The \fB\-\-node\fR option can not be used in conjunction
-with the \fB\-\-jobid\fR option. When the \fB\-\-jobid\fR option is
-used in conjunction with the \fB\-\-up\fR, \fB\-\-down\fR or
-\fB\-\-drained\fR option,
-all nodes allocated to that job will considered the nodes used as a
+\fBNOTE:\fR The \fB\-\-node\fR option can not be used in conjunction
+with the \fB\-\-jobid\fR option. When the \fB\-\-jobid\fR option is
+used in conjunction with the \fB\-\-up\fR, \fB\-\-down\fR or
+\fB\-\-drained\fR option,
+all nodes allocated to that job will considered the nodes used as a
trigger event.
.TP
@@ -114,8 +114,8 @@ trigger event.
The specified action should follow the event by this time interval.
Specify a negative value if action should preceded the event.
The default value is zero if no \fB\-\-offset\fR option is specified.
-The resolution of this time is about 20 seconds, so to execute
-a script not less than five minutes prior to a job reaching its
+The resolution of this time is about 20 seconds, so to execute
+a script not less than five minutes prior to a job reaching its
time limit, specify \fB\-\-offset=320\fR (5 minutes plus 20 seconds).
.TP
@@ -123,12 +123,12 @@ time limit, specify \fB\-\-offset=320\fR (5 minutes plus 20 seconds).
Execute the program at the specified fully qualified pathname
when the event occurs.
The program will be executed as the user who sets the trigger.
-If the program fails to terminate within 5 minutes, it will
+If the program fails to terminate within 5 minutes, it will
be killed along with any spawned processes.
.TP
\fB\-Q\fR, \fB\-\-quiet\fR
-Do not report non\-fatal errors.
+Do not report non\-fatal errors.
This can be useful to clear triggers which may have already been purged.
.TP
@@ -138,9 +138,9 @@ Trigger an event when the system configuration changes.
.TP
\fB\-\-set\fP
Register an event trigger based upon the supplied options.
-NOTE: An event is only triggered once. A new event trigger
-must be set established for future events of the same type
-to be processed.
+NOTE: An event is only triggered once. A new event trigger
+must be set established for future events of the same type
+to be processed.
.TP
\fB\-t\fR, \fB\-\-time\fR
@@ -159,7 +159,7 @@ Specify either a user name or user ID.
.TP
\fB\-v\fR, \fB\-\-verbose\fR
-Print detailed event logging. This includes time\-stamps on data structures,
+Print detailed event logging. This includes time\-stamps on data structures,
record counts, etc.
.TP
@@ -181,13 +181,13 @@ Resource ID: job ID or host names or "*" for any host
.TP
\fBTYPE\fP
-Trigger type: \fItime\fR or \fIfini\fR (for jobs only),
+Trigger type: \fItime\fR or \fIfini\fR (for jobs only),
\fIdown\fR or \fIup\fR (for jobs or nodes), or
\fIdrained\fR, \fIidle\fR or \fIreconfig\fR (for nodes only)
.TP
\fBOFFSET\fP
-Time offset in seconds. Negative numbers indicated the action should
+Time offset in seconds. Negative numbers indicated the action should
occur before the event (if possible)
.TP
@@ -199,7 +199,7 @@ Name of the user requesting the action
Pathname of the program to execute when the event occurs
.SH "EXAMPLES"
-Execute the program "/usr/sbin/slurm_admin_notify" whenever
+Execute the program "/usr/sbin/slurm_admin_notify" whenever
any node in the cluster goes down. The subject line will include
the node names which have entered the down state (passed as an
argument to the script by SLURM).
@@ -228,7 +228,7 @@ any node in the cluster remains in the idle state for at least
.fi
.PP
-Execute the program "/home/joe/clean_up" when job 1234 is within
+Execute the program "/home/joe/clean_up" when job 1234 is within
10 minutes of reaching its time limit.
.nf
diff --git a/doc/man/man1/sview.1 b/doc/man/man1/sview.1
index 1f8f9f59b49..fa63859e335 100644
--- a/doc/man/man1/sview.1
+++ b/doc/man/man1/sview.1
@@ -1,45 +1,45 @@
.TH "sview" "1" "SLURM 2.0" "July 2009" "SLURM Commands"
.SH "NAME"
-.LP
+.LP
sview \- graphical user interface to view and modify SLURM state.
.SH "SYNOPSIS"
-.LP
+.LP
sview
.SH "DESCRIPTION"
-.LP
-sview can be used to view SLURM configuration, job,
-step, node and partitions state information.
+.LP
+sview can be used to view SLURM configuration, job,
+step, node and partitions state information.
Authorized users can also modify select information.
.LP
The primary display modes are \fIJobs\fR and \fIPartitions\fR, each with a selection tab.
-There is also an optional map of the nodes on the left side of the window which
+There is also an optional map of the nodes on the left side of the window which
will show the nodes associated with each job or partition.
-Left\-click on the tab of the display you would like to see.
+Left\-click on the tab of the display you would like to see.
Right\-click on the tab in order to control which fields will be displayed.
.LP
-Within the display window, left\-click on the header to control the sort
+Within the display window, left\-click on the header to control the sort
order of entries (e.g. increasing or decreasing) in the diplay.
You can also left\-click and drag the headers to move them right or left in the display.
-If a JobID has an arrow next to it, click on that arrow to display or hide
-information about that job's steps.
+If a JobID has an arrow next to it, click on that arrow to display or hide
+information about that job's steps.
Right\-click on a line of the display to get more information about the record.
.LP
-There is an \fIAdmin Mode\fR option which permits the user root to modify many of
+There is an \fIAdmin Mode\fR option which permits the user root to modify many of
the fields displayed, such as node state or job time limit.
In the mode, a \fISLURM Reconfigure\fR Action is also available.
-It is recommended that \fIAdmin Mode\fR be used only while modifications are
-actively being made.
-Disable \fIAdmin Mode\fR immediately after the changes to avoid possibly making
-unintended changes.
+It is recommended that \fIAdmin Mode\fR be used only while modifications are
+actively being made.
+Disable \fIAdmin Mode\fR immediately after the changes to avoid possibly making
+unintended changes.
.SH "NOTES"
-The sview command can only be build if \fIgtk+\-2.0\fR is installed.
+The sview command can only be build if \fIgtk+\-2.0\fR is installed.
Systems lacking these libraries will have SLURM installed without
the sview command.
-On larger systems (2000+ nodes) some gtk themes can considerably slow down
+On larger systems (2000+ nodes) some gtk themes can considerably slow down
the grid display. If you think this is happening you may
try defining SVIEW_GRID_SPEEDUP=1 in your environment. This will use
a code path to try to avoid functions that typically take a
@@ -68,6 +68,6 @@ FOR A PARTICULAR PURPOSE. See the GNU General Public License for more
details.
.SH "SEE ALSO"
-.LP
-sinfo(1), squeue(1), scontrol(1), slurm.conf(5),
+.LP
+sinfo(1), squeue(1), scontrol(1), slurm.conf(5),
sched_setaffinity(2), numa(3)
diff --git a/doc/man/man3/slurm_allocate_resources.3 b/doc/man/man3/slurm_allocate_resources.3
index 6f18756e270..8f227ae1fa5 100644
--- a/doc/man/man3/slurm_allocate_resources.3
+++ b/doc/man/man3/slurm_allocate_resources.3
@@ -3,44 +3,44 @@
slurm_allocate_resources, slurm_allocate_resources_blocking,
slurm_allocation_msg_thr_create, slurm_allocation_msg_thr_destroy,
slurm_allocation_lookup, slurm_allocation_lookup_lite,
-slurm_confirm_allocation,
-slurm_free_submit_response_response_msg, slurm_init_job_desc_msg,
+slurm_confirm_allocation,
+slurm_free_submit_response_response_msg, slurm_init_job_desc_msg,
slurm_job_will_run, slurm_read_hostfile, slurm_submit_batch_job
\- Slurm job initiation functions
.SH "SYNTAX"
-.LP
+.LP
#include <slurm/slurm.h>
-.LP
+.LP
int \fBslurm_allocate_resources\fR (
-.br
+.br
job_desc_msg_t *\fIjob_desc_msg_ptr\fP,
-.br
+.br
resource_allocation_response_msg_t **\fIslurm_alloc_msg_pptr\fP
-.br
+.br
);
-.LP
+.LP
resource_allocation_response_msg_t *\fBslurm_allocate_resources_blocking\fR (
-.br
+.br
job_desc_msg_t *\fIjob_desc_msg_ptr\fP,
-.br
+.br
time_t \fItimeout\fP, void \fI(*pending_callback)(uint32_t job_id)\fP
-.br
+.br
);
-.LP
+.LP
allocation_msg_thread_t *\fBslurm_allocation_msg_thr_create\fR (
-.br
+.br
uint16_t *\fIport\fP,
-.br
+.br
slurm_allocation_callbacks_t *\fIcallbacks\fP
-.br
+.br
);
-.LP
+.LP
void *\fBslurm_allocation_msg_thr_destroy\fR (
-.br
+.br
allocation_msg_thread_t *\fIslurm_alloc_msg_thr_ptr\fP
-.br
+.br
);
-.LP
+.LP
int \fBslurm_allocation_lookup\fR {
.br
uint32_t \fIjobid\fP,
@@ -48,7 +48,7 @@ int \fBslurm_allocation_lookup\fR {
resource_allocation_response_msg_t **\fIslurm_alloc_msg_pptr\fP
.br
);
-.LP
+.LP
int \fBslurm_allocation_lookup_lite\fR {
.br
uint32_t \fIjobid\fP,
@@ -56,106 +56,106 @@ int \fBslurm_allocation_lookup_lite\fR {
resource_allocation_response_msg_t **\fIslurm_alloc_msg_pptr\fP
.br
);
-.LP
+.LP
int \fBslurm_confirm_allocation\fR (
-.br
+.br
old_job_alloc_msg_t *\fIold_job_desc_msg_ptr\fP,
-.br
+.br
resource_allocation_response_msg_t **\fIslurm_alloc_msg_pptr\fP
-.br
+.br
);
.LP
-void \fBslurm_free_resource_allocation_response_msg\fR (
-.br
- resource_allocation_response_msg_t *\fIslurm_alloc_msg_ptr\fP
-.br
+void \fBslurm_free_resource_allocation_response_msg\fR (
+.br
+ resource_allocation_response_msg_t *\fIslurm_alloc_msg_ptr\fP
+.br
);
.LP
-void \fBslurm_free_submit_response_response_msg\fR (
-.br
- submit_response_msg_t *\fIslurm_submit_msg_ptr\fP
-.br
+void \fBslurm_free_submit_response_response_msg\fR (
+.br
+ submit_response_msg_t *\fIslurm_submit_msg_ptr\fP
+.br
);
.LP
void \fBslurm_init_job_desc_msg\fR (
-.br
+.br
job_desc_msg_t *\fIjob_desc_msg_ptr\fP
-.br
+.br
);
.LP
int \fBslurm_job_will_run\fR (
-.br
+.br
job_desc_msg_t *\fIjob_desc_msg_ptr\fP,
-.br
+.br
);
.LP
int \fBslurm_read_hostfile\fR (
-.br
+.br
char *\fIfilename\fP, int \fIn\fP
-.br
+.br
);
.LP
int \fBslurm_submit_batch_job\fR (
-.br
+.br
job_desc_msg_t *\fIjob_desc_msg_ptr\fP,
-.br
- submit_response_msg_t **\fIslurm_submit_msg_pptr\fP
-.br
+.br
+ submit_response_msg_t **\fIslurm_submit_msg_pptr\fP
+.br
);
.SH "ARGUMENTS"
-.LP
-.TP
+.LP
+.TP
\fIjob_desc_msg_ptr\fP
-Specifies the pointer to a job request specification. See slurm.h for full details
-on the data structure's contents.
+Specifies the pointer to a job request specification. See slurm.h for full details
+on the data structure's contents.
.TP
\fIcallbacks\fP
Specifies the pointer to a allocation callbacks structure. See
slurm.h for full details on the data structure's contents.
-.TP
+.TP
\fIold_job_desc_msg_ptr\fP
-Specifies the pointer to a description of an existing job. See slurm.h for
-full details on the data structure's contents.
-.TP
+Specifies the pointer to a description of an existing job. See slurm.h for
+full details on the data structure's contents.
+.TP
\fIslurm_alloc_msg_pptr\fP
-Specifies the double pointer to the structure to be created and filled with a
-description of the created resource allocation (job): job ID, list of allocated nodes,
-processor count per allocated node, etc. See slurm.h for full details on the data
-structure's contents.
-.TP
+Specifies the double pointer to the structure to be created and filled with a
+description of the created resource allocation (job): job ID, list of allocated nodes,
+processor count per allocated node, etc. See slurm.h for full details on the data
+structure's contents.
+.TP
\fIslurm_alloc_msg_ptr\fP
-Specifies the pointer to the structure to be created and filled in by the function
+Specifies the pointer to the structure to be created and filled in by the function
\fIslurm_allocate_resources\fP,
\fIslurm_allocate_resources_blocking\fP,
-\fIslurm_allocation_lookup\fP, \fIslurm_allocation_lookup_lite\fP,
+\fIslurm_allocation_lookup\fP, \fIslurm_allocation_lookup_lite\fP,
\fIslurm_confirm_allocation\fP or \fIslurm_job_will_run\fP.
-.TP
+.TP
\fIslurm_alloc_msg_thr_ptr\fP
Specigies the pointer to the structure created and returned by the
function \fIslurm_allocation_msg_thr_create\fP. Must be destroyed
with function \fIslurm_allocation_msg_thr_destroy\fP.
-.TP
+.TP
\fIslurm_submit_msg_pptr\fP
-Specifies the double pointer to the structure to be created and filled with a description
+Specifies the double pointer to the structure to be created and filled with a description
of the created job: job ID, etc. See slurm.h for full details on the
-data structure's contents.
+data structure's contents.
.TP
\fIslurm_submit_msg_ptr\fP
Specifies the pointer to the structure to be created and filled in by the function \fIslurm_submit_batch_job\fP.
.SH "DESCRIPTION"
-.LP
-\fBslurm_allocate_resources\fR Request a resource allocation for a job. If
-successful, a job entry is created. Note that if the job's requested node
-count or time allocation are outside of the partition's limits then a job
-entry will be created, a warning indication will be placed in the \fIerror_code\fP field of the response message, and the job will be left
+.LP
+\fBslurm_allocate_resources\fR Request a resource allocation for a job. If
+successful, a job entry is created. Note that if the job's requested node
+count or time allocation are outside of the partition's limits then a job
+entry will be created, a warning indication will be placed in the \fIerror_code\fP field of the response message, and the job will be left
queued until the partition's limits are changed.
-Always release the response message when no longer required using
+Always release the response message when no longer required using
the function \fBslurm_free_resource_allocation_response_msg\fR. This
function only makes the request once. If the allocation is not
avaliable immediately the node_cnt variable in the resp will be 0. If
you want a function that will block until either an error is recieved
or an allocation is granted you can use the
-\fIslurm_allocate_resources_blocking\fP function described below.
+\fIslurm_allocate_resources_blocking\fP function described below.
.LP
\fBslurm_allocate_resources_blocking\fR Request a resource allocation for a
job. This call will block until the allocation is granted, an error
@@ -173,38 +173,38 @@ message is recieved from the controller. This message thread is
needed to receive messages from the controller about node failure in
an allocation and other important messages. Although technically not
required, it could be very helpful to inform about problems with the
-allocation.
+allocation.
.LP
\fBslurm_allocation_msg_thr_destroy\fR Shutdown the message handler
talking with the controller dealing with messages from the controller during
- an allocation.
+ an allocation.
.LP
-\fBslurm_confirm_allocation\fR Return detailed information on a specific
+\fBslurm_confirm_allocation\fR Return detailed information on a specific
existing job allocation. \fBOBSOLETE FUNCTION: Use slurm_allocation_lookup
-instead.\fR This function may only be successfully executed by the job's
+instead.\fR This function may only be successfully executed by the job's
owner or user root.
-.LP
-\fBslurm_free_resource_allocation_response_msg\fR Release the storage generated in response
-to a call of the function \fBslurm_allocate_resources\fR,
+.LP
+\fBslurm_free_resource_allocation_response_msg\fR Release the storage generated in response
+to a call of the function \fBslurm_allocate_resources\fR,
\fBslurm_allocation_lookup\fR, or \fBslurm_allocation_lookup_lite\fR.
-.LP
-\fBslurm_free_submit_response_msg\fR Release the storage generated in response
+.LP
+\fBslurm_free_submit_response_msg\fR Release the storage generated in response
to a call of the function \fBslurm_submit_batch_job\fR.
-.LP
-\fBslurm_init_job_desc_msg\fR Initialize the contents of a job descriptor with default values.
+.LP
+\fBslurm_init_job_desc_msg\fR Initialize the contents of a job descriptor with default values.
Execute this function before issuing a request to submit or modify a job.
-.LP
-\fBslurm_job_will_run\fR Determine if the supplied job description could be executed immediately.
-.LP
+.LP
+\fBslurm_job_will_run\fR Determine if the supplied job description could be executed immediately.
+.LP
\fBslurm_read_hostfile\fR Read a SLURM hostfile specified by
"filename". "filename" must contain a list of SLURM NodeNames, one
per line. Reads up to "n" number of hostnames from the file. Returns
a string representing a hostlist ranged string of the contents
of the file. This is a helper function, it does not contact any SLURM
-daemons.
-.LP
-\fBslurm_submit_batch_job\fR Submit a job for later execution. Note that if
-the job's requested node count or time allocation are outside of the partition's limits then a job entry will be created, a warning indication will be placed in the \fIerror_code\fP field of the response message, and the job will be left queued until the partition's limits are changed and resources are available. Always release the response message when no
+daemons.
+.LP
+\fBslurm_submit_batch_job\fR Submit a job for later execution. Note that if
+the job's requested node count or time allocation are outside of the partition's limits then a job entry will be created, a warning indication will be placed in the \fIerror_code\fP field of the response message, and the job will be left queued until the partition's limits are changed and resources are available. Always release the response message when no
longer required using the function \fBslurm_free_submit_response_msg\fR.
.SH "RETURN VALUE"
.LP
@@ -225,53 +225,53 @@ On success, zero is returned. On error, \-1 is returned, and Slurm error code is
.LP
\fBESLURM_TOO_MANY_REQUESTED_NODES\fR the job requested use of more nodes than can be made available to in the requested (or default) partition.
.LP
-\fBESLURM_ERROR_ON_DESC_TO_RECORD_COPY\fR unable to create the job due to internal resources being exhausted. Try again later.
+\fBESLURM_ERROR_ON_DESC_TO_RECORD_COPY\fR unable to create the job due to internal resources being exhausted. Try again later.
.LP
-\fBESLURM_JOB_MISSING_SIZE_SPECIFICATION\fR the job failed to specify some size specification. At least one of the following must be supplied: required processor count, required node count, or required node list.
+\fBESLURM_JOB_MISSING_SIZE_SPECIFICATION\fR the job failed to specify some size specification. At least one of the following must be supplied: required processor count, required node count, or required node list.
.LP
-\fBESLURM_JOB_SCRIPT_MISSING\fR failed to identify executable program to be queued.
+\fBESLURM_JOB_SCRIPT_MISSING\fR failed to identify executable program to be queued.
.LP
-\fBESLURM_USER_ID_MISSING\fR identification of the job's owner was not provided.
+\fBESLURM_USER_ID_MISSING\fR identification of the job's owner was not provided.
.LP
-\fBESLURM_DUPLICATE_JOB_ID\fR the requested job id is already in use.
+\fBESLURM_DUPLICATE_JOB_ID\fR the requested job id is already in use.
.LP
-\fBESLURM_NOT_TOP_PRIORITY\fR job can not be started immediately because higher priority jobs are waiting to use this partition.
+\fBESLURM_NOT_TOP_PRIORITY\fR job can not be started immediately because higher priority jobs are waiting to use this partition.
.LP
-\fBESLURM_REQUESTED_NODE_CONFIG_UNAVAILABLE\fR the requested node configuration is not available (at least not in sufficient quantity) to satisfy the request.
+\fBESLURM_REQUESTED_NODE_CONFIG_UNAVAILABLE\fR the requested node configuration is not available (at least not in sufficient quantity) to satisfy the request.
.LP
-\fBESLURM_REQUESTED_PART_CONFIG_UNAVAILABLE\fR the requested partition
-configuration is not available to satisfy the request. This is not a fatal
-error, but indicates that the job will be left queued until the partition's
-configuration is changed. This typically indicates that the job's requested
-node count is outside of the node count range its partition is configured
-to support (e.g. the job wants 64 nodes and the partition will only schedule
-jobs using between 1 and 32 nodes). Alternately, the job's time limit exceeds
-the partition's time limit.
+\fBESLURM_REQUESTED_PART_CONFIG_UNAVAILABLE\fR the requested partition
+configuration is not available to satisfy the request. This is not a fatal
+error, but indicates that the job will be left queued until the partition's
+configuration is changed. This typically indicates that the job's requested
+node count is outside of the node count range its partition is configured
+to support (e.g. the job wants 64 nodes and the partition will only schedule
+jobs using between 1 and 32 nodes). Alternately, the job's time limit exceeds
+the partition's time limit.
.LP
-\fBESLURM_NODES_BUSY\fR the requested nodes are already in use.
+\fBESLURM_NODES_BUSY\fR the requested nodes are already in use.
.LP
-\fBESLURM_INVALID_FEATURE\fR the requested feature(s) does not exist.
+\fBESLURM_INVALID_FEATURE\fR the requested feature(s) does not exist.
.LP
-\fBESLURM_INVALID_JOB_ID\fR the requested job id does not exist.
+\fBESLURM_INVALID_JOB_ID\fR the requested job id does not exist.
.LP
-\fBESLURM_INVALID_NODE_NAME\fR the requested node name(s) is/are not valid.
+\fBESLURM_INVALID_NODE_NAME\fR the requested node name(s) is/are not valid.
.LP
-\fBESLURM_INVALID_PARTITION_NAME\fR the requested partition name is not valid.
+\fBESLURM_INVALID_PARTITION_NAME\fR the requested partition name is not valid.
.LP
-\fBESLURM_TRANSITION_STATE_NO_UPDATE\fR the requested job configuration change can not take place at this time. Try again later.
+\fBESLURM_TRANSITION_STATE_NO_UPDATE\fR the requested job configuration change can not take place at this time. Try again later.
.LP
-\fBESLURM_ALREADY_DONE\fR the specified job has already completed and can not be modified.
+\fBESLURM_ALREADY_DONE\fR the specified job has already completed and can not be modified.
.LP
-\fBESLURM_ACCESS_DENIED\fR the requesting user lacks authorization for the requested action (e.g. trying to delete or modify another user's job).
+\fBESLURM_ACCESS_DENIED\fR the requesting user lacks authorization for the requested action (e.g. trying to delete or modify another user's job).
.LP
-\fBESLURM_INTERCONNECT_FAILURE\fR failed to configure the node interconnect.
+\fBESLURM_INTERCONNECT_FAILURE\fR failed to configure the node interconnect.
.LP
-\fBESLURM_BAD_DIST\fR task distribution specification is invalid.
+\fBESLURM_BAD_DIST\fR task distribution specification is invalid.
.LP
-\fBSLURM_PROTOCOL_SOCKET_IMPL_TIMEOUT\fR Timeout in communicating with
+\fBSLURM_PROTOCOL_SOCKET_IMPL_TIMEOUT\fR Timeout in communicating with
SLURM controller.
.SH "NON-BLOCKING EXAMPLE"
-.LP
+.LP
#include <stdio.h>
.br
#include <stdlib.h>
@@ -281,25 +281,25 @@ SLURM controller.
#include <slurm/slurm.h>
.br
#include <slurm/slurm_errno.h>
-.LP
+.LP
int main (int argc, char *argv[])
-.br
+.br
{
-.br
+.br
job_desc_msg_t job_desc_msg;
-.br
+.br
resource_allocation_response_msg_t* slurm_alloc_msg_ptr ;
-.LP
+.LP
slurm_init_job_desc_msg( &job_desc_msg );
-.br
+.br
job_desc_msg. name = ("job01\0");
-.br
+.br
job_desc_msg. job_min_memory = 1024;
-.br
+.br
job_desc_msg. time_limit = 200;
-.br
+.br
job_desc_msg. min_nodes = 400;
-.br
+.br
job_desc_msg. user_id = getuid();
.br
job_desc_msg. group_id = getgid();
@@ -309,39 +309,39 @@ int main (int argc, char *argv[])
&slurm_alloc_msg_ptr)) {
.br
slurm_perror ("slurm_allocate_resources error");
-.br
+.br
exit (1);
.br
}
-.br
- printf ("Allocated nodes %s to job_id %u\\n",
-.br
- slurm_alloc_msg_ptr\->node_list,
+.br
+ printf ("Allocated nodes %s to job_id %u\\n",
+.br
+ slurm_alloc_msg_ptr\->node_list,
.br
slurm_alloc_msg_ptr\->job_id );
-.br
+.br
if (slurm_kill_job(slurm_alloc_msg_ptr\->job_id, SIGKILL, 0)) {
-.br
+.br
printf ("kill errno %d\\n", slurm_get_errno());
-.br
+.br
exit (1);
-.br
+.br
}
.br
- printf ("canceled job_id %u\\n",
+ printf ("canceled job_id %u\\n",
.br
slurm_alloc_msg_ptr\->job_id );
-.br
+.br
slurm_free_resource_allocation_response_msg(
.br
slurm_alloc_msg_ptr);
-.br
+.br
exit (0);
-.br
+.br
}
.SH "BLOCKING EXAMPLE"
-.LP
+.LP
#include <stdio.h>
.br
#include <stdlib.h>
@@ -351,30 +351,30 @@ int main (int argc, char *argv[])
#include <slurm/slurm.h>
.br
#include <slurm/slurm_errno.h>
-.LP
+.LP
int main (int argc, char *argv[])
-.br
+.br
{
-.br
+.br
job_desc_msg_t job_desc_msg;
-.br
+.br
resource_allocation_response_msg_t* slurm_alloc_msg_ptr ;
-.LP
+.LP
slurm_init_job_desc_msg( &job_desc_msg );
-.br
+.br
job_desc_msg. name = ("job01\0");
-.br
+.br
job_desc_msg. job_min_memory = 1024;
-.br
+.br
job_desc_msg. time_limit = 200;
-.br
+.br
job_desc_msg. min_nodes = 400;
-.br
+.br
job_desc_msg. user_id = getuid();
.br
job_desc_msg. group_id = getgid();
.br
- if (!(slurm_alloc_msg_ptr =
+ if (!(slurm_alloc_msg_ptr =
.br
slurm_allocate_resources_blocking(&job_desc_msg, 0, NULL))) {
.br
@@ -383,35 +383,35 @@ int main (int argc, char *argv[])
exit (1);
.br
}
-.br
- printf ("Allocated nodes %s to job_id %u\\n",
-.br
- slurm_alloc_msg_ptr\->node_list,
+.br
+ printf ("Allocated nodes %s to job_id %u\\n",
+.br
+ slurm_alloc_msg_ptr\->node_list,
.br
slurm_alloc_msg_ptr\->job_id );
-.br
+.br
if (slurm_kill_job(slurm_alloc_msg_ptr\->job_id, SIGKILL, 0)) {
-.br
+.br
printf ("kill errno %d\\n", slurm_get_errno());
-.br
+.br
exit (1);
-.br
+.br
}
.br
- printf ("canceled job_id %u\\n",
+ printf ("canceled job_id %u\\n",
.br
slurm_alloc_msg_ptr\->job_id );
-.br
+.br
slurm_free_resource_allocation_response_msg(
.br
slurm_alloc_msg_ptr);
-.br
+.br
exit (0);
-.br
+.br
}
.SH "NOTE"
-These functions are included in the libslurm library,
+These functions are included in the libslurm library,
which must be linked to your process for use
(e.g. "cc \-lslurm myprog.c").
@@ -433,8 +433,8 @@ WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
FOR A PARTICULAR PURPOSE. See the GNU General Public License for more
details.
.SH "SEE ALSO"
-.LP
-\fBhostlist_create\fR(3), \fBhostlist_shift\fR(3), \fBhostlist_destroy\fR(3),
-\fBscancel\fR(1), \fBsrun\fR(1), \fBslurm_free_job_info_msg\fR(3),
-\fBslurm_get_errno\fR(3), \fBslurm_load_jobs\fR(3),
+.LP
+\fBhostlist_create\fR(3), \fBhostlist_shift\fR(3), \fBhostlist_destroy\fR(3),
+\fBscancel\fR(1), \fBsrun\fR(1), \fBslurm_free_job_info_msg\fR(3),
+\fBslurm_get_errno\fR(3), \fBslurm_load_jobs\fR(3),
\fBslurm_perror\fR(3), \fBslurm_strerror\fR(3)
diff --git a/doc/man/man3/slurm_checkpoint_error.3 b/doc/man/man3/slurm_checkpoint_error.3
index a99912742cd..6c8c01e1ac2 100644
--- a/doc/man/man3/slurm_checkpoint_error.3
+++ b/doc/man/man3/slurm_checkpoint_error.3
@@ -2,11 +2,11 @@
.SH "NAME"
slurm_checkpoint_able, slurm_checkpoint_complete, slurm_checkpoint_create,
-slurm_checkpoint_disable, slurm_checkpoint_enable, slurm_checkpoint_error,
+slurm_checkpoint_disable, slurm_checkpoint_enable, slurm_checkpoint_error,
slurm_checkpoint_restart, slurm_checkpoint_vacate \- Slurm checkpoint functions
.SH "SYNTAX"
-.LP
+.LP
#include <slurm/slurm.h>
.LP
.LP
@@ -117,7 +117,7 @@ int \fBslurm_checkpoint_vacate\fR (
);
.SH "ARGUMENTS"
-.LP
+.LP
.TP
\fIbegin_time\fP
When to begin the operation.
@@ -126,11 +126,11 @@ When to begin the operation.
Error code for checkpoint operation. Only the highest value is preserved.
.TP
\fIerror_msg\fP
-Error message for checkpoint operation. Only the \fIerror_msg\fP value for the highest
+Error message for checkpoint operation. Only the \fIerror_msg\fP value for the highest
\fIerror_code\fP is preserved.
.TP
\fIimage_dir\fP
-Directory specification for where the checkpoint file should be read from or
+Directory specification for where the checkpoint file should be read from or
written to. The default value is specified by the \fIJobCheckpointDir\fP
SLURM configuration parameter.
.TP
@@ -147,7 +147,7 @@ Nodes to send the request.
Time at which last checkpoint operation began (if one is in progress), otherwise zero.
.TP
\fIstep_id\fP
-SLURM job step ID to perform the operation upon.
+SLURM job step ID to perform the operation upon.
May be NO_VAL if the operation is to be performed on all steps of the specified job.
Specify SLURM_BATCH_SCRIPT to checkpoint a batch job.
.TP
@@ -158,19 +158,19 @@ If non\-zero then restart the job on the same nodes that it was checkpointed fro
.LP
\fBslurm_checkpoint_able\fR
Report if checkpoint operations can presently be issued for the specified job step.
-If yes, returns SLURM_SUCCESS and sets \fIstart_time\fP if checkpoint operation is
+If yes, returns SLURM_SUCCESS and sets \fIstart_time\fP if checkpoint operation is
presently active. Returns ESLURM_DISABLED if checkpoint operation is disabled.
.LP
\fBslurm_checkpoint_complete\fR
Note that a requested checkpoint has been completed.
.LP
\fBslurm_checkpoint_create\fR
-Request a checkpoint for the identified job step.
+Request a checkpoint for the identified job step.
Continue its execution upon completion of the checkpoint.
.LP
\fBslurm_checkpoint_disable\fR
-Make the identified job step non\-checkpointable.
-This can be issued as needed to prevent checkpointing while
+Make the identified job step non\-checkpointable.
+This can be issued as needed to prevent checkpointing while
a job step is in a critical section or for other reasons.
.LP
\fBslurm_checkpoint_enable\fR
@@ -181,9 +181,9 @@ Get error information about the last checkpoint operation for a given job step.
.LP
\fBslurm_checkpoint_restart\fR
Request that a previously checkpointed job resume execution.
-It may continue execution on different nodes than were
+It may continue execution on different nodes than were
originally used.
-Execution may be delayed if resources are not immediately
+Execution may be delayed if resources are not immediately
available.
.LP
\fBslurm_checkpoint_vacate\fR
@@ -193,14 +193,14 @@ Terminate its execution upon completion of the checkpoint.
.SH "RETURN VALUE"
.LP
-Zero is returned upon success.
+Zero is returned upon success.
On error, \-1 is returned, and the Slurm error code is set appropriately.
.SH "ERRORS"
.LP
-\fBESLURM_INVALID_JOB_ID\fR the requested job or job step id does not exist.
+\fBESLURM_INVALID_JOB_ID\fR the requested job or job step id does not exist.
.LP
-\fBESLURM_ACCESS_DENIED\fR the requesting user lacks authorization for the requested
-action (e.g. trying to delete or modify another user's job).
+\fBESLURM_ACCESS_DENIED\fR the requesting user lacks authorization for the requested
+action (e.g. trying to delete or modify another user's job).
.LP
\fBESLURM_JOB_PENDING\fR the requested job is still pending.
.LP
@@ -212,7 +212,7 @@ This will occur when a request for checkpoint is issued when they have been disa
\fBESLURM_NOT_SUPPORTED\fR the requested operation is not supported on this system.
.SH "EXAMPLE"
-.LP
+.LP
#include <stdio.h>
.br
#include <stdlib.h>
@@ -220,11 +220,11 @@ This will occur when a request for checkpoint is issued when they have been disa
#include <slurm/slurm.h>
.br
#include <slurm/slurm_errno.h>
-.LP
+.LP
int main (int argc, char *argv[])
-.br
+.br
{
-.br
+.br
uint32_t job_id, step_id;
.LP
if (argc < 3) {
@@ -242,17 +242,17 @@ int main (int argc, char *argv[])
if (slurm_checkpoint_disable(job_id, step_id)) {
.br
slurm_perror ("slurm_checkpoint_error:");
-.br
+.br
exit (1);
.br
}
-.br
+.br
exit (0);
-.br
+.br
}
.SH "NOTE"
-These functions are included in the libslurm library,
+These functions are included in the libslurm library,
which must be linked to your process for use
(e.g. "cc \-lslurm myprog.c").
@@ -276,5 +276,5 @@ FOR A PARTICULAR PURPOSE. See the GNU General Public License for more
details.
.SH "SEE ALSO"
-.LP
+.LP
\fBsrun\fR(1), \fBsqueue\fR(1), \fBfree\fR(3), \fBslurm.conf\fR(5)
diff --git a/doc/man/man3/slurm_complete_job.3 b/doc/man/man3/slurm_complete_job.3
index 882d926c0f8..611cd1281e2 100644
--- a/doc/man/man3/slurm_complete_job.3
+++ b/doc/man/man3/slurm_complete_job.3
@@ -2,53 +2,53 @@
.SH "NAME"
slurm_complete_job \- Slurm job completion call
.SH "SYNTAX"
-.LP
+.LP
#include <slurm/slurm.h>
.LP
int \fBslurm_complete_job\fR (
-.br
- uint32_t \fIjob_id\fP,
+.br
+ uint32_t \fIjob_id\fP,
.br
uint32_t \fIjob_return_code\fP
-.br
+.br
);
.SH "ARGUMENTS"
-.LP
-.TP
+.LP
+.TP
\fIjob_id\fP
Slurm job id number.
-.TP
+.TP
\fIjob_return_code\fP
Exit code of the program executed.
.SH "DESCRIPTION"
-.LP
-\fBslurm_complete_job\fR Note the termination of a job. This function may only be
+.LP
+\fBslurm_complete_job\fR Note the termination of a job. This function may only be
successfully executed by the job's owner or user root.
.SH "RETURN VALUE"
.LP
-On success, zero is returned. On error, \-1 is returned, and Slurm error code
+On success, zero is returned. On error, \-1 is returned, and Slurm error code
is set appropriately.
.SH "ERRORS"
.LP
\fBSLURM_PROTOCOL_VERSION_ERROR\fR Protocol version has changed, re\-link your code.
.LP
-\fBESLURM_INVALID_JOB_ID\fR the requested job id does not exist.
+\fBESLURM_INVALID_JOB_ID\fR the requested job id does not exist.
.LP
-\fBESLURM_ALREADY_DONE\fR the specified job has already completed and can
-not be modified.
+\fBESLURM_ALREADY_DONE\fR the specified job has already completed and can
+not be modified.
.LP
-\fBESLURM_ACCESS_DENIED\fR the requesting user lacks authorization for the requested action (e.g. trying to delete or modify another user's job).
+\fBESLURM_ACCESS_DENIED\fR the requesting user lacks authorization for the requested action (e.g. trying to delete or modify another user's job).
.LP
-\fBESLURM_INTERCONNECT_FAILURE\fR failed to configure the node interconnect.
+\fBESLURM_INTERCONNECT_FAILURE\fR failed to configure the node interconnect.
.LP
-\fBSLURM_PROTOCOL_SOCKET_IMPL_TIMEOUT\fR Timeout in communicating with
+\fBSLURM_PROTOCOL_SOCKET_IMPL_TIMEOUT\fR Timeout in communicating with
SLURM controller.
.SH "NOTE"
-These functions are included in the libslurm library,
+These functions are included in the libslurm library,
which must be linked to your process for use
(e.g. "cc \-lslurm myprog.c").
@@ -71,5 +71,5 @@ WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
FOR A PARTICULAR PURPOSE. See the GNU General Public License for more
details.
.SH "SEE ALSO"
-.LP
+.LP
\fBslurm_get_errno\fR(3), \fBslurm_perror\fR(3), \fBslurm_strerror\fR(3)
diff --git a/doc/man/man3/slurm_free_ctl_conf.3 b/doc/man/man3/slurm_free_ctl_conf.3
index aa9091b80da..6d1ec7acb91 100644
--- a/doc/man/man3/slurm_free_ctl_conf.3
+++ b/doc/man/man3/slurm_free_ctl_conf.3
@@ -1,74 +1,74 @@
.TH "Slurm API" "3" "April 2007" "Morris Jette" "Slurm informational calls"
.SH "NAME"
-slurm_free_ctl_conf, slurm_load_ctl_conf,
+slurm_free_ctl_conf, slurm_load_ctl_conf,
slurm_print_ctl_conf \- Slurm information reporting functions
.SH "SYNTAX"
-.LP
+.LP
#include <stdio.h>
.br
#include <slurm/slurm.h>
.LP
long \fBslurm_api_version\fR ();
-.LP
+.LP
void \fBslurm_free_ctl_conf\fR (
-.br
+.br
slurm_ctl_conf_t *\fIconf_info_msg_ptr\fP
-.br
+.br
);
.LP
int \fBslurm_load_ctl_conf\fR (
-.br
+.br
time_t \fIupdate_time\fP,
-.br
+.br
slurm_ctl_conf_t **\fIconf_info_msg_pptr\fP
-.br
+.br
);
-.LP
+.LP
void \fBslurm_print_ctl_conf\fR (
.br
FILE *\fIout_file\fp,
.br
slurm_ctl_conf_t *\fIconf_info_msg_ptr\fP
-.br
+.br
);
.SH "ARGUMENTS"
-.LP
-.TP
+.LP
+.TP
\fIconf_info_msg_pptr\fP
-Specifies the double pointer to the structure to be created and filled with the
-time of the last configuration update and detailed configuration information.
-Configuration information includes control machine names, file names, timer
-values, etc. See slurm.h for full details on the data structure's contents.
-.TP
+Specifies the double pointer to the structure to be created and filled with the
+time of the last configuration update and detailed configuration information.
+Configuration information includes control machine names, file names, timer
+values, etc. See slurm.h for full details on the data structure's contents.
+.TP
\fIconf_info_msg_ptr\fP
-Specifies the pointer to the structure created by \fBslurm_load_ctl_conf\fR.
-.TP
+Specifies the pointer to the structure created by \fBslurm_load_ctl_conf\fR.
+.TP
\fIout_file\fP
Specifies the file to print data to.
-.TP
+.TP
\fIupdate_time\fP
For all of the following informational calls, if update_time is equal to or
greater than the last time changes where made to that information, new information
-is not returned. Otherwise all the configuration. job, node, or partition records
+is not returned. Otherwise all the configuration. job, node, or partition records
are returned.
.SH "DESCRIPTION"
.LP
\fBslurm_api_version\fR Return the SLURM API version number.
-.LP
-\fBslurm_free_ctl_conf\fR Release the storage generated by the
+.LP
+\fBslurm_free_ctl_conf\fR Release the storage generated by the
\fBslurm_load_ctl_conf\fR function.
-.LP
+.LP
\fBslurm_load_ctl_conf\fR Returns a slurm_ctl_conf_t that contains
Slurm configuration records.
-.LP
+.LP
\fBslurm_print_ctl_conf\fR Prints the contents of the data structure loaded by the
\fBslurm_load_ctl_conf\fR function.
.SH "RETURN VALUE"
.LP
-For \fBslurm_api_version\fR the SLURM API version number is returned.
-All other functions return zero on success and \-1 on error with the
+For \fBslurm_api_version\fR the SLURM API version number is returned.
+All other functions return zero on success and \-1 on error with the
SLURM error code set appropriately.
.SH "ERRORS"
.LP
@@ -76,25 +76,25 @@ SLURM error code set appropriately.
.LP
\fBSLURM_PROTOCOL_VERSION_ERROR\fR Protocol version has changed, re\-link your code.
.LP
-\fBSLURM_PROTOCOL_SOCKET_IMPL_TIMEOUT\fR Timeout in communicating with
+\fBSLURM_PROTOCOL_SOCKET_IMPL_TIMEOUT\fR Timeout in communicating with
SLURM controller.
.SH "EXAMPLE"
-.LP
+.LP
#include <stdio.h>
.br
#include <slurm/slurm.h>
.br
#include <slurm/slurm_errno.h>
-.LP
+.LP
int main (int argc, char *argv[])
-.br
+.br
{
.br
slurm_ctl_conf_t * conf_info_msg_ptr = NULL;
.br
long version = slurm_api_version;
.LP
- /* We can use the SLURM version number to determine how
+ /* We can use the SLURM version number to determine how
.br
* API should be used */
.br
@@ -120,28 +120,28 @@ int main (int argc, char *argv[])
.br
/* The easy way to print */
.br
- slurm_print_ctl_conf (stdout,
+ slurm_print_ctl_conf (stdout,
.br
conf_info_msg_ptr);
.LP
/* The hard way */
.br
- printf ("control_machine = %s\\n",
+ printf ("control_machine = %s\\n",
.br
slurm_ctl_conf_ptr\->control_machine);
.br
- printf ("server_timeout = %u\\n",
+ printf ("server_timeout = %u\\n",
.br
slurm_ctl_conf_ptr\->server_timeout);
.LP
slurm_free_ctl_conf (conf_info_msg_ptr);
.br
exit (0);
-.br
+.br
}
.SH "NOTE"
-These functions are included in the libslurm library,
+These functions are included in the libslurm library,
which must be linked to your process for use
(e.g. "cc \-lslurm myprog.c").
@@ -163,7 +163,7 @@ WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
FOR A PARTICULAR PURPOSE. See the GNU General Public License for more
details.
.SH "SEE ALSO"
-.LP
-\fBscontrol\fR(1),
+.LP
+\fBscontrol\fR(1),
\fBslurm_get_errno\fR(3), \fBslurm_perror\fR(3), \fBslurm_strerror\fR(3)
diff --git a/doc/man/man3/slurm_free_job_info_msg.3 b/doc/man/man3/slurm_free_job_info_msg.3
index e8ec50e9e97..7f8188c4a57 100644
--- a/doc/man/man3/slurm_free_job_info_msg.3
+++ b/doc/man/man3/slurm_free_job_info_msg.3
@@ -1,8 +1,8 @@
.TH "Slurm API" "3" "September 2006" "Morris Jette" "Slurm job information reporting functions"
.SH "NAME"
-slurm_free_job_alloc_info_response_msg, slurm_free_job_info_msg,
+slurm_free_job_alloc_info_response_msg, slurm_free_job_info_msg,
slurm_get_end_time, slurm_get_rem_time, slurm_get_select_jobinfo,
-slurm_load_jobs, slurm_pid2jobid,
+slurm_load_jobs, slurm_pid2jobid,
slurm_print_job_info, slurm_print_job_info_msg
\- Slurm job information reporting functions
.LP
@@ -10,7 +10,7 @@ ISLURM_GET_REM_TIME, ISLURM_GET_REM_TIME2
\- Fortran callable extensions
.SH "SYNTAX"
-.LP
+.LP
#include <stdio.h>
.br
#include <time.h>
@@ -20,47 +20,47 @@ ISLURM_GET_REM_TIME, ISLURM_GET_REM_TIME2
#include <sys/types.h>
.LP
void \fBslurm_free_job_alloc_info_response_msg\fR (
-.br
+.br
job_alloc_info_response_msg_t *\fIjob_alloc_info_msg_ptr\fP
-.br
+.br
);
-.LP
+.LP
void \fBslurm_free_job_info_msg\fR (
-.br
+.br
job_info_msg_t *\fIjob_info_msg_ptr\fP
-.br
+.br
);
-.LP
+.LP
int \fBslurm_load_job\fR (
-.br
+.br
job_info_msg_t **\fIjob_info_msg_pptr\fP,
.br
uint32_t \fIjob_id\fP
-.br
+.br
);
-.LP
-.LP
+.LP
+.LP
int \fBslurm_load_jobs\fR (
-.br
+.br
time_t \fIupdate_time\fP,
-.br
+.br
job_info_msg_t **\fIjob_info_msg_pptr\fP,
.br
uint16_t \fIshow_flags\fP
-.br
+.br
);
-.LP
+.LP
int \fBslurm_pid2jobid\fR (
.br
pid_t \fIjob_pid\fP,
.br
uint32_t *\fIjob_id_ptr\fP
-.br
+.br
);
.LP
int \fBslurm_get_end_time\fR (
.br
- uint32_t \fIjobid\fP,
+ uint32_t \fIjobid\fP,
.br
time_t *\fIend_time_ptr\fP
.br
@@ -71,7 +71,7 @@ long \fBslurm_get_rem_time\fR (
uint32_t \fIjob_id\fP
.br
);
-.LP
+.LP
void \fBslurm_print_job_info\fR (
.br
FILE *\fIout_file\fP,
@@ -79,9 +79,9 @@ void \fBslurm_print_job_info\fR (
job_info_t *\fIjob_ptr\fP,
.br
int \fIone_liner\fP
-.br
+.br
);
-.LP
+.LP
void \fBslurm_print_job_info_msg\fR (
.br
FILE *\fIout_file\fP,
@@ -89,14 +89,14 @@ void \fBslurm_print_job_info_msg\fR (
job_info_msg_t *\fIjob_info_msg_ptr\fP,
.br
int \fIone_liner\fP
-.br
+.br
);
.LP
int \fBslurm_get_select_jobinfo\fR (
.br
select_jobinfo_t \fIjobinfo\fP,
.br
- enum select_data_type \fIdata_type\fP,
+ enum select_data_type \fIdata_type\fP,
.br
void *\fIdata\fP
);
@@ -109,139 +109,139 @@ REM_TIME = ISLURM_GET_REM_TIME(JOBID)
.br
REM_TIME = ISLURM_GET_REM_TIME2()
.LP
-ISLURM_GET_REM_TIME2() is equivalent to ISLURM_GET_REM_TIME() except
-that the JOBID is taken from the SLURM_JOB_ID environment variable,
+ISLURM_GET_REM_TIME2() is equivalent to ISLURM_GET_REM_TIME() except
+that the JOBID is taken from the SLURM_JOB_ID environment variable,
which is set by SLURM for tasks which it launches.
-Both functions return the number of seconds remaining before the job
+Both functions return the number of seconds remaining before the job
reaches the end of it's allocated time.
.SH "ARGUMENTS"
-.TP
+.TP
\fIdata_type\fP
-Identifies the type of data to retrieve \fIjobinfo\fP. Note that different types of
-data are associated with different computer types and different configurations.
+Identifies the type of data to retrieve \fIjobinfo\fP. Note that different types of
+data are associated with different computer types and different configurations.
.TP
\fIdata\fP
The data value identified with \fIdata_type\fP is returned in the location specified
-by \fIdata\fP. If a type of data is requested that does not exist on a particular
+by \fIdata\fP. If a type of data is requested that does not exist on a particular
computer type or configuration, \fBslurm_get_select_jobinfo\fR returns an error.
-See the slurm.h header file for identification of the data types associated
+See the slurm.h header file for identification of the data types associated
with each value of \fIdata_type\fP.
.TP
\fIend_time_ptr\fP
-Specified a pointer to a storage location into which the expected termination
+Specified a pointer to a storage location into which the expected termination
time of a job is placed.
-.TP
+.TP
\fIjob_info_msg_pptr\fP
-Specifies the double pointer to the structure to be created and filled with
-the time of the last job update, a record count, and detailed information
-about each job. Detailed job information is written to fixed sized records
-and includes: ID number, name, user ID, state, assigned or requested node
-names, indexes into the node table, etc. In the case of indexes into the
-node table, this is an array of integers with pairs of start and end index
-number into the node information records and the data is terminated with a
-value of \-1. See slurm.h for full details on the data structure's contents.
-.TP
+Specifies the double pointer to the structure to be created and filled with
+the time of the last job update, a record count, and detailed information
+about each job. Detailed job information is written to fixed sized records
+and includes: ID number, name, user ID, state, assigned or requested node
+names, indexes into the node table, etc. In the case of indexes into the
+node table, this is an array of integers with pairs of start and end index
+number into the node information records and the data is terminated with a
+value of \-1. See slurm.h for full details on the data structure's contents.
+.TP
\fIjob_id\fP
Specifies a slurm job id. If zero, use the SLURM_JOB_ID environment variable
to get the jobid.
-.TP
+.TP
\fIjob_id_ptr\fP
-Specifies a pointer to a storage location into which a Slurm job id may be
+Specifies a pointer to a storage location into which a Slurm job id may be
placed.
-.TP
+.TP
\fIjob_info_msg_ptr\fP
Specifies the pointer to the structure created by \fBslurm_load_job\fR
-or \fBslurm_load_jobs\fR.
+or \fBslurm_load_jobs\fR.
.TP
\fIjobinfo\fP
Job\-specific information as constructed by Slurm's NodeSelect plugin.
This data object is returned for each job by the \fBslurm_load_job\fR or
\fBslurm_load_jobs\fR function.
-.TP
+.TP
\fIjob_pid\fP
Specifies a process id of some process on the current node.
.TP
\fIjob_ptr\fP
-Specifies a pointer to a single job records from the \fIjob_info_msg_ptr\fP
+Specifies a pointer to a single job records from the \fIjob_info_msg_ptr\fP
data structure.
-.TP
+.TP
\fIone_liner\fP
Print one record per line if non\-zero.
-.TP
+.TP
\fIout_file\fP
Specifies the file to print data to.
-.TP
+.TP
\fIshow_flags\fP
-Job filtering flags, may be ORed.
-Information about jobs in partitions that are configured as
-hidden and partitions that the user's group is unable to utilize
+Job filtering flags, may be ORed.
+Information about jobs in partitions that are configured as
+hidden and partitions that the user's group is unable to utilize
are not reported by default.
-The \fBSHOW_ALL\fP flag will cause information about jobs in all
+The \fBSHOW_ALL\fP flag will cause information about jobs in all
partitions to be displayed.
-.TP
+.TP
\fIupdate_time\fP
-For all of the following informational calls, if update_time is equal to or
-greater than the last time changes where made to that information, new
-information is not returned. Otherwise all the configuration. job, node,
+For all of the following informational calls, if update_time is equal to or
+greater than the last time changes where made to that information, new
+information is not returned. Otherwise all the configuration. job, node,
or partition records are returned.
.SH "DESCRIPTION"
.LP
\fBslurm_free_resource_allocation_response_msg\fR Free slurm resource
allocation response message.
-.LP
-\fBslurm_free_job_info_msg\fR Release the storage generated by the
+.LP
+\fBslurm_free_job_info_msg\fR Release the storage generated by the
\fBslurm_load_jobs\fR function.
-.LP
-\fBslurm_get_end_time\fR Returns the expected termination time of a specified
-SLURM job. The time corresponds to the exhaustion of the job\'s or partition\'s
-time limit. NOTE: The data is cached locally and only retrieved from the
+.LP
+\fBslurm_get_end_time\fR Returns the expected termination time of a specified
+SLURM job. The time corresponds to the exhaustion of the job\'s or partition\'s
+time limit. NOTE: The data is cached locally and only retrieved from the
SLURM controller once per minute.
.LP
-\fBslurm_get_rem_time\fR Returns the number of seconds remaining before the
-expected termination time of a specified SLURM job id. The time corresponds
-to the exhaustion of the job\'s or partition\'s time limit. NOTE: The data is
+\fBslurm_get_rem_time\fR Returns the number of seconds remaining before the
+expected termination time of a specified SLURM job id. The time corresponds
+to the exhaustion of the job\'s or partition\'s time limit. NOTE: The data is
cached locally and only retrieved from the SLURM controller once per minute.
-.LP
-\fBslurm_load_job\fR Returns a job_info_msg_t that contains an update time,
+.LP
+\fBslurm_load_job\fR Returns a job_info_msg_t that contains an update time,
record count, and array of job_table records for some specific job ID.
-.LP
-\fBslurm_load_jobs\fR Returns a job_info_msg_t that contains an update time,
+.LP
+\fBslurm_load_jobs\fR Returns a job_info_msg_t that contains an update time,
record count, and array of job_table records for all jobs.
-.LP
-\fBslurm_pid2jobid\fR Returns a Slurm job id corresponding to the supplied
-local process id. This only works for processes which Slurm spawns and their
+.LP
+\fBslurm_pid2jobid\fR Returns a Slurm job id corresponding to the supplied
+local process id. This only works for processes which Slurm spawns and their
descendants.
-.LP
-\fBslurm_print_job_info\fR Prints the contents of the data structure
-describing a single job records from the data loaded by the
+.LP
+\fBslurm_print_job_info\fR Prints the contents of the data structure
+describing a single job records from the data loaded by the
\fBslurm_load_node\fR function.
-.LP
-\fBslurm_print_job_info_msg\fR Prints the contents of the data structure
+.LP
+\fBslurm_print_job_info_msg\fR Prints the contents of the data structure
describing all job records loaded by the \fBslurm_load_node\fR function.
.SH "RETURN VALUE"
.LP
For \fBslurm_get_rem_time\fR on success a number of seconds is returned.
-For all other functions zero is returned on success.
+For all other functions zero is returned on success.
On error, \-1 is returned, and Slurm error code is set appropriately.
.SH "ERRORS"
.LP
\fBSLURM_NO_CHANGE_IN_DATA\fR Data has not changed since \fBupdate_time\fR.
.LP
-\fBSLURM_PROTOCOL_VERSION_ERROR\fR Protocol version has changed, re\-link
+\fBSLURM_PROTOCOL_VERSION_ERROR\fR Protocol version has changed, re\-link
your code.
.LP
\fBESLURM_INVALID_JOB_ID\fR Request for information about a non\-existent job.
.LP
-\fBSLURM_PROTOCOL_SOCKET_IMPL_TIMEOUT\fR Timeout in communicating with
+\fBSLURM_PROTOCOL_SOCKET_IMPL_TIMEOUT\fR Timeout in communicating with
SLURM controller.
.LP
\fBINVAL\fR Invalid function argument.
.SH "EXAMPLE"
-.LP
+.LP
#include <stdio.h>
.br
#include <slurm/slurm.h>
@@ -249,11 +249,11 @@ SLURM controller.
#include <slurm/slurm_errno.h>
.br
#include <sys/types.h>
-.LP
+.LP
int main (int argc, char *argv[])
-.br
+.br
{
-.br
+.br
int i;
.br
job_info_msg_t * job_info_msg = NULL;
@@ -264,7 +264,7 @@ int main (int argc, char *argv[])
.LP
/* get and dump some job information */
.br
- if ( slurm_load_jobs ((time_t) NULL,
+ if ( slurm_load_jobs ((time_t) NULL,
.br
&job_buffer_ptr, SHOW_ALL) ) {
.br
@@ -292,15 +292,15 @@ int main (int argc, char *argv[])
.br
printf ("Jobs updated at %lx, record count %d\\n",
.br
- job_buffer_ptr\->last_update,
+ job_buffer_ptr\->last_update,
.br
job_buffer_ptr\->record_count);
.br
for (i = 0; i < job_buffer_ptr\->record_count; i++) {
.br
- printf ("JobId=%u UserId=%u\\n",
+ printf ("JobId=%u UserId=%u\\n",
.br
- job_buffer_ptr\->job_array[i].job_id,
+ job_buffer_ptr\->job_array[i].job_id,
.br
job_buffer_ptr\->job_array[i].user_id);
.br
@@ -320,7 +320,7 @@ int main (int argc, char *argv[])
.br
printf("JobId=%u Rotate=%u\\n",
.br
- job_buffer_ptr\->job_array[0].job_id,
+ job_buffer_ptr\->job_array[0].job_id,
.br
rotate);
.br
@@ -337,16 +337,16 @@ int main (int argc, char *argv[])
printf ("Slurm job id = %u\\n", job_id);
.br
exit (0);
-.br
+.br
}
.SH "NOTES"
-These functions are included in the libslurm library,
+These functions are included in the libslurm library,
which must be linked to your process for use
(e.g. "cc \-lslurm myprog.c").
.LP
-Some data structures contain index values to cross\-reference each other.
-If the \fIshow_flags\fP argument is not set to SHOW_ALL when getting this
+Some data structures contain index values to cross\-reference each other.
+If the \fIshow_flags\fP argument is not set to SHOW_ALL when getting this
data, these index values will be invalid.
.LP
The \fBslurm_hostlist_\fR functions can be used to convert SLURM node list
@@ -372,10 +372,10 @@ FOR A PARTICULAR PURPOSE. See the GNU General Public License for more
details.
.SH "SEE ALSO"
-.LP
-\fBscontrol\fR(1), \fBsqueue\fR(1),
-\fBslurm_hostlist_create\fR(3), \fBslurm_hostlist_shift\fR(3),
+.LP
+\fBscontrol\fR(1), \fBsqueue\fR(1),
+\fBslurm_hostlist_create\fR(3), \fBslurm_hostlist_shift\fR(3),
\fBslurm_hostlist_destroy\fR(3),
-\fBslurm_allocation_lookup\fR(3),
+\fBslurm_allocation_lookup\fR(3),
\fBslurm_get_errno\fR(3), \fBslurm_perror\fR(3), \fBslurm_strerror\fR(3)
diff --git a/doc/man/man3/slurm_free_job_step_info_response_msg.3 b/doc/man/man3/slurm_free_job_step_info_response_msg.3
index a393e79bf04..448d0b49b51 100644
--- a/doc/man/man3/slurm_free_job_step_info_response_msg.3
+++ b/doc/man/man3/slurm_free_job_step_info_response_msg.3
@@ -6,31 +6,31 @@ slurm_print_job_step_info, slurm_print_job_step_info_msg
\- Slurm job step information reporting functions
.SH "SYNTAX"
-.LP
+.LP
#include <stdio.h>
.br
#include <slurm/slurm.h>
.LP
void \fBslurm_free_job_step_info_response_msg\fR (
-.br
+.br
job_step_info_response_msg_t *\fIjob_step_info_msg_ptr\fP
-.br
+.br
);
.LP
void \fBslurm_get_job_steps\fR (
-.br
+.br
time_t *\fIupdate_time\fP,
.br
- uint32_t \fIjob_id\fP,
+ uint32_t \fIjob_id\fP,
.br
- uint32_t \fIstep_id\fP,
+ uint32_t \fIstep_id\fP,
.br
job_step_info_response_msg_t **\fIjob_step_info_msg_pptr\fP,
.br
uint16_t \fIshow_flags\fP
-.br
+.br
);
-.LP
+.LP
void \fBslurm_print_job_step_info\fR (
.br
FILE *\fIout_file\fp,
@@ -38,9 +38,9 @@ void \fBslurm_print_job_step_info\fR (
job_step_info_t *\fIjob_step_ptr\fP,
.br
int \fIone_liner\fP
-.br
+.br
);
-.LP
+.LP
void \fBslurm_print_job_step_info_msg\fR (
.br
FILE *\fIout_file\fp,
@@ -48,39 +48,39 @@ void \fBslurm_print_job_step_info_msg\fR (
job_step_info_response_msg_t *\fIjob_step_info_msg_ptr\fP,
.br
int \fIone_liner\fP
-.br
+.br
);
.SH "ARGUMENTS"
-.LP
+.LP
.TP
\fIjob_id\fP
Specifies a slurm job ID. A value of zero implies all jobs.
-.TP
+.TP
\fIjob_step_info_msg_pptr\fP
-Specifies the double pointer to the structure to be created and filled
-with the time of the last node update, a record count, and detailed
-information about each job step specified. Detailed job step information
+Specifies the double pointer to the structure to be created and filled
+with the time of the last node update, a record count, and detailed
+information about each job step specified. Detailed job step information
is written to fixed sized records and includes: job_id, step_id, node
-names, etc. See slurm.h for full details on the data structure's contents.
-.TP
+names, etc. See slurm.h for full details on the data structure's contents.
+.TP
\fIjob_step_info_msg_ptr\fP
-Specifies the pointer to the structure created by the function
-\fBslurm_get_job_steps\fP.
+Specifies the pointer to the structure created by the function
+\fBslurm_get_job_steps\fP.
.TP
\fIjob_step_ptr\fP
-Specifies a pointer to a single job step records from the \fIjob_step_info_msg_pptr\fP
+Specifies a pointer to a single job step records from the \fIjob_step_info_msg_pptr\fP
data structure.
-.TP
+.TP
\fIone_liner\fP
Print one record per line if non\-zero.
-.TP
+.TP
\fIout_file\fP
Specifies the file to print data to.
-.TP
+.TP
\fIshow_flags\fP
Job filtering flags, may be ORed.
-Information about job steps in partitions that are configured as
-hidden and partitions that the user's group is unable to utilize
+Information about job steps in partitions that are configured as
+hidden and partitions that the user's group is unable to utilize
are not reported by default.
The \fBSHOW_ALL\fP flag will cause information about job steps in all
partitions to be displayed.
@@ -88,28 +88,28 @@ partitions to be displayed.
.TP
\fIstep_id\fP
Specifies a slurm job step ID. A value of zero implies all job steps.
-.TP
+.TP
\fIupdate_time\fP
For all of the following informational calls, if update_time is equal to or greater than the last time changes where made to that information, new information is not returned. Otherwise all the configuration. job, node, or partition records are returned.
.SH "DESCRIPTION"
-.LP
-\fBslurm_free_job_step_info_response_msg\fR Release the storage generated by
+.LP
+\fBslurm_free_job_step_info_response_msg\fR Release the storage generated by
the \fBslurm_get_job_steps\fR function.
.LP
-\fBslurm_get_job_steps\fR Loads into details about job steps that satisfy
-the \fIjob_id\fP and/or \fIstep_id\fP specifications provided if the data
+\fBslurm_get_job_steps\fR Loads into details about job steps that satisfy
+the \fIjob_id\fP and/or \fIstep_id\fP specifications provided if the data
has been updated since the \fIupdate_time\fP specified.
-.LP
-\fBslurm_print_job_step_info\fR Prints the contents of the data structure
-describing a single job step records from the data loaded by the
+.LP
+\fBslurm_print_job_step_info\fR Prints the contents of the data structure
+describing a single job step records from the data loaded by the
\fslurm_get_job_steps\fR function.
-.LP
-\fBslurm_print_job_step_info_msg\fR Prints the contents of the data
+.LP
+\fBslurm_print_job_step_info_msg\fR Prints the contents of the data
structure describing all job step records loaded by the
\fslurm_get_job_steps\fR function.
.SH "RETURN VALUE"
.LP
-On success, zero is returned. On error, \-1 is returned, and Slurm error
+On success, zero is returned. On error, \-1 is returned, and Slurm error
code is set appropriately.
.SH "ERRORS"
.LP
@@ -117,20 +117,20 @@ code is set appropriately.
.LP
\fBSLURM_PROTOCOL_VERSION_ERROR\fR Protocol version has changed, re\-link your code.
.LP
-\fBSLURM_PROTOCOL_SOCKET_IMPL_TIMEOUT\fR Timeout in communicating with
+\fBSLURM_PROTOCOL_SOCKET_IMPL_TIMEOUT\fR Timeout in communicating with
SLURM controller.
.SH "EXAMPLE"
-.LP
+.LP
#include <stdio.h>
.br
#include <slurm/slurm.h>
.br
#include <slurm/slurm_errno.h>
-.LP
+.LP
int main (int argc, char *argv[])
-.br
+.br
{
-.br
+.br
int i;
.br
job_step_info_response_msg_t * step_info_ptr = NULL;
@@ -151,7 +151,7 @@ int main (int argc, char *argv[])
.LP
/* The easy way to print... */
.br
- slurm_print_job_step_info_msg (stdout,
+ slurm_print_job_step_info_msg (stdout,
.br
step_info_ptr);
.LP
@@ -169,36 +169,36 @@ int main (int argc, char *argv[])
.br
printf ("Steps updated at %lx, record count %d\\n",
.br
- step_info_ptr\->last_update,
+ step_info_ptr\->last_update,
.br
step_info_ptr\->job_step_count);
.br
for (i = 0; i < step_info_ptr\->job_step_count; i++) {
.br
- printf ("JobId=%u StepId=%u\\n",
+ printf ("JobId=%u StepId=%u\\n",
.br
- step_info_ptr\->job_steps[i].job_id,
+ step_info_ptr\->job_steps[i].job_id,
.br
step_info_ptr\->job_steps[i].step_id);
.br
- }
+ }
.LP
slurm_free_job_step_info_response_msg(step_info_ptr);
.br
exit (0);
-.br
+.br
}
.SH "NOTES"
-These functions are included in the libslurm library,
+These functions are included in the libslurm library,
which must be linked to your process for use
(e.g. "cc \-lslurm myprog.c").
.LP
-Some data structures contain index values to cross\-reference each other.
+Some data structures contain index values to cross\-reference each other.
If the \fIshow_flags\fP argument is not set to SHOW_ALL when getting this
data, these index values will be invalid.
.LP
-The \fBslurm_hostlist_\fR functions can be used to convert SLURM node list
+The \fBslurm_hostlist_\fR functions can be used to convert SLURM node list
expressions into a collection of individual node names.
.SH "COPYING"
@@ -220,10 +220,10 @@ FOR A PARTICULAR PURPOSE. See the GNU General Public License for more
details.
.SH "SEE ALSO"
-.LP
-\fBscontrol\fR(1), \fBsqueue\fR(1),
-\fBslurm_hostlist_create\fR(3), \fBslurm_hostlist_shift\fR(3),
+.LP
+\fBscontrol\fR(1), \fBsqueue\fR(1),
+\fBslurm_hostlist_create\fR(3), \fBslurm_hostlist_shift\fR(3),
\fBslurm_hostlist_destroy\fR(3),
-\fBslurm_get_errno\fR(3), \fBslurm_load_jobs\fR(3),
+\fBslurm_get_errno\fR(3), \fBslurm_load_jobs\fR(3),
\fBslurm_perror\fR(3), \fBslurm_strerror\fR(3)
diff --git a/doc/man/man3/slurm_free_node_info.3 b/doc/man/man3/slurm_free_node_info.3
index 259d08f89eb..452258354c9 100644
--- a/doc/man/man3/slurm_free_node_info.3
+++ b/doc/man/man3/slurm_free_node_info.3
@@ -1,30 +1,30 @@
.TH "Slurm API" "3" "January 2006" "Morris Jette" "Slurm node informational calls"
.SH "NAME"
-slurm_free_node_info, slurm_load_node,
+slurm_free_node_info, slurm_load_node,
slurm_print_node_info_msg, slurm_print_node_table, slurm_sprint_node_table
\- Slurm node information reporting functions
.SH "SYNTAX"
-.LP
+.LP
#include <stdio.h>
.br
#include <slurm/slurm.h>
.LP
void \fBslurm_free_node_info\fR (
-.br
+.br
node_info_msg_t *\fInode_info_msg_ptr\fP
-.br
+.br
);
-.LP
+.LP
int \fBslurm_load_node\fR (
-.br
- time_t \fIupdate_time\fP,
-.br
+.br
+ time_t \fIupdate_time\fP,
+.br
node_info_msg_t **\fInode_info_msg_pptr\fP,
.br
uint16_t \fIshow_flags\fP
-.br
+.br
);
-.LP
+.LP
void \fBslurm_print_node_info_msg\fR (
.br
FILE *\fIout_file\fp,
@@ -32,9 +32,9 @@ void \fBslurm_print_node_info_msg\fR (
node_info_msg_t *\fInode_info_msg_ptr\fP,
.br
int \fIone_liner\fP
-.br
+.br
);
-.LP
+.LP
void \fBslurm_print_node_table\fR (
.br
FILE *\fIout_file\fp,
@@ -44,9 +44,9 @@ void \fBslurm_print_node_table\fR (
int \fInode_scaling\fP
.br
int \fIone_liner\fP
-.br
+.br
);
-.LP
+.LP
char *\fBslurm_sprint_node_table\fR (
.br
node_info_t *\fInode_ptr\fP,
@@ -54,90 +54,90 @@ char *\fBslurm_sprint_node_table\fR (
int \fInode_scaling\fP
.br
int \fIone_liner\fP
-.br
+.br
);
.SH "ARGUMENTS"
-.LP
-.TP
+.LP
+.TP
\fInode_info_msg_ptr\fP
-Specifies the pointer to the structure created by \fBslurm_load_node\fR.
-.TP
+Specifies the pointer to the structure created by \fBslurm_load_node\fR.
+.TP
\fInode_info_msg_pptr\fP
-Specifies the double pointer to the structure to be created and filled with
-the time of the last node update, a record count, and detailed information
-about each node. Detailed node information is written to fixed sized records
-and includes: name, state, processor count, memory size, etc. See slurm.h for
-full details on the data structure's contents.
-.TP
+Specifies the double pointer to the structure to be created and filled with
+the time of the last node update, a record count, and detailed information
+about each node. Detailed node information is written to fixed sized records
+and includes: name, state, processor count, memory size, etc. See slurm.h for
+full details on the data structure's contents.
+.TP
\fInode_info_msg_ptr\fP
-Specifies the pointer to the structure created by \fBslurm_load_node\fR.
+Specifies the pointer to the structure created by \fBslurm_load_node\fR.
.TP
\fInode_ptr\fP
-Specifies a pointer to a single node records from the \fInode_info_msg_ptr\fP
+Specifies a pointer to a single node records from the \fInode_info_msg_ptr\fP
data structure.
-.TP
+.TP
\fInode_scaling\fP
number of nodes each node represents default is 1.
-.TP
+.TP
\fIone_liner\fP
Print one record per line if non\-zero.
-.TP
+.TP
\fIout_file\fP
Specifies the file to print data to.
-.TP
+.TP
\fIshow_flags\fP
Job filtering flags, may be ORed.
-Information about nodes in partitions that are configured as
-hidden and partitions that the user's group is unable to utilize
+Information about nodes in partitions that are configured as
+hidden and partitions that the user's group is unable to utilize
are not reported by default.
The \fBSHOW_ALL\fP flag will cause information about nodes in all
partitions to be displayed.
-.TP
+.TP
\fIupdate_time\fP
-For all of the following informational calls, if update_time is equal to
-or greater than the last time changes where made to that information, new
-information is not returned. Otherwise all the configuration. job, node,
+For all of the following informational calls, if update_time is equal to
+or greater than the last time changes where made to that information, new
+information is not returned. Otherwise all the configuration. job, node,
or partition records are returned.
.SH "DESCRIPTION"
-.LP
+.LP
\fBslurm_free_node_info\fR Release the storage generated by the
\fBslurm_load_node\fR function.
-.LP
-\fBslurm_load_node\fR Returns a \fInode_info_msg_t\fP that contains an update
+.LP
+\fBslurm_load_node\fR Returns a \fInode_info_msg_t\fP that contains an update
time, record count, and array of node_table records for all nodes.
-.LP
-\fBslurm_print_node_info_msg\fR Prints the contents of the data structure
-describing all node records from the data loaded by the \fBslurm_load_node\fR
+.LP
+\fBslurm_print_node_info_msg\fR Prints the contents of the data structure
+describing all node records from the data loaded by the \fBslurm_load_node\fR
function.
-.LP
-\fBslurm_print_node_table\fR Prints the contents of the data structure
+.LP
+\fBslurm_print_node_table\fR Prints the contents of the data structure
describing a single node record loaded by the \fBslurm_load_node\fR function.
.SH "RETURN VALUE"
.LP
-On success, zero is returned. On error, \-1 is returned, and Slurm error code
+On success, zero is returned. On error, \-1 is returned, and Slurm error code
is set appropriately.
.SH "ERRORS"
.LP
\fBSLURM_NO_CHANGE_IN_DATA\fR Data has not changed since \fBupdate_time\fR.
.LP
-\fBSLURM_PROTOCOL_VERSION_ERROR\fR Protocol version has changed, re\-link
+\fBSLURM_PROTOCOL_VERSION_ERROR\fR Protocol version has changed, re\-link
your code.
.LP
-\fBSLURM_PROTOCOL_SOCKET_IMPL_TIMEOUT\fR Timeout in communicating with
+\fBSLURM_PROTOCOL_SOCKET_IMPL_TIMEOUT\fR Timeout in communicating with
SLURM controller.
.SH "EXAMPLE"
-.LP
+.LP
#include <stdio.h>
.br
#include <slurm/slurm.h>
.br
#include <slurm/slurm_errno.h>
-.LP
+.LP
int main (int argc, char *argv[])
-.br
+.br
{
-.br
+.br
int i, j, k;
.br
partition_info_msg_t *part_info_ptr = NULL;
@@ -150,7 +150,7 @@ int main (int argc, char *argv[])
.LP
/* get and dump some node information */
.br
- if ( slurm_load_node ((time_t) NULL,
+ if ( slurm_load_node ((time_t) NULL,
.br
&node_buffer_ptr, SHOW_ALL) ) {
.br
@@ -178,13 +178,13 @@ int main (int argc, char *argv[])
.br
for (i = 0; i < node_buffer_ptr\->node_count; i++) {
.br
- printf ("NodeName=%s CPUs=%u\\n",
+ printf ("NodeName=%s CPUs=%u\\n",
.br
- node_buffer_ptr\->node_array[i].name,
+ node_buffer_ptr\->node_array[i].name,
.br
node_buffer_ptr\->node_array[i].cpus);
.br
- }
+ }
.LP
/* get and dump some partition information */
.br
@@ -194,7 +194,7 @@ int main (int argc, char *argv[])
.br
/* not changed since */
.br
- if ( slurm_load_partitions ((time_t) NULL,
+ if ( slurm_load_partitions ((time_t) NULL,
.br
&part_buffer_ptr) ) {
.br
@@ -208,7 +208,7 @@ int main (int argc, char *argv[])
.br
part_ptr = &part_info_ptr\->partition_array[i];
.br
- printf ("PartitionName=%s Nodes=",
+ printf ("PartitionName=%s Nodes=",
.br
part_ptr\->name);
.br
@@ -218,9 +218,9 @@ int main (int argc, char *argv[])
.br
break;
.br
- for (k = part_ptr\->node_inx[j];
+ for (k = part_ptr\->node_inx[j];
.br
- k <= part_ptr\->node_inx[j+1];
+ k <= part_ptr\->node_inx[j+1];
.br
k++) {
.br
@@ -241,15 +241,15 @@ int main (int argc, char *argv[])
slurm_free_partition_info (part_buffer_ptr);
.br
exit (0);
-.br
+.br
}
.SH "NOTES"
-These functions are included in the libslurm library,
+These functions are included in the libslurm library,
which must be linked to your process for use
(e.g. "cc \-lslurm myprog.c").
.LP
-Some data structures contain index values to cross\-reference each other.
+Some data structures contain index values to cross\-reference each other.
If the \fIshow_flags\fP argument is not set to SHOW_ALL when getting this
data, these index values will be invalid.
@@ -271,8 +271,8 @@ WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
FOR A PARTICULAR PURPOSE. See the GNU General Public License for more
details.
.SH "SEE ALSO"
-.LP
-\fBscontrol\fR(1), \fBsqueue\fR(1), \fBslurm_allocation_lookup\fR(3),
+.LP
+\fBscontrol\fR(1), \fBsqueue\fR(1), \fBslurm_allocation_lookup\fR(3),
\fBslurm_get_errno\fR(3), \fBslurm_load_partitions\fR(3),
\fBslurm_perror\fR(3), \fBslurm_strerror\fR(3)
diff --git a/doc/man/man3/slurm_free_partition_info.3 b/doc/man/man3/slurm_free_partition_info.3
index 617f7fa3112..bdb53e401ec 100644
--- a/doc/man/man3/slurm_free_partition_info.3
+++ b/doc/man/man3/slurm_free_partition_info.3
@@ -1,6 +1,6 @@
.TH "Slurm API" "3" "September 2006" "Morris Jette" "Slurm partition information reporting functions"
.SH "NAME"
-slurm_free_partition_info_msg, slurm_load_partitions,
+slurm_free_partition_info_msg, slurm_load_partitions,
slurm_print_partition_info, slurm_print_partition_info_msg
\- Slurm partition information reporting functions
.SH "SYNTAX"
@@ -10,21 +10,21 @@ slurm_print_partition_info, slurm_print_partition_info_msg
#include <slurm/slurm.h>
.LP
void \fBslurm_free_partition_info_msg\fR (
-.br
+.br
partition_info_msg_t *\fIpartition_info_msg_ptr\fP
-.br
+.br
);
-.LP
+.LP
int \fBslurm_load_partitions\fR (
-.br
- time_t \fIupdate_time\fR,
-.br
+.br
+ time_t \fIupdate_time\fR,
+.br
partition_info_msg_t **\fIpartition_info_msg_pptr\fP,
.br
uint16_t \fIshow_flags\fP
-.br
+.br
);
-.LP
+.LP
void \fBslurm_print_partition_info\fR (
.br
FILE *\fIout_file\fP,
@@ -32,9 +32,9 @@ void \fBslurm_print_partition_info\fR (
partition_info_t *\fIpartition_ptr\fP,
.br
int \fIone_liner\fP
-.br
+.br
);
-.LP
+.LP
void \fBslurm_print_partition_info_msg\fR (
.br
FILE *\fIout_file\fP,
@@ -42,55 +42,55 @@ void \fBslurm_print_partition_info_msg\fR (
partition_info_msg_t *\fIpartition_info_msg_ptr\fP,
.br
int \fIone_liner\fP
-.br
+.br
);
.SH "ARGUMENTS"
-.LP
-.TP
+.LP
+.TP
\fIone_liner\fP
Print one record per line if non\-zero.
-.TP
+.TP
\fIout_file\fP
Specifies the file to print data to.
.TP
\fIpartition_info_msg_pptr\fP
-Specifies the double pointer to the structure to be created and filled with the time
-of the last partition update, a record count, and detailed information about each
-partition. Detailed partition information is written to fixed sized records and includes:
-name, state, job time limit, job size limit, node names, indexes into the node table,
-etc. In the case of indexes into the node table, this is an array of integers with
-pairs of start and end index number into the node information records and the
-data is terminated with a value of \-1. See slurm.h for full details on the data
-structure's contents.
-.TP
+Specifies the double pointer to the structure to be created and filled with the time
+of the last partition update, a record count, and detailed information about each
+partition. Detailed partition information is written to fixed sized records and includes:
+name, state, job time limit, job size limit, node names, indexes into the node table,
+etc. In the case of indexes into the node table, this is an array of integers with
+pairs of start and end index number into the node information records and the
+data is terminated with a value of \-1. See slurm.h for full details on the data
+structure's contents.
+.TP
\fIpartition_info_msg_ptr\fP
-Specifies the pointer to the structure created by \fBslurm_load_partitions\fP.
-.TP
+Specifies the pointer to the structure created by \fBslurm_load_partitions\fP.
+.TP
\fIshow_flags\fP
Job filtering flags, may be ORed.
-Information about partitions that are configured as
-hidden and partitions that the user's group is unable to utilize
+Information about partitions that are configured as
+hidden and partitions that the user's group is unable to utilize
are not reported by default.
-The \fBSHOW_ALL\fP flag will cause information about partitions
+The \fBSHOW_ALL\fP flag will cause information about partitions
to be displayed.
.TP
\fIupdate_time\fP
-For all of the following informational calls, if update_time is equal to or greater
-than the last time changes where made to that information, new information is
-not returned. Otherwise all the configuration. job, node, or partition records
+For all of the following informational calls, if update_time is equal to or greater
+than the last time changes where made to that information, new information is
+not returned. Otherwise all the configuration. job, node, or partition records
are returned.
.SH "DESCRIPTION"
-.LP
-\fBslurm_free_partition_info_msg\fR Release the storage generated by the
+.LP
+\fBslurm_free_partition_info_msg\fR Release the storage generated by the
\fBslurm_load_partitions\fR function.
-.LP
-\fBslurm_load_partitions\fR Returns a partition_info_msg_t that contains an
+.LP
+\fBslurm_load_partitions\fR Returns a partition_info_msg_t that contains an
update time, record count, and array of partition_table records for all partitions.
-.LP
-\fBslurm_print_partition_info\fR Prints the contents of the data structure describing a
+.LP
+\fBslurm_print_partition_info\fR Prints the contents of the data structure describing a
single partition records from the data loaded by the \fBslurm_load_partitions\fR function.
-.LP
-\fBslurm_print_partition_info_msg\fR Prints the contents of the data structure describing
+.LP
+\fBslurm_print_partition_info_msg\fR Prints the contents of the data structure describing
all partition records loaded by the \fBslurm_load_partitions\fR function.
.SH "RETURN VALUE"
.LP
@@ -99,13 +99,13 @@ On success, zero is returned. On error, \-1 is returned, and Slurm error code is
.LP
\fBSLURM_NO_CHANGE_IN_DATA\fR Data has not changed since \fBupdate_time\fR.
.LP
-\fBSLURM_PROTOCOL_VERSION_ERROR\fR Protocol version has changed, re\-link
+\fBSLURM_PROTOCOL_VERSION_ERROR\fR Protocol version has changed, re\-link
your code.
.LP
-\fBSLURM_PROTOCOL_SOCKET_IMPL_TIMEOUT\fR Timeout in communicating with
+\fBSLURM_PROTOCOL_SOCKET_IMPL_TIMEOUT\fR Timeout in communicating with
SLURM controller.
.SH "EXAMPLE"
-.LP
+.LP
#include <stdio.h>
.br
#include <stdlib.h>
@@ -113,9 +113,9 @@ SLURM controller.
#include <slurm/slurm.h>
.br
#include <slurm/slurm_errno.h>
-.LP
+.LP
int main (int argc, char *argv[])
-.br
+.br
{
.br
int i;
@@ -138,7 +138,7 @@ int main (int argc, char *argv[])
.LP
/* The easy way to print... */
.br
- slurm_print_partition_info_msg (stdout,
+ slurm_print_partition_info_msg (stdout,
.br
part_info_ptr, 0);
.LP
@@ -156,15 +156,15 @@ int main (int argc, char *argv[])
.br
printf("Partitions updated at %lx, records=%d\\n",
.br
- part_info_ptr\->last_update,
+ part_info_ptr\->last_update,
.br
part_info_ptr\->record_count);
.br
for (i = 0; i < part_info_ptr\->record_count; i++) {
.br
- printf ("PartitionName=%s Nodes=%s\\n",
+ printf ("PartitionName=%s Nodes=%s\\n",
.br
- part_info_ptr\->partition_array[i].name,
+ part_info_ptr\->partition_array[i].name,
.br
part_info_ptr\->partition_array[i].nodes );
.br
@@ -173,15 +173,15 @@ int main (int argc, char *argv[])
slurm_free_partition_info_msg (part_info_ptr);
.br
exit (0);
-.br
+.br
}
.SH "NOTES"
-These functions are included in the libslurm library,
+These functions are included in the libslurm library,
which must be linked to your process for use
(e.g. "cc \-lslurm myprog.c").
.LP
-Some data structures contain index values to cross\-reference each other.
+Some data structures contain index values to cross\-reference each other.
If the \fIshow_flags\fP argument is not set to SHOW_ALL when getting this
data, these index values will be invalid.
.LP
@@ -207,10 +207,10 @@ FOR A PARTICULAR PURPOSE. See the GNU General Public License for more
details.
.SH "SEE ALSO"
-.LP
-\fBscontrol\fR(1), \fBsinfo\fR(1), \fBsqueue\fR(1),
-\fBslurm_hostlist_create\fR(3), \fBslurm_hostlist_shift\fR(3),
+.LP
+\fBscontrol\fR(1), \fBsinfo\fR(1), \fBsqueue\fR(1),
+\fBslurm_hostlist_create\fR(3), \fBslurm_hostlist_shift\fR(3),
\fBslurm_hostlist_destroy\fR(3),
-\fBslurm_get_errno\fR(3), \fBslurm_load_node\fR(3),
+\fBslurm_get_errno\fR(3), \fBslurm_load_node\fR(3),
\fBslurm_perror\fR(3), \fBslurm_strerror\fR(3)
diff --git a/doc/man/man3/slurm_get_errno.3 b/doc/man/man3/slurm_get_errno.3
index 6b03c37abd5..ade9ebb1535 100644
--- a/doc/man/man3/slurm_get_errno.3
+++ b/doc/man/man3/slurm_get_errno.3
@@ -4,59 +4,59 @@ slurm_get_errno, slurm_perror, slurm_strerror \- Slurm error handling functions
.SH "SYNTAX"
.LP
#include <slurm/slurm_errno.h>
-.LP
+.LP
int \fBslurm_get_errno\fR ( );
.LP
-void \fBslurm_perror\fR (
-.br
- char *\fIheader\fP
-.br
+void \fBslurm_perror\fR (
+.br
+ char *\fIheader\fP
+.br
);
.LP
char * \fBslurm_strerror\fR (
-.br
+.br
int \fIerrnum\fP
-.br
+.br
);
.SH "ARGUMENTS"
-.LP
-.TP
+.LP
+.TP
\fIerrnum\fP
A Slurm error code.
-.TP
+.TP
\fIheader\fP
-A pointer to a string used as a message header for printing along with an error description.
+A pointer to a string used as a message header for printing along with an error description.
.SH "DESCRIPTION"
-.LP
+.LP
\fBslurm_get_errno\fR Return the error code as set by the Slurm API function executed.
-.LP
+.LP
\fBslurm_perror\fR Print to standard error the supplied header followed by a colon followed by a text description of the last Slurm error code generated.
-.LP
+.LP
\fBslurm_strerror\fR Given a Slurm error code, return a pointer to a text description of the error's meaning.
.SH "RETURN VALUE"
.LP
\fBslurm_get_errno\fR returns an error code or zero if no error was generated by the last Slurm function call executed. \fBslurm_strerror\fR returns a pointer to a text string, which is empty if no error was generated by the last Slurm function call executed.
.SH "EXAMPLE"
-.LP
+.LP
#include <stdio.h>
.br
#include <slurm/slurm.h>
.br
#include <slurm/slurm_errno.h>
-.LP
+.LP
int main (int argc, char *argv[])
-.br
+.br
{
.br
/* assume Slurm API function failed here */
.br
- fprintf (stderr, "Slurm function errno = %d\\n",
+ fprintf (stderr, "Slurm function errno = %d\\n",
.br
slurm_get_errno ());
.br
fprintf (stderr, "Slurm function errno = %d %s\\n",
.br
- slurm_get_errno (),
+ slurm_get_errno (),
.br
slurm_strerror (slurm_get_errno ()));
.br
@@ -67,7 +67,7 @@ int main (int argc, char *argv[])
}
.SH "NOTE"
-These functions are included in the libslurm library,
+These functions are included in the libslurm library,
which must be linked to your process for use
(e.g. "cc \-lslurm myprog.c").
@@ -89,23 +89,23 @@ WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
FOR A PARTICULAR PURPOSE. See the GNU General Public License for more
details.
.SH "SEE ALSO"
-.LP
+.LP
\fBslurm_allocate_resources\fR(3),
-\fBslurm_complete_job\fR(3), \fBslurm_complete_job_step\fR(3),
-\fBslurm_allocation_lookup\fR(3),
-\fBslurm_free_ctl_conf\fR(3), \fBslurm_free_job_info_msg\fR(3),
-\fBslurm_free_job_step_create_response_msg\fR(3),
-\fBslurm_free_node_info\fR(3), \fBslurm_free_partition_info\fR(3),
-\fBslurm_free_resource_allocation_response_msg\fR(3),
-\fBslurm_free_submit_response_response_msg\fR(3),
+\fBslurm_complete_job\fR(3), \fBslurm_complete_job_step\fR(3),
+\fBslurm_allocation_lookup\fR(3),
+\fBslurm_free_ctl_conf\fR(3), \fBslurm_free_job_info_msg\fR(3),
+\fBslurm_free_job_step_create_response_msg\fR(3),
+\fBslurm_free_node_info\fR(3), \fBslurm_free_partition_info\fR(3),
+\fBslurm_free_resource_allocation_response_msg\fR(3),
+\fBslurm_free_submit_response_response_msg\fR(3),
\fBslurm_get_job_steps\fR(3),
-\fBslurm_init_job_desc_msg\fR(3), \fBslurm_init_part_desc_msg\fR(3),
-\fBslurm_job_step_create\fR(3), \fBslurm_job_will_run\fR(3),
-\fBslurm_kill_job\fR(3), \fBslurm_kill_job_step\fR(3),
-\fBslurm_load_ctl_conf\fR(3), \fBslurm_load_jobs\fR(3),
-\fBslurm_load_node\fR(3), \fBslurm_load_partitions\fR(3),
+\fBslurm_init_job_desc_msg\fR(3), \fBslurm_init_part_desc_msg\fR(3),
+\fBslurm_job_step_create\fR(3), \fBslurm_job_will_run\fR(3),
+\fBslurm_kill_job\fR(3), \fBslurm_kill_job_step\fR(3),
+\fBslurm_load_ctl_conf\fR(3), \fBslurm_load_jobs\fR(3),
+\fBslurm_load_node\fR(3), \fBslurm_load_partitions\fR(3),
\fBslurm_pid2jobid\fR(3),
-\fBslurm_reconfigure\fR(3), \fBslurm_shutdown\fR(3), \fBslurm_submit_batch_job\fR(3),
+\fBslurm_reconfigure\fR(3), \fBslurm_shutdown\fR(3), \fBslurm_submit_batch_job\fR(3),
\fBslurm_update_job\fR(3), \fBslurm_update_node\fR(3), \fBslurm_update_partition\fR(3)
-
+
diff --git a/doc/man/man3/slurm_hostlist_create.3 b/doc/man/man3/slurm_hostlist_create.3
index 5cbb3a64f6a..9d75f2ceffd 100644
--- a/doc/man/man3/slurm_hostlist_create.3
+++ b/doc/man/man3/slurm_hostlist_create.3
@@ -5,9 +5,9 @@ slurm_hostlist_create, slurm_hostlist_shift, slurm_hostlist_destroy
\- Slurm host list support functions
.SH "SYNTAX"
-.LP
+.LP
#include <slurm/slurm.h>
-.LP
+.LP
.LP
hostlist_t \fBslurm_hostlist_create\fR (
.br
@@ -28,48 +28,48 @@ void \fBslurm_hostlist_destroy\fR (
);
.SH "ARGUMENTS"
-.LP
+.LP
.TP
\fInode_list\fP
-A list of nodes as returned by the
-\fBslurm_job_step_create\fR functions. The returned value may include a simple
-range format to describe numeric ranges of values and/or multiple numeric
+A list of nodes as returned by the
+\fBslurm_job_step_create\fR functions. The returned value may include a simple
+range format to describe numeric ranges of values and/or multiple numeric
values (e.g. "linux[1\-3,6]" represents "linux1", "linux2", "linux3", and "linux6").
.TP
\fIhost_list\fP
-A hostlist created by the \fBslurm_hostlist_create\fR function.
+A hostlist created by the \fBslurm_hostlist_create\fR function.
.SH "DESCRIPTION"
.LP
-\fBslurm_hostlist_create\fR creates a database of node names from a range format
-describing node names. Use \fBslurm_hostlist_destroy\fR to release storage associated
+\fBslurm_hostlist_create\fR creates a database of node names from a range format
+describing node names. Use \fBslurm_hostlist_destroy\fR to release storage associated
with the database when no longer required.
.LP
-\fBslurm_hostlist_shift\fR extracts the first entry from the host list database created
+\fBslurm_hostlist_shift\fR extracts the first entry from the host list database created
by the \fBslurm_hostlist_create\fR function.
.LP
-\fBslurm_hostlist_destroy\fR releases storage associated with a database created by
+\fBslurm_hostlist_destroy\fR releases storage associated with a database created by
\fBslurm_hostlist_create\fR when no longer required.
.SH "RETURN VALUE"
.LP
-\fBslurm_hostlist_create\fR returns the host list database or NULL if memory can not be
+\fBslurm_hostlist_create\fR returns the host list database or NULL if memory can not be
allocated for the database.
.LP
-\fBslurm_hostlist_shift\fR returns a character string or NULL if no entries remain in
+\fBslurm_hostlist_shift\fR returns a character string or NULL if no entries remain in
the database.
.SH "EXAMPLE"
-.LP
+.LP
#include <stdio.h>
.br
#include <hostlist.h>
.br
#include <slurm.h>
-.LP
+.LP
int main (int argc, char *argv[])
-.br
+.br
{
.br
hostlist_t my_hostlist;
@@ -92,16 +92,16 @@ int main (int argc, char *argv[])
.LP
while ( (host = slurm_hostlist_shift(my_hostlist)) )
.br
- printf ("host = %s\\n", host);
+ printf ("host = %s\\n", host);
.LP
slurm_hostlist_destroy (my_hostlist) ;
.br
exit (0);
-.br
+.br
}
.SH "NOTE"
-These functions are included in the libslurm library,
+These functions are included in the libslurm library,
which must be linked to your process for use
(e.g. "cc \-lslurm myprog.c").
@@ -124,5 +124,5 @@ FOR A PARTICULAR PURPOSE. See the GNU General Public License for more
details.
.SH "SEE ALSO"
-.LP
+.LP
\fBslurm_get_job_steps\fR(3), \fBslurm_load_jobs\fR(3), \fBslurm_load_partitions\fB(3)
diff --git a/doc/man/man3/slurm_job_step_create.3 b/doc/man/man3/slurm_job_step_create.3
index af9356b5129..90a2b4ce539 100644
--- a/doc/man/man3/slurm_job_step_create.3
+++ b/doc/man/man3/slurm_job_step_create.3
@@ -5,9 +5,9 @@ slurm_free_job_step_create_response_msg, slurm_job_step_create
\- Slurm job step initiation functions
.SH "SYNTAX"
-.LP
+.LP
#include <slurm/slurm.h>
-.LP
+.LP
.LP
void \fBslurm_free_job_step_create_response_msg\fR (
.br
@@ -17,32 +17,32 @@ void \fBslurm_free_job_step_create_response_msg\fR (
.LP
int \fBslurm_job_step_create\fR (
.br
- job_step_create_request_msg_t *\fIslurm_step_alloc_req_msg_ptr\fP,
+ job_step_create_request_msg_t *\fIslurm_step_alloc_req_msg_ptr\fP,
.br
job_step_create_response_msg_t **\fIslurm_step_alloc_resp_msg_pptr\fP
.br
);
.SH "ARGUMENTS"
-.LP
+.LP
.TP
\fIslurm_step_alloc_req_msg_ptr\fP
-Specifies the pointer to the structure with job step request specification. See
+Specifies the pointer to the structure with job step request specification. See
slurm.h for full details on the data structure's contents.
.TP
\fIslurm_step_alloc_resp_msg_pptr\fP
-Specifies the double pointer to the structure to be created and filled with a description of the
-created job step: node allocation, credentials, etc. See slurm.h for full details on the data
-structure's contents.
+Specifies the double pointer to the structure to be created and filled with a description of the
+created job step: node allocation, credentials, etc. See slurm.h for full details on the data
+structure's contents.
.SH "DESCRIPTION"
.LP
-\fBslurm_free_job_step_create_response_msg\fR Release the storage generated in response
+\fBslurm_free_job_step_create_response_msg\fR Release the storage generated in response
to a call of the function \fBslurm_job_step_create\fR.
.LP
-\fBslurm_job_step_create\fR Initialize a job step including the allocation of nodes to
-it from those already allocate to that job. Always release the response message when no
-longer required using the function \fBslurm_free_job_step_create_response_msg\fR.
-The list of host names returned may be matched to their data in the proper order by
-using the functions \fBhostlist_create\fR, \fBhostlist_shift\fR, and
+\fBslurm_job_step_create\fR Initialize a job step including the allocation of nodes to
+it from those already allocate to that job. Always release the response message when no
+longer required using the function \fBslurm_free_job_step_create_response_msg\fR.
+The list of host names returned may be matched to their data in the proper order by
+using the functions \fBhostlist_create\fR, \fBhostlist_shift\fR, and
\fBhostlist_destroy\fR.
.SH "RETURN VALUE"
.LP
@@ -51,24 +51,24 @@ On success, zero is returned. On error, \-1 is returned, and Slurm error code is
.LP
\fBSLURM_PROTOCOL_VERSION_ERROR\fR Protocol version has changed, re\-link your code.
.LP
-\fBESLURM_INVALID_JOB_ID\fR the requested job id does not exist.
+\fBESLURM_INVALID_JOB_ID\fR the requested job id does not exist.
.LP
-\fBESLURM_ALREADY_DONE\fR the specified job has already completed and can not be modified.
+\fBESLURM_ALREADY_DONE\fR the specified job has already completed and can not be modified.
.LP
-\fBESLURM_ACCESS_DENIED\fR the requesting user lacks authorization for the requested action (e.g. trying to delete or modify another user's job).
+\fBESLURM_ACCESS_DENIED\fR the requesting user lacks authorization for the requested action (e.g. trying to delete or modify another user's job).
.LP
\fBESLURM_DISABLED\fR the ability to create a job step is currently disabled.
This is indicative of the job being suspended. Retry the call as desired.
.LP
-\fBESLURM_INTERCONNECT_FAILURE\fR failed to configure the node interconnect.
+\fBESLURM_INTERCONNECT_FAILURE\fR failed to configure the node interconnect.
.LP
-\fBESLURM_BAD_DIST\fR task distribution specification is invalid.
+\fBESLURM_BAD_DIST\fR task distribution specification is invalid.
.LP
-\fBSLURM_PROTOCOL_SOCKET_IMPL_TIMEOUT\fR Timeout in communicating with
+\fBSLURM_PROTOCOL_SOCKET_IMPL_TIMEOUT\fR Timeout in communicating with
SLURM controller.
.SH "NOTE"
-These functions are included in the libslurm library,
+These functions are included in the libslurm library,
which must be linked to your process for use
(e.g. "cc \-lslurm myprog.c").
@@ -90,7 +90,7 @@ WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
FOR A PARTICULAR PURPOSE. See the GNU General Public License for more
details.
.SH "SEE ALSO"
-.LP
-\fBhostlist_create\fR(3), \fBhostlist_shift\fR(3), \fBhostlist_destroy\fR(3),
-\fBsrun\fR(1),
+.LP
+\fBhostlist_create\fR(3), \fBhostlist_shift\fR(3), \fBhostlist_destroy\fR(3),
+\fBsrun\fR(1),
\fBslurm_get_errno\fR(3), \fBslurm_perror\fR(3), \fBslurm_strerror\fR(3)
diff --git a/doc/man/man3/slurm_kill_job.3 b/doc/man/man3/slurm_kill_job.3
index c1d3de09012..e599318f445 100644
--- a/doc/man/man3/slurm_kill_job.3
+++ b/doc/man/man3/slurm_kill_job.3
@@ -4,65 +4,65 @@ slurm_kill_job, slurm_kill_job_step,
slurm_signal_job, slurm_signal_job_step,
slurm_terminate_job, slurm_terminate_job_step \- Slurm job signal calls
.SH "SYNTAX"
-.LP
+.LP
#include <slurm/slurm.h>
.LP
int \fBslurm_kill_job\fR (
-.br
+.br
uint32_t \fIjob_id\fP,
-.br
+.br
uint16_t \fIsignal\fP,
.br
uint16_t \fIbatch_flag\fP
-.br
+.br
);
.LP
int \fBslurm_kill_job_step\fR (
-.br
+.br
uint32_t \fIjob_id\fP,
-.br
+.br
uint32_t \fIjob_step_id\fP,
-.br
+.br
uint16_t \fIsignal\fP
-.br
+.br
);
.LP
int \fBslurm_signal_job\fR (
-.br
+.br
uint32_t \fIjob_id\fP,
-.br
+.br
uint16_t \fIsignal\fP
-.br
+.br
);
.LP
int \fBslurm_signal_job_step\fR (
-.br
+.br
uint32_t \fIjob_id\fP,
-.br
+.br
uint32_t \fIjob_step_id\fP,
-.br
+.br
uint16_t \fIsignal\fP
-.br
+.br
);
.LP
int \fBslurm_terminate_job\fR (
-.br
+.br
uint32_t \fIjob_id\fP,
-.br
+.br
);
.LP
int \fBslurm_terminate_job_step\fR (
-.br
+.br
uint32_t \fIjob_id\fP,
-.br
+.br
uint32_t \fIjob_step_id\fP,
-.br
+.br
);
.SH "ARGUMENTS"
-.LP
+.LP
\fIbatch_flag\fP
If non\-zero then signal only the batch job shell.
-.TP
+.TP
\fIjob_id\fP
Slurm job id number.
.TP
@@ -72,29 +72,29 @@ Slurm job step id number.
\fIsignal\fp
Signal to be sent to the job or job step.
.SH "DESCRIPTION"
-.LP
-\fBslurm_kill_job\fR Request that a signal be sent to either the batch job shell
-(if \fIbatch_flag\fP is non\-zero) or all steps of the specified job.
+.LP
+\fBslurm_kill_job\fR Request that a signal be sent to either the batch job shell
+(if \fIbatch_flag\fP is non\-zero) or all steps of the specified job.
If the job is pending and the signal is SIGKILL, the job will be terminated immediately.
This function may only be successfully executed by the job's owner or user root.
-.LP
-\fBslurm_kill_job_step\fR Request that a signal be sent to a specific job step.
+.LP
+\fBslurm_kill_job_step\fR Request that a signal be sent to a specific job step.
This function may only be successfully executed by the job's owner or user root.
.LP
\fBslurm_signal_job\fR Request that the specified signal be sent to all
-steps of an existing job.
+steps of an existing job.
.LP
\fBslurm_signal_job_step\fR Request that the specified signal be sent to
-an existing job step.
+an existing job step.
.LP
\fBslurm_terminate_job\fR Request termination of all steps of an
existing job by sending a REQUEST_TERMINATE_JOB rpc to all slurmd in
-the the job allocation, and then calls slurm_complete_job().
+the the job allocation, and then calls slurm_complete_job().
\fBslurm_signal_job_step\fR Request that terminates a job step by
sending a REQUEST_TERMINATE_TASKS rpc to all slurmd of a job step, and
then calls slurm_complete_job_step() after verifying that all nodes in
the job step no longer have running tasks from the job step. (May
-take over 35 seconds to return.)
+take over 35 seconds to return.)
.SH "RETURN VALUE"
.LP
On success, zero is returned. On error, \-1 is returned, and Slurm error code is set appropriately.
@@ -104,21 +104,21 @@ On success, zero is returned. On error, \-1 is returned, and Slurm error code is
.LP
\fBESLURM_DEFAULT_PARTITION_NOT_SET\fR the system lacks a valid default partition.
.LP
-\fBESLURM_INVALID_JOB_ID\fR the requested job id does not exist.
+\fBESLURM_INVALID_JOB_ID\fR the requested job id does not exist.
.LP
\fBESLURM_JOB_SCRIPT_MISSING\fR the \fIbatch_flag\fP was set for a non\-batch job.
.LP
-\fBESLURM_ALREADY_DONE\fR the specified job has already completed and can not be modified.
+\fBESLURM_ALREADY_DONE\fR the specified job has already completed and can not be modified.
.LP
-\fBESLURM_ACCESS_DENIED\fR the requesting user lacks authorization for the requested action (e.g. trying to delete or modify another user's job).
+\fBESLURM_ACCESS_DENIED\fR the requesting user lacks authorization for the requested action (e.g. trying to delete or modify another user's job).
.LP
-\fBESLURM_INTERCONNECT_FAILURE\fR failed to configure the node interconnect.
+\fBESLURM_INTERCONNECT_FAILURE\fR failed to configure the node interconnect.
.LP
-\fBSLURM_PROTOCOL_SOCKET_IMPL_TIMEOUT\fR Timeout in communicating with
+\fBSLURM_PROTOCOL_SOCKET_IMPL_TIMEOUT\fR Timeout in communicating with
SLURM controller.
.SH "NOTE"
-These functions are included in the libslurm library,
+These functions are included in the libslurm library,
which must be linked to your process for use
(e.g. "cc \-lslurm myprog.c").
@@ -140,6 +140,6 @@ WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
FOR A PARTICULAR PURPOSE. See the GNU General Public License for more
details.
.SH "SEE ALSO"
-.LP
-\fBscancel\fR(1), \fBslurm_get_errno\fR(3),
+.LP
+\fBscancel\fR(1), \fBslurm_get_errno\fR(3),
\fBslurm_perror\fR(3), \fBslurm_strerror\fR(3)
diff --git a/doc/man/man3/slurm_load_reservations.3 b/doc/man/man3/slurm_load_reservations.3
index 8aebc9e443d..0c103c0495a 100644
--- a/doc/man/man3/slurm_load_reservations.3
+++ b/doc/man/man3/slurm_load_reservations.3
@@ -1,6 +1,6 @@
.TH "Slurm API" "3" "January 2009" "David Bremer" "Slurm reservation information reporting functions"
.SH "NAME"
-slurm_load_reservations, slurm_free_reservation_info_msg,
+slurm_load_reservations, slurm_free_reservation_info_msg,
slurm_print_reservation_info, slurm_sprint_reservation_info,
slurm_print_reservation_info_msg
\- Slurm reservation information reporting functions
@@ -9,39 +9,39 @@ slurm_print_reservation_info_msg
#include <stdio.h>
.br
#include <slurm/slurm.h>
-.LP
+.LP
int \fBslurm_load_reservations\fR (
-.br
- time_t \fIupdate_time\fR,
-.br
+.br
+ time_t \fIupdate_time\fR,
+.br
reserve_info_msg_t **\fIreservation_info_msg_pptr\fP
-.br
+.br
);
.LP
void \fBslurm_free_reservation_info_msg\fR (
-.br
+.br
reserve_info_msg_t *\fIreservation_info_msg_ptr\fP
-.br
+.br
);
-.LP
+.LP
void \fBslurm_print_reservation_info\fR (
.br
- FILE *\fIout_file\fP,
+ FILE *\fIout_file\fP,
.br
reserve_info_t *\fIreservation_ptr\fP,
.br
int \fIone_liner\fP
-.br
+.br
);
-.LP
+.LP
char * \fBslurm_sprint_reservation_info\fR (
.br
reserve_info_t *\fIreservation_ptr\fP,
.br
int \fIone_liner\fP
-.br
+.br
);
-.LP
+.LP
void \fBslurm_print_reservation_info_msg\fR (
.br
FILE *\fIout_file\fP,
@@ -49,67 +49,67 @@ void \fBslurm_print_reservation_info_msg\fR (
reserve_info_msg_t *\fIreservation_info_msg_ptr\fP,
.br
int \fIone_liner\fP
-.br
+.br
);
.SH "ARGUMENTS"
-.LP
-.TP
+.LP
+.TP
\fIone_liner\fP
Print one record per line if non\-zero.
-.TP
+.TP
\fIout_file\fP
Specifies the file to print data to.
.TP
\fIreservation_info_msg_pptr\fP
-Specifies the double pointer to the structure to be created and filled
-with the time of the last reservation update, a record count, and detailed
-information about each reservation. Detailed reservation information is
-written to fixed sized records and includes: reservation name, time limits,
-access restrictions, etc. See slurm.h for full details on the data
-structure's contents.
-.TP
+Specifies the double pointer to the structure to be created and filled
+with the time of the last reservation update, a record count, and detailed
+information about each reservation. Detailed reservation information is
+written to fixed sized records and includes: reservation name, time limits,
+access restrictions, etc. See slurm.h for full details on the data
+structure's contents.
+.TP
\fIreservation_info_msg_ptr\fP
-Specifies the pointer to the structure created by \fBslurm_load_reservations\fP.
+Specifies the pointer to the structure created by \fBslurm_load_reservations\fP.
.TP
\fIupdate_time\fP
-For all of the following informational calls, if update_time is equal to or greater
-than the last time changes where made to that information, new information is
-not returned. Otherwise all the configuration. job, node, or reservation records
+For all of the following informational calls, if update_time is equal to or greater
+than the last time changes where made to that information, new information is
+not returned. Otherwise all the configuration. job, node, or reservation records
are returned.
.SH "DESCRIPTION"
-.LP
-\fBslurm_load_reservations\fR Returns a reserve_info_msg_t that contains an
+.LP
+\fBslurm_load_reservations\fR Returns a reserve_info_msg_t that contains an
update time, record count, and array of reservation_table records for all reservations.
-.LP
-\fBslurm_free_reservation_info_msg\fR Release the storage generated by the
+.LP
+\fBslurm_free_reservation_info_msg\fR Release the storage generated by the
\fBslurm_load_reservations\fR function.
-.LP
-\fBslurm_print_reservation_info\fR Prints the contents of the data structure
-describing one of the reservation records from the data loaded by the
+.LP
+\fBslurm_print_reservation_info\fR Prints the contents of the data structure
+describing one of the reservation records from the data loaded by the
\fBslurm_load_reservations\fR function.
-.LP
-\fBslurm_sprint_reservation_info\fR Prints the sames info as
-\fBslurm_print_reservation_info\fR, but prints to a string that must be freed
+.LP
+\fBslurm_sprint_reservation_info\fR Prints the sames info as
+\fBslurm_print_reservation_info\fR, but prints to a string that must be freed
by the caller, rather than printing to a file.
-.LP
-\fBslurm_print_reservation_info_msg\fR Prints the contents of the data
-structure describing all reservation records loaded by the
+.LP
+\fBslurm_print_reservation_info_msg\fR Prints the contents of the data
+structure describing all reservation records loaded by the
\fBslurm_load_reservations\fR function.
.SH "RETURN VALUE"
.LP
-On success, zero is returned. On error, \-1 is returned, and Slurm error code
+On success, zero is returned. On error, \-1 is returned, and Slurm error code
is set appropriately.
.SH "ERRORS"
.LP
\fBSLURM_NO_CHANGE_IN_DATA\fR Data has not changed since \fBupdate_time\fR.
.LP
-\fBSLURM_PROTOCOL_VERSION_ERROR\fR Protocol version has changed, re\-link
+\fBSLURM_PROTOCOL_VERSION_ERROR\fR Protocol version has changed, re\-link
your code.
.LP
-\fBSLURM_PROTOCOL_SOCKET_IMPL_TIMEOUT\fR Timeout in communicating with
+\fBSLURM_PROTOCOL_SOCKET_IMPL_TIMEOUT\fR Timeout in communicating with
SLURM controller.
.SH "EXAMPLE"
-.LP
+.LP
#include <stdio.h>
.br
#include <stdlib.h>
@@ -117,9 +117,9 @@ SLURM controller.
#include <slurm/slurm.h>
.br
#include <slurm/slurm_errno.h>
-.LP
+.LP
int main (int argc, char *argv[])
-.br
+.br
{
.br
int i;
@@ -142,7 +142,7 @@ int main (int argc, char *argv[])
.LP
/* The easy way to print... */
.br
- slurm_print_reservation_info_msg(stdout,
+ slurm_print_reservation_info_msg(stdout,
.br
res_info_ptr, 0);
.LP
@@ -160,15 +160,15 @@ int main (int argc, char *argv[])
.br
printf("reservations updated at %lx, records=%d\\n",
.br
- res_info_ptr\->last_update,
+ res_info_ptr\->last_update,
.br
res_info_ptr\->record_count);
.br
for (i = 0; i < res_info_ptr\->record_count; i++) {
.br
- printf ("reservationName=%s Nodes=%s\\n",
+ printf ("reservationName=%s Nodes=%s\\n",
.br
- res_info_ptr\->reservation_array[i].name,
+ res_info_ptr\->reservation_array[i].name,
.br
res_info_ptr\->reservation_array[i].node_list );
.br
@@ -177,11 +177,11 @@ int main (int argc, char *argv[])
slurm_free_reservation_info_msg (res_info_ptr);
.br
return 0;
-.br
+.br
}
.SH "NOTES"
-These functions are included in the libslurm library,
+These functions are included in the libslurm library,
which must be linked to your process for use
(e.g. "cc \-lslurm myprog.c").
.LP
@@ -207,10 +207,10 @@ FOR A PARTICULAR PURPOSE. See the GNU General Public License for more
details.
.SH "SEE ALSO"
-.LP
-\fBscontrol\fR(1), \fBsinfo\fR(1), \fBsqueue\fR(1),
-\fBslurm_hostlist_create\fR(3), \fBslurm_hostlist_shift\fR(3),
+.LP
+\fBscontrol\fR(1), \fBsinfo\fR(1), \fBsqueue\fR(1),
+\fBslurm_hostlist_create\fR(3), \fBslurm_hostlist_shift\fR(3),
\fBslurm_hostlist_destroy\fR(3),
-\fBslurm_get_errno\fR(3), \fBslurm_load_node\fR(3),
+\fBslurm_get_errno\fR(3), \fBslurm_load_node\fR(3),
\fBslurm_perror\fR(3), \fBslurm_strerror\fR(3)
diff --git a/doc/man/man3/slurm_reconfigure.3 b/doc/man/man3/slurm_reconfigure.3
index a04c25569db..dabc039a4b8 100644
--- a/doc/man/man3/slurm_reconfigure.3
+++ b/doc/man/man3/slurm_reconfigure.3
@@ -1,286 +1,286 @@
.TH "Slurm API" "3" "May 2009" "Morris Jette" "Slurm administrative calls"
.SH "NAME"
-slurm_create_partition, slurm_create_reservation,
-slurm_delete_partition, slurm_delete_reservation,
+slurm_create_partition, slurm_create_reservation,
+slurm_delete_partition, slurm_delete_reservation,
slurm_init_part_desc_msg, slurm_init_resv_desc_msg,
-slurm_reconfigure, slurm_shutdown, slurm_takeover, slurm_update_job,
+slurm_reconfigure, slurm_shutdown, slurm_takeover, slurm_update_job,
,slurm_init_update_node_msg slurm_update_node, slurm_update_partition,
slurm_update_reservation
-\- Slurm administrative functions
+\- Slurm administrative functions
.SH "SYNTAX"
-.LP
+.LP
#include <slurm/slurm.h>
.LP
-int \fBslurm_create_partition\fR (
-.br
- update_part_msg_t *\fIupdate_part_msg_ptr\fP
-.br
+int \fBslurm_create_partition\fR (
+.br
+ update_part_msg_t *\fIupdate_part_msg_ptr\fP
+.br
);
.LP
-int \fBslurm_create_reservation\fR (
-.br
- reserve_request_msg_t *\fIupdate_resv_msg_ptr\fP
-.br
+int \fBslurm_create_reservation\fR (
+.br
+ reserve_request_msg_t *\fIupdate_resv_msg_ptr\fP
+.br
);
.LP
-int \fBslurm_delete_partition\fR (
-.br
- delete_part_msg_t *\fIdelete_part_msg_ptr\fP
-.br
+int \fBslurm_delete_partition\fR (
+.br
+ delete_part_msg_t *\fIdelete_part_msg_ptr\fP
+.br
);
.LP
-int \fBslurm_delete_reservation\fR (
-.br
- reservation_name_msg_t *\fIdelete_resv_msg_ptr\fP
-.br
+int \fBslurm_delete_reservation\fR (
+.br
+ reservation_name_msg_t *\fIdelete_resv_msg_ptr\fP
+.br
);
.LP
void \fBslurm_init_part_desc_msg\fR (
.br
- update_part_msg_t *\fIupdate_part_msg_ptr\fP
-.br
+ update_part_msg_t *\fIupdate_part_msg_ptr\fP
+.br
);
.LP
void \fBslurm_init_resv_desc_msg\fR (
.br
- reserve_request_msg_t *\fIupdate_resv_msg_ptr\fP
-.br
+ reserve_request_msg_t *\fIupdate_resv_msg_ptr\fP
+.br
);
-.LP
+.LP
int \fBslurm_reconfigure\fR ( );
-.LP
-int \fBslurm_shutdown\fR (
+.LP
+int \fBslurm_shutdown\fR (
.br
uint16_t \fIshutdown_options\fP
.br
);
-.LP
+.LP
int \fBslurm_takeover\fR ( );
.LP
int \fBslurm_update_job\fR (
-.br
+.br
job_desc_msg_t *\fIupdate_job_msg_ptr\fP
-.br
+.br
);
.LP
void \fBslurm_init_update_node_msg\fR(
.br
- update_node_msg_t *\fIupdate_node_msg_ptr\fP
-.br
+ update_node_msg_t *\fIupdate_node_msg_ptr\fP
+.br
);
.LP
-int \fBslurm_update_node\fR (
-.br
- update_node_msg_t *\fIupdate_node_msg_ptr\fP
-.br
+int \fBslurm_update_node\fR (
+.br
+ update_node_msg_t *\fIupdate_node_msg_ptr\fP
+.br
);
.LP
-int \fBslurm_update_partition\fR (
-.br
- update_part_msg_t *\fIupdate_part_msg_ptr\fP
-.br
+int \fBslurm_update_partition\fR (
+.br
+ update_part_msg_t *\fIupdate_part_msg_ptr\fP
+.br
);
.LP
-int \fBslurm_update_reservation\fR (
-.br
- reserve_request_msg_t *\fIupdate_resv_msg_ptr\fP
-.br
+int \fBslurm_update_reservation\fR (
+.br
+ reserve_request_msg_t *\fIupdate_resv_msg_ptr\fP
+.br
);
.SH "ARGUMENTS"
-.LP
-.TP
+.LP
+.TP
\fIshutdown_options\fP
0: all slurm daemons are shutdown
.br
1: slurmctld generates a core file
.br
2: only the slurmctld is shutdown (no core file)
-.TP
+.TP
\fIdelete_part_msg_ptr\fP
-Specifies the pointer to a partition delete request specification.
-See slurm.h for full details on the data structure's contents.
-.TP
+Specifies the pointer to a partition delete request specification.
+See slurm.h for full details on the data structure's contents.
+.TP
\fIdelete_resv_msg_ptr\fP
-Specifies the pointer to a reservation delete request specification.
-See slurm.h for full details on the data structure's contents.
+Specifies the pointer to a reservation delete request specification.
+See slurm.h for full details on the data structure's contents.
.TP
\fIupdate_job_msg_ptr\fP
-Specifies the pointer to a job update request specification. See slurm.h
-for full details on the data structure's contents.
-.TP
+Specifies the pointer to a job update request specification. See slurm.h
+for full details on the data structure's contents.
+.TP
\fIupdate_node_msg_ptr\fP
-Specifies the pointer to a node update request specification. See slurm.h
-for full details on the data structure's contents.
-.TP
+Specifies the pointer to a node update request specification. See slurm.h
+for full details on the data structure's contents.
+.TP
\fIupdate_part_msg_ptr\fP
-Specifies the pointer to a partition create or update request specification.
-See slurm.h for full details on the data structure's contents.
-.TP
+Specifies the pointer to a partition create or update request specification.
+See slurm.h for full details on the data structure's contents.
+.TP
\fIupdate_resv_msg_ptr\fP
-Specifies the pointer to a reservation create or update request specification.
-See slurm.h for full details on the data structure's contents.
+Specifies the pointer to a reservation create or update request specification.
+See slurm.h for full details on the data structure's contents.
.SH "DESCRIPTION"
-.LP
-\fBslurm_create_partition\fR Request that a new partition be created.
-Initialize the data structure using the \fBslurm_init_part_desc_msg\fR
+.LP
+\fBslurm_create_partition\fR Request that a new partition be created.
+Initialize the data structure using the \fBslurm_init_part_desc_msg\fR
function prior to setting values of the parameters to be changed.
-Note: \fBslurm_init_part_desc_msg\fR is not equivalent to setting the data
+Note: \fBslurm_init_part_desc_msg\fR is not equivalent to setting the data
structure values to zero. A partition name must be set for the call to
succeed.
This function may only be successfully executed by user root.
-.LP
-\fBslurm_create_reservation\fR Request that a new reservation be created.
-Initialize the data structure using the \fBslurm_init_resv_desc_msg\fR
+.LP
+\fBslurm_create_reservation\fR Request that a new reservation be created.
+Initialize the data structure using the \fBslurm_init_resv_desc_msg\fR
function prior to setting values of the parameters to be changed.
-Note: \fBslurm_init_resv_desc_msg\fR is not equivalent to setting the data
-structure values to zero. The reservation's time limits, user or
+Note: \fBslurm_init_resv_desc_msg\fR is not equivalent to setting the data
+structure values to zero. The reservation's time limits, user or
account restrictions, and node names or a node count must be specified for
the call to succeed.
This function may only be successfully executed by user root.
-.LP
-\fBslurm_delete_partition\fR Request that the specified partition be deleted.
-All jobs associated with the identified partition will be terminated and
+.LP
+\fBslurm_delete_partition\fR Request that the specified partition be deleted.
+All jobs associated with the identified partition will be terminated and
purged. This function may only be successfully executed by user root.
-.LP
-\fBslurm_delete_reservation\fR Request that the specified reservation be
+.LP
+\fBslurm_delete_reservation\fR Request that the specified reservation be
deleted. This function may only be successfully executed by user root.
-.LP
-\fBslurm_init_part_desc_msg\fR Initialize the contents of a partition
-descriptor with default values. Note: \fBslurm_init_part_desc_msg\fR is
-not equivalent to setting the data structure values to zero. Execute
-this function before executing \fBslurm_create_partition\fR or
+.LP
+\fBslurm_init_part_desc_msg\fR Initialize the contents of a partition
+descriptor with default values. Note: \fBslurm_init_part_desc_msg\fR is
+not equivalent to setting the data structure values to zero. Execute
+this function before executing \fBslurm_create_partition\fR or
\fBslurm_update_partition\fR.
-.LP
-\fBslurm_init_resv_desc_msg\fR Initialize the contents of a reservation
-descriptor with default values. Note: \fBslurm_init_resv_desc_msg\fR is
-not equivalent to setting the data structure values to zero. Execute this
-function before executing \fBslurm_create_reservation\fR or
+.LP
+\fBslurm_init_resv_desc_msg\fR Initialize the contents of a reservation
+descriptor with default values. Note: \fBslurm_init_resv_desc_msg\fR is
+not equivalent to setting the data structure values to zero. Execute this
+function before executing \fBslurm_create_reservation\fR or
\fBslurm_update_reservation\fR.
-.LP
-\fBslurm_reconfigure\fR Request that the Slurm controller re\-read its
-configuration file. The new configuration parameters take effect
+.LP
+\fBslurm_reconfigure\fR Request that the Slurm controller re\-read its
+configuration file. The new configuration parameters take effect
immediately. This function may only be successfully executed by user root.
-.LP
-\fBslurm_shutdown\fR Request that the Slurm controller terminate. This
+.LP
+\fBslurm_shutdown\fR Request that the Slurm controller terminate. This
function may only be successfully executed by user root.
-.LP
-\fBslurm_takeover\fR Request that the Slurm primary controller shutdown
+.LP
+\fBslurm_takeover\fR Request that the Slurm primary controller shutdown
immediately and the backup controller take over.
This function may only be successfully executed by user root.
-.LP
-\fBslurm_update_job\fR Request that the configuration of a job be updated. Note
-that most, but not all parameters of a job may be changed by this function.
-Initialize the data structure using the \fBslurm_init_job_desc_msg\fR function
-prior to setting values of the parameters to be changed. Note:
-\fBslurm_init_job_desc_msg\fR is not equivalent to setting the data structure
-values to zero. This function may only be successfully executed by user root.
-Note the job priority of zero represents a job that will not be scheduled.
-Slurm uses the priority one to represent jobs that can not be scheduled until
-additional nodes are returned to service (i.e. not DOWN, DRAINED, or FAILED).
+.LP
+\fBslurm_update_job\fR Request that the configuration of a job be updated. Note
+that most, but not all parameters of a job may be changed by this function.
+Initialize the data structure using the \fBslurm_init_job_desc_msg\fR function
+prior to setting values of the parameters to be changed. Note:
+\fBslurm_init_job_desc_msg\fR is not equivalent to setting the data structure
+values to zero. This function may only be successfully executed by user root.
+Note the job priority of zero represents a job that will not be scheduled.
+Slurm uses the priority one to represent jobs that can not be scheduled until
+additional nodes are returned to service (i.e. not DOWN, DRAINED, or FAILED).
This permits lower priority jobs to utilize those resources which are available.
-.LP
-\fBslurm_init_update_node_msg\fR Initialize the contents of an update mpde
-descriptor with default values. Note: \fBslurm_init_update_node_msg\fR is
-not equivalent to setting the data structure values to zero. Execute
+.LP
+\fBslurm_init_update_node_msg\fR Initialize the contents of an update mpde
+descriptor with default values. Note: \fBslurm_init_update_node_msg\fR is
+not equivalent to setting the data structure values to zero. Execute
this function before executing \fBslurm_update_node\fR.
-.LP
-\fBslurm_update_node\fR Request that the state of one or more nodes be updated.
-Note that the state of a node (e.g. DRAINING, IDLE, etc.) may be changed, but
-its hardware configuration may not be changed by this function. If the hardware
+.LP
+\fBslurm_update_node\fR Request that the state of one or more nodes be updated.
+Note that the state of a node (e.g. DRAINING, IDLE, etc.) may be changed, but
+its hardware configuration may not be changed by this function. If the hardware
configuration of a node changes, update the Slurm configuration file and execute
-the \fBslurm_reconfigure\fR function. This function may only be successfully
-executed by user root. If used by some autonomous program, the state value
-most likely to be used is \fBNODE_STATE_DRAIN\fR or \fBNODE_STATE_FAILING\fR.
-The node state flag \fBNODE_STATE_NO_RESPOND\fR may be specified without
-changing the underlying node state. Note that the node's
-\fBNODE_STATE_NO_RESPOND\fR flag will be cleared as soon as the slurmd
+the \fBslurm_reconfigure\fR function. This function may only be successfully
+executed by user root. If used by some autonomous program, the state value
+most likely to be used is \fBNODE_STATE_DRAIN\fR or \fBNODE_STATE_FAILING\fR.
+The node state flag \fBNODE_STATE_NO_RESPOND\fR may be specified without
+changing the underlying node state. Note that the node's
+\fBNODE_STATE_NO_RESPOND\fR flag will be cleared as soon as the slurmd
daemon on that node communicates with the slurmctld daemon.
-Likewise the state \fBNODE_STATE_DOWN\fR indicates that the slurmd daemon
-is not responding (and has not responded for an interval at least as long
-as the \fBSlurmdTimeout\fR configuration parameter). The node will leave the
+Likewise the state \fBNODE_STATE_DOWN\fR indicates that the slurmd daemon
+is not responding (and has not responded for an interval at least as long
+as the \fBSlurmdTimeout\fR configuration parameter). The node will leave the
\fBNODE_STATE_DOWN\fR state as soon as the slurmd daemon communicates.
-.LP
-\fBslurm_update_partition\fR Request that the configuration of a
-partition be updated. Note that most, but not all parameters of a
-partition may be changed by this function. Initialize the data
-structure using the \fBslurm_init_part_desc_msg\fR function prior
-to setting values of the parameters to be changed. Note:
-\fBslurm_init_part_desc_msg\fR is not equivalent to setting the
-data structure values to zero. This function may only be
+.LP
+\fBslurm_update_partition\fR Request that the configuration of a
+partition be updated. Note that most, but not all parameters of a
+partition may be changed by this function. Initialize the data
+structure using the \fBslurm_init_part_desc_msg\fR function prior
+to setting values of the parameters to be changed. Note:
+\fBslurm_init_part_desc_msg\fR is not equivalent to setting the
+data structure values to zero. This function may only be
successfully executed by user root.
-.LP
-\fBslurm_update_reservation\fR Request that the configuration of a
-reservation be updated. Initialize the data structure using the
-\fBslurm_init_resv_desc_msg\fR function prior to setting values of
-the parameters to be changed. Note: \fBslurm_init_resv_desc_msg\fR
-is not equivalent to setting the data structure values to zero. This
+.LP
+\fBslurm_update_reservation\fR Request that the configuration of a
+reservation be updated. Initialize the data structure using the
+\fBslurm_init_resv_desc_msg\fR function prior to setting values of
+the parameters to be changed. Note: \fBslurm_init_resv_desc_msg\fR
+is not equivalent to setting the data structure values to zero. This
function may only be successfully executed by user root.
.SH "RETURN VALUE"
.LP
-On success, zero is returned. On error, \-1 is returned, and the Slurm error
+On success, zero is returned. On error, \-1 is returned, and the Slurm error
code is set appropriately.
.LP
-Exception: A successful slurm_create_reservation call returns a string
+Exception: A successful slurm_create_reservation call returns a string
containing the name of the reservation, in memory to be freed by the caller.
A failed call returns NULL and sets the Slurm error code.
.SH "ERRORS"
.LP
-\fBSLURM_PROTOCOL_VERSION_ERROR\fR Protocol version has changed, re\-link your
+\fBSLURM_PROTOCOL_VERSION_ERROR\fR Protocol version has changed, re\-link your
code.
.LP
-\fBESLURM_INVALID_NODE_NAME\fR The requested node name(s) is/are not valid.
+\fBESLURM_INVALID_NODE_NAME\fR The requested node name(s) is/are not valid.
.LP
-\fBESLURM_INVALID_NODE_STATE\fR The specified state node state or requested
-node state transition is not valid.
+\fBESLURM_INVALID_NODE_STATE\fR The specified state node state or requested
+node state transition is not valid.
.LP
-\fBESLURM_INVALID_PARTITION_NAME\fR The requested partition name is not valid.
+\fBESLURM_INVALID_PARTITION_NAME\fR The requested partition name is not valid.
.LP
\fBESLURM_INVALID_AUTHTYPE_CHANGE\fR The \fBAuthType\fR parameter can
not be changed using the \fBslurm_reconfigure\fR function, but all SLURM
-daemons and commands must be restarted. See \fBslurm.conf\fR(5) for more
+daemons and commands must be restarted. See \fBslurm.conf\fR(5) for more
information.
.LP
-\fBESLURM_INVALID_SCHEDTYPE_CHANGE\fR The \fBSchedulerType\fR parameter can
-not be changed using the \fBslurm_reconfigure\fR function, but the
-\fBslurmctld\fR daemon must be restarted. Manual changes to existing job
+\fBESLURM_INVALID_SCHEDTYPE_CHANGE\fR The \fBSchedulerType\fR parameter can
+not be changed using the \fBslurm_reconfigure\fR function, but the
+\fBslurmctld\fR daemon must be restarted. Manual changes to existing job
parameters may also be required. See \fBslurm.conf\fR(5) for more information.
.LP
\fBESLURM_INVALID_SWITCHTYPE_CHANGE\fR The \fBSwitchType\fR parameter can
not be changed using the \fBslurm_reconfigure\fR function, but all
-SLURM daemons and commands must be restarted. All previously running
+SLURM daemons and commands must be restarted. All previously running
jobs will be lost. See \fBslurm.conf\fR(5) for more information.
.LP
-\fBESLURM_ACCESS_DENIED\fR The requesting user lacks authorization for
-the requested action (e.g. trying to delete or modify another user's job).
+\fBESLURM_ACCESS_DENIED\fR The requesting user lacks authorization for
+the requested action (e.g. trying to delete or modify another user's job).
.LP
-\fBSLURM_PROTOCOL_SOCKET_IMPL_TIMEOUT\fR Timeout in communicating with
+\fBSLURM_PROTOCOL_SOCKET_IMPL_TIMEOUT\fR Timeout in communicating with
SLURM controller.
.LP
-\fBESLURM_RESERVATION_ACCESS\fR Requestor is not authorized to access the
+\fBESLURM_RESERVATION_ACCESS\fR Requestor is not authorized to access the
reservation.
.LP
-\fBESLURM_RESERVATION_INVALID\fR Invalid reservation parameter given,
+\fBESLURM_RESERVATION_INVALID\fR Invalid reservation parameter given,
e.g. wrong name given.
.LP
\fBESLURM_INVALID_TIME_VALUE\fR Invalid time value.
.LP
-\fBESLURM_RESERVATION_BUSY\fR Reservation is busy, e.g. trying to delete a
+\fBESLURM_RESERVATION_BUSY\fR Reservation is busy, e.g. trying to delete a
reservation while in use.
.LP
-\fBESLURM_RESERVATION_NOT_USABLE\fR Reservation not usable, e.g. trying to
+\fBESLURM_RESERVATION_NOT_USABLE\fR Reservation not usable, e.g. trying to
use an expired reservation.
.SH "EXAMPLE"
-.LP
+.LP
#include <stdio.h>
.br
#include <slurm/slurm.h>
.br
#include <slurm/slurm_errno.h>
-.LP
+.LP
int main (int argc, char *argv[])
-.br
+.br
{
-.br
+.br
job_desc_msg_t update_job_msg;
.br
update_node_msg_t update_node_msg;
@@ -292,105 +292,105 @@ int main (int argc, char *argv[])
reserve_request_msg_t resv_msg;
.br
char *resv_name = NULL;
-.LP
+.LP
if (slurm_reconfigure ( )) {
.br
slurm_perror ("slurm_reconfigure error");
-.br
+.br
exit (1);
.br
}
-.LP
+.LP
slurm_init_job_desc_msg( &update_job_msg );
-.br
+.br
update_job_msg.job_id = 1234;
-.br
+.br
update_job_msg time_limit = 200;
-.br
- if (slurm_update_job (&update_job_msg)) {
+.br
+ if (slurm_update_job (&update_job_msg)) {
.br
slurm_perror ("slurm_update_job error");
-.br
+.br
exit (1);
.br
}
-.LP
+.LP
slurm_init_part_desc_msg ( &update_part_msg );
.br
update_part_msg.name = "test.partition";
.br
update_part_msg.state_up = 0; /* partition down */
-.br
- if (slurm_create_partition (&update_part_msg)) {
+.br
+ if (slurm_create_partition (&update_part_msg)) {
.br
slurm_perror ("slurm_create_partition error");
-.br
+.br
exit (1);
.br
}
-.LP
+.LP
update_part_msg.state_up = 1; /* partition up */
-.br
- if (slurm_update_partition (&update_part_msg)) {
+.br
+ if (slurm_update_partition (&update_part_msg)) {
.br
slurm_perror ("slurm_update_partition error");
-.br
+.br
exit (1);
.br
}
-.LP
+.LP
delete_part_msg.name = "test.partition";
-.br
- if (slurm_delete_partition (&delete_part_msg)) {
+.br
+ if (slurm_delete_partition (&delete_part_msg)) {
.br
slurm_perror ("slurm_delete_partition error");
-.br
+.br
exit (1);
.br
}
-.LP
+.LP
slurm_init_update_node_msg (&update_node_msg);
.br
update_node_msg.node_names = "lx[10\-12]";
.br
update_node_msg.node_state = NODE_STATE_DRAINING ;
-.br
- if (slurm_update_node (&update_node_msg)) {
+.br
+ if (slurm_update_node (&update_node_msg)) {
.br
slurm_perror ("slurm_update_node error");
-.br
+.br
exit (1);
-.br
+.br
}
-.LP
+.LP
slurm_init_resv_desc_msg ( &resv_msg );
.br
- resv_msg.start_time = time(NULL) + 60*60; /* One hour from now */
+ resv_msg.start_time = time(NULL) + 60*60; /* One hour from now */
.br
resv_msg.duration = 720; /* 12 hours/720 minutes */
.br
- resv_msg.node_cnt = 10;
+ resv_msg.node_cnt = 10;
.br
resv_msg.accounts = "admin";
-.br
- resv_name = slurm_create_reservation (&resv_msg);
+.br
+ resv_name = slurm_create_reservation (&resv_msg);
.br
if (!resv_name) {
.br
slurm_perror ("slurm_create_reservation error");
-.br
+.br
exit (1);
.br
}
.br
free(resv_name);
-.br
+.br
exit (0);
-.br
+.br
}
.SH "NOTE"
-These functions are included in the libslurm library,
+These functions are included in the libslurm library,
which must be linked to your process for use
(e.g. "cc \-lslurm myprog.c").
@@ -412,6 +412,6 @@ WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
FOR A PARTICULAR PURPOSE. See the GNU General Public License for more
details.
.SH "SEE ALSO"
-.LP
+.LP
\fBscontrol\fR(1), \fBslurm_get_errno\fR(3), \fBslurm_init_job_desc_msg\fR(3),
\fBslurm_perror\fR(3), \fBslurm_strerror\fR(3), \fBslurm.conf\fR(5)
diff --git a/doc/man/man3/slurm_resume.3 b/doc/man/man3/slurm_resume.3
index 70942cb8cca..676eddc7f2a 100644
--- a/doc/man/man3/slurm_resume.3
+++ b/doc/man/man3/slurm_resume.3
@@ -4,7 +4,7 @@
slurm_suspend, slurm_resume, slurm_requeue \- Slurm suspend, resume and requeue functions
.SH "SYNTAX"
-.LP
+.LP
#include <slurm/slurm.h>
.LP
.LP
@@ -27,7 +27,7 @@ int \fBslurm_requeue\fR (
);
.SH "ARGUMENTS"
-.LP
+.LP
.TP
\fIjob_id\fP
SLURM job ID to perform the operation upon.
@@ -42,12 +42,12 @@ Resume execution of a previously suspended job.
.LP
\fBslurm_requeue\fR
Requeue a running or pending SLURM batch job.
-The job script will be restarted from its beginning,
+The job script will be restarted from its beginning,
ignoring any previous checkpoint.
.SH "RETURN VALUE"
.LP
-Zero is returned upon success.
+Zero is returned upon success.
On error, \-1 is returned, and the Slurm error code is set appropriately.
.SH "ERRORS"
.LP
@@ -56,10 +56,10 @@ On error, \-1 is returned, and the Slurm error code is set appropriately.
resume a job that is not currently suspended, or
requeue a job on which the operation has been disabled).
.LP
-\fBESLURM_INVALID_JOB_ID\fR the requested job id does not exist.
+\fBESLURM_INVALID_JOB_ID\fR the requested job id does not exist.
.LP
-\fBESLURM_ACCESS_DENIED\fR the requesting user lacks authorization for the
-requested action (e.g. not user root or SlurmUser).
+\fBESLURM_ACCESS_DENIED\fR the requesting user lacks authorization for the
+requested action (e.g. not user root or SlurmUser).
.LP
\fBESLURM_JOB_PENDING\fR the requested job is still pending.
.LP
@@ -68,7 +68,7 @@ requested action (e.g. not user root or SlurmUser).
\fBESLURM_NOT_SUPPORTED\fR the requested operation is not supported on this system.
.SH "NOTE"
-These functions are included in the libslurm library,
+These functions are included in the libslurm library,
which must be linked to your process for use
(e.g. "cc \-lslurm myprog.c").
@@ -91,5 +91,5 @@ FOR A PARTICULAR PURPOSE. See the GNU General Public License for more
details.
.SH "SEE ALSO"
-.LP
+.LP
\fBscontrol\fR(1)
diff --git a/doc/man/man3/slurm_slurmd_status.3 b/doc/man/man3/slurm_slurmd_status.3
index 1f4ff24faf3..0091610997f 100644
--- a/doc/man/man3/slurm_slurmd_status.3
+++ b/doc/man/man3/slurm_slurmd_status.3
@@ -6,19 +6,19 @@ slurm_free_slurmd_status, slurm_load_slurmd_status, slurm_print_slurmd_status
\- Slurmd status functions
.SH "SYNTAX"
-.LP
+.LP
#include <slurm/slurm.h>
.LP
.LP
void \fBslurm_free_slurmd_status\fR (
.br
- slurmd_status_t* \fIslurmd_status_ptr\fP
+ slurmd_status_t* \fIslurmd_status_ptr\fP
.br
);
.LP
int \fBslurm_load_slurmd_status\fR (
.br
- slurmd_status_t** \fIslurmd_status_ptr\fP
+ slurmd_status_t** \fIslurmd_status_ptr\fP
.br
);
.LP
@@ -26,14 +26,14 @@ void \fBslurm_print_slurmd_status\fR (
.br
FILE *\fIout\fP,
.br
- slurmd_status_t* \fIslurmd_status_pptr\fP
+ slurmd_status_t* \fIslurmd_status_pptr\fP
.br
);
.SH "ARGUMENTS"
-.LP
+.LP
.TP
-\fIslurmd_status_ptr\fP
+\fIslurmd_status_ptr\fP
Slurmd status pointer. Created by \fBslurm_load_slurmd_status\fR,
used in subsequent function calls, and destroyed by
\fBslurm_free_slurmd_status\fR.
@@ -41,7 +41,7 @@ used in subsequent function calls, and destroyed by
.SH "DESCRIPTION"
.LP
\fBslurm_free_slurmd_status\fR free slurmd state information.
-.LP
+.LP
\fBslurm_load_slurmd_status\fR issue RPC to get the status of slurmd
daemon on this machine.
.LP
diff --git a/doc/man/man3/slurm_step_ctx_create.3 b/doc/man/man3/slurm_step_ctx_create.3
index 13b35e7f693..dd50639632c 100644
--- a/doc/man/man3/slurm_step_ctx_create.3
+++ b/doc/man/man3/slurm_step_ctx_create.3
@@ -7,19 +7,19 @@ slurm_step_ctx_params_t_init, slurm_jobinfo_ctx_get,
slurm_spawn_kill, slurm_step_ctx_destroy \- Slurm task spawn functions
.SH "SYNTAX"
-.LP
+.LP
#include <slurm/slurm.h>
-.LP
+.LP
.LP
slurm_step_ctx \fBslurm_step_ctx_create\fR (
.br
- slurm_step_ctx_params_t *\fIstep_req\fP
+ slurm_step_ctx_params_t *\fIstep_req\fP
.br
);
.LP
slurm_step_ctx \fBslurm_step_ctx_create_no_alloc\fR (
.br
- slurm_step_ctx_params_t *\fIstep_req\fP
+ slurm_step_ctx_params_t *\fIstep_req\fP
.br
);
.LP
@@ -41,9 +41,9 @@ int \fBslurm_step_ctx_get\fR (
.LP
int \fBslurm_jobinfo_ctx_get\fR (
.br
- switch_jobinfo_t \fIjobinfo\fP,
+ switch_jobinfo_t \fIjobinfo\fP,
.br
- int \fIdata_type\fP,
+ int \fIdata_type\fP,
.br
void *\fIdata\fP
.br
@@ -51,7 +51,7 @@ int \fBslurm_jobinfo_ctx_get\fR (
.LP
void \fBslurm_step_ctx_params_t_init\fR (
.br
- slurm_step_ctx_params_t *\fIstep_req\fP
+ slurm_step_ctx_params_t *\fIstep_req\fP
.br
);
.LP
@@ -77,10 +77,10 @@ int \fBslurm_step_ctx_destroy\fR {
.br
);
.SH "ARGUMENTS"
-.LP
+.LP
.TP
\fIstep_req\fP
-Specifies the pointer to the structure with job step request specification. See
+Specifies the pointer to the structure with job step request specification. See
slurm.h for full details on the data structure's contents.
.TP
\fIctx\fP
@@ -100,25 +100,25 @@ upon the switch plugin in use.
.TP
\fIfd_array\fP
Array of socket file descriptors to be connected to the initiated tasks.
-Tasks will be connected to these file descriptors in order of their
+Tasks will be connected to these file descriptors in order of their
task id.
This socket will carry standard input, output and error for the task.
\fIjobinfo\fP
Switch\-specific job information as returned by \fBslurm_step_ctx_get\fR.
.TP
\fIsignal\fP
-Signal to be sent to the spawned tasks.
+Signal to be sent to the spawned tasks.
.SH "DESCRIPTION"
.LP
\fBslurm_jobinfo_ctx_get\fR Get values from a \fIjobinfo\fR field as
-returned by \fBslurm_step_ctx_get\fR. The operation of this function
+returned by \fBslurm_step_ctx_get\fR. The operation of this function
is highly dependent upon the switch plugin in use.
.LP
-\fBslurm_step_ctx_create\fR Create a job step context. To avoid memory
+\fBslurm_step_ctx_create\fR Create a job step context. To avoid memory
leaks call \fBslurm_step_ctx_destroy\fR when the use of this context is
-finished. NOTE: this function creates a slurm job step. Call \fBslurm_spawn\fR
+finished. NOTE: this function creates a slurm job step. Call \fBslurm_spawn\fR
in a timely fashion to avoid having job step credentials time out. If
-\fBslurm_spawn\fR is not used, explicitly cancel the job step.
+\fBslurm_spawn\fR is not used, explicitly cancel the job step.
.LP
\fBslurm_step_ctx_create_no_alloc\fR Same as above, only no
allocation is made. To avoid memory leaks call
@@ -126,7 +126,7 @@ allocation is made. To avoid memory leaks call
.LP
\fBslurm_step_ctx_daemon_per_node_hack\fR Hack the step context to run
a single process per node, regardless of the settings selected at
-slurm_step_ctx_create time.
+slurm_step_ctx_create time.
.LP
\fBslurm_step_ctx_get\fR Get values from a job step context.
\fIctx_key\fP identifies the fields to be gathered from the job step context.
@@ -137,17 +137,17 @@ of \fIctx_key\fP. See the \fBCONTEXT KEYS\fR section for details.
structure that you will pass to slurm_step_ctx_create().
.LP
\fBslurm_spawn\fR Spawn tasks based upon a job step context
-and establish communications with the tasks using the socket
+and establish communications with the tasks using the socket
file descriptors specified.
-Note that this function can only be called once for each job
-step context.
+Note that this function can only be called once for each job
+step context.
Establish a new job step context for each set of tasks to be spawned.
.LP
-\fBslurm_spawn_kill\fR Signal the tasks spawned for this context
+\fBslurm_spawn_kill\fR Signal the tasks spawned for this context
by \fBslurm_spawn\fR.
.LP
\fBslurm_step_ctx_destroy\fR Destroy a job step context created by
-\fBslurm_step_ctx_create\fR.
+\fBslurm_step_ctx_create\fR.
.SH "CONEXT KEYS"
.TP
\fBSLURM_STEP_CTX_ARGS\fR
@@ -156,17 +156,17 @@ Accepts two additional arguments, the first of type int and
the second of type char **.
.TP
\fBSLURM_STEP_CTX_CHDIR\fR
-Have the remote process change directory to the specified location
+Have the remote process change directory to the specified location
before beginning execution. Accepts one argument of type
char * identifying the directory's pathname. By default
the remote process will execute in the same directory pathname
-from which it is spawned. NOTE: This assumes that same directory
-pathname exists on the other nodes.
+from which it is spawned. NOTE: This assumes that same directory
+pathname exists on the other nodes.
.TP
\fBSLURM_STEP_CTX_ENV\fR
Sets the environment variable count and values for the executable.
Accepts two additional arguments, the first of type int and
-the second of type char **. By default the current environment
+the second of type char **. By default the current environment
variables are copied to started task's environment.
.TP
\fBSLURM_STEP_CTX_RESP\fR
@@ -179,28 +179,28 @@ Accepts one additional argument of type uint32_t *.
.TP
\fBSLURM_STEP_CTX_TASKS\fR
Get the number of tasks per node for a given job.
-Accepts one additional argument of type uint32_t **.
-This argument will be set to point to an array with the
+Accepts one additional argument of type uint32_t **.
+This argument will be set to point to an array with the
task counts of each node in an element of the array.
-See \fBSLURM_STEP_CTX_TID\fR below to determine the
+See \fBSLURM_STEP_CTX_TID\fR below to determine the
task ID numbers associated with each of those tasks.
.TP
\fBSLURM_STEP_CTX_TID\fR
-Get the task ID numbers associated with the tasks allocated to
+Get the task ID numbers associated with the tasks allocated to
a specific node.
Accepts two additional arguments, the first of type int and
-the second of type uint32_t **. The first argument identifies
-the node number of interest (zero origin). The second argument
-will be set to point to an array with the task ID numbers of
-each task allocated to the node (also zero origin).
-See \fBSLURM_STEP_CTX_TASKS\fR above to determine how many
+the second of type uint32_t **. The first argument identifies
+the node number of interest (zero origin). The second argument
+will be set to point to an array with the task ID numbers of
+each task allocated to the node (also zero origin).
+See \fBSLURM_STEP_CTX_TASKS\fR above to determine how many
tasks are associated with each node.
.SH "RETURN VALUE"
.LP
For \fB slurm_step_ctx_create\fR a context is return upon success. On error
NULL is returned and the Slurm error code is set appropriately.
.LP
-For all other functions zero is returned upon success.
+For all other functions zero is returned upon success.
On error, \-1 is returned, and the Slurm error code is set appropriately.
.SH "ERRORS"
.LP
@@ -208,20 +208,20 @@ On error, \-1 is returned, and the Slurm error code is set appropriately.
.LP
\fBSLURM_PROTOCOL_VERSION_ERROR\fR Protocol version has changed, re\-link your code.
.LP
-\fBESLURM_INVALID_JOB_ID\fR the requested job id does not exist.
+\fBESLURM_INVALID_JOB_ID\fR the requested job id does not exist.
.LP
-\fBESLURM_ALREADY_DONE\fR the specified job has already completed and can not be modified.
+\fBESLURM_ALREADY_DONE\fR the specified job has already completed and can not be modified.
.LP
-\fBESLURM_ACCESS_DENIED\fR the requesting user lacks authorization for the requested action (e.g. trying to delete or modify another user's job).
+\fBESLURM_ACCESS_DENIED\fR the requesting user lacks authorization for the requested action (e.g. trying to delete or modify another user's job).
.LP
\fBESLURM_DISABLED\fR the ability to create a job step is currently disabled.
This is indicative of the job being suspended. Retry the call as desired.
.LP
-\fBESLURM_INTERCONNECT_FAILURE\fR failed to configure the node interconnect.
+\fBESLURM_INTERCONNECT_FAILURE\fR failed to configure the node interconnect.
.LP
-\fBESLURM_BAD_DIST\fR task distribution specification is invalid.
+\fBESLURM_BAD_DIST\fR task distribution specification is invalid.
.LP
-\fBSLURM_PROTOCOL_SOCKET_IMPL_TIMEOUT\fR Timeout in communicating with
+\fBSLURM_PROTOCOL_SOCKET_IMPL_TIMEOUT\fR Timeout in communicating with
SLURM controller.
.SH "EXAMPLE
.LP
@@ -229,7 +229,7 @@ SEE \fBslurm_step_launch\fR(3) man page for an example of slurm_step_ctx_create
and slurm_step_launch in use together.
.SH "NOTE"
-These functions are included in the libslurm library,
+These functions are included in the libslurm library,
which must be linked to your process for use
(e.g. "cc \-lslurm myprog.c").
@@ -251,8 +251,8 @@ WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
FOR A PARTICULAR PURPOSE. See the GNU General Public License for more
details.
.SH "SEE ALSO"
-.LP
-\fBslurm_allocate_resources\fR(3), \fBslurm_job_step_create\fR(3),
-\fBslurm_kill_job\fR(3),
+.LP
+\fBslurm_allocate_resources\fR(3), \fBslurm_job_step_create\fR(3),
+\fBslurm_kill_job\fR(3),
\fBslurm_get_errno\fR(3), \fBslurm_perror\fR(3), \fBslurm_strerror\fR(3),
-\fBsrun\fR(1)
+\fBsrun\fR(1)
diff --git a/doc/man/man3/slurm_step_launch.3 b/doc/man/man3/slurm_step_launch.3
index fb2c4a7393b..1e7bbff7050 100644
--- a/doc/man/man3/slurm_step_launch.3
+++ b/doc/man/man3/slurm_step_launch.3
@@ -7,13 +7,13 @@ slurm_step_launch_fwd_signal, slurm_step_launch_wait_start,
slurm_step_launch_wait_finish, slurm_step_launch_abort \- Slurm job step launch functions
.SH "SYNTAX"
-.LP
+.LP
#include <slurm/slurm.h>
-.LP
+.LP
.LP
void \fBslurm_step_launch_params_t_init\fR (
.br
- slurm_step_launch_params_t *\fIlaunch_req\fP
+ slurm_step_launch_params_t *\fIlaunch_req\fP
.br
);
.LP
@@ -54,7 +54,7 @@ void \fBslurm_step_launch_abort\fR {
);
.SH "ARGUMENTS"
-.LP
+.LP
.TP
\fIcallbacks\fP
Identify functions to be called when various events occur.
@@ -64,7 +64,7 @@ Job step context. Created by \fBslurm_step_ctx_create\fR, used in subsequent
function calls, and destroyed by \fBslurm_step_ctx_destroy\fR.
.TP
\fIlaunch_req\fP
-Pointer to a structure allocated by the user containing specifications of
+Pointer to a structure allocated by the user containing specifications of
the job step to be launched.
.SH "DESCRIPTION"
@@ -80,24 +80,24 @@ with running tasks.
.LP
\fBslurm_step_launch_wait_start\fR Block until all tasks have started.
.LP
-\fBslurm_step_launch_wait_finish\fR Block until all tasks have finished
+\fBslurm_step_launch_wait_finish\fR Block until all tasks have finished
(or failed to start altogether).
.LP
-\fBslurm_step_launch_abort\fR Abort an in-progress launch, or terminate
+\fBslurm_step_launch_abort\fR Abort an in-progress launch, or terminate
the fully launched job step. Can be called from a signal handler.
.SH "IO Redirection"
.LP
-Use the \fIlocal_fds\fR entry in \fIslurm_step_launch_params_t\fR
-to specify file descriptors to be used for standard input, output
-and error. Any \fIlocal_fds\fR not specified will result in the launched
+Use the \fIlocal_fds\fR entry in \fIslurm_step_launch_params_t\fR
+to specify file descriptors to be used for standard input, output
+and error. Any \fIlocal_fds\fR not specified will result in the launched
tasks using the calling process's standard input, output and error.
Threads created by \fBslurm_step_launch\fR will completely handle
copying data between the remote processes and the specified local file
-descriptors.
+descriptors.
.LP
-Use the substructure in \fIslurm_step_io_fds_t\fR to restrict the
-redirection of I/O to a specific node or task ID. For example, to
+Use the substructure in \fIslurm_step_io_fds_t\fR to restrict the
+redirection of I/O to a specific node or task ID. For example, to
redirect standard output only from task 0, set
.LP
.nf
@@ -105,14 +105,14 @@ params.local_fs.out.taskid=0;
.fi
.LP
Use the \fIremote_*_filename\fR fields in \fIslurm_step_launch_params_t\fR
-to have launched tasks read and/or write directly to local files
+to have launched tasks read and/or write directly to local files
rather than transferring data over the network to the calling process.
These strings support many of the same format options as the \fBsrun\fR
-command. Any \fIremote_*_filename\fR fields set will supersede the
-corresponding \fIlocal_fds\fR entries. For example, the following
+command. Any \fIremote_*_filename\fR fields set will supersede the
+corresponding \fIlocal_fds\fR entries. For example, the following
code will direct each task to write standard output and standard
-error to local files with names containing the task ID (e.g.
-"/home/bob/test_output/run1.out.0" and
+error to local files with names containing the task ID (e.g.
+"/home/bob/test_output/run1.out.0" and
"/home/bob/test_output/run.1.err.0" for task 0).
.LP
.nf
@@ -132,17 +132,17 @@ or SLURM_ERROR if the job step is aborted during launch.
.LP
\fBSLURM_PROTOCOL_VERSION_ERROR\fR Protocol version has changed, re\-link your code.
.LP
-\fBESLURM_INVALID_JOB_ID\fR the requested job id does not exist.
+\fBESLURM_INVALID_JOB_ID\fR the requested job id does not exist.
.LP
-\fBESLURM_ALREADY_DONE\fR the specified job has already completed and can not be modified.
+\fBESLURM_ALREADY_DONE\fR the specified job has already completed and can not be modified.
.LP
-\fBESLURM_ACCESS_DENIED\fR the requesting user lacks authorization for the requested action (e.g. trying to delete or modify another user's job).
+\fBESLURM_ACCESS_DENIED\fR the requesting user lacks authorization for the requested action (e.g. trying to delete or modify another user's job).
.LP
-\fBESLURM_INTERCONNECT_FAILURE\fR failed to configure the node interconnect.
+\fBESLURM_INTERCONNECT_FAILURE\fR failed to configure the node interconnect.
.LP
-\fBESLURM_BAD_DIST\fR task distribution specification is invalid.
+\fBESLURM_BAD_DIST\fR task distribution specification is invalid.
.LP
-\fBSLURM_PROTOCOL_SOCKET_IMPL_TIMEOUT\fR Timeout in communicating with
+\fBSLURM_PROTOCOL_SOCKET_IMPL_TIMEOUT\fR Timeout in communicating with
SLURM controller.
.SH "EXAMPLE
@@ -222,7 +222,7 @@ int main (int argc, char *argv[])
.fi
.SH "NOTE"
-These functions are included in the libslurm library,
+These functions are included in the libslurm library,
which must be linked to your process for use
(e.g. "cc \-lslurm myprog.c").
@@ -245,7 +245,7 @@ WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
FOR A PARTICULAR PURPOSE. See the GNU General Public License for more
details.
.SH "SEE ALSO"
-.LP
-\fBslurm_step_ctx_create\fR(3), \fBslurm_step_ctx_destroy\fR(3),
+.LP
+\fBslurm_step_ctx_create\fR(3), \fBslurm_step_ctx_destroy\fR(3),
\fBslurm_get_errno\fR(3), \fBslurm_perror\fR(3), \fBslurm_strerror\fR(3),
-\fBsalloc\fR(1), \fBsrun\fR(1)
+\fBsalloc\fR(1), \fBsrun\fR(1)
diff --git a/doc/man/man5/bluegene.conf.5 b/doc/man/man5/bluegene.conf.5
index 41973e3ffb7..2bf1634c1e0 100644
--- a/doc/man/man5/bluegene.conf.5
+++ b/doc/man/man5/bluegene.conf.5
@@ -1,47 +1,47 @@
.TH "bluegene.conf" "5" "April 2008" "bluegene.conf 2.0" "Slurm configuration file"
.SH "NAME"
-bluegene.conf \- Slurm configuration file for BlueGene systems
+bluegene.conf \- Slurm configuration file for BlueGene systems
.SH "DESCRIPTION"
-\fB/etc/bluegene.conf\fP is an ASCII file which describes BlueGene specific
-SLURM configuration information. This includes specifications for bgblock
+\fB/etc/bluegene.conf\fP is an ASCII file which describes BlueGene specific
+SLURM configuration information. This includes specifications for bgblock
layout, configuration, logging, etc.
The file location can be modified at system build time using the
-DEFAULT_SLURM_CONF parameter. The file will always be located in the
-same directory as the \fBslurm.conf\fP file.
+DEFAULT_SLURM_CONF parameter. The file will always be located in the
+same directory as the \fBslurm.conf\fP file.
.LP
Paramter names are case insensitive.
-Any text following a "#" in the configuration file is treated
-as a comment through the end of that line.
+Any text following a "#" in the configuration file is treated
+as a comment through the end of that line.
The size of each line in the file is limited to 1024 characters.
-Changes to the configuration file take effect upon restart of
-SLURM daemons, daemon receipt of the SIGHUP signal, or execution
+Changes to the configuration file take effect upon restart of
+SLURM daemons, daemon receipt of the SIGHUP signal, or execution
of the command "scontrol reconfigure" unless otherwise noted.
.LP
-There are some differences between Bluegene/L and Bluegene/P in respects to the contents of the bluegene.conf file.
+There are some differences between Bluegene/L and Bluegene/P in respects to the contents of the bluegene.conf file.
.SH "The Bluegene/L specific options are:"
.TP
\fBAltBlrtsImage\fR
-Alternative BlrtsImage. This is an optional field only used for
+Alternative BlrtsImage. This is an optional field only used for
mulitple images on a system and should be followed by a Groups= with
-the user groups allowed to use this image (i.e. Groups=da,jette) if
+the user groups allowed to use this image (i.e. Groups=da,jette) if
Groups= is not stated then this image will be able to be used by all
groups. You can put as many alternative images as you want in the conf file.
.TP
\fBAltLinuxImage\fR
-Alternative LinuxImage. This is an optional field only used for
+Alternative LinuxImage. This is an optional field only used for
mulitple images on a system and should be followed by a Groups= with
-the user groups allowed to use this image (i.e. Groups=da,jette) if
+the user groups allowed to use this image (i.e. Groups=da,jette) if
Groups= is not stated then this image will be able to be used by all
groups. You can put as many alternative images as you want in the conf file.
.TP
\fBAltRamDiskImage\fR
-Alternative RamDiskImage. This is an optional field only used for
+Alternative RamDiskImage. This is an optional field only used for
mulitple images on a system and should be followed by a Groups= with
-the user groups allowed to use this image (i.e. Groups=da,jette) if
+the user groups allowed to use this image (i.e. Groups=da,jette) if
Groups= is not stated then this image will be able to be used by all
groups. You can put as many alternative images as you want in the conf file.
@@ -63,17 +63,17 @@ There is no default value and this must be specified.
.SH "The Bluegene/P specific options are:"
.TP
\fBAltCnloadImage\fR
-Alternative CnloadImage. This is an optional field only used for
+Alternative CnloadImage. This is an optional field only used for
mulitple images on a system and should be followed by a Groups= with
-the user groups allowed to use this image (i.e. Groups=da,jette) if
+the user groups allowed to use this image (i.e. Groups=da,jette) if
Groups= is not stated then this image will be able to be used by all
groups. You can put as many alternative images as you want in the conf file.
.TP
\fBAltIoloadImage\fR
-Alternative IoloadImage. This is an optional field only used for
+Alternative IoloadImage. This is an optional field only used for
mulitple images on a system and should be followed by a Groups= with
-the user groups allowed to use this image (i.e. Groups=da,jette) if
+the user groups allowed to use this image (i.e. Groups=da,jette) if
Groups= is not stated then this image will be able to be used by all
groups. You can put as many alternative images as you want in the conf file.
@@ -90,9 +90,9 @@ There is no default value and this must be specified.
.SH "All options below are common on all Bluegene systems:"
.TP
\fBAltMloaderImage\fR
-Alternative MloaderImage. This is an optional field only used for
+Alternative MloaderImage. This is an optional field only used for
mulitple images on a system and should be followed by a Groups= with
-the user groups allowed to use this image (i.e. Groups=da,jette) if
+the user groups allowed to use this image (i.e. Groups=da,jette) if
Groups= is not stated then this image will be able to be used by all
groups. You can put as many alternative images as you want in the conf file.
@@ -104,7 +104,7 @@ is usually 512)
.TP
\fBBridgeAPILogFile\fR
-Fully qualified pathname of a into which the Bridge API logs are
+Fully qualified pathname of a into which the Bridge API logs are
to be written.
There is no default value.
@@ -138,13 +138,13 @@ Describes how SLURM should create bgblocks.
\fBSTATIC\fR: Create and use the defined non\-overlapping bgblocks.
.TP
\fBOVERLAP\fR: Create and use the defined bgblocks, which may overlap.
-It is highly recommended that none of the bgblocks have any passthroughs
-in the X\-dimension.
+It is highly recommended that none of the bgblocks have any passthroughs
+in the X\-dimension.
\fBUse this mode with extreme caution.\fR
.TP
\fBDYNAMIC\fR: Create and use bglblocks as needed for each job.
Bgblocks will not be defined in the bluegene.conf file.
-Dynamic partitioning may introduce fragmentation of resources
+Dynamic partitioning may introduce fragmentation of resources
and starvation of larger jobs.
\fBUse this mode with caution.\fR
.RE
@@ -157,7 +157,7 @@ There is no default value and this must be specified.
.TP
\fBNodeCardNodeCount\fR
Number of c\-nodes per node card.
-There is no default value and this must be specified. (For bgl systems this
+There is no default value and this must be specified. (For bgl systems this
is usually 32)
.TP
@@ -166,10 +166,10 @@ The Numpsets used for creation of all bgblocks. This value really means the
number of IOnodes on a base partition. This number must be the smallest
number if you have a heterogeneous system.
There is no default value and this must be specified. The typical settings
-for bgl systems goes as follows... For IO rich systems 64 is the value that
-should be used to create small blocks. For systems that are not IO rich, or
+for bgl systems goes as follows... For IO rich systems 64 is the value that
+should be used to create small blocks. For systems that are not IO rich, or
you do not wish to create small blocks, 8 is usually the number to use.
-For bgp IO rich systems 32 is the value that should be used to create small
+For bgp IO rich systems 32 is the value that should be used to create small
blocks since you can only have 2 ionodes per nodecard instead of 4 like on bgl.
.LP
@@ -177,8 +177,8 @@ Each bgblock is defined by the base partitions used to construct it.
Ordering is very important for laying out switch wires. Please create
blocks with smap, and once done don't change the order of blocks created.
A bgblock is implicitly created containing all resources on the system.
-Bgblocks must not overlap in static mode (except for implicitly
-created bgblock). This will be the case when smap is used to create
+Bgblocks must not overlap in static mode (except for implicitly
+created bgblock). This will be the case when smap is used to create
a configuration file
All Nodes defined here must also be defined in the slurm.conf file.
Define only the numeric coordinates of the bgblocks here. The prefix
@@ -197,25 +197,25 @@ The default value is TORUS.
\fBMESH\fR: Communication occur over a mesh.
.TP
\fBSMALL\fR: The base partition is divided into more than one bgblock.
-The administrator should define the number of single node cards and
-quarter base partition blocks using the options \fB32CNBlocks\fR and
-\fB128CNBlocks\fR respectively for a Bluegene L system. \fB16CNBlocks\fR,
-\fB64CNBlocks\fR, and \fB256CNBlocks\fR are also available for
-Bluegene P systems. Keep in mind you
+The administrator should define the number of single node cards and
+quarter base partition blocks using the options \fB32CNBlocks\fR and
+\fB128CNBlocks\fR respectively for a Bluegene L system. \fB16CNBlocks\fR,
+\fB64CNBlocks\fR, and \fB256CNBlocks\fR are also available for
+Bluegene P systems. Keep in mind you
must have enough ionodes to make all these configurations possible.
The total number of c\-nodes in defined blocks must not exceed
\fBBasePartitionNodeCnt\fR.
-If not specified, the base partition will be divided into four
+If not specified, the base partition will be divided into four
blocks.
See example below.
.TP
-\fBTORUS\fR: Communications occur over a torus (end\-points of network
+\fBTORUS\fR: Communications occur over a torus (end\-points of network
directly connect.
.RE
.SH "EXAMPLE"
-.LP
+.LP
.br
##################################################################
.br
diff --git a/doc/man/man5/slurm.conf.5 b/doc/man/man5/slurm.conf.5
index c9789c57090..ea77b11d39d 100644
--- a/doc/man/man5/slurm.conf.5
+++ b/doc/man/man5/slurm.conf.5
@@ -1,7 +1,7 @@
.TH "slurm.conf" "5" "August 2009" "slurm.conf 2.1" "Slurm configuration file"
.SH "NAME"
-slurm.conf \- Slurm configuration file
+slurm.conf \- Slurm configuration file
.SH "DESCRIPTION"
\fB/etc/slurm.conf\fP is an ASCII file which describes general SLURM
configuration information, the nodes to be managed, information about
@@ -16,18 +16,18 @@ location of this file. The SLURM daemons also allow you to override
both the built\-in and environment\-provided location using the "\-f"
option on the command line.
.LP
-Note the while SLURM daemons create log files and other files as needed,
-it treats the lack of parent directories as a fatal error.
+Note the while SLURM daemons create log files and other files as needed,
+it treats the lack of parent directories as a fatal error.
This prevents the daemons from running if critical file systems are
-not mounted and will minimize the risk of cold\-starting (starting
+not mounted and will minimize the risk of cold\-starting (starting
without preserving jobs).
.LP
-The contents of the file are case insensitive except for the names of nodes
-and partitions. Any text following a "#" in the configuration file is treated
-as a comment through the end of that line.
+The contents of the file are case insensitive except for the names of nodes
+and partitions. Any text following a "#" in the configuration file is treated
+as a comment through the end of that line.
The size of each line in the file is limited to 1024 characters.
-Changes to the configuration file take effect upon restart of
-SLURM daemons, daemon receipt of the SIGHUP signal, or execution
+Changes to the configuration file take effect upon restart of
+SLURM daemons, daemon receipt of the SIGHUP signal, or execution
of the command "scontrol reconfigure" unless otherwise noted.
.LP
If a line begins with the word "Include" followed by whitespace
@@ -39,7 +39,7 @@ The overall configuration parameters available include:
.TP
\fBAccountingStorageBackupHost\fR
The name of the backup machine hosting the accounting storage database.
-If used with the accounting_storage/slurmdbd plugin, this is where the backup
+If used with the accounting_storage/slurmdbd plugin, this is where the backup
slurmdbd would be running.
Only used for database type storage plugins, ignored otherwise.
@@ -47,14 +47,14 @@ Only used for database type storage plugins, ignored otherwise.
\fBAccountingStorageEnforce\fR
This controls what level of enforcement you want on associations when new
jobs are submitted. Valid options are any combination of associations, limits,
-and wckeys, or all for all things. If limits is set associations is implied.
-If wckeys is set both limits and associations are implied along with
-TrackWckey being set. By enforcing Associations no new job is allowed to run
-unless a corresponding association exists in the system. If limits are
-enforced users can be limited by association to how many nodes or how long
-jobs can run or other limits. With wckeys enforced jobs will not be scheduled
-unless a valid workload characterization key is specified. This value may not
-be reset via "scontrol reconfig". It only takes effect upon restart
+and wckeys, or all for all things. If limits is set associations is implied.
+If wckeys is set both limits and associations are implied along with
+TrackWckey being set. By enforcing Associations no new job is allowed to run
+unless a corresponding association exists in the system. If limits are
+enforced users can be limited by association to how many nodes or how long
+jobs can run or other limits. With wckeys enforced jobs will not be scheduled
+unless a valid workload characterization key is specified. This value may not
+be reset via "scontrol reconfig". It only takes effect upon restart
of the slurmctld daemon.
.TP
@@ -122,44 +122,44 @@ Also see \fBDefaultStorageUser\fR.
.TP
\fBAuthType\fR
-The authentication method for communications between SLURM
-components.
-Acceptable values at present include "auth/none", "auth/authd",
+The authentication method for communications between SLURM
+components.
+Acceptable values at present include "auth/none", "auth/authd",
and "auth/munge".
The default value is "auth/munge".
-"auth/none" includes the UID in each communication, but it is not verified.
-This may be fine for testing purposes, but
+"auth/none" includes the UID in each communication, but it is not verified.
+This may be fine for testing purposes, but
\fBdo not use "auth/none" if you desire any security\fR.
"auth/authd" indicates that Brett Chun's authd is to be used (see
"http://www.theether.org/authd/" for more information. Note that
authd is no longer actively supported).
"auth/munge" indicates that LLNL's MUNGE is to be used
-(this is the best supported authentication mechanism for SLURM,
+(this is the best supported authentication mechanism for SLURM,
see "http://home.gna.org/munge/" for more information).
-All SLURM daemons and commands must be terminated prior to changing
-the value of \fBAuthType\fR and later restarted (SLURM jobs can be
+All SLURM daemons and commands must be terminated prior to changing
+the value of \fBAuthType\fR and later restarted (SLURM jobs can be
preserved).
.TP
\fBBackupAddr\fR
The name that \fBBackupController\fR should be referred to in
-establishing a communications path. This name will
-be used as an argument to the gethostbyname() function for
-identification. For example, "elx0000" might be used to designate
-the Ethernet address for node "lx0000".
-By default the \fBBackupAddr\fR will be identical in value to
+establishing a communications path. This name will
+be used as an argument to the gethostbyname() function for
+identification. For example, "elx0000" might be used to designate
+the Ethernet address for node "lx0000".
+By default the \fBBackupAddr\fR will be identical in value to
\fBBackupController\fR.
.TP
\fBBackupController\fR
-The name of the machine where SLURM control functions are to be
+The name of the machine where SLURM control functions are to be
executed in the event that \fBControlMachine\fR fails. This node
-may also be used as a compute server if so desired. It will come into service
-as a controller only upon the failure of ControlMachine and will revert
-to a "standby" mode when the ControlMachine becomes available once again.
+may also be used as a compute server if so desired. It will come into service
+as a controller only upon the failure of ControlMachine and will revert
+to a "standby" mode when the ControlMachine becomes available once again.
This should be a node name without the full domain name. I.e., the hostname
-returned by the \fIgethostname()\fR function cut at the first dot (e.g. use
-"tux001" rather than "tux001.my.com").
+returned by the \fIgethostname()\fR function cut at the first dot (e.g. use
+"tux001" rather than "tux001.my.com").
While not essential, it is recommended that you specify a backup controller.
See the \fBRELOCATING CONTROLLERS\fR section if you change this.
@@ -181,9 +181,9 @@ The default value is 0 to disable caching group data.
.TP
\fBCheckpointType\fR
-The system\-initiated checkpoint method to be used for user jobs.
-The slurmctld daemon must be restarted for a change in \fBCheckpointType\fR
-to take effect.
+The system\-initiated checkpoint method to be used for user jobs.
+The slurmctld daemon must be restarted for a change in \fBCheckpointType\fR
+to take effect.
Supported values presently include:
.RS
.TP 18
@@ -212,35 +212,35 @@ when multiple clusters report to the same database.
.TP
\fBCompleteWait\fR
The time, in seconds, given for a job to remain in COMPLETING state
-before any additional jobs are scheduled.
+before any additional jobs are scheduled.
If set to zero, pending jobs will be started as soon as possible.
-Since a COMPLETING job's resources are released for use by other
-jobs as soon as the \fBEpilog\fR completes on each individual node,
-this can result in very fragmented resource allocations.
-To provide jobs with the minimum response time, a value of zero is
+Since a COMPLETING job's resources are released for use by other
+jobs as soon as the \fBEpilog\fR completes on each individual node,
+this can result in very fragmented resource allocations.
+To provide jobs with the minimum response time, a value of zero is
recommended (no waiting).
-To minimize fragmentation of resources, a value equal to \fBKillWait\fR
-plus two is recommended.
+To minimize fragmentation of resources, a value equal to \fBKillWait\fR
+plus two is recommended.
In that case, setting \fBKillWait\fR to a small value may be beneficial.
The default value of \fBCompleteWait\fR is zero seconds.
The value may not exceed 65533.
.TP
\fBControlAddr\fR
-Name that \fBControlMachine\fR should be referred to in
-establishing a communications path. This name will
-be used as an argument to the gethostbyname() function for
-identification. For example, "elx0000" might be used to designate
-the Ethernet address for node "lx0000".
-By default the \fBControlAddr\fR will be identical in value to
+Name that \fBControlMachine\fR should be referred to in
+establishing a communications path. This name will
+be used as an argument to the gethostbyname() function for
+identification. For example, "elx0000" might be used to designate
+the Ethernet address for node "lx0000".
+By default the \fBControlAddr\fR will be identical in value to
\fBControlMachine\fR.
.TP
\fBControlMachine\fR
The short hostname of the machine where SLURM control functions are
-executed (i.e. the name returned by the command "hostname -s", use
-"tux001" rather than "tux001.my.com").
-This value must be specified.
+executed (i.e. the name returned by the command "hostname -s", use
+"tux001" rather than "tux001.my.com").
+This value must be specified.
In order to support some high availability architectures, multiple
hostnames may be listed with comma separators and one \fBControlAddr\fR
must be specified. The high availability system must insure that the
@@ -249,7 +249,7 @@ See the \fBRELOCATING CONTROLLERS\fR section if you change this.
.TP
\fBCryptoType\fR
-The cryptographic signature tool to be used in the creation of
+The cryptographic signature tool to be used in the creation of
job step credentials.
The slurmctld daemon must be restarted for a change in \fBCryptoType\fR
to take effect.
@@ -259,7 +259,7 @@ The default value is "crypto/munge".
.TP
\fBDebugFlags\fR
Defines specific subsystems which should provide more detailed event logging.
-Multiple subsystems can be specified with comma separators.
+Multiple subsystems can be specified with comma separators.
Valid subsystems available today (with more to come) include:
.RS
.TP 15
@@ -278,14 +278,14 @@ Sched/wiki and wiki2 communications
.TP
\fBDefMemPerCPU\fR
-Default real memory size available per allocated CPU in MegaBytes.
+Default real memory size available per allocated CPU in MegaBytes.
Used to avoid over\-subscribing memory and causing paging.
\fBDefMemPerCPU\fR would generally be used if individual processors
-are allocated to jobs (\fBSelectType=select/cons_res\fR).
+are allocated to jobs (\fBSelectType=select/cons_res\fR).
The default value is 0 (unlimited).
Also see \fBDefMemPerNode\fR and \fBMaxMemPerCPU\fR.
\fBDefMemPerCPU\fR and \fBDefMemPerNode\fR are mutually exclusive.
-NOTE: Enforcement of memory limits currently requires enabling of
+NOTE: Enforcement of memory limits currently requires enabling of
accounting, which samples memory use on a periodic basis (data need
not be stored, just collected).
@@ -294,12 +294,12 @@ not be stored, just collected).
Default real memory size available per allocated node in MegaBytes.
Used to avoid over\-subscribing memory and causing paging.
\fBDefMemPerNode\fR would generally be used if whole nodes
-are allocated to jobs (\fBSelectType=select/linear\fR) and
+are allocated to jobs (\fBSelectType=select/linear\fR) and
resources are shared (\fBShared=yes\fR or \fBShared=force\fR).
The default value is 0 (unlimited).
Also see \fBDefMemPerCPU\fR and \fBMaxMemPerNode\fR.
\fBDefMemPerCPU\fR and \fBDefMemPerNode\fR are mutually exclusive.
-NOTE: Enforcement of memory limits currently requires enabling of
+NOTE: Enforcement of memory limits currently requires enabling of
accounting, which samples memory use on a periodic basis (data need
not be stored, just collected).
@@ -364,15 +364,15 @@ The default value is "NO", meaning user root will be able to execute jobs.
.TP
\fBEnforcePartLimits\fR
If set to "YES" then jobs which exceed a partition's size and/or time limits
-will be rejected at submission time. If set to "NO" then the job will be
+will be rejected at submission time. If set to "NO" then the job will be
accepted and remain queued until the partition limits are altered.
The default value is "NO".
.TP
\fBEpilog\fR
-Fully qualified pathname of a script to execute as user root on every
-node when a user's job completes (e.g. "/usr/local/slurm/epilog"). This may
-be used to purge files, disable user login, etc.
+Fully qualified pathname of a script to execute as user root on every
+node when a user's job completes (e.g. "/usr/local/slurm/epilog"). This may
+be used to purge files, disable user login, etc.
By default there is no epilog.
See \fBProlog and Epilog Scripts\fR for more information.
@@ -380,8 +380,8 @@ See \fBProlog and Epilog Scripts\fR for more information.
\fBEpilogMsgTime\fR
The number of microseconds the the slurmctld daemon requires to process
an epilog completion message from the slurmd dameons. This parameter can
-be used to prevent a burst of epilog completion messages from being sent
-at the same time which should help prevent lost messages and improve
+be used to prevent a burst of epilog completion messages from being sent
+at the same time which should help prevent lost messages and improve
throughput for large jobs.
The default value is 2000 microseconds.
For a 1000 node job, this spreads the epilog completion messages out over
@@ -389,13 +389,13 @@ two seconds.
.TP
\fBEpilogSlurmctld\fR
-Fully qualified pathname of a program for the slurmctld to execute
+Fully qualified pathname of a program for the slurmctld to execute
upon termination of a job allocation (e.g.
-"/usr/local/slurm/epilog_controller").
-The program executes as SlurmUser, which gives it permission to drain
+"/usr/local/slurm/epilog_controller").
+The program executes as SlurmUser, which gives it permission to drain
nodes and requeue the job if a failure occurs or cancel the job if appropriate.
-The program can be used to reboot nodes or perform other work to prepare
-resources for use.
+The program can be used to reboot nodes or perform other work to prepare
+resources for use.
See \fBProlog and Epilog Scripts\fR for more information.
.TP
@@ -417,9 +417,9 @@ slurm.conf configuration file and any node with less than the
configured resources will be set DOWN.
.TP
\fB0\fR
-Base scheduling decisions upon the actual configuration of each individual
+Base scheduling decisions upon the actual configuration of each individual
node except that the node's processor count in SLURM's configuration must
-match the actual hardware configuration if \fBSchedulerType=sched/gang\fR
+match the actual hardware configuration if \fBSchedulerType=sched/gang\fR
or \fBSelectType=select/cons_res\fR are configured (both of those plugins
maintain resource allocation information using bitmaps for the cores in the
system and must remain static, while the node's memory and disk space can
@@ -428,24 +428,24 @@ be established later).
\fB2\fR
Consider the configuration of each node to be that specified in the
slurm.conf configuration file and any node with less than the
-configured resources will \fBnot\fR be set DOWN.
+configured resources will \fBnot\fR be set DOWN.
This can be useful for testing purposes.
.RE
.TP
\fBFirstJobId\fR
-The job id to be used for the first submitted to SLURM without a
-specific requested value. Job id values generated will incremented by 1
-for each subsequent job. This may be used to provide a meta\-scheduler
-with a job id space which is disjoint from the interactive jobs.
+The job id to be used for the first submitted to SLURM without a
+specific requested value. Job id values generated will incremented by 1
+for each subsequent job. This may be used to provide a meta\-scheduler
+with a job id space which is disjoint from the interactive jobs.
The default value is 1.
.TP
\fBGetEnvTimeout\fR
Used for Moab scheduled jobs only. Controls how long job should wait
-in seconds for loading the user's environment before attempting to
-load it from a cache file. Applies when the srun or sbatch
-\fI--get-user-env\fR option is used. If set to 0 then always load
+in seconds for loading the user's environment before attempting to
+load it from a cache file. Applies when the srun or sbatch
+\fI--get-user-env\fR option is used. If set to 0 then always load
the user's environment from the cache file.
The default value is 2 seconds.
@@ -456,37 +456,37 @@ The default value is zero, which disables execution.
.TP
\fBHealthCheckProgram\fR
-Fully qualified pathname of a script to execute as user root periodically
-on all compute nodes that are not in the DOWN state. This may be used to
+Fully qualified pathname of a script to execute as user root periodically
+on all compute nodes that are not in the DOWN state. This may be used to
verify the node is fully operational and DRAIN the node or send email
-if a problem is detected.
+if a problem is detected.
Any action to be taken must be explicitly performed by the program
(e.g. execute "scontrol update NodeName=foo State=drain Reason=tmp_file_system_full"
to drain a node).
The interval is controlled using the \fBHealthCheckInterval\fR parameter.
-Note that the \fBHealthCheckProgram\fR will be executed at the same time
+Note that the \fBHealthCheckProgram\fR will be executed at the same time
on all nodes to minimize its impact upon parallel programs.
This program is will be killed if it does not terminate normally within
-60 seconds.
+60 seconds.
By default, no program will be executed.
.TP
\fBInactiveLimit\fR
The interval, in seconds, a job or job step is permitted to be inactive
-before it is terminated. A job or job step is considered inactive if
-the associated srun command is not responding to slurm daemons. This
-could be due to the termination of the srun command or the program
-being is a stopped state. A batch job is considered inactive if it
+before it is terminated. A job or job step is considered inactive if
+the associated srun command is not responding to slurm daemons. This
+could be due to the termination of the srun command or the program
+being is a stopped state. A batch job is considered inactive if it
has no active job steps (e.g. periods of pre\- and post\-processing).
-This limit permits defunct jobs to be purged in a timely fashion
+This limit permits defunct jobs to be purged in a timely fashion
without waiting for their time limit to be reached.
This value should reflect the possibility that the srun command may
-stopped by a debugger or considerable time could be required for batch
-job pre\- and post\-processing.
-This limit is ignored for jobs running in partitions with the
-\fBRootOnly\fR flag set (the scheduler running as root will be
+stopped by a debugger or considerable time could be required for batch
+job pre\- and post\-processing.
+This limit is ignored for jobs running in partitions with the
+\fBRootOnly\fR flag set (the scheduler running as root will be
responsible for the job).
-The default value is unlimited (zero).
+The default value is unlimited (zero).
May not exceed 65533.
.TP
@@ -496,17 +496,17 @@ Acceptable values at present include "jobacct_gather/aix" (for AIX operating
system), "jobacct_gather/linux" (for Linux operating system) and "jobacct_gather/none"
(no accounting data collected).
The default value is "jobacct_gather/none".
-In order to use the \fBsacct\fR tool, "jobacct_gather/aix" or "jobacct_gather/linux"
+In order to use the \fBsacct\fR tool, "jobacct_gather/aix" or "jobacct_gather/linux"
must be configured.
.TP
\fBJobAcctGatherFrequency\fR
The job accounting sampling interval.
For jobacct_gather/none this parameter is ignored.
-For jobacct_gather/aix and jobacct_gather/linux the parameter is a number is
+For jobacct_gather/aix and jobacct_gather/linux the parameter is a number is
seconds between sampling job state.
-The default value is 30 seconds.
-A value of zero disables real the periodic job sampling and provides accounting
+The default value is 30 seconds.
+A value of zero disables real the periodic job sampling and provides accounting
information only on job termination (reducing SLURM interference with the job).
.TP
@@ -544,20 +544,20 @@ Also see \fBDefaultStoragePort\fR.
.TP
\fBJobCompType\fR
The job completion logging mechanism type.
-Acceptable values at present include "jobcomp/none", "jobcomp/filetxt",
+Acceptable values at present include "jobcomp/none", "jobcomp/filetxt",
"jobcomp/mysql", "jobcomp/pgsql", and "jobcomp/script"".
-The default value is "jobcomp/none", which means that upon job completion
-the record of the job is purged from the system. If using the accounting
-infrastructure this plugin may not be of interest since the information
+The default value is "jobcomp/none", which means that upon job completion
+the record of the job is purged from the system. If using the accounting
+infrastructure this plugin may not be of interest since the information
here is redundant.
-The value "jobcomp/filetxt" indicates that a record of the job should be
+The value "jobcomp/filetxt" indicates that a record of the job should be
written to a text file specified by the \fBJobCompLoc\fR parameter.
-The value "jobcomp/mysql" indicates that a record of the job should be
+The value "jobcomp/mysql" indicates that a record of the job should be
written to a mysql database specified by the \fBJobCompLoc\fR parameter.
-The value "jobcomp/pgsql" indicates that a record of the job should be
+The value "jobcomp/pgsql" indicates that a record of the job should be
written to a PostgreSQL database specified by the \fBJobCompLoc\fR parameter.
-The value "jobcomp/script" indicates that a script specified by the
-\fBJobCompLoc\fR parameter is to be executed with environment variables
+The value "jobcomp/script" indicates that a script specified by the
+\fBJobCompLoc\fR parameter is to be executed with environment variables
indicating the job information.
.TP
@@ -568,60 +568,60 @@ Also see \fBDefaultStorageUser\fR.
.TP
\fBJobCredentialPrivateKey\fR
-Fully qualified pathname of a file containing a private key used for
+Fully qualified pathname of a file containing a private key used for
authentication by SLURM daemons.
This parameter is ignored if \fBCryptoType=crypto/munge\fR.
.TP
\fBJobCredentialPublicCertificate\fR
-Fully qualified pathname of a file containing a public key used for
+Fully qualified pathname of a file containing a public key used for
authentication by SLURM daemons.
This parameter is ignored if \fBCryptoType=crypto/munge\fR.
.TP
\fBJobFileAppend\fR
-This option controls what to do if a job's output or error file
-exist when the job is started.
-If \fBJobFileAppend\fR is set to a value of 1, then append to
+This option controls what to do if a job's output or error file
+exist when the job is started.
+If \fBJobFileAppend\fR is set to a value of 1, then append to
the existing file.
By default, any existing file is truncated.
.TP
\fBJobRequeue\fR
-This option controls what to do by default after a node failure.
-If \fBJobRequeue\fR is set to a value of 1, then any job running
+This option controls what to do by default after a node failure.
+If \fBJobRequeue\fR is set to a value of 1, then any job running
on the failed node will be requeued for execution on different nodes.
-If \fBJobRequeue\fR is set to a value of 0, then any job running
+If \fBJobRequeue\fR is set to a value of 0, then any job running
on the failed node will be terminated.
-Use the \fBsbatch\fR \fI\-\-no\-requeue\fR or \fI\-\-requeue\fR
+Use the \fBsbatch\fR \fI\-\-no\-requeue\fR or \fI\-\-requeue\fR
option to change the default behavior for individual jobs.
The default value is 1.
.TP
\fBKillOnBadExit\fR
-If set to 1, the job will be terminated immediately when one of the
-processes is crashed or aborted. With default value of 0, if one of
-the processes is crashed or aborted the other processes will continue
+If set to 1, the job will be terminated immediately when one of the
+processes is crashed or aborted. With default value of 0, if one of
+the processes is crashed or aborted the other processes will continue
to run.
.TP
\fBKillWait\fR
-The interval, in seconds, given to a job's processes between the
-SIGTERM and SIGKILL signals upon reaching its time limit.
-If the job fails to terminate gracefully in the interval specified,
-it will be forcibly terminated.
+The interval, in seconds, given to a job's processes between the
+SIGTERM and SIGKILL signals upon reaching its time limit.
+If the job fails to terminate gracefully in the interval specified,
+it will be forcibly terminated.
The default value is 30 seconds.
The value may not exceed 65533.
.TP
\fBLicenses\fR
-Specification of licenses (or other resources available on all
+Specification of licenses (or other resources available on all
nodes of the cluster) which can be allocated to jobs.
-License names can optionally be followed by an asterisk
+License names can optionally be followed by an asterisk
and count with a default count of one.
Multiple license names should be comma separated (e.g.
"Licenses=foo*4,bar").
-Note that SLURM prevents jobs from being scheduled if their
+Note that SLURM prevents jobs from being scheduled if their
required license specification is not available.
SLURM does not prevent jobs from using licenses that are
not explicitly listed in the job submission specification.
@@ -633,25 +633,25 @@ The default value is "/bin/mail".
.TP
\fBMaxJobCount\fR
-The maximum number of jobs SLURM can have in its active database
-at one time. Set the values of \fBMaxJobCount\fR and \fBMinJobAge\fR
-to insure the slurmctld daemon does not exhaust its memory or other
-resources. Once this limit is reached, requests to submit additional
-jobs will fail. The default value is 5000 jobs. This value may not
-be reset via "scontrol reconfig". It only takes effect upon restart
+The maximum number of jobs SLURM can have in its active database
+at one time. Set the values of \fBMaxJobCount\fR and \fBMinJobAge\fR
+to insure the slurmctld daemon does not exhaust its memory or other
+resources. Once this limit is reached, requests to submit additional
+jobs will fail. The default value is 5000 jobs. This value may not
+be reset via "scontrol reconfig". It only takes effect upon restart
of the slurmctld daemon.
May not exceed 65533.
.TP
\fBMaxMemPerCPU\fR
-Maximum real memory size available per allocated CPU in MegaBytes.
+Maximum real memory size available per allocated CPU in MegaBytes.
Used to avoid over\-subscribing memory and causing paging.
\fBMaxMemPerCPU\fR would generally be used if individual processors
are allocated to jobs (\fBSelectType=select/cons_res\fR).
The default value is 0 (unlimited).
Also see \fBDefMemPerCPU\fR and \fBMaxMemPerNode\fR.
\fBMaxMemPerCPU\fR and \fBMaxMemPerNode\fR are mutually exclusive.
-NOTE: Enforcement of memory limits currently requires enabling of
+NOTE: Enforcement of memory limits currently requires enabling of
accounting, which samples memory use on a periodic basis (data need
not be stored, just collected).
@@ -665,7 +665,7 @@ resources are shared (\fBShared=yes\fR or \fBShared=force\fR).
The default value is 0 (unlimited).
Also see \fBDefMemPerNode\fR and \fBMaxMemPerCPU\fR.
\fBMaxMemPerCPU\fR and \fBMaxMemPerNode\fR are mutually exclusive.
-NOTE: Enforcement of memory limits currently requires enabling of
+NOTE: Enforcement of memory limits currently requires enabling of
accounting, which samples memory use on a periodic basis (data need
not be stored, just collected).
@@ -677,39 +677,39 @@ on a single node. The default \fBMaxTasksPerNode\fR is 128.
.TP
\fBMessageTimeout\fR
Time permitted for a round\-trip communication to complete
-in seconds. Default value is 10 seconds. For systems with
-shared nodes, the slurmd daemon could be paged out and
+in seconds. Default value is 10 seconds. For systems with
+shared nodes, the slurmd daemon could be paged out and
necessitate higher values.
.TP
\fBMinJobAge\fR
-The minimum age of a completed job before its record is purged from
-SLURM's active database. Set the values of \fBMaxJobCount\fR and
-\fBMinJobAge\fR to insure the slurmctld daemon does not exhaust
-its memory or other resources. The default value is 300 seconds.
+The minimum age of a completed job before its record is purged from
+SLURM's active database. Set the values of \fBMaxJobCount\fR and
+\fBMinJobAge\fR to insure the slurmctld daemon does not exhaust
+its memory or other resources. The default value is 300 seconds.
A value of zero prevents any job record purging.
May not exceed 65533.
.TP
\fBMpiDefault\fR
-Identifies the default type of MPI to be used.
+Identifies the default type of MPI to be used.
Srun may override this configuration parameter in any case.
-Currently supported versions include:
-\fBmpichgm\fR,
+Currently supported versions include:
+\fBmpichgm\fR,
\fBmvapich\fR,
-\fBnone\fR (default, which works for many other versions of MPI including
+\fBnone\fR (default, which works for many other versions of MPI including
LAM MPI and Open MPI).
.TP
\fBMpiParams\fR
-MPI parameters.
+MPI parameters.
Used to identify ports used by OpenMPI only and the input format is
"ports=12000\-12999" to identify a range of communication ports to be used.
.TP
\fBOverTimeLimit\fR
-Number of minutes by which a job can exceed its time limit before
-being canceled.
+Number of minutes by which a job can exceed its time limit before
+being canceled.
The configured job time limit is treated as a \fIsoft\fR limit.
Adding \fBOverTimeLimit\fR to the \fIsoft\fR limit provides a \fIhard\fR
limit, at which point the job is canceled.
@@ -721,9 +721,9 @@ A value of "UNLIMITED" is also supported.
.TP
\fBPluginDir\fR
-Identifies the places in which to look for SLURM plugins.
-This is a colon\-separated list of directories, like the PATH
-environment variable.
+Identifies the places in which to look for SLURM plugins.
+This is a colon\-separated list of directories, like the PATH
+environment variable.
The default value is "/usr/local/lib/slurm".
.TP
@@ -744,14 +744,14 @@ which jobs are capable of preempting other jobs while \fBPreemptMode\fR
controls the mechanism used to preempt the lower priority jobs.
Jobs which are being gang scheduled (time sliced) rather than being preempted
will always make use of a suspend/resume mechanism.
-The \fBGANG\fR option can be specified in addition to a preemption
+The \fBGANG\fR option can be specified in addition to a preemption
method specification with the two options comma separated.
.RS
.TP 12
\fBOFF\fR
is the default value and disables job preemption and gang scheduling.
-This is the only option compatible with \fBSchedulerType=sched/wiki\fR
-or \fBSchedulerType=sched/wiki2\fR (used by Maui and Moab respectively,
+This is the only option compatible with \fBSchedulerType=sched/wiki\fR
+or \fBSchedulerType=sched/wiki2\fR (used by Maui and Moab respectively,
which provide their own job preemption functionality).
.TP
\fBCANCEL\fR
@@ -768,16 +768,16 @@ preempts jobs by requeuing them (if possible) or canceling them.
.TP
\fBSUSPEND\fR
preempts jobs by suspending them.
-A suspended job will resume execution once the high priority job
+A suspended job will resume execution once the high priority job
preempting it completes.
The \fBSUSPEND\fR may only be used with the \fBGANG\fR option
-(the gang scheduler module performs the job resume operation).
+(the gang scheduler module performs the job resume operation).
.RE
.TP
\fBPreemptType\fR
-This specifies the plugin used to identify which jobs can be
-preempted in order to start a pending job.
+This specifies the plugin used to identify which jobs can be
+preempted in order to start a pending job.
.RS
.TP
\fBpreempt/none\fR
@@ -786,7 +786,7 @@ This is the default.
.TP
\fBpreempt/partition_prio\fR
Job preemption is based upon partition priority.
-Jobs in higher priority partitions (queues) may preempt jobs from lower
+Jobs in higher priority partitions (queues) may preempt jobs from lower
priority partitions.
.TP
\fBpreempt/qos\fR
@@ -799,12 +799,12 @@ This is not compatible with \fBPreemptMode=OFF\fR or \fBPreemptMode=SUSPEND\fR
.TP
\fBPriorityDecayHalfLife\fR
This controls how long prior resource use is considered in determining
-how over\- or under\-serviced an association is (user, bank account and
-cluster) in determining job priority. If set to 0 no decay will be applied.
-This is helpful if you want to enforce hard time limits per association. If
+how over\- or under\-serviced an association is (user, bank account and
+cluster) in determining job priority. If set to 0 no decay will be applied.
+This is helpful if you want to enforce hard time limits per association. If
set to 0 \fBPriorityUsageResetPeriod\fR must be set to some interval.
Applicable only if \fBPriorityType=priority/multifactor\fR.
-The unit is a time string (i.e. min, hr:min:00, days\-hr:min:00,
+The unit is a time string (i.e. min, hr:min:00, days\-hr:min:00,
or days\-hr). The default value is 7\-0 (7 days).
.TP
@@ -820,17 +820,17 @@ Specifies the job age which will be given the maximum age factor in computing
priority. For example, a value of 30 minutes would result in all jobs over
30 minutes old would get the same age\-based priority.
Applicable only if PriorityType=priority/multifactor.
-The unit is a time string (i.e. min, hr:min:00, days\-hr:min:00,
+The unit is a time string (i.e. min, hr:min:00, days\-hr:min:00,
or days\-hr). The default value is 7\-0 (7 days).
.TP
\fBPriorityUsageResetPeriod\fR
-At this interval the usage of associations will be reset to 0. This is used
-if you want to enforce hard limits of time usage per association. If
-PriorityDecayHalfLife is set to be 0 no decay will happen and this is the
-only way to reset the usage accumulated by running jobs. By default this is
+At this interval the usage of associations will be reset to 0. This is used
+if you want to enforce hard limits of time usage per association. If
+PriorityDecayHalfLife is set to be 0 no decay will happen and this is the
+only way to reset the usage accumulated by running jobs. By default this is
turned off and it is advised to use the PriorityDecayHalfLife option to avoid
-not having anything running on your cluster, but if your schema is set up to
+not having anything running on your cluster, but if your schema is set up to
only allow certain amounts of time on your system this is the way to do it.
Applicable only if PriorityType=priority/multifactor.
.RS
@@ -839,7 +839,7 @@ Applicable only if PriorityType=priority/multifactor.
Never clear historic usage. The default value.
.TP
\fBNOW\fR
-Clear the historic usage now.
+Clear the historic usage now.
Executed at startup and reconfiguration time.
.TP
\fBDAILY\fR
@@ -863,8 +863,8 @@ Cleared on the first day of each year at time 00:00.
This specifies the plugin to be used in establishing a job's scheduling
priority. Supported values are "priority/basic" (jobs are prioritized
by order of arrival, also suitable for sched/wiki and sched/wiki2) and
-"priority/multifactor" (jobs are prioritized based upon size, age,
-fair\-share of allocation, etc).
+"priority/multifactor" (jobs are prioritized based upon size, age,
+fair\-share of allocation, etc).
The default value is "priority/basic".
.TP
@@ -911,91 +911,91 @@ Multiple values may be specified with a comma separator.
Acceptable values include:
.RS
.TP
-\fBaccounts\fR
-(NON-SLURMDBD ACCOUNTING ONLY) prevents users from viewing any account
+\fBaccounts\fR
+(NON-SLURMDBD ACCOUNTING ONLY) prevents users from viewing any account
definitions unless they are coordinators of them.
.TP
\fBjobs\fR
prevents users from viewing jobs or job steps belonging
-to other users. (NON-SLURMDBD ACCOUNTING ONLY) prevents users from viewing
-job records belonging to other users unless they are coordinators of
+to other users. (NON-SLURMDBD ACCOUNTING ONLY) prevents users from viewing
+job records belonging to other users unless they are coordinators of
the association running the job when using sacct.
.TP
\fBnodes\fR
prevents users from viewing node state information.
.TP
-\fBpartitions\fR
+\fBpartitions\fR
prevents users from viewing partition state information.
.TP
-\fBreservations\fR
+\fBreservations\fR
prevents regular users from viewing reservations.
.TP
-\fBusage\fR
-(NON-SLURMDBD ACCOUNTING ONLY) prevents users from viewing
+\fBusage\fR
+(NON-SLURMDBD ACCOUNTING ONLY) prevents users from viewing
usage of any other user. This applies to sreport.
.TP
-\fBusers\fR
-(NON-SLURMDBD ACCOUNTING ONLY) prevents users from viewing
-information of any user other than themselves, this also makes it so users can
-only see associations they deal with.
-Coordinators can see associations of all users they are coordinator of,
+\fBusers\fR
+(NON-SLURMDBD ACCOUNTING ONLY) prevents users from viewing
+information of any user other than themselves, this also makes it so users can
+only see associations they deal with.
+Coordinators can see associations of all users they are coordinator of,
but can only see themselves when listing users.
.RE
.TP
\fBProctrackType\fR
-Identifies the plugin to be used for process tracking.
-The slurmd daemon uses this mechanism to identify all processes
-which are children of processes it spawns for a user job.
+Identifies the plugin to be used for process tracking.
+The slurmd daemon uses this mechanism to identify all processes
+which are children of processes it spawns for a user job.
The slurmd daemon must be restarted for a change in ProctrackType
to take effect.
-NOTE: "proctrack/linuxproc" and "proctrack/pgid" can fail to
-identify all processes associated with a job since processes
-can become a child of the init process (when the parent process
-terminates) or change their process group.
-To reliably track all processes, one of the other mechanisms
-utilizing kernel modifications is preferable.
+NOTE: "proctrack/linuxproc" and "proctrack/pgid" can fail to
+identify all processes associated with a job since processes
+can become a child of the init process (when the parent process
+terminates) or change their process group.
+To reliably track all processes, one of the other mechanisms
+utilizing kernel modifications is preferable.
NOTE: "proctrack/linuxproc" is not compatible with "switch/elan."
Acceptable values at present include:
.RS
-.TP
-\fBproctrack/aix\fR which uses an AIX kernel extension and is
+.TP
+\fBproctrack/aix\fR which uses an AIX kernel extension and is
the default for AIX systems
.TP
-\fBproctrack/linuxproc\fR which uses linux process tree using
+\fBproctrack/linuxproc\fR which uses linux process tree using
parent process IDs
.TP
-\fBproctrack/rms\fR which uses Quadrics kernel patch and is the
-default if "SwitchType=switch/elan"
+\fBproctrack/rms\fR which uses Quadrics kernel patch and is the
+default if "SwitchType=switch/elan"
.TP
\fBproctrack/sgi_job\fR which uses SGI's Process Aggregates (PAGG)
-kernel module, see \fIhttp://oss.sgi.com/projects/pagg/\fR
-for more information
+kernel module, see \fIhttp://oss.sgi.com/projects/pagg/\fR
+for more information
.TP
-\fBproctrack/pgid\fR which uses process group IDs and is the
+\fBproctrack/pgid\fR which uses process group IDs and is the
default for all other systems
.RE
.TP
\fBProlog\fR
-Fully qualified pathname of a program for the slurmd to execute
+Fully qualified pathname of a program for the slurmd to execute
whenever it is asked to run a job step from a new job allocation (e.g.
"/usr/local/slurm/prolog"). The slurmd executes the script before starting
the first job step. This may be used to purge files, enable user login, etc.
-By default there is no prolog. Any configured script is expected to
+By default there is no prolog. Any configured script is expected to
complete execution quickly (in less time than \fBMessageTimeout\fR).
See \fBProlog and Epilog Scripts\fR for more information.
.TP
\fBPrologSlurmctld\fR
-Fully qualified pathname of a program for the slurmctld to execute
+Fully qualified pathname of a program for the slurmctld to execute
before granting a new job allocation (e.g.
-"/usr/local/slurm/prolog_controller").
-The program executes as SlurmUser, which gives it permission to drain
+"/usr/local/slurm/prolog_controller").
+The program executes as SlurmUser, which gives it permission to drain
nodes and requeue the job if a failure occurs or cancel the job if appropriate.
-The program can be used to reboot nodes or perform other work to prepare
-resources for use.
-While this program is running, the nodes associated with the job will be
+The program can be used to reboot nodes or perform other work to prepare
+resources for use.
+While this program is running, the nodes associated with the job will be
have a POWER_UP/CONFIGURING flag set in their state, which can be readily
viewed.
A non\-zero exit code will result in the job being requeued (where possible)
@@ -1016,7 +1016,7 @@ A list of comma separated resource limit names.
The slurmd daemon uses these names to obtain the associated (soft) limit
values from the users process environment on the submit node.
These limits are then propagated and applied to the jobs that
-will run on the compute nodes.
+will run on the compute nodes.
This parameter can be useful when system limits vary among nodes.
Any resource limits that do not appear in the list are not propagated.
However, the user can override this by specifying which resource limits
@@ -1026,7 +1026,7 @@ the default action is to propagate all limits.
Only one of the parameters, either
\fBPropagateResourceLimits\fR or \fBPropagateResourceLimitsExcept\fR,
may be specified.
-The following limit names are supported by SLURM (although some
+The following limit names are supported by SLURM (although some
options may not be supported on some systems):
.RS
.TP 10
@@ -1078,11 +1078,11 @@ See \fBPropagateResourceLimits\fR above for a list of valid limit names.
.TP
\fBResumeProgram\fR
-SLURM supports a mechanism to reduce power consumption on nodes that
-remain idle for an extended period of time.
+SLURM supports a mechanism to reduce power consumption on nodes that
+remain idle for an extended period of time.
This is typically accomplished by reducing voltage and frequency or powering
-the node down.
-\fBResumeProgram\fR is the program that will be executed when a node
+the node down.
+\fBResumeProgram\fR is the program that will be executed when a node
in power save mode is assigned work to perform.
For reasons of reliability, \fBResumeProgram\fR may execute more than once
for a node when the \fBslurmctld\fR daemon crashes and is restarted.
@@ -1093,43 +1093,43 @@ The argument to the program will be the names of nodes to
be removed from power savings mode (using SLURM's hostlist
expression format).
By default no program is run.
-Related configuration options include \fBResumeTimeout\fR, \fBResumeRate\fR,
-\fBSuspendRate\fR, \fBSuspendTime\fR, \fBSuspendTimeout\fR, \fBSuspendProgram\fR,
+Related configuration options include \fBResumeTimeout\fR, \fBResumeRate\fR,
+\fBSuspendRate\fR, \fBSuspendTime\fR, \fBSuspendTimeout\fR, \fBSuspendProgram\fR,
\fBSuspendExcNodes\fR, and \fBSuspendExcParts\fR.
More information is available at the SLURM web site
(https://computing.llnl.gov/linux/slurm/power_save.html).
.TP
\fBResumeRate\fR
-The rate at which nodes in power save mode are returned to normal
-operation by \fBResumeProgram\fR.
-The value is number of nodes per minute and it can be used to prevent
-power surges if a large number of nodes in power save mode are
+The rate at which nodes in power save mode are returned to normal
+operation by \fBResumeProgram\fR.
+The value is number of nodes per minute and it can be used to prevent
+power surges if a large number of nodes in power save mode are
assigned work at the same time (e.g. a large job starts).
-A value of zero results in no limits being imposed.
+A value of zero results in no limits being imposed.
The default value is 300 nodes per minute.
-Related configuration options include \fBResumeTimeout\fR, \fBResumeProgram\fR,
-\fBSuspendRate\fR, \fBSuspendTime\fR, \fBSuspendTimeout\fR, \fBSuspendProgram\fR,
+Related configuration options include \fBResumeTimeout\fR, \fBResumeProgram\fR,
+\fBSuspendRate\fR, \fBSuspendTime\fR, \fBSuspendTimeout\fR, \fBSuspendProgram\fR,
\fBSuspendExcNodes\fR, and \fBSuspendExcParts\fR.
.TP
\fBResumeTimeout\fR
-Maximum time permitted (in second) between when a node is resume request
-is issued and when the node is actually available for use.
+Maximum time permitted (in second) between when a node is resume request
+is issued and when the node is actually available for use.
Nodes which fail to respond in this time frame may be marked DOWN and
the jobs scheduled on the node requeued.
The default value is 60 seconds.
-Related configuration options include \fBResumeProgram\fR, \fBResumeRate\fR,
-\fBSuspendRate\fR, \fBSuspendTime\fR, \fBSuspendTimeout\fR, \fBSuspendProgram\fR,
+Related configuration options include \fBResumeProgram\fR, \fBResumeRate\fR,
+\fBSuspendRate\fR, \fBSuspendTime\fR, \fBSuspendTimeout\fR, \fBSuspendProgram\fR,
\fBSuspendExcNodes\fR and \fBSuspendExcParts\fR.
More information is available at the SLURM web site
(https://computing.llnl.gov/linux/slurm/power_save.html).
.TP
\fBResvOverRun\fR
-Describes how long a job already running in a reservation should be
-permitted to execute after the end time of the reservation has been
-reached.
+Describes how long a job already running in a reservation should be
+permitted to execute after the end time of the reservation has been
+reached.
The time period is specified in minutes and the default value is 0
(kill the job immediately).
The value may not exceed 65533 minutes, although a value of "UNLIMITED"
@@ -1138,7 +1138,7 @@ is terminated.
.TP
\fBReturnToService\fR
-Controls when a DOWN node will be returned to service.
+Controls when a DOWN node will be returned to service.
The default value is 0.
Supported values include
.RS
@@ -1150,13 +1150,13 @@ and resumes communications).
.TP
\fB1\fR
A DOWN node will become available for use upon registration with a
-valid configuration only if it was set DOWN due to being non\-responsive.
-If the node was set DOWN for any other reason (low memory, prolog failure,
-epilog failure, etc.), its state will not automatically be changed.
+valid configuration only if it was set DOWN due to being non\-responsive.
+If the node was set DOWN for any other reason (low memory, prolog failure,
+epilog failure, etc.), its state will not automatically be changed.
.TP
\fB2\fR
A DOWN node will become available for use upon registration with a
-valid configuration. The node could have been set DOWN for any reason.
+valid configuration. The node could have been set DOWN for any reason.
.RE
.TP
@@ -1189,18 +1189,18 @@ The following options apply only to \fBSchedulerType=sched/backfill\fR.
.RS
.TP
\fBinterval=#\fR
-The number of seconds between iterations.
+The number of seconds between iterations.
Higher values result in less overhead and responsiveness.
The default value is 5 seconds on BlueGene systems and 10 seconds otherwise.
.TP
\fBmax_job_bf=#\fR
-The maximum number of jobs to attempt backfill scheduling for
+The maximum number of jobs to attempt backfill scheduling for
(i.e. the queue depth).
Higher values result in more overhead and less responsiveness.
Until an attempt is made to backfill schedule a job, its expected
initiation time value will not be set.
The default value is 50.
-In the case of large clusters (more than 1000 nodes) configured with
+In the case of large clusters (more than 1000 nodes) configured with
\fBSelectType=select/cons_res\fR, setting a smaller value may be
desirable.
.RE
@@ -1227,8 +1227,8 @@ The default value is 30 seconds.
.TP
\fBSchedulerType\fR
-Identifies the type of scheduler to be used.
-Note the \fBslurmctld\fR daemon must be restarted for a change in
+Identifies the type of scheduler to be used.
+Note the \fBslurmctld\fR daemon must be restarted for a change in
scheduler type to become effective (reconfiguring a running daemon has
no effect for this parameter).
The \fBscontrol\fR command can be used to manually change job priorities
@@ -1237,14 +1237,14 @@ Acceptable values include:
.RS
.TP
\fBsched/builtin\fR
-for the built\-in FIFO (First In First Out) scheduler.
+for the built\-in FIFO (First In First Out) scheduler.
This is the default.
.TP
\fBsched/backfill\fR
for a backfill scheduling module to augment the default FIFO scheduling.
-Backfill scheduling will initiate lower\-priority jobs if doing
+Backfill scheduling will initiate lower\-priority jobs if doing
so does not delay the expected initiation time of any higher
-priority job.
+priority job.
Effectiveness of backfill scheduling is dependent upon users specifying
job time limits, otherwise all jobs will have the same time limit and
backfilling is impossible.
@@ -1254,7 +1254,7 @@ Note documentation for the \fBSchedulerParameters\fR option above.
Defunct option. See \fBPreemptType\fR and \fBPreemptMode\fR options.
.TP
\fBsched/hold\fR
-to hold all newly arriving jobs if a file "/etc/slurm.hold"
+to hold all newly arriving jobs if a file "/etc/slurm.hold"
exists otherwise use the built\-in FIFO scheduler
.TP
\fBsched/wiki\fR
@@ -1266,44 +1266,44 @@ for the Wiki interface to the Moab Cluster Suite
.TP
\fBSelectType\fR
-Identifies the type of resource selection algorithm to be used.
-Acceptable values include
+Identifies the type of resource selection algorithm to be used.
+Acceptable values include
.RS
.TP
\fBselect/linear\fR
for allocation of entire nodes assuming a
-one\-dimensional array of nodes in which sequentially ordered
-nodes are preferable.
-This is the default value for non\-BlueGene systems.
+one\-dimensional array of nodes in which sequentially ordered
+nodes are preferable.
+This is the default value for non\-BlueGene systems.
.TP
\fBselect/cons_res\fR
The resources within a node are individually allocated as
-consumable resources.
-Note that whole nodes can be allocated to jobs for selected
+consumable resources.
+Note that whole nodes can be allocated to jobs for selected
partitions by using the \fIShared=Exclusive\fR option.
See the partition \fBShared\fR parameter for more information.
.TP
\fBselect/bluegene\fR
-for a three\-dimensional BlueGene system.
+for a three\-dimensional BlueGene system.
The default value is "select/bluegene" for BlueGene systems.
.RE
.TP
\fBSelectTypeParameters\fR
-The permitted values of \fBSelectTypeParameters\fR depend upon the
+The permitted values of \fBSelectTypeParameters\fR depend upon the
configured value of \fBSelectType\fR.
\fBSelectType=select/bluegene\fR supports no \fBSelectTypeParameters\fR.
-The only supported option for \fBSelectType=select/linear\fR is
-\fBCR_Memory\fR, which treats memory as a consumable resource and
+The only supported option for \fBSelectType=select/linear\fR is
+\fBCR_Memory\fR, which treats memory as a consumable resource and
prevents memory over subscription with job preemption or gang scheduling.
The following values are supported for \fBSelectType=select/cons_res\fR:
.RS
.TP
\fBCR_CPU\fR
CPUs are consumable resources.
-There is no notion of sockets, cores or threads;
-do not define those values in the node specification. If these
-are defined, unexpected results will happen when hyper\-threading
+There is no notion of sockets, cores or threads;
+do not define those values in the node specification. If these
+are defined, unexpected results will happen when hyper\-threading
is enabled Procs= should be used instead.
On a multi\-core system, each core will be considered a CPU.
On a multi\-core and hyper\-threaded system, each thread will be
@@ -1312,39 +1312,39 @@ On single\-core systems, each CPUs will be considered a CPU.
.TP
\fBCR_CPU_Memory\fR
CPUs and memory are consumable resources.
-There is no notion of sockets, cores or threads;
-do not define those values in the node specification. If these
-are defined, unexpected results will happen when hyper\-threading
+There is no notion of sockets, cores or threads;
+do not define those values in the node specification. If these
+are defined, unexpected results will happen when hyper\-threading
is enabled Procs= should be used instead.
Setting a value for \fBDefMemPerCPU\fR is strongly recommended.
.TP
\fBCR_Core\fR
Cores are consumable resources.
-On nodes with hyper\-threads, each thread is counted as a CPU to
-satisfy a job's resource requirement, but multiple jobs are not
-allocated threads on the same core.
+On nodes with hyper\-threads, each thread is counted as a CPU to
+satisfy a job's resource requirement, but multiple jobs are not
+allocated threads on the same core.
.TP
\fBCR_Core_Memory\fR
Cores and memory are consumable resources.
-On nodes with hyper\-threads, each thread is counted as a CPU to
-satisfy a job's resource requirement, but multiple jobs are not
-allocated threads on the same core.
+On nodes with hyper\-threads, each thread is counted as a CPU to
+satisfy a job's resource requirement, but multiple jobs are not
+allocated threads on the same core.
Setting a value for \fBDefMemPerCPU\fR is strongly recommended.
.TP
\fBCR_Socket\fR
-Sockets are consumable resources.
-On nodes with multiple cores, each core or thread is counted as a CPU
-to satisfy a job's resource requirement, but multiple jobs are not
+Sockets are consumable resources.
+On nodes with multiple cores, each core or thread is counted as a CPU
+to satisfy a job's resource requirement, but multiple jobs are not
allocated resources on the same socket.
-Note that jobs requesting one CPU will only be given access to
+Note that jobs requesting one CPU will only be given access to
that one CPU, but no other job will share the socket.
.TP
\fBCR_Socket_Memory\fR
-Memory and sockets are consumable resources.
-On nodes with multiple cores, each core or thread is counted as a CPU
+Memory and sockets are consumable resources.
+On nodes with multiple cores, each core or thread is counted as a CPU
to satisfy a job's resource requirement, but multiple jobs are not
allocated resources on the same socket.
-Note that jobs requesting one CPU will only be given access to
+Note that jobs requesting one CPU will only be given access to
that one CPU, but no other job will share the socket.
Setting a value for \fBDefMemPerCPU\fR is strongly recommended.
.TP
@@ -1356,80 +1356,80 @@ Setting a value for \fBDefMemPerCPU\fR is strongly recommended.
.TP
\fBSlurmUser\fR
-The name of the user that the \fBslurmctld\fR daemon executes as.
+The name of the user that the \fBslurmctld\fR daemon executes as.
For security purposes, a user other than "root" is recommended.
-This user must exist on all nodes of the cluster for authentication
+This user must exist on all nodes of the cluster for authentication
of communications between SLURM components.
-The default value is "root".
+The default value is "root".
.TP
\fBSlurmdUser\fR
-The name of the user that the \fBslurmd\fR daemon executes as.
-This user must exist on all nodes of the cluster for authentication
+The name of the user that the \fBslurmd\fR daemon executes as.
+This user must exist on all nodes of the cluster for authentication
of communications between SLURM components.
-The default value is "root".
+The default value is "root".
.TP
\fBSlurmctldDebug\fR
-The level of detail to provide \fBslurmctld\fR daemon's logs.
-Values from 0 to 9 are legal, with `0' being "quiet" operation and `9'
+The level of detail to provide \fBslurmctld\fR daemon's logs.
+Values from 0 to 9 are legal, with `0' being "quiet" operation and `9'
being insanely verbose.
The default value is 3.
.TP
\fBSlurmctldLogFile\fR
-Fully qualified pathname of a file into which the \fBslurmctld\fR daemon's
+Fully qualified pathname of a file into which the \fBslurmctld\fR daemon's
logs are written.
The default value is none (performs logging via syslog).
.TP
\fBSlurmctldPidFile\fR
-Fully qualified pathname of a file into which the \fBslurmctld\fR daemon
+Fully qualified pathname of a file into which the \fBslurmctld\fR daemon
may write its process id. This may be used for automated signal processing.
The default value is "/var/run/slurmctld.pid".
.TP
\fBSlurmctldPort\fR
-The port number that the SLURM controller, \fBslurmctld\fR, listens
-to for work. The default value is SLURMCTLD_PORT as established at system
-build time. If none is explicitly specified, it will be set to 6817.
-NOTE: Either \fBslurmctld\fR and \fBslurmd\fR daemons must not
-execute on the same nodes or the values of \fBSlurmctldPort\fR and
+The port number that the SLURM controller, \fBslurmctld\fR, listens
+to for work. The default value is SLURMCTLD_PORT as established at system
+build time. If none is explicitly specified, it will be set to 6817.
+NOTE: Either \fBslurmctld\fR and \fBslurmd\fR daemons must not
+execute on the same nodes or the values of \fBSlurmctldPort\fR and
\fBSlurmdPort\fR must be different.
.TP
\fBSlurmctldTimeout\fR
-The interval, in seconds, that the backup controller waits for the
-primary controller to respond before assuming control.
+The interval, in seconds, that the backup controller waits for the
+primary controller to respond before assuming control.
The default value is 120 seconds.
May not exceed 65533.
.TP
\fBSlurmdDebug\fR
-The level of detail to provide \fBslurmd\fR daemon's logs.
-Values from 0 to 9 are legal, with `0' being "quiet" operation and `9' being
+The level of detail to provide \fBslurmd\fR daemon's logs.
+Values from 0 to 9 are legal, with `0' being "quiet" operation and `9' being
insanely verbose.
The default value is 3.
.TP
\fBSlurmdLogFile\fR
-Fully qualified pathname of a file into which the \fBslurmd\fR daemon's
+Fully qualified pathname of a file into which the \fBslurmd\fR daemon's
logs are written.
The default value is none (performs logging via syslog).
-Any "%h" within the name is replaced with the hostname on which the
+Any "%h" within the name is replaced with the hostname on which the
\fBslurmd\fR is running.
.TP
\fBSlurmdPidFile\fR
-Fully qualified pathname of a file into which the \fBslurmd\fR daemon may write
+Fully qualified pathname of a file into which the \fBslurmd\fR daemon may write
its process id. This may be used for automated signal processing.
The default value is "/var/run/slurmd.pid".
.TP
\fBSlurmdPort\fR
-The port number that the SLURM compute node daemon, \fBslurmd\fR, listens
-to for work. The default value is SLURMD_PORT as established at system
-build time. If none is explicitly specified, its value will be 6818.
+The port number that the SLURM compute node daemon, \fBslurmd\fR, listens
+to for work. The default value is SLURMD_PORT as established at system
+build time. If none is explicitly specified, its value will be 6818.
NOTE: Either slurmctld and slurmd daemons must not execute
on the same nodes or the values of \fBSlurmctldPort\fR and \fBSlurmdPort\fR
must be different.
@@ -1449,12 +1449,12 @@ different shared memory region and lose track of any running jobs.
.TP
\fBSlurmdTimeout\fR
-The interval, in seconds, that the SLURM controller waits for \fBslurmd\fR
-to respond before configuring that node's state to DOWN.
-A value of zero indicates the node will not be tested by \fBslurmctld\fR to
-confirm the state of \fBslurmd\fR, the node will not be automatically set to
-a DOWN state indicating a non\-responsive \fBslurmd\fR, and some other tool
-will take responsibility for monitoring the state of each compute node
+The interval, in seconds, that the SLURM controller waits for \fBslurmd\fR
+to respond before configuring that node's state to DOWN.
+A value of zero indicates the node will not be tested by \fBslurmctld\fR to
+confirm the state of \fBslurmd\fR, the node will not be automatically set to
+a DOWN state indicating a non\-responsive \fBslurmd\fR, and some other tool
+will take responsibility for monitoring the state of each compute node
and its \fBslurmd\fR daemon.
SLURM's hierarchical communication mechanism is used to ping the \fBslurmd\fR
daemons in order to minimize system noise and overhead.
@@ -1477,36 +1477,36 @@ may be overridden by srun's \fB\-\-prolog\fR parameter.
.TP
\fBStateSaveLocation\fR
-Fully qualified pathname of a directory into which the SLURM controller,
-\fBslurmctld\fR, saves its state (e.g. "/usr/local/slurm/checkpoint").
+Fully qualified pathname of a directory into which the SLURM controller,
+\fBslurmctld\fR, saves its state (e.g. "/usr/local/slurm/checkpoint").
SLURM state will saved here to recover from system failures.
\fBSlurmUser\fR must be able to create files in this directory.
-If you have a \fBBackupController\fR configured, this location should be
-readable and writable by both systems.
-Since all running and pending job information is stored here, the use of
+If you have a \fBBackupController\fR configured, this location should be
+readable and writable by both systems.
+Since all running and pending job information is stored here, the use of
a reliable file system (e.g. RAID) is recommended.
The default value is "/tmp".
-If any slurm daemons terminate abnormally, their core files will also be written
+If any slurm daemons terminate abnormally, their core files will also be written
into this directory.
.TP
\fBSuspendExcNodes\fR
-Specifies the nodes which are to not be placed in power save mode, even
+Specifies the nodes which are to not be placed in power save mode, even
if the node remains idle for an extended period of time.
Use SLURM's hostlist expression to identify nodes.
By default no nodes are excluded.
-Related configuration options include \fBResumeTimeout\fR, \fBResumeProgram\fR,
-\fBResumeRate\fR, \fBSuspendProgram\fR, \fBSuspendRate\fR, \fBSuspendTime\fR,
+Related configuration options include \fBResumeTimeout\fR, \fBResumeProgram\fR,
+\fBResumeRate\fR, \fBSuspendProgram\fR, \fBSuspendRate\fR, \fBSuspendTime\fR,
\fBSuspendTimeout\fR, and \fBSuspendExcParts\fR.
.TP
\fBSuspendExcParts\fR
-Specifies the partitions whose nodes are to not be placed in power save
+Specifies the partitions whose nodes are to not be placed in power save
mode, even if the node remains idle for an extended period of time.
Multiple partitions can be identified and separated by commas.
By default no nodes are excluded.
-Related configuration options include \fBResumeTimeout\fR, \fBResumeProgram\fR,
-\fBResumeRate\fR, \fBSuspendProgram\fR, \fBSuspendRate\fR, \fBSuspendTime\fR
+Related configuration options include \fBResumeTimeout\fR, \fBResumeProgram\fR,
+\fBResumeRate\fR, \fBSuspendProgram\fR, \fBSuspendRate\fR, \fBSuspendTime\fR
\fBSuspendTimeout\fR, and \fBSuspendExcNodes\fR.
.TP
@@ -1514,15 +1514,15 @@ Related configuration options include \fBResumeTimeout\fR, \fBResumeProgram\fR,
\fBSuspendProgram\fR is the program that will be executed when a node
remains idle for an extended period of time.
This program is expected to place the node into some power save mode.
-This can be used to reduce the frequency and voltage of a node or
+This can be used to reduce the frequency and voltage of a node or
completely power the node off.
The program executes as \fBSlurmUser\fR.
The argument to the program will be the names of nodes to
be placed into power savings mode (using SLURM's hostlist
expression format).
By default, no program is run.
-Related configuration options include \fBResumeTimeout\fR, \fBResumeProgram\fR,
-\fBResumeRate\fR, \fBSuspendRate\fR, \fBSuspendTime\fR, \fBSuspendTimeout\fR,
+Related configuration options include \fBResumeTimeout\fR, \fBResumeProgram\fR,
+\fBResumeRate\fR, \fBSuspendRate\fR, \fBSuspendTime\fR, \fBSuspendTimeout\fR,
\fBSuspendExcNodes\fR, and \fBSuspendExcParts\fR.
.TP
@@ -1532,28 +1532,28 @@ The value is number of nodes per minute and it can be used to prevent
a large drop in power power consumption (e.g. after a large job completes).
A value of zero results in no limits being imposed.
The default value is 60 nodes per minute.
-Related configuration options include \fBResumeTimeout\fR, \fBResumeProgram\fR,
-\fBResumeRate\fR, \fBSuspendProgram\fR, \fBSuspendTime\fR, \fBSuspendTimeout\fR,
+Related configuration options include \fBResumeTimeout\fR, \fBResumeProgram\fR,
+\fBResumeRate\fR, \fBSuspendProgram\fR, \fBSuspendTime\fR, \fBSuspendTimeout\fR,
\fBSuspendExcNodes\fR, and \fBSuspendExcParts\fR.
.TP
\fBSuspendTime\fR
-Nodes which remain idle for this number of seconds will be placed into
-power save mode by \fBSuspendProgram\fR.
+Nodes which remain idle for this number of seconds will be placed into
+power save mode by \fBSuspendProgram\fR.
A value of \-1 disables power save mode and is the default.
-Related configuration options include \fBResumeTimeout\fR, \fBResumeProgram\fR,
-\fBResumeRate\fR, \fBSuspendProgram\fR, \fBSuspendRate\fR, \fBSuspendTimeout\fR,
+Related configuration options include \fBResumeTimeout\fR, \fBResumeProgram\fR,
+\fBResumeRate\fR, \fBSuspendProgram\fR, \fBSuspendRate\fR, \fBSuspendTimeout\fR,
\fBSuspendExcNodes\fR, and \fBSuspendExcParts\fR.
.TP
\fBSuspendTimeout\fR
-Maximum time permitted (in second) between when a node suspend request
+Maximum time permitted (in second) between when a node suspend request
is issued and when the node shutdown.
-At that time the node must ready for a resume request to be issued
-as needed for new work.
+At that time the node must ready for a resume request to be issued
+as needed for new work.
The default value is 30 seconds.
-Related configuration options include \fBResumeProgram\fR, \fBResumeRate\fR,
-\fBResumeTimeout\fR, \fBSuspendRate\fR, \fBSuspendTime\fR, \fBSuspendProgram\fR,
+Related configuration options include \fBResumeProgram\fR, \fBResumeRate\fR,
+\fBResumeTimeout\fR, \fBSuspendRate\fR, \fBSuspendTime\fR, \fBSuspendProgram\fR,
\fBSuspendExcNodes\fR and \fBSuspendExcParts\fR.
More information is available at the SLURM web site
(https://computing.llnl.gov/linux/slurm/power_save.html).
@@ -1561,15 +1561,15 @@ More information is available at the SLURM web site
.TP
\fBSwitchType\fR
Identifies the type of switch or interconnect used for application
-communications.
+communications.
Acceptable values include
-"switch/none" for switches not requiring special processing for job launch
+"switch/none" for switches not requiring special processing for job launch
or termination (Myrinet, Ethernet, and InfiniBand),
"switch/elan" for Quadrics Elan 3 or Elan 4 interconnect.
The default value is "switch/none".
-All SLURM daemons, commands and running jobs must be restarted for a
+All SLURM daemons, commands and running jobs must be restarted for a
change in \fBSwitchType\fR to take effect.
-If running jobs exist at the time \fBslurmctld\fR is restarted with a new
+If running jobs exist at the time \fBslurmctld\fR is restarted with a new
value of \fBSwitchType\fR, records of all jobs in any state may be lost.
.TP
@@ -1580,19 +1580,19 @@ See \fBTaskProlog\fR for execution order details.
.TP
\fBTaskPlugin\fR
-Identifies the type of task launch plugin, typically used to provide
-resource management within a node (e.g. pinning tasks to specific
+Identifies the type of task launch plugin, typically used to provide
+resource management within a node (e.g. pinning tasks to specific
processors).
Acceptable values include
"task/none" for systems requiring no special handling and
-"task/affinity" to enable the \-\-cpu_bind and/or \-\-mem_bind
+"task/affinity" to enable the \-\-cpu_bind and/or \-\-mem_bind
srun options.
The default value is "task/none".
-If you "task/affinity" and encounter problems, it may be due to
-the variety of system calls used to implement task affinity on
-different operating systems.
-If that is the case, you may want to use Portable Linux
-Process Affinity (PLPA, see http://www.open-mpi.org/software/plpa),
+If you "task/affinity" and encounter problems, it may be due to
+the variety of system calls used to implement task affinity on
+different operating systems.
+If that is the case, you may want to use Portable Linux
+Process Affinity (PLPA, see http://www.open-mpi.org/software/plpa),
which is supported by SLURM.
.TP
@@ -1603,8 +1603,8 @@ If \fBNone\fR, \fBSockets\fR, \fBCores\fR, \fBThreads\fR,
and/or \fBVerbose\fR are specified, they will override
the \fB\-\-cpu_bind\fR option specified by the user
in the \fBsrun\fR command.
-\fBNone\fR, \fBSockets\fR, \fBCores\fR and \fBThreads\fR are mutually
-exclusive and since they decrease scheduling flexibility are not generally
+\fBNone\fR, \fBSockets\fR, \fBCores\fR and \fBThreads\fR are mutually
+exclusive and since they decrease scheduling flexibility are not generally
recommended (select no more than one of them).
\fBCpusets\fR and \fBSched\fR
are mutually exclusive (select only one of them).
@@ -1612,7 +1612,7 @@ are mutually exclusive (select only one of them).
.RS
.TP 10
\fBCores\fR
-Always bind to cores.
+Always bind to cores.
Overrides user options or automatic binding.
.TP
\fBCpusets\fR
@@ -1620,7 +1620,7 @@ Use cpusets to perform task affinity functions.
By default, \fBSched\fR task binding is performed.
.TP
\fBNone\fR
-Perform no task binding.
+Perform no task binding.
Overrides user options or automatic binding.
.TP
\fBSched\fR
@@ -1628,27 +1628,27 @@ Use \fIsched_setaffinity\fR or \fIplpa_sched_setaffinity\fR
(if available) to bind tasks to processors.
.TP
\fBSockets\fR
-Always bind to sockets.
+Always bind to sockets.
Overrides user options or automatic binding.
.TP
\fBThreads\fR
-Always bind to threads.
+Always bind to threads.
Overrides user options or automatic binding.
.TP
\fBVerbose\fR
-Verbosely report binding before tasks run.
+Verbosely report binding before tasks run.
Overrides user options.
.RE
.TP
\fBTaskProlog\fR
-Fully qualified pathname of a program to be execute as the slurm job's
+Fully qualified pathname of a program to be execute as the slurm job's
owner prior to initiation of each task.
-Besides the normal environment variables, this has SLURM_TASK_PID
-available to identify the process ID of the task being started.
-Standard output from this program of the form
-"export NAME=value" will be used to set environment variables
-for the task being spawned.
+Besides the normal environment variables, this has SLURM_TASK_PID
+available to identify the process ID of the task being started.
+Standard output from this program of the form
+"export NAME=value" will be used to set environment variables
+for the task being spawned.
Standard output from this program of the form
"print ..." will cause that line (without the leading "print ")
to be printed to the job's standard output.
@@ -1676,20 +1676,20 @@ environment variable
.TP
\fBTmpFS\fR
-Fully qualified pathname of the file system available to user jobs for
+Fully qualified pathname of the file system available to user jobs for
temporary storage. This parameter is used in establishing a node's \fBTmpDisk\fR
-space.
+space.
The default value is "/tmp".
.TP
\fBTopologyPlugin\fR
Identifies the plugin to be used for determining the network topology
-and optimizing job allocations to minimize network contention.
-Acceptable values include
-"topology/3d_torus" (default for Cray XT, IBM BlueGene and Sun Constellation
+and optimizing job allocations to minimize network contention.
+Acceptable values include
+"topology/3d_torus" (default for Cray XT, IBM BlueGene and Sun Constellation
systems, best\-fit logic over three\-dimensional topology)
"topology/none" (default for other systems, best\-fit
-logic over one\-dimensional topology) and
+logic over one\-dimensional topology) and
"topology/tree" (determine the network topology based
upon information contained in a topology.conf file).
See \fBNETWORK TOPOLOGY\fR below for details.
@@ -1698,7 +1698,7 @@ information directly from the network.
.TP
\fBTrackWCKey\fR
-Boolean yes or no. Used to set display and track of the Workload
+Boolean yes or no. Used to set display and track of the Workload
Characterization Key. Must be set to track wckey usage.
.TP
@@ -1718,17 +1718,17 @@ systems.
\fBUnkillableStepProgram\fR
If the processes in a job step are determined to be unkillable for a period
of time specified by the \fBUnkillableStepTimeout\fR variable, the program
-specified by \fBUnkillableStepProgram\fR will be executed.
+specified by \fBUnkillableStepProgram\fR will be executed.
This program can be used to take special actions to clean up the unkillable
-processes and/or notify computer administrators.
-The program will be run \fBSlurmdUser\fR (usually "root").
+processes and/or notify computer administrators.
+The program will be run \fBSlurmdUser\fR (usually "root").
By default no program is run.
.TP
\fBUnkillableStepTimeout\fR
The length of time, in seconds, that SLURM will wait before deciding that
processes in a job step are unkillable (after they have been signaled with
-SIGKILL) and execute \fBUnkillableStepProgram\fR as described above.
+SIGKILL) and execute \fBUnkillableStepProgram\fR as described above.
The default timeout value is 60 seconds.
.TP
@@ -1760,69 +1760,69 @@ lines (see above), where \fBslurm\fR is the service\-name, should be added.
.TP
\fBWaitTime\fR
-Specifies how many seconds the srun command should by default wait after
-the first task terminates before terminating all remaining tasks. The
-"\-\-wait" option on the srun command line overrides this value.
+Specifies how many seconds the srun command should by default wait after
+the first task terminates before terminating all remaining tasks. The
+"\-\-wait" option on the srun command line overrides this value.
If set to 0, this feature is disabled.
May not exceed 65533 seconds.
.LP
-The configuration of nodes (or machines) to be managed by SLURM is
-also specified in \fB/etc/slurm.conf\fR.
+The configuration of nodes (or machines) to be managed by SLURM is
+also specified in \fB/etc/slurm.conf\fR.
Changes in node configuration (e.g. adding nodes, changing their
processor count, etc.) require restarting the slurmctld daemon.
Only the NodeName must be supplied in the configuration file.
All other node configuration information is optional.
-It is advisable to establish baseline node configurations,
-especially if the cluster is heterogeneous.
-Nodes which register to the system with less than the configured resources
-(e.g. too little memory), will be placed in the "DOWN" state to
-avoid scheduling jobs on them.
-Establishing baseline configurations will also speed SLURM's
-scheduling process by permitting it to compare job requirements
-against these (relatively few) configuration parameters and
-possibly avoid having to check job requirements
+It is advisable to establish baseline node configurations,
+especially if the cluster is heterogeneous.
+Nodes which register to the system with less than the configured resources
+(e.g. too little memory), will be placed in the "DOWN" state to
+avoid scheduling jobs on them.
+Establishing baseline configurations will also speed SLURM's
+scheduling process by permitting it to compare job requirements
+against these (relatively few) configuration parameters and
+possibly avoid having to check job requirements
against every individual node's configuration.
-The resources checked at node registration time are: Procs,
-RealMemory and TmpDisk.
-While baseline values for each of these can be established
-in the configuration file, the actual values upon node
-registration are recorded and these actual values may be
-used for scheduling purposes (depending upon the value of
+The resources checked at node registration time are: Procs,
+RealMemory and TmpDisk.
+While baseline values for each of these can be established
+in the configuration file, the actual values upon node
+registration are recorded and these actual values may be
+used for scheduling purposes (depending upon the value of
\fBFastSchedule\fR in the configuration file.
.LP
-Default values can be specified with a record in which
-"NodeName" is "DEFAULT".
-The default entry values will apply only to lines following it in the
-configuration file and the default values can be reset multiple times
+Default values can be specified with a record in which
+"NodeName" is "DEFAULT".
+The default entry values will apply only to lines following it in the
+configuration file and the default values can be reset multiple times
in the configuration file with multiple entries where "NodeName=DEFAULT".
-The "NodeName=" specification must be placed on every line
-describing the configuration of nodes.
-In fact, it is generally possible and desirable to define the
+The "NodeName=" specification must be placed on every line
+describing the configuration of nodes.
+In fact, it is generally possible and desirable to define the
configurations of all nodes in only a few lines.
-This convention permits significant optimization in the scheduling
-of larger clusters.
+This convention permits significant optimization in the scheduling
+of larger clusters.
In order to support the concept of jobs requiring consecutive nodes
-on some architectures,
+on some architectures,
node specifications should be place in this file in consecutive order.
No single node name may be listed more than once in the configuration
file.
-Use "DownNodes=" to record the state of nodes which are temporarily
-in a DOWN, DRAIN or FAILING state without altering permanent
+Use "DownNodes=" to record the state of nodes which are temporarily
+in a DOWN, DRAIN or FAILING state without altering permanent
configuration information.
-A job step's tasks are allocated to nodes in order the nodes appear
-in the configuration file. There is presently no capability within
+A job step's tasks are allocated to nodes in order the nodes appear
+in the configuration file. There is presently no capability within
SLURM to arbitrarily order a job step's tasks.
.LP
Multiple node names may be comma separated (e.g. "alpha,beta,gamma")
-and/or a simple node range expression may optionally be used to
-specify numeric ranges of nodes to avoid building a configuration
-file with large numbers of entries.
-The node range expression can contain one pair of square brackets
-with a sequence of comma separated numbers and/or ranges of numbers
+and/or a simple node range expression may optionally be used to
+specify numeric ranges of nodes to avoid building a configuration
+file with large numbers of entries.
+The node range expression can contain one pair of square brackets
+with a sequence of comma separated numbers and/or ranges of numbers
separated by a "\-" (e.g. "linux[0\-64,128]", or "lx[15,18,32\-33]").
-Note that the numeric ranges can include one or more leading
-zeros to indicate the numeric portion has a fixed number of digits
+Note that the numeric ranges can include one or more leading
+zeros to indicate the numeric portion has a fixed number of digits
(e.g. "linux[0000\-1023]").
Up to two numeric ranges can be included in the expression
(e.g. "rack[0\-63]_blade[0\-41]").
@@ -1834,13 +1834,13 @@ On BlueGene systems only, the square brackets should contain
pairs of three digit numbers separated by a "x".
These numbers indicate the boundaries of a rectangular prism
(e.g. "bgl[000x144,400x544]").
-See BlueGene documentation for more details.
+See BlueGene documentation for more details.
The node configuration specified the following information:
.TP
\fBNodeName\fR
-Name that SLURM uses to refer to a node (or base partition for
-BlueGene systems).
+Name that SLURM uses to refer to a node (or base partition for
+BlueGene systems).
Typically this would be the string that "/bin/hostname \-s" returns.
It may also be the fully qualified domain name as returned by "/bin/hostname \-f"
(e.g. "foo1.bar.com"), or any valid domain name associated with the host
@@ -1851,19 +1851,19 @@ must be at the end of the string).
Only short hostname forms are compatible with the
switch/elan and switch/federation plugins at this time.
It may also be an arbitrary string if \fBNodeHostname\fR is specified.
-If the \fBNodeName\fR is "DEFAULT", the values specified
-with that record will apply to subsequent node specifications
-unless explicitly set to other values in that node record or
-replaced with a different set of default values.
-For architectures in which the node order is significant,
-nodes will be considered consecutive in the order defined.
-For example, if the configuration for "NodeName=charlie" immediately
-follows the configuration for "NodeName=baker" they will be
+If the \fBNodeName\fR is "DEFAULT", the values specified
+with that record will apply to subsequent node specifications
+unless explicitly set to other values in that node record or
+replaced with a different set of default values.
+For architectures in which the node order is significant,
+nodes will be considered consecutive in the order defined.
+For example, if the configuration for "NodeName=charlie" immediately
+follows the configuration for "NodeName=baker" they will be
considered adjacent in the computer.
.TP
\fBNodeHostname\fR
-Typically this would be the string that "/bin/hostname \-s" returns.
+Typically this would be the string that "/bin/hostname \-s" returns.
It may also be the fully qualified domain name as returned by "/bin/hostname \-f"
(e.g. "foo1.bar.com"), or any valid domain name associated with the host
through the host database (/etc/hosts) or DNS, depending on the resolver
@@ -1873,23 +1873,23 @@ must be at the end of the string).
Only short hostname forms are compatible with the
switch/elan and switch/federation plugins at this time.
A node range expression can be used to specify a set of nodes.
-If an expression is used, the number of nodes identified by
-\fBNodeHostname\fR on a line in the configuration file must
+If an expression is used, the number of nodes identified by
+\fBNodeHostname\fR on a line in the configuration file must
be identical to the number of nodes identified by \fBNodeName\fR.
-By default, the \fBNodeHostname\fR will be identical in value to
+By default, the \fBNodeHostname\fR will be identical in value to
\fBNodeName\fR.
.TP
\fBNodeAddr\fR
-Name that a node should be referred to in establishing
-a communications path.
-This name will be used as an
-argument to the gethostbyname() function for identification.
-If a node range expression is used to designate multiple nodes,
+Name that a node should be referred to in establishing
+a communications path.
+This name will be used as an
+argument to the gethostbyname() function for identification.
+If a node range expression is used to designate multiple nodes,
they must exactly match the entries in the \fBNodeName\fR
-(e.g. "NodeName=lx[0\-7] NodeAddr="elx[0\-7]").
+(e.g. "NodeName=lx[0\-7] NodeAddr="elx[0\-7]").
\fBNodeAddr\fR may also contain IP addresses.
-By default, the \fBNodeAddr\fR will be identical in value to
+By default, the \fBNodeAddr\fR will be identical in value to
\fBNodeName\fR.
.TP
@@ -1903,12 +1903,12 @@ The default value is 1.
.TP
\fBFeature\fR
-A comma delimited list of arbitrary strings indicative of some
-characteristic associated with the node.
-There is no value associated with a feature at this time, a node
-either has a feature or it does not.
-If desired a feature may contain a numeric component indicating,
-for example, processor speed.
+A comma delimited list of arbitrary strings indicative of some
+characteristic associated with the node.
+There is no value associated with a feature at this time, a node
+either has a feature or it does not.
+If desired a feature may contain a numeric component indicating,
+for example, processor speed.
By default a node has no features.
.TP
@@ -1916,7 +1916,7 @@ By default a node has no features.
Number of logical processors on the node (e.g. "2").
If \fBProcs\fR is omitted, it will set equal to the product of
\fBSockets\fR, \fBCoresPerSocket\fR, and \fBThreadsPerCore\fR.
-The default value is 1.
+The default value is 1.
.TP
\fBRealMemory\fR
@@ -1925,8 +1925,8 @@ The default value is 1.
.TP
\fBReason\fR
-Identifies the reason for a node being in state "DOWN", "DRAINED"
-"DRAINING", "FAIL" or "FAILING".
+Identifies the reason for a node being in state "DOWN", "DRAINED"
+"DRAINING", "FAIL" or "FAILING".
Use quotes to enclose a reason having more than one word.
.TP
@@ -1934,83 +1934,83 @@ Use quotes to enclose a reason having more than one word.
Number of physical processor sockets/chips on the node (e.g. "2").
If Sockets is omitted, it will be inferred from
\fBProcs\fR, \fBCoresPerSocket\fR, and \fBThreadsPerCore\fR.
-\fBNOTE\fR: If you have multi\-core processors, you will likely
+\fBNOTE\fR: If you have multi\-core processors, you will likely
need to specify these parameters.
The default value is 1.
.TP
\fBState\fR
-State of the node with respect to the initiation of user jobs.
-Acceptable values are "DOWN", "DRAIN", "FAIL", "FAILING" and "UNKNOWN".
+State of the node with respect to the initiation of user jobs.
+Acceptable values are "DOWN", "DRAIN", "FAIL", "FAILING" and "UNKNOWN".
"DOWN" indicates the node failed and is unavailable to be allocated work.
"DRAIN" indicates the node is unavailable to be allocated work.
-"FAIL" indicates the node is expected to fail soon, has
-no jobs allocated to it, and will not be allocated
+"FAIL" indicates the node is expected to fail soon, has
+no jobs allocated to it, and will not be allocated
to any new jobs.
-"FAILING" indicates the node is expected to fail soon, has
-one or more jobs allocated to it, but will not be allocated
+"FAILING" indicates the node is expected to fail soon, has
+one or more jobs allocated to it, but will not be allocated
to any new jobs.
-"UNKNOWN" indicates the node's state is undefined (BUSY or IDLE),
-but will be established when the \fBslurmd\fR daemon on that node
+"UNKNOWN" indicates the node's state is undefined (BUSY or IDLE),
+but will be established when the \fBslurmd\fR daemon on that node
registers.
The default value is "UNKNOWN".
-Also see the \fBDownNodes\fR parameter below.
+Also see the \fBDownNodes\fR parameter below.
.TP
\fBThreadsPerCore\fR
Number of logical threads in a single physical core (e.g. "2").
Note that the SLURM can allocate resources to jobs down to the
resolution of a core. If your system is configured with more than
-one thread per core, execution of a different job on each thread
-is not supported.
+one thread per core, execution of a different job on each thread
+is not supported.
A job can execute a one task per thread from within one job step or
-execute a distinct job step on each of the threads.
-Note also if you are running with more than 1 thread per core and running
-the select/cons_res plugin you will want to set the SelectTypeParameters
+execute a distinct job step on each of the threads.
+Note also if you are running with more than 1 thread per core and running
+the select/cons_res plugin you will want to set the SelectTypeParameters
variable to something other than CR_CPU to avoid unexpected results.
The default value is 1.
.TP
\fBTmpDisk\fR
-Total size of temporary disk storage in \fBTmpFS\fR in MegaBytes
-(e.g. "16384"). \fBTmpFS\fR (for "Temporary File System")
-identifies the location which jobs should use for temporary storage.
-Note this does not indicate the amount of free
-space available to the user on the node, only the total file
-system size. The system administration should insure this file
-system is purged as needed so that user jobs have access to
-most of this space.
-The Prolog and/or Epilog programs (specified in the configuration file)
-might be used to insure the file system is kept clean.
+Total size of temporary disk storage in \fBTmpFS\fR in MegaBytes
+(e.g. "16384"). \fBTmpFS\fR (for "Temporary File System")
+identifies the location which jobs should use for temporary storage.
+Note this does not indicate the amount of free
+space available to the user on the node, only the total file
+system size. The system administration should insure this file
+system is purged as needed so that user jobs have access to
+most of this space.
+The Prolog and/or Epilog programs (specified in the configuration file)
+might be used to insure the file system is kept clean.
The default value is 0.
.TP
\fBWeight\fR
-The priority of the node for scheduling purposes.
-All things being equal, jobs will be allocated the nodes with
-the lowest weight which satisfies their requirements.
-For example, a heterogeneous collection of nodes might
+The priority of the node for scheduling purposes.
+All things being equal, jobs will be allocated the nodes with
+the lowest weight which satisfies their requirements.
+For example, a heterogeneous collection of nodes might
be placed into a single partition for greater system
-utilization, responsiveness and capability. It would be
-preferable to allocate smaller memory nodes rather than larger
-memory nodes if either will satisfy a job's requirements.
-The units of weight are arbitrary, but larger weights
-should be assigned to nodes with more processors, memory,
+utilization, responsiveness and capability. It would be
+preferable to allocate smaller memory nodes rather than larger
+memory nodes if either will satisfy a job's requirements.
+The units of weight are arbitrary, but larger weights
+should be assigned to nodes with more processors, memory,
disk space, higher processor speed, etc.
Note that if a job allocation request can not be satisfied
using the nodes with the lowest weight, the set of nodes
with the next lowest weight is added to the set of nodes
-under consideration for use (repeat as needed for higher
-weight values). If you absolutely want to minimize the number
-of higher weight nodes allocated to a job (at a cost of higher
-scheduling overhead), give each node a distinct \fBWeight\fR
-value and they will be added to the pool of nodes being
+under consideration for use (repeat as needed for higher
+weight values). If you absolutely want to minimize the number
+of higher weight nodes allocated to a job (at a cost of higher
+scheduling overhead), give each node a distinct \fBWeight\fR
+value and they will be added to the pool of nodes being
considered for scheduling individually.
The default value is 1.
.LP
-The "DownNodes=" configuration permits you to mark certain nodes as in a
-DOWN, DRAIN, FAIL, or FAILING state without altering the permanent
+The "DownNodes=" configuration permits you to mark certain nodes as in a
+DOWN, DRAIN, FAIL, or FAILING state without altering the permanent
configuration information listed under a "NodeName=" specification.
.TP
@@ -2019,15 +2019,15 @@ Any node name, or list of node names, from the "NodeName=" specifications.
.TP
\fBReason\fR
-Identifies the reason for a node being in state "DOWN", "DRAIN",
-"FAIL" or "FAILING.
+Identifies the reason for a node being in state "DOWN", "DRAIN",
+"FAIL" or "FAILING.
\Use quotes to enclose a reason having more than one word.
.TP
\fBState\fR
-State of the node with respect to the initiation of user jobs.
+State of the node with respect to the initiation of user jobs.
Acceptable values are "BUSY", "DOWN", "DRAIN", "FAIL",
-"FAILING, "IDLE", and "UNKNOWN".
+"FAILING, "IDLE", and "UNKNOWN".
"DOWN" indicates the node failed and is unavailable to be allocated work.
"DRAIN" indicates the node is unavailable to be allocated work.
"FAIL" indicates the node is expected to fail soon, has
@@ -2036,25 +2036,25 @@ to any new jobs.
"FAILING" indicates the node is expected to fail soon, has
one or more jobs allocated to it, but will not be allocated
to any new jobs.
-"FUTURE" indicates the node is defined for future use and need not
-exist when the SLURM daemons are started. These nodes can be made available
-for use simply by updating the node state using the scontrol command rather
-than restarting the slurmctld daemon. After these nodes are made available,
-change their \fRState\fR in the slurm.conf file. Until these nodes are made
-available, they will not be seen using any SLURM commands or APIs nor will
-any attempt be made to contact them.
-"UNKNOWN" indicates the node's state is undefined (BUSY or IDLE),
-but will be established when the \fBslurmd\fR daemon on that node
+"FUTURE" indicates the node is defined for future use and need not
+exist when the SLURM daemons are started. These nodes can be made available
+for use simply by updating the node state using the scontrol command rather
+than restarting the slurmctld daemon. After these nodes are made available,
+change their \fRState\fR in the slurm.conf file. Until these nodes are made
+available, they will not be seen using any SLURM commands or APIs nor will
+any attempt be made to contact them.
+"UNKNOWN" indicates the node's state is undefined (BUSY or IDLE),
+but will be established when the \fBslurmd\fR daemon on that node
registers.
The default value is "UNKNOWN".
.LP
-The partition configuration permits you to establish different job
-limits or access controls for various groups (or partitions) of nodes.
-Nodes may be in more than one partition, making partitions serve
-as general purpose queues.
-For example one may put the same set of nodes into two different
-partitions, each with different constraints (time limit, job sizes,
+The partition configuration permits you to establish different job
+limits or access controls for various groups (or partitions) of nodes.
+Nodes may be in more than one partition, making partitions serve
+as general purpose queues.
+For example one may put the same set of nodes into two different
+partitions, each with different constraints (time limit, job sizes,
groups allowed to use the partition, etc.).
Jobs are allocated resources within a single partition.
Default values can be specified with a record in which
@@ -2065,7 +2065,7 @@ in the configuration file with multiple entries where "PartitionName=DEFAULT".
The "PartitionName=" specification must be placed on every line
describing the configuration of partitions.
\fBNOTE:\fR Put all parameters for each partition on a single line.
-Each line of partition configuration information should
+Each line of partition configuration information should
represent a different partition.
The partition configuration file contains the following information:
@@ -2079,42 +2079,42 @@ The default value is "ALL".
.TP
\fBAllowGroups\fR
-Comma separated list of group IDs which may execute jobs in the partition.
-If at least one group associated with the user attempting to execute the
+Comma separated list of group IDs which may execute jobs in the partition.
+If at least one group associated with the user attempting to execute the
job is in AllowGroups, he will be permitted to use this partition.
Jobs executed as user root can use any partition without regard to
the value of AllowGroups.
-If user root attempts to execute a job as another user (e.g. using
-srun's \-\-uid option), this other user must be in one of groups
+If user root attempts to execute a job as another user (e.g. using
+srun's \-\-uid option), this other user must be in one of groups
identified by AllowGroups for the job to successfully execute.
-The default value is "ALL".
+The default value is "ALL".
.TP
\fBDefault\fR
-If this keyword is set, jobs submitted without a partition
+If this keyword is set, jobs submitted without a partition
specification will utilize this partition.
-Possible values are "YES" and "NO".
+Possible values are "YES" and "NO".
The default value is "NO".
.TP
\fBDisableRootJobs\fR
If set to "YES" then user root will be prevented from running any jobs
on this partition.
-The default value will be the value of \fBDisableRootJobs\fR set
+The default value will be the value of \fBDisableRootJobs\fR set
outside of a partition specification (which is "NO", allowing user
root to execute jobs).
.TP
\fBHidden\fR
-Specifies if the partition and its jobs are to be hidden by default.
-Hidden partitions will by default not be reported by the SLURM
+Specifies if the partition and its jobs are to be hidden by default.
+Hidden partitions will by default not be reported by the SLURM
APIs or commands.
-Possible values are "YES" and "NO".
+Possible values are "YES" and "NO".
The default value is "NO".
.TP
\fBMaxNodes\fR
-Maximum count of nodes (c\-nodes for BlueGene systems) which
+Maximum count of nodes (c\-nodes for BlueGene systems) which
may be allocated to any single job.
The default value is "UNLIMITED", which is represented internally as \-1.
This limit does not apply to jobs executed by SlurmUser or user root.
@@ -2122,10 +2122,10 @@ This limit does not apply to jobs executed by SlurmUser or user root.
.TP
\fBMaxTime\fR
Maximum run time limit for jobs.
-Format is minutes, minutes:seconds, hours:minutes:seconds,
+Format is minutes, minutes:seconds, hours:minutes:seconds,
days\-hours, days\-hours:minutes, days\-hours:minutes:seconds or
-"UNLIMITED".
-Time resolution is one minute and second values are rounded up to
+"UNLIMITED".
+Time resolution is one minute and second values are rounded up to
the next minute.
This limit does not apply to jobs executed by SlurmUser or user root.
@@ -2137,23 +2137,23 @@ Format is the same as for MaxTime.
.TP
\fBMinNodes\fR
-Minimum count of nodes (or base partitions for BlueGene systems) which
+Minimum count of nodes (or base partitions for BlueGene systems) which
may be allocated to any single job.
The default value is 1.
This limit does not apply to jobs executed by SlurmUser or user root.
.TP
\fBNodes\fR
-Comma separated list of nodes (or base partitions for BlueGene systems)
-which are associated with this partition.
-Node names may be specified using the node range expression syntax
-described above. A blank list of nodes
-(i.e. "Nodes= ") can be used if one wants a partition to exist,
+Comma separated list of nodes (or base partitions for BlueGene systems)
+which are associated with this partition.
+Node names may be specified using the node range expression syntax
+described above. A blank list of nodes
+(i.e. "Nodes= ") can be used if one wants a partition to exist,
but have no resources (possibly on a temporary basis).
.TP
\fBPartitionName\fR
-Name by which the partition may be referenced (e.g. "Interactive").
+Name by which the partition may be referenced (e.g. "Interactive").
This name can be specified by users when submitting jobs.
If the \fBPartitionName\fR is "DEFAULT", the values specified
with that record will apply to subsequent partition specifications
@@ -2162,28 +2162,28 @@ replaced with a different set of default values.
.TP
\fBPriority\fR
-Jobs submitted to a higher priority partition will be dispatched
+Jobs submitted to a higher priority partition will be dispatched
before pending jobs in lower priority partitions and if possible
they will preempt running jobs from lower priority partitions.
-Note that a partition's priority takes precedence over a job's
+Note that a partition's priority takes precedence over a job's
priority.
The value may not exceed 65533.
.TP
\fBRootOnly\fR
-Specifies if only user ID zero (i.e. user \fIroot\fR) may allocate resources
-in this partition. User root may allocate resources for any other user,
-but the request must be initiated by user root.
-This option can be useful for a partition to be managed by some
-external entity (e.g. a higher\-level job manager) and prevents
+Specifies if only user ID zero (i.e. user \fIroot\fR) may allocate resources
+in this partition. User root may allocate resources for any other user,
+but the request must be initiated by user root.
+This option can be useful for a partition to be managed by some
+external entity (e.g. a higher\-level job manager) and prevents
users from directly using those resources.
-Possible values are "YES" and "NO".
+Possible values are "YES" and "NO".
The default value is "NO".
.TP
\fBShared\fR
-Controls the ability of the partition to execute more than one job at a
+Controls the ability of the partition to execute more than one job at a
time on each resource (node, socket or core depending upon the value
of \fBSelectTypeParameters\fR).
If resources are to be shared, avoiding memory over\-subscription
@@ -2210,11 +2210,11 @@ For more information see the following web pages:
.TP 12
\fBEXCLUSIVE\fR
Allocates entire nodes to jobs even with select/cons_res configured.
-This can be used to allocate whole nodes in some partitions
+This can be used to allocate whole nodes in some partitions
and individual processors in other partitions.
-.TP
+.TP
\fBFORCE\fR
-Make all resources in the partition available for sharing
+Make all resources in the partition available for sharing
without any means for users to disable it.
May be followed with a colon and maximum number of jobs in
running or suspended state.
@@ -2227,35 +2227,35 @@ with gang scheduling (\fBSchedulerType=sched/gang\fR).
\fBYES\fR
Make nodes in the partition available for sharing, but provides
the user with a means of getting dedicated resources.
-If \fBSelectType=select/cons_res\fR, then resources will be
-over\-subscribed unless explicitly disabled in the job submit
+If \fBSelectType=select/cons_res\fR, then resources will be
+over\-subscribed unless explicitly disabled in the job submit
request using the "\-\-exclusive" option.
With \fBSelectType=select/bluegene\fR or \fBSelectType=select/linear\fR,
resources will only be over\-subscribed when explicitly requested
by the user using the "\-\-share" option on job submission.
-May be followed with a colon and maximum number of jobs in
+May be followed with a colon and maximum number of jobs in
running or suspended state.
For example "Shared=YES:4" enables each node, socket or
core to execute up to four jobs at once.
-Recommended only for systems running with gang scheduling
+Recommended only for systems running with gang scheduling
(\fBSchedulerType=sched/gang\fR).
.RE
.TP
\fBState\fR
-State of partition or availability for use. Possible values
+State of partition or availability for use. Possible values
are "UP" or "DOWN". The default value is "UP".
.SH "Prolog and Epilog Scripts"
-There are a variety of prolog and epilog program options that
-execute with various permissions and at various times.
-The four options most likely to be used are:
+There are a variety of prolog and epilog program options that
+execute with various permissions and at various times.
+The four options most likely to be used are:
\fBProlog\fR and \fBEpilog\fR (executed once on each compute node
for each job) plus \fBPrologSlurmctld\fR and \fBEpilogSlurmctld\fR
(executed once on the \fBControlMachine\fR for each job).
-NOTE: Standard output and error messages are normally not preserved.
-Explicitly write output and error messages to an appropriate location
+NOTE: Standard output and error messages are normally not preserved.
+Explicitly write output and error messages to an appropriate location
if you which to preserve that information.
NOTE: The Prolog script is ONLY run on any individual
@@ -2279,11 +2279,11 @@ BlueGene partition name.
Available on BlueGene systems only.
.TP
\fBSLURM_JOB_ACCOUNT\fR
-Account name used for the job.
+Account name used for the job.
Available in \fBPrologSlurmctld\fR and \fBEpilogSlurmctld\fR only.
.TP
\fBSLURM_JOB_CONSTRAINTS\fR
-Features required to run the job.
+Features required to run the job.
Available in \fBPrologSlurmctld\fR and \fBEpilogSlurmctld\fR only.
.TP
\fBSLURM_JOB_GID\fR
@@ -2319,38 +2319,38 @@ User name of the job's owner.
.SH "NETWORK TOPOLOGY"
SLURM is able to optimize job allocations to minimize network contention.
-Special SLURM logic is used to optimize allocations on systems with a
+Special SLURM logic is used to optimize allocations on systems with a
three\-dimensional interconnect (BlueGene, Sun Constellation, etc.)
-and information about configuring those systems are available on
+and information about configuring those systems are available on
web pages available here: <https://computing.llnl.gov/linux/slurm/>.
-For a hierarchical network, SLURM needs to have detailed information
+For a hierarchical network, SLURM needs to have detailed information
about how nodes are configured on the network switches.
.LP
-Given network topology information, SLURM allocates all of a job's
-resources onto a single leaf of the network (if possible) using a best\-fit
+Given network topology information, SLURM allocates all of a job's
+resources onto a single leaf of the network (if possible) using a best\-fit
algorithm.
Otherwise it will allocate a job's resources onto multiple leaf switches
-so as to minimize the use of higher\-level switches.
+so as to minimize the use of higher\-level switches.
The \fBTopologyPlugin\fR parameter controls which plugin is used to
-collect network topology information.
-The only values presently supported are
-"topology/3d_torus" (default for IBM BlueGene, Sun Constellation and
+collect network topology information.
+The only values presently supported are
+"topology/3d_torus" (default for IBM BlueGene, Sun Constellation and
Cray XT systems, performs best\-fit logic over three\-dimensional topology),
-"topology/none" (default for other systems,
+"topology/none" (default for other systems,
best\-fit logic over one\-dimensional topology),
"topology/tree" (determine the network topology based
upon information contained in a topology.conf file,
see "man topology.conf" for more information).
Future plugins may gather topology information directly from the network.
-The topology information is optional.
+The topology information is optional.
If not provided, SLURM will perform a best\-fit algorithm assuming the
-nodes are in a one\-dimensional array as configured and the communications
+nodes are in a one\-dimensional array as configured and the communications
cost is related to the node distance in this array.
.SH "RELOCATING CONTROLLERS"
-If the cluster's computers used for the primary or backup controller
-will be out of service for an extended period of time, it may be
-desirable to relocate them.
+If the cluster's computers used for the primary or backup controller
+will be out of service for an extended period of time, it may be
+desirable to relocate them.
In order to do so, follow this procedure:
.LP
1. Stop the SLURM daemons
@@ -2361,20 +2361,20 @@ In order to do so, follow this procedure:
.br
4. Restart the SLURM daemons
.LP
-There should be no loss of any running or pending jobs.
-Insure that any nodes added to the cluster have the current
-slurm.conf file installed.
+There should be no loss of any running or pending jobs.
+Insure that any nodes added to the cluster have the current
+slurm.conf file installed.
.LP
-\fBCAUTION:\fR If two nodes are simultaneously configured as the
-primary controller (two nodes on which \fBControlMachine\fR specify
-the local host and the \fBslurmctld\fR daemon is executing on each),
+\fBCAUTION:\fR If two nodes are simultaneously configured as the
+primary controller (two nodes on which \fBControlMachine\fR specify
+the local host and the \fBslurmctld\fR daemon is executing on each),
system behavior will be destructive.
-If a compute node has an incorrect \fBControlMachine\fR or
-\fBBackupController\fR parameter, that node may be rendered
+If a compute node has an incorrect \fBControlMachine\fR or
+\fBBackupController\fR parameter, that node may be rendered
unusable, but no other harm will result.
.SH "EXAMPLE"
-.LP
+.LP
#
.br
# Sample /etc/slurm.conf for dev[0\-25].llnl.gov
@@ -2397,7 +2397,7 @@ BackupAddr=edev1
.br
AuthType=auth/munge
.br
-Epilog=/usr/local/slurm/epilog
+Epilog=/usr/local/slurm/epilog
.br
Prolog=/usr/local/slurm/prolog
.br
@@ -2501,8 +2501,8 @@ details.
.SH "SEE ALSO"
.LP
-\fBbluegene.conf\fR(5), \fBgethostbyname\fR(3),
-\fBgetrlimit\fR(2), \fBgroup\fR(5), \fBhostname\fR(1),
-\fBscontrol\fR(1), \fBslurmctld\fR(8), \fBslurmd\fR(8),
-\fBslurmdbd\fR(8), \fBslurmdbd.conf\fR(5), \fBsrun(1)\fR,
+\fBbluegene.conf\fR(5), \fBgethostbyname\fR(3),
+\fBgetrlimit\fR(2), \fBgroup\fR(5), \fBhostname\fR(1),
+\fBscontrol\fR(1), \fBslurmctld\fR(8), \fBslurmd\fR(8),
+\fBslurmdbd\fR(8), \fBslurmdbd.conf\fR(5), \fBsrun(1)\fR,
\fBspank(8)\fR, \fBsyslog\fR(2), \fBtopology.conf\fR(5), \fBwiki.conf\fR(5)
diff --git a/doc/man/man5/slurmdbd.conf.5 b/doc/man/man5/slurmdbd.conf.5
index f8998b2c74c..e810068ce78 100644
--- a/doc/man/man5/slurmdbd.conf.5
+++ b/doc/man/man5/slurmdbd.conf.5
@@ -1,21 +1,21 @@
.TH "slurmdbd.conf" "5" "February 2009" "slurmdbd.conf 2.0" "Slurm configuration file"
.SH "NAME"
-slurmdbd.conf \- Slurm Database Daemon (SlurmDBD) configuration file
+slurmdbd.conf \- Slurm Database Daemon (SlurmDBD) configuration file
.SH "DESCRIPTION"
-\fB/etc/slurmdb.conf\fP is an ASCII file which describes Slurm Database
+\fB/etc/slurmdb.conf\fP is an ASCII file which describes Slurm Database
Daemon (SlurmDBD) configuration information.
The file location can be modified at system build time using the
-DEFAULT_SLURM_CONF parameter.
+DEFAULT_SLURM_CONF parameter.
.LP
-The contents of the file are case insensitive except for the names of nodes
-and files. Any text following a "#" in the configuration file is treated
-as a comment through the end of that line.
+The contents of the file are case insensitive except for the names of nodes
+and files. Any text following a "#" in the configuration file is treated
+as a comment through the end of that line.
The size of each line in the file is limited to 1024 characters.
-Changes to the configuration file take effect upon restart of
+Changes to the configuration file take effect upon restart of
SlurmDbd or daemon receipt of the SIGHUP signal unless otherwise noted.
.LP
-This file should be only on the computer where SlurmDBD executes and
+This file should be only on the computer where SlurmDBD executes and
should only be readable by the user which executes SlurmDBD (e.g. "slurm").
This file should be protected from unauthorized access since it
contains a database password.
@@ -23,8 +23,8 @@ The overall configuration parameters available include:
.TP
\fBArchiveDir\fR
-If ArchiveScript is not set the slurmdbd will generate a text file that can be
-read in anytime with sacctmgr load filename. This directory is where the
+If ArchiveScript is not set the slurmdbd will generate a text file that can be
+read in anytime with sacctmgr load filename. This directory is where the
file will be placed archive has ran. Default is /tmp.
.TP
@@ -38,11 +38,11 @@ Boolean, yes to archive job data, no other wise. Default is no.
.TP
\fBArchiveScript\fR
This script is executed periodically in order to transfer accounting
-records out of the database into an archive. The script is executed
+records out of the database into an archive. The script is executed
with a no arguments, The following environment variables are set.
.RS
.TP
-\fBSLURM_ARCHIVE_EVENTS\fR
+\fBSLURM_ARCHIVE_EVENTS\fR
1 for archive events 0 otherwise.
.TP
\fBSLURM_ARCHIVE_LAST_EVENT\fR
@@ -54,13 +54,13 @@ Time of last event start to archive.
\fBSLURM_ARCHIVE_LAST_JOB\fR
Time of last job submit to archive.
.TP
-\fBSLURM_ARCHIVE_STEPS\fR
+\fBSLURM_ARCHIVE_STEPS\fR
1 for archive steps 0 otherwise.
.TP
\fBSLURM_ARCHIVE_LAST_STEP\fR
Time of last step start to archive.
.TP
-\fBSLURM_ARCHIVE_SUSPEND\fR
+\fBSLURM_ARCHIVE_SUSPEND\fR
1 for archive suspend data 0 otherwise.
.TP
\fBSLURM_ARCHIVE_LAST_SUSPEND\fR
@@ -78,126 +78,126 @@ Boolean, yes to archive suspend data, no other wise. Default is no.
.TP
\fBAuthInfo\fR
-Additional information to be used for authentication of communications
+Additional information to be used for authentication of communications
with the Slurm control daemon (slurmctld) on each cluster.
The interpretation of this option is specific to the configured \fBAuthType\fR.
-In the case of \fIauth/munge\fR, this can be configured to use a Munge daemon
-specifically configured to provide authentication between clusters while the
-default Munge daemon provides authentication within a cluster.
+In the case of \fIauth/munge\fR, this can be configured to use a Munge daemon
+specifically configured to provide authentication between clusters while the
+default Munge daemon provides authentication within a cluster.
In that case, this will specify the pathname of the socket to use.
-The default value is NULL, which results in the default authentication
+The default value is NULL, which results in the default authentication
mechanism being used.
.TP
\fBAuthType\fR
-Define the authentication method for communications between SLURM
-components.
-Acceptable values at present include "auth/none", "auth/authd",
+Define the authentication method for communications between SLURM
+components.
+Acceptable values at present include "auth/none", "auth/authd",
and "auth/munge".
-The default value is "auth/none", which means the UID included in
-communication messages is not verified.
-This may be fine for testing purposes, but
+The default value is "auth/none", which means the UID included in
+communication messages is not verified.
+This may be fine for testing purposes, but
\fBdo not use "auth/none" if you desire any security\fR.
"auth/authd" indicates that Brett Chun's authd is to be used (see
"http://www.theether.org/authd/" for more information).
"auth/munge" indicates that LLNL's Munge system is to be used
-(this is the best supported authentication mechanism for SLURM,
+(this is the best supported authentication mechanism for SLURM,
see "http://home.gna.org/munge/" for more information).
-SlurmDbd must be terminated prior to changing the value of \fBAuthType\fR
+SlurmDbd must be terminated prior to changing the value of \fBAuthType\fR
and later restarted.
.TP
\fBDbdBackupHost\fR
-The name of the machine where the backup Slurm Database Daemon is executed.
+The name of the machine where the backup Slurm Database Daemon is executed.
This host must have access to the same underlying database specified by
the 'Storage' options mentioned below.
This should be a node name without the full domain name. I.e., the hostname
-returned by the \fIgethostname()\fR function cut at the first dot (e.g. use
+returned by the \fIgethostname()\fR function cut at the first dot (e.g. use
"tux001" rather than "tux001.my.com").
.TP
\fBDbdHost\fR
-The name of the machine where the Slurm Database Daemon is executed.
+The name of the machine where the Slurm Database Daemon is executed.
This should be a node name without the full domain name. I.e., the hostname
-returned by the \fIgethostname()\fR function cut at the first dot (e.g. use
+returned by the \fIgethostname()\fR function cut at the first dot (e.g. use
"tux001" rather than "tux001.my.com"). This value must be specified.
.TP
\fBDbdPort\fR
-The port number that the Slurm Database Daemon (slurmdbd) listens
-to for work. The default value is SLURMDBD_PORT as established at system
+The port number that the Slurm Database Daemon (slurmdbd) listens
+to for work. The default value is SLURMDBD_PORT as established at system
build time. If none is explicitly specified, it will be set to 6819.
This value must be equal to the \fBSlurmDbdPort\fR parameter in the
slurm.conf file.
.TP
\fBDebugLevel\fR
-The level of detail to provide the Slurm Database Daemon's logs.
-Values from 0 to 9 are legal, with `0' being "quiet" operation and
+The level of detail to provide the Slurm Database Daemon's logs.
+Values from 0 to 9 are legal, with `0' being "quiet" operation and
`9' being insanely verbose.
The default value is 3.
.TP
\fBDefaultQOS\fR
-When adding a new cluster this will be used as the qos for the cluster
+When adding a new cluster this will be used as the qos for the cluster
unless something is explicitly set by the admin with the create.
-
+
.TP
\fBLogFile\fR
-Fully qualified pathname of a file into which the Slurm Database Daemon's
+Fully qualified pathname of a file into which the Slurm Database Daemon's
logs are written.
The default value is none (performs logging via syslog).
.TP
\fBMessageTimeout\fR
Time permitted for a round\-trip communication to complete
-in seconds. Default value is 10 seconds.
+in seconds. Default value is 10 seconds.
.TP
\fBPidFile\fR
-Fully qualified pathname of a file into which the Slurm Database Daemon
+Fully qualified pathname of a file into which the Slurm Database Daemon
may write its process ID. This may be used for automated signal processing.
The default value is "/var/run/slurmdbd.pid".
.TP
\fBPluginDir\fR
-Identifies the places in which to look for SLURM plugins.
-This is a colon\-separated list of directories, like the PATH
-environment variable.
+Identifies the places in which to look for SLURM plugins.
+This is a colon\-separated list of directories, like the PATH
+environment variable.
The default value is "/usr/local/lib/slurm".
.TP
\fBPrivateData\fR
This controls what type of information is hidden from regular users.
By default, all information is visible to all users.
-User \fBSlurmUser\fR, \fBroot\fR, and users with AdminLevel=Admin can always
+User \fBSlurmUser\fR, \fBroot\fR, and users with AdminLevel=Admin can always
view all information.
Multiple values may be specified with a comma separator.
Acceptable values include:
.RS
.TP
-\fBaccounts\fR
-prevents users from viewing any account definitions unless they are
+\fBaccounts\fR
+prevents users from viewing any account definitions unless they are
coordinators of them.
.TP
-\fBjobs\fR
+\fBjobs\fR
prevents users from viewing job records belonging
to other users unless they are coordinators of the association running the job
when using sacct.
.TP
-\fBreservations\fR
-restricts getting reservation information to users with operator status
+\fBreservations\fR
+restricts getting reservation information to users with operator status
and above.
.TP
-\fBusage\fR
-prevents users from viewing usage of any other user.
+\fBusage\fR
+prevents users from viewing usage of any other user.
This applys to sreport.
.TP
-\fBusers\fR
-prevents users from viewing information of any user
-other than themselves, this also makes it so users can only see
-associations they deal with.
-Coordinators can see associations of all users they are coordinator of,
+\fBusers\fR
+prevents users from viewing information of any user
+other than themselves, this also makes it so users can only see
+associations they deal with.
+Coordinators can see associations of all users they are coordinator of,
but can only see themselves when listing users.
.RE
@@ -224,7 +224,7 @@ If zero (default), then job step records are never purged.
.TP
\fBPurgeSuspendMonths\fR
-Records of individual suspend times for jobs over this age are purged from the
+Records of individual suspend times for jobs over this age are purged from the
database.
Aggregated information will be preserved indefinitely.
The time is a numeric value and is a number of months.
@@ -232,11 +232,11 @@ If zero (default), then job step records are never purged.
.TP
\fBSlurmUser\fR
-The name of the user that the \fBslurmctld\fR daemon executes as.
+The name of the user that the \fBslurmctld\fR daemon executes as.
This user must exist on the machine executing the Slurm Database Daemon
and have the same user ID as the hosts on which \fBslurmctld\fR execute.
For security purposes, a user other than "root" is recommended.
-The default value is "root".
+The default value is "root".
.TP
\fBStorageHost\fR
@@ -247,20 +247,20 @@ Ideally this should be the host on which slurmdbd executes.
.TP
\fBStorageBackupHost\fR
Define the name of the backup host the database is running where we are going
-to store the data. This can be viewed as a backup solution when the
-StorageHost is not responding. It is up to the backup solution to enforce the
-coherency of the accounting information between the two hosts. With clustered
+to store the data. This can be viewed as a backup solution when the
+StorageHost is not responding. It is up to the backup solution to enforce the
+coherency of the accounting information between the two hosts. With clustered
database solutions (acitve/passive HA), you would not need to use this feature.
Default is none.
.TP
\fBStorageLoc\fR
-Specify the name of the database as the location where accounting
+Specify the name of the database as the location where accounting
records are written.
.TP
\fBStoragePass\fR
-Define the password used to gain access to the database to store
+Define the password used to gain access to the database to store
the job accounting data.
.TP
@@ -271,7 +271,7 @@ with the database.
.TP
\fBStorageType\fR
Define the accounting storage mechanism type.
-Acceptable values at present include
+Acceptable values at present include
"accounting_storage/gold", "accounting_storage/mysql", and
"accounting_storage/pgsql".
The value "accounting_storage/gold" indicates that account records
@@ -279,13 +279,13 @@ will be written to Gold
(http://www.clusterresources.com/pages/products/gold-allocation-manager.php),
which maintains its own database.
The value "accounting_storage/mysql" indicates that accounting records
-should be written to a MySQL database specified by the
+should be written to a MySQL database specified by the
\fStorageLoc\fR parameter.
The value "accounting_storage/pgsql" indicates that accounting records
-should be written to a PostgreSQL database specified by the
-\fBStorageLoc\fR parameter. This plugin is not complete and
+should be written to a PostgreSQL database specified by the
+\fBStorageLoc\fR parameter. This plugin is not complete and
should not be used if wanting to use associations. It will however work with
-basic accounting of jobs and job steps. If interested in
+basic accounting of jobs and job steps. If interested in
completing please email slurm-dev@lists.llnl.gov.
This value must be specified.
@@ -296,11 +296,11 @@ with to store the job accounting data.
.TP
\fBTrackWCKey\fR
-Boolean yes or no. Used to set display and track of the Workload
+Boolean yes or no. Used to set display and track of the Workload
Characterization Key. Must be set to track wckey usage.
.SH "EXAMPLE"
-.LP
+.LP
#
.br
# Sample /etc/slurmdbd.conf
diff --git a/doc/man/man5/topology.conf.5 b/doc/man/man5/topology.conf.5
index e14eb927b6d..ef0c6f1590a 100644
--- a/doc/man/man5/topology.conf.5
+++ b/doc/man/man5/topology.conf.5
@@ -5,17 +5,17 @@ topology.conf \- Slurm configuration file for defining the network topology
.SH "DESCRIPTION"
\fB/etc/topology.conf\fP is an ASCII file which describes the
-cluster's network topology for optimized job resource allocation.
+cluster's network topology for optimized job resource allocation.
The file location can be modified at system build time using the
-DEFAULT_SLURM_CONF parameter. The file will always be located in the
-same directory as the \fBslurm.conf\fP file.
+DEFAULT_SLURM_CONF parameter. The file will always be located in the
+same directory as the \fBslurm.conf\fP file.
.LP
Paramter names are case insensitive.
-Any text following a "#" in the configuration file is treated
-as a comment through the end of that line.
+Any text following a "#" in the configuration file is treated
+as a comment through the end of that line.
The size of each line in the file is limited to 1024 characters.
-Changes to the configuration file take effect upon restart of
-SLURM daemons, daemon receipt of the SIGHUP signal, or execution
+Changes to the configuration file take effect upon restart of
+SLURM daemons, daemon receipt of the SIGHUP signal, or execution
of the command "scontrol reconfigure" unless otherwise noted.
.LP
The network topology configuration one one line defining a switch name and
@@ -47,7 +47,7 @@ The units used are arbitrary and this information is currently not used.
It may be used in the future to optimize resource allocations.
.SH "EXAMPLE"
-.LP
+.LP
.br
##################################################################
.br
diff --git a/doc/man/man5/wiki.conf.5 b/doc/man/man5/wiki.conf.5
index c7004b5fed3..e6f45689e3c 100644
--- a/doc/man/man5/wiki.conf.5
+++ b/doc/man/man5/wiki.conf.5
@@ -2,34 +2,34 @@
.SH "NAME"
wiki.conf \- Slurm configuration file for wiki and wiki2 scheduler plugins
.SH "DESCRIPTION"
-\fB/etc/wiki.conf\fP is an ASCII file which describes wiki and wiki2
-scheduler specific SLURM configuration information.
+\fB/etc/wiki.conf\fP is an ASCII file which describes wiki and wiki2
+scheduler specific SLURM configuration information.
The file location can be modified at system build time using the
-DEFAULT_SLURM_CONF parameter. The file will always be located in the
-same directory as the \fBslurm.conf\fP file.
+DEFAULT_SLURM_CONF parameter. The file will always be located in the
+same directory as the \fBslurm.conf\fP file.
.LP
Paramter names are case insensitive.
-Any text following a "#" in the configuration file is treated
-as a comment through the end of that line.
+Any text following a "#" in the configuration file is treated
+as a comment through the end of that line.
The size of each line in the file is limited to 1024 characters.
-Changes to the configuration file take effect upon restart of
-SLURM daemons, daemon receipt of the SIGHUP signal, or execution
+Changes to the configuration file take effect upon restart of
+SLURM daemons, daemon receipt of the SIGHUP signal, or execution
of the command "scontrol reconfigure" unless otherwise noted.
.LP
The overall configuration parameters available include:
.TP
\fBAuthKey\fR
-Authentication key for communications.
-This should be no more than a 32\-bit unsigned integer and match the
-KEY configured in the \fBmoab\-private.cnf\fR file (for the Moab Scheduler)
+Authentication key for communications.
+This should be no more than a 32\-bit unsigned integer and match the
+KEY configured in the \fBmoab\-private.cnf\fR file (for the Moab Scheduler)
or the \fB\-\-with-key=\fR value used to configure the Maui Scheduler.
.TP
\fBEHost\fR
Name the computer on which Moab server executes.
-It is used in establishing a communications path for event notification.
-By default \fBEHost\fR will be identical in value to the
+It is used in establishing a communications path for event notification.
+By default \fBEHost\fR will be identical in value to the
\fBControlAddr\fR configured in slurm.conf.
Not applicable to wiki plugin, only the wiki2 plugin.
@@ -43,44 +43,44 @@ Not applicable to wiki plugin, only the wiki2 plugin.
.TP
\fBEPort\fR
-Port to be used to notify Moab of events (job submitted to SLURM,
-job terminates, etc.).
+Port to be used to notify Moab of events (job submitted to SLURM,
+job terminates, etc.).
This numeric value should match EPORT configured in the
\fBmoab.cnf\fR file.
Not applicable to wiki plugin, only the wiki2 plugin.
.TP
\fBExcludePartitions\fR
-Identifies partitions whose jobs are to be scheduled directly
-by SLURM rather than Moab/Maui.
-This only effects jobs which are submitted using SLURM
+Identifies partitions whose jobs are to be scheduled directly
+by SLURM rather than Moab/Maui.
+This only effects jobs which are submitted using SLURM
commands (i.e. srun, salloc or sbatch, NOT msub from Moab).
-These jobs will be scheduled on a First\-Come\-First\-Served
-basis directly by SLURM.
-Note that SLURM recognizes jobs submitted via msub based
+These jobs will be scheduled on a First\-Come\-First\-Served
+basis directly by SLURM.
+Note that SLURM recognizes jobs submitted via msub based
upon the value \fBFirstJobId\fR configured in \fIslurm.conf\fR.
Set the values \fBMINJOBID\fR and \fBMAXJOBID\fR in \fImoab.cfg\fR
-accordingly.
+accordingly.
For example MINJOBID=1, MAXJOBID=65535 and FirstJobId=65536.
-Jobs submitted using msub will have job ID values in the range
+Jobs submitted using msub will have job ID values in the range
of 1 and 65535 while jobs submitted directly using SLURM commands
will have a job ID of 65536 or higher.
-Moab/Maui controls for resource reservation, fair share
+Moab/Maui controls for resource reservation, fair share
scheduling, etc. will not apply to the initiation of these jobs.
-While Moab/Maui will not control the initiation of jobs in these
+While Moab/Maui will not control the initiation of jobs in these
partitions, it will account for and report the jobs.
If more than one partition is to be scheduled directly by
SLURM, use a comma separator between their names.
-This may provide faster response times than Moab/Maui scheduling.
+This may provide faster response times than Moab/Maui scheduling.
.TP
\fBHidePartitionJobs\fR
Identifies partitions whose jobs are not to be reported to Moab/Maui.
These jobs will not be accounted for or otherwise visible to Moab/Maui.
Any partitions listed here must also be listed in \fBExcludePartitions\fR.
-This only effects jobs which are submitted using SLURM commands (i.e.
+This only effects jobs which are submitted using SLURM commands (i.e.
\fIsrun\fR, \fIsalloc\fR or \fIsbatch\fR, NOT \fImsub\fR from Moab).
-If more than one partition is to have its jobs hidden, use a comma
+If more than one partition is to have its jobs hidden, use a comma
separator between their names.
.TP
@@ -94,7 +94,7 @@ No data compression. Each host name is listed individually.
.TP
\fB1\fR
SLURM hostlist expressions are exchanged with task counts
-(e.g. "tux[0\-16]*2") in job state information and job
+(e.g. "tux[0\-16]*2") in job state information and job
initiation requests.
.TP
\fB2\fR
@@ -103,19 +103,19 @@ SLURM hostlist expressions are used to report node state information.
.TP
\fBJobAggregationTime\fR
-This is used to avoid notifying Moab of large numbers of events
+This is used to avoid notifying Moab of large numbers of events
occuring about the same time.
-If an event occurs within this number of seconds since Moab was
+If an event occurs within this number of seconds since Moab was
last notified of an event, another notification is not sent.
This should be an integer number of seconds.
The default value is 10 seconds.
-The value should match JOBAGGREGATIONTIME configured in the
+The value should match JOBAGGREGATIONTIME configured in the
\fBmoab.cnf\fR file.
Not applicable to wiki plugin, only the wiki2 plugin.
.TP
\fBJobPriority\fR
-Controls initial job priority.
+Controls initial job priority.
The default value is "hold".
Not applicable to wiki plugin, only the wiki2 plugin.
.RS
@@ -128,7 +128,7 @@ Hold all incomming jobs until Moab or Maui tell them to run
.RE
.SH "EXAMPLE"
-.LP
+.LP
.br
##################################################################
.br
@@ -164,7 +164,7 @@ EHost=tux0
.br
EHostBackup=tux1
.br
-# Moab event notifcation throttle, matches JOBAGGREGATIONTIME
+# Moab event notifcation throttle, matches JOBAGGREGATIONTIME
.br
# in moab.cfg (integer value in seconds)
.br
diff --git a/doc/man/man8/slurmctld.8 b/doc/man/man8/slurmctld.8
index 43b852b9373..f77b143e958 100644
--- a/doc/man/man8/slurmctld.8
+++ b/doc/man/man8/slurmctld.8
@@ -4,22 +4,22 @@ slurmctld \- The central management daemon of Slurm.
.SH "SYNOPSIS"
\fBslurmctld\fR [\fIOPTIONS\fR...]
.SH "DESCRIPTION"
-\fBslurmctld\fR is the central management daemon of Slurm. It monitors
-all other Slurm daemons and resources, accepts work (jobs), and allocates
-resources to those jobs. Given the critical functionality of \fBslurmctld\fR,
-there may be a backup server to assume these functions in the event that
-the primary server fails.
+\fBslurmctld\fR is the central management daemon of Slurm. It monitors
+all other Slurm daemons and resources, accepts work (jobs), and allocates
+resources to those jobs. Given the critical functionality of \fBslurmctld\fR,
+there may be a backup server to assume these functions in the event that
+the primary server fails.
.TP
OPTIONS
.TP
\fB\-c\fR
-Clear all previous \fBslurmctld\fR state from its last checkpoint.
-If not specified, previously running jobs will be preserved along
-with the state of DOWN, DRAINED and DRAINING nodes and the associated
+Clear all previous \fBslurmctld\fR state from its last checkpoint.
+If not specified, previously running jobs will be preserved along
+with the state of DOWN, DRAINED and DRAINING nodes and the associated
reason field for those nodes.
.TP
\fB\-D\fR
-Debug mode. Execute \fBslurmctld\fR in the foreground with logging to stdout.
+Debug mode. Execute \fBslurmctld\fR in the foreground with logging to stdout.
.TP
\fB\-f <file>\fR
Read configuration from the specified file. See \fBNOTES\fR below.
diff --git a/doc/man/man8/slurmd.8 b/doc/man/man8/slurmd.8
index e81a7a57f0c..6cfde1df931 100644
--- a/doc/man/man8/slurmd.8
+++ b/doc/man/man8/slurmd.8
@@ -7,14 +7,14 @@ slurmd \- The compute node daemon for SLURM.
\fBslurmd\fR [\fIOPTIONS\fR...]
.SH "DESCRIPTION"
-\fBslurmd\fR is the compute node daemon of Slurm. It monitors all tasks
-running on the compute node , accepts work (tasks), launches tasks, and kills
+\fBslurmd\fR is the compute node daemon of Slurm. It monitors all tasks
+running on the compute node , accepts work (tasks), launches tasks, and kills
running tasks upon request.
.TP
OPTIONS
.TP
\fB\-c\fR
-Clear system locks as needed. This may be required if \fBslurmd\fR terminated
+Clear system locks as needed. This may be required if \fBslurmd\fR terminated
abnormally.
.TP
\fB\-d <file>\fR
diff --git a/doc/man/man8/slurmdbd.8 b/doc/man/man8/slurmdbd.8
index 0a3f377f011..df8725ada3c 100644
--- a/doc/man/man8/slurmdbd.8
+++ b/doc/man/man8/slurmdbd.8
@@ -12,7 +12,7 @@ for Slurm. This is particularly useful for archiving accounting records.
OPTIONS
.TP
\fB\-D\fR
-Debug mode. Execute \fBslurmdbd\fR in the foreground with logging to stdout.
+Debug mode. Execute \fBslurmdbd\fR in the foreground with logging to stdout.
.TP
\fB\-h\fR
Help; print a brief summary of command options.
diff --git a/doc/man/man8/slurmstepd.8 b/doc/man/man8/slurmstepd.8
index 3a81beca981..3bbd3a711a7 100644
--- a/doc/man/man8/slurmstepd.8
+++ b/doc/man/man8/slurmstepd.8
@@ -4,11 +4,11 @@ slurmstepd \- The job step manager for SLURM.
.SH "SYNOPSIS"
\fBslurmstepd\fR
.SH "DESCRIPTION"
-\fBslurmstepd\fR is a job step manager for SLURM.
-It is spawned by the \fBslurmd\fR daemon when a job step is launched
-and terminates when the job step does.
+\fBslurmstepd\fR is a job step manager for SLURM.
+It is spawned by the \fBslurmd\fR daemon when a job step is launched
+and terminates when the job step does.
It is responsible for managing input and output (stdin, stdout and stderr)
-for the job step along with its accounting and signal processing.
+for the job step along with its accounting and signal processing.
\fBslurmstepd\fR should not be initiated by users or system administrators.
.SH "COPYING"
Copyright (C) 2006 The Regents of the University of California.
diff --git a/doc/man/man8/spank.8 b/doc/man/man8/spank.8
index e159add109a..237f0b36527 100644
--- a/doc/man/man8/spank.8
+++ b/doc/man/man8/spank.8
@@ -1,14 +1,14 @@
.TH "SPANK" "8" "June 2009" "SPANK" "SLURM plug\-in architecture for Node and job (K)control"
.SH "NAME"
-\fBSPANK\fR \- SLURM Plug\-in Architecture for Node and job (K)control
+\fBSPANK\fR \- SLURM Plug\-in Architecture for Node and job (K)control
.SH "DESCRIPTION"
This manual briefly describes the capabilities of the SLURM Plug\-in
architecture for Node and job Kontrol (\fBSPANK\fR) as well as the \fBSPANK\fR
configuration file: (By default: \fBplugstack.conf\fP.)
.LP
-\fBSPANK\fR provides a very generic interface for stackable plug\-ins
+\fBSPANK\fR provides a very generic interface for stackable plug\-ins
which may be used to dynamically modify the job launch code in
SLURM. \fBSPANK\fR plugins may be built without access to SLURM source
code. They need only be compiled against SLURM's \fBspank.h\fR header file,
@@ -45,7 +45,7 @@ Plugins may query the context in which they are running with the
\fBSPANK\fR plugins may be called from multiple points during the SLURM job
launch. A plugin may define the following functions:
.TP 2
-\fBslurm_spank_init\fR
+\fBslurm_spank_init\fR
Called just after plugins are loaded. In remote context, this is just
after job step is initialized. This function is called before any plugin
option processing.
@@ -59,30 +59,30 @@ the \fBinit\fR callback, then process user options, and finally take some
action in \fBslurm_spank_init_post_opt\fR if necessary.
.TP
\fBslurm_spank_local_user_init\fR
-Called in local (\fBsrun\fR) context only after all
-options have been processed.
+Called in local (\fBsrun\fR) context only after all
+options have been processed.
This is called after the job ID and step IDs are available.
-This happens in \fBsrun\fR after the allocation is made, but before
+This happens in \fBsrun\fR after the allocation is made, but before
tasks are launched.
.TP
-\fBslurm_spank_user_init\fR
+\fBslurm_spank_user_init\fR
Called after privileges are temporarily dropped. (remote context only)
.TP
\fBslurm_spank_task_init_privileged\fR
Called for each task just after fork, but before all elevated privileges
are dropped. (remote context only)
.TP
-\fBslurm_spank_task_init\fR
+\fBslurm_spank_task_init\fR
Called for each task just before execve(2). (remote context only)
.TP
-\fBslurm_spank_task_post_fork\fR
+\fBslurm_spank_task_post_fork\fR
Called for each task from parent process after fork(2) is complete.
Due to the fact that \fBslurmd\fR does not exec any tasks until all
tasks have completed fork(2), this call is guaranteed to run before
the user task is executed. (remote context only)
.TP
\fBslurm_spank_task_exit\fR
-Called for each task as its exit status is collected by SLURM.
+Called for each task as its exit status is collected by SLURM.
(remote context only)
.TP
\fBslurm_spank_exit\fR
@@ -115,7 +115,7 @@ which has the following prototype:
.LP
The return value is 1 if the symbol is supported, 0 if not.
.LP
-\fBSPANK\fR plugins do not have direct access to internally defined SLURM
+\fBSPANK\fR plugins do not have direct access to internally defined SLURM
data structures. Instead, information about the currently executing
job is obtained via the \fBspank_get_item\fR function call.
.nf
@@ -155,12 +155,12 @@ searches the job's environment for the environment variable
of length \fIlen\fR. \fBspank_setenv\fR allows a \fBSPANK\fR
plugin to set or overwrite a variable in the job's environment,
and \fBspank_unsetenv\fR unsets an environment variable in
-the job's environment. The prototypes are:
+the job's environment. The prototypes are:
.nf
- spank_err_t \fBspank_getenv\fR (spank_t spank, const char *var,
+ spank_err_t \fBspank_getenv\fR (spank_t spank, const char *var,
char *buf, int len);
- spank_err_t \fBspank_setenv\fR (spank_t spank, const char *var,
+ spank_err_t \fBspank_setenv\fR (spank_t spank, const char *var,
const char *val, int overwrite);
spank_err_t \fBspank_unsetenv\fR (spank_t spank, const char *var);
.fi
@@ -169,21 +169,21 @@ These are only necessary in remote context since modifications of
the standard process environment using \fBsetenv\fR(3), \fBgetenv\fR(3),
and \fBunsetenv\fR(3) may be used in local context.
.LP
-Functions are also available from within the \fBSPANK\fR plugins to
-establish environment variables to be exported to the SLURM
-\fBPrologSlurmctld\fR, \fBProlog\fR, \fBEpilog\fR and \fBEpilogSlurmctld\fR
+Functions are also available from within the \fBSPANK\fR plugins to
+establish environment variables to be exported to the SLURM
+\fBPrologSlurmctld\fR, \fBProlog\fR, \fBEpilog\fR and \fBEpilogSlurmctld\fR
programs. While designed for \fBSPANK\fR plugin use, hackers could
insert arbitrary environment variables, so their use by the various
prolog and epilog programs should avoid possible security compromises.
SLURM does block the setting of LD_PRELOAD and PATH as a precausionary measure.
-These environment variables are not otherwise visible
-to the job or \fBSPANK\fR functions.
-These environment variable functons may only called from the local contact.
-The syntax of these functions is identical to the getenv,
+These environment variables are not otherwise visible
+to the job or \fBSPANK\fR functions.
+These environment variable functons may only called from the local contact.
+The syntax of these functions is identical to the getenv,
setenv, and unsetenv functions respectively:
.nf
char *\fBspank_get_job_env\fR(const char *name);
- int \fBspank_set_job_env\fR(const char *name, const char *value,
+ int \fBspank_set_job_env\fR(const char *name, const char *value,
int overwrite);
int \fBspank_unset_job_env\fR(const char *name);
.fi
@@ -219,12 +219,12 @@ a \fBstruct spank_option\fR which is declared in \fB<slurm/spank.h>\fR as
.nf
struct spank_option {
- char * name;
+ char * name;
char * arginfo;
- char * usage;
+ char * usage;
int has_arg;
- int val;
- spank_opt_cb_f cb;
+ int val;
+ spank_opt_cb_f cb;
};
.fi
@@ -241,7 +241,7 @@ an argument.
.TP
.I usage
is a short description of the option suitable for \-\-help output.
-.TP
+.TP
.I has_arg
0 if option takes an argument, 1 if option takes no argument, and
2 if the option takes an optional argument. (See \fBgetopt_long\fR(3)).
@@ -251,26 +251,26 @@ A plugin\-local value to return to the option callback function.
.TP
.I cb
A callback function that is invoked when the plugin option is
-registered with SLURM. \fBspank_opt_cb_f\fR is typedef'd in
-\fB<slurm/spank.h>\fR as
+registered with SLURM. \fBspank_opt_cb_f\fR is typedef'd in
+\fB<slurm/spank.h>\fR as
.nf
- typedef int (*spank_opt_cb_f) (int val, const char *optarg,
+ typedef int (*spank_opt_cb_f) (int val, const char *optarg,
int remote);
.fi
Where \fIval\fR is the value of the \fIval\fR field in the \fBspank_option\fR
struct, \fIoptarg\fR is the supplied argument if applicable, and \fIremote\fR
-is 0 if the function is being called from the "local" host
+is 0 if the function is being called from the "local" host
(e.g. \fBsrun\fR) or 1 from the "remote" host (\fBslurmd\fR).
.LP
Plugin options may be registered with SLURM using
the \fBspank_option_register\fR function. This function is only valid
-when called from the plugin's \fBslurm_spank_init\fR handler, and
+when called from the plugin's \fBslurm_spank_init\fR handler, and
registers one option at a time. The prototype is
.nf
- spank_err_t spank_option_register (spank_t sp,
+ spank_err_t spank_option_register (spank_t sp,
struct spank_option *opt);
.fi
@@ -299,7 +299,7 @@ the use of \fBspank_option_register\fR is preferred. When using the
filled with zeros. A \fBSPANK_OPTIONS_TABLE_END\fR macro is provided
in \fB<slurm/spank.h>\fR for this purpose.
.LP
-When an option is provided by the user on the local side, \fBSLURM\fR will
+When an option is provided by the user on the local side, \fBSLURM\fR will
immediately invoke the option's callback with \fIremote\fR=0. This
is meant for the plugin to do local sanity checking of the option before
the value is sent to the remote side during job launch. If the argument
@@ -317,12 +317,12 @@ functionality based on the value of user\-provided options.
The default \fBSPANK\fR plug\-in stack configuration file is
\fBplugstack.conf\fR in the same directory as \fBslurm.conf\fR(5),
though this may be changed via the SLURM config parameter
-\fIPlugStackConfig\fR. Normally the \fBplugstack.conf\fR file
+\fIPlugStackConfig\fR. Normally the \fBplugstack.conf\fR file
should be identical on all nodes of the cluster.
The config file lists \fBSPANK\fR plugins,
one per line, along with whether the plugin is \fIrequired\fR or
\fIoptional\fR, and any global arguments that are to be passed to
-the plugin for runtime configuration. Comments are preceded with '#'
+the plugin for runtime configuration. Comments are preceded with '#'
and extend to the end of the line. If the configuration file
is missing or empty, it will simply be ignored.
.LP
@@ -369,7 +369,7 @@ a spank plugin stack.
The \fBSPANK\fR config file is re\-read on each job launch, so editing
the config file will not affect running jobs. However care should
be taken so that a partially edited config file is not read by a
-launching job.
+launching job.
.SH "EXAMPLES"
.LP
@@ -382,19 +382,19 @@ Simple \fBSPANK\fR config file:
# required? plugin args
#
optional renice.so min_prio=\-10
-required /usr/lib/slurm/test.so
+required /usr/lib/slurm/test.so
.fi
.LP
The following is a simple \fBSPANK\fR plugin to modify the nice value
-of job tasks. This plugin adds a \-\-renice=[prio] option to \fBsrun\fR
+of job tasks. This plugin adds a \-\-renice=[prio] option to \fBsrun\fR
which users can use to set the priority of all remote tasks. Priority may
also be specified via a SLURM_RENICE environment variable. A minimum
priority may be established via a "min_prio" parameter in \fBplugstack.conf\fR
(See above for example).
.nf
-/*
+/*
* To compile:
* gcc \-shared \-o renice.so renice.c
*
@@ -453,7 +453,7 @@ int slurm_spank_init (spank_t sp, int ac, char **av)
for (i = 0; i < ac; i++) {
if (strncmp ("min_prio=", av[i], 9) == 0) {
const char *optarg = av[i] + 9;
- if (_str2prio (optarg, &min_prio) < 0)
+ if (_str2prio (optarg, &min_prio) < 0)
slurm_error ("Ignoring invalid min_prio value: %s", av[i]);
}
else {
@@ -474,7 +474,7 @@ int slurm_spank_task_post_fork (spank_t sp, int ac, char **av)
int taskid;
if (prio == PRIO_NOT_SET) {
- /*
+ /*
* See if SLURM_RENICE env var is set by user
*/
char val [1024];
@@ -488,11 +488,11 @@ int slurm_spank_task_post_fork (spank_t sp, int ac, char **av)
}
if (prio < min_prio)
- slurm_error ("%s=%d not allowed, using min=%d",
+ slurm_error ("%s=%d not allowed, using min=%d",
PRIO_ENV_VAR, prio, min_prio);
}
- if (prio < min_prio)
+ if (prio < min_prio)
prio = min_prio;
spank_get_item (sp, S_TASK_GLOBAL_ID, &taskid);
@@ -514,7 +514,7 @@ static int _str2prio (const char *str, int *p2int)
char *p;
l = strtol (str, &p, 10);
- if ((*p != '\0') || (l < \-20) || (l > 20))
+ if ((*p != '\0') || (l < \-20) || (l > 20))
return (\-1);
*p2int = (int) l;
@@ -528,14 +528,14 @@ static int _renice_opt_process (int val, const char *optarg, int remote)
slurm_error ("renice: invalid argument!");
return (\-1);
}
-
+
if (_str2prio (optarg, &prio) < 0) {
slurm_error ("Bad value for \-\-renice: %s", optarg);
return (\-1);
}
- if (prio < min_prio)
- slurm_error ("\-\-renice=%d not allowed, will use min=%d",
+ if (prio < min_prio)
+ slurm_error ("\-\-renice=%d not allowed, will use min=%d",
prio, min_prio);
return (0);
--
GitLab