Newer
Older
This file describes changes in recent versions of SLURM. It primarily
documents those changes that are of interest to users and admins.
* Changes in SLURM 2.2.0.pre0
=============================
-- Added SLURM_VERSION_NUMBER and removed SLURM_API_VERSION from slurm/slurm.h.
* Changes in SLURM 2.1.1
=============================
Danny Auble
committed
-- Fix for case sensitive databases when a slurmctld has a mixed case
clustername to lower case the string to easy compares.
Danny Auble
committed
-- Fix squeue if job is completing and failed to print remaining
nodes instead of failed message.
-- Fix sview core when searching for partitions by state.
Danny Auble
committed
-- Fixed setting the start time when querying in sacct to the
beginning of the day if not set previously.
-- Defined slurm_free_reservation_info_msg and slurm_free_topo_info_msg
in common/slurm_protocol_defs.h
-- Improve sview layout of blocks in use.
-- A user can now change the dimensions of the grid in sview.
-- BLUEGENE - improved startup speed further for large numbers of defined
blocks
-- Fix to _get_job_min_nodes() in wiki2/get_jobs.c suggested by Michal Novotny
-- BLUEGENE - fixed issues when updating a pending job when a node
count was incorrect for the asked for connection type.
Danny Auble
committed
-- BLUEGENE - fixed issue when combining blocks that are in ready states to
make a larger block from those or make multiple smaller blocks by
splitting the larger block. Previously this would only work with block
in a free state.
Danny Auble
committed
-- Fix bug in wiki(2) plugins where if HostFormat=2 and the task list is
greater than 64 we don't truncate. Previously this would mess up Moab
by sending a truncated task list when doing a get jobs.
-- Added update slurmctld debug level to sview when in admin mode.
-- Added logic to make sure if enforcing a memory limit when using the
jobacct_gather plugin a user can no longer turn off the logic to enforce
the limit.
-- Replaced many calls to getpwuid() with reentrant uid_to_string()
Danny Auble
committed
-- The slurmstepd will now refresh it's log file handle on a reconfig,
previously if a log was rolled any output from the stepd was lost.
* Changes in SLURM 2.1.0-pre9
=============================
-- Added the "scontrol update SlurmctldDebug" as the preferred alternative to
the "scontrol setdebug" command.
Danny Auble
committed
-- BLUEGENE - made it so when removing a block in an error state the nodes in
the block are set correctly in accounting as not in error.
Danny Auble
committed
-- Fixed issue where if slurmdbd is not up qos' are set up correctly for
-- scontrol, squeue, sview all display the correct node, cpu count along with
correct corresponding nodelist on completing jobs.
-- Patch (Mark Grondona) fixes serious security vulnerability in SLURM in
the spank_job_env functionality.
-- Improve spank_job_env interface and documentation
-- Add ESPANK_NOT_LOCAL error code to spank_err_t
-- Made the #define DECAY_INTERVAL used in the priority/multifactor plugin
a slurm.conf variable (PriorityCalcPeriod)
Danny Auble
committed
-- Added new macro SLURM_VERSION for use in autoconf scripts to determine
current version of slurm installed on system when building against the api.
-- Patch from Matthieu Hautreux that adds an entry into the error file when
a job or step receives a TERM or KILL signal.
Danny Auble
committed
-- Make it so env var SLURM_SRUN_COMM_HOST is overwritten if already in
* Changes in SLURM 2.1.0-pre8
=============================
-- Rearranged the "scontrol show job" output into functional groupings
-- Change the salloc/sbatch/srun -P option to -d (dependency)
-- Removed the srun -d option; must use srun --slurmd-debug instead
-- When running the mysql plugin natively MUNGE errors are now eliminated
when sending updates to slurmctlds.
-- Check to make sure we have a default account before looking to
fill in default association.
-- Accounting - Slurmctld and slurmdbd will now set uids of users which were
created after the start of the daemons on reconfig. Slurmdbd will
attempt to set previously non-existant uids every hour.
Danny Auble
committed
-- Patch from Aaron Knister and Mark Grondona, to parse correctly quoted
#SBATCH options in a batch script.
-- job_desc_msg_t - in, out, err have been changed to std_in, std_out,
and std_err respectfully. Needed for PySLURM, since Python sees (in)
as a keyword.
-- Changed the type of addr to struct sockaddr_in in _message_socket_accept()
Danny Auble
committed
in sattach.c, step_launch.c, and allocate_msg.c, and moved the function
into a common place for all the calls since the code was very similar.
-- proctrack/lua support has been added see contribs/lua/protrack.lua
-- replaced local gtk m4 test with AM_PATH_GTK_2_0
-- changed AC_CHECK_LIB to AC_SEARCH_LIBS to avoid extra libs in
compile lines.
-- Patch from Matthieu Hautreux to improve error message in slurmd/req.c
-- Added support for split groups from (Matthiu Hautreux CEA)
-- Patch from Mark Grondona to move blcr scripts into pkglibexecdir
-- Patch from Doug Parisek to calculate a job's projected start time under the
builtin scheduler.
-- Removed most global variables out of src/common/jobacct_common.h
* Changes in SLURM 2.1.0-pre7
=============================
Danny Auble
committed
-- BLUEGENE - make 2.1 run correctly on a real bluegene cluster
-- sacctmgr - Display better debug for when an admin specifies a non-existant
Danny Auble
committed
parent account when changing parent accounts.
-- Added a mechanism to the slurmd to defer the epilog from starting until
after a running prolog has finished.
-- If a node reboots inbetween checking status the node is marked down unless
ReturnToService=2
Danny Auble
committed
-- Added -R option to slurmctld to recover partition state also when
restarting or reconfiguring.
* Changes in SLURM 2.1.0-pre6
=============================
-- When getting information about nodes in hidden partitions, return a node
name of NULL rather than returning no information about the node so that
node index information is still valid.
-- When querying database for jobs in certain state and a time period is
Danny Auble
committed
given only jobs in that state during the period will be returned,
previously if a time period was given in sacct jobs eligible to run or
running would be displayed, which is still the default if no states are
requested.
-- One can now query jobs based on size (nodes and or cpus) (mysql plugin only)
Don Lipari
committed
-- Applied patch from Mark Grondona that tests for a missing config file before
any other processing in spank_init(). This now prevents fatal errors from
being mistakenly treated as recoverable.
-- --enable-debug no longer has to be stated at configure time to have
the slurmctld or slurmstepd dump core on a seg fault.
-- Moved the errant slurm_job_node_ready() declaration from job_info.h to
slurm.h and deleted job_info.h.
slurm_job_cpus_allocated_on_node() API for working with the
job_resources_t structure.
Danny Auble
committed
-- BLUEGENE - speed up start up for systems that have many blocks (100+)
configured on the system.
Danny Auble
committed
* Changes in SLURM 2.1.0-pre5
=============================
-- Add squeue option "--start" to report expected start time of pending jobs.
-- Sched/backfill plugin modified to set expected start time of pending jobs.
-- Add SchedulerParameters option of "max_job_bf=#" to control how far down
the queue of pending jobs that SLURM searches in an attempt backfill
schedule them. The default value is 50 jobs.
-- Fixed cause of squeue -o "%C" seg fault.
-- Add -"-signal=<int>@<time>" option to salloc, sbatch and srun commands to
notify programs before reaching the end of their time limit.
-- Add scontrol option to update a running job's EndTime (also resets the
job's time limit).
-- Add new job wait reason, ReqNodeNotAvail: Required node is not available
(down or drained).
-- Log when slurmctld or slurmd are started with small core file limit.
-- Permit job's owner to change features, processor count, minimum and
maximun node counts of pending jobs (the operation was previously
restricted to user root)
-- Applied patch from Chuck Clouston for scontrol man page with clarifications
and additional info
-- Change slurm errno name from ESLURM_TOO_MANY_REQUESTED_NODES to
ESLURM_INVALID_NODE_COUNT to better reflect its meaning.
-- Fix bug in sched/backfill which could result in invalid memory reference
when trying to schedule jobs submitted with --exclude option.
-- Fix for slurmctld deadlock at startup with PreemptMode=SUSPEND,GANG.
-- Completely disable logging of sched/wiki and sched/wiki2 (Maui & Moab)
message traffic unless DebugFlag=Wiki is configured.
-- Change scontrol show job info: ReqProcs (number of processors requested)
is replaced by NumProcs (number of processors requested or actually
allocated) and ReqNodes (number of nodes requested) is replaced by
NumNodes (number of nodes requested or actually allocated).
Danny Auble
committed
-- Fixed issue when max nodes wasn't specified and was later set by limit
to not request that as the actual maximum.
-- Move job preemption (for requeue, checkpoint and kill modes only) out of
gang scheduling module. Make identification of preemptable jobs an argument
to the select_g_job_test function rather than calling preempt plugin from
the select plugin. Make output of srun --test-only option include a list
of preempted job IDs.
-- Better record keeping for front end systems when registering.
-- Enable memory allocation logic for jobs step (i.e. allocate resources
within the job's memory allocation and enforce limits).
-- sview and "scontrol show config" now report as SLURM_VERSION the version
of slurmctld rather than that of the command.
-- Change SuspendTime configuration parameter from 16-bits to 32-bits.
-- Add environment variable support to sattach, salloc, sbatch and srun
to permit user control over exit codes so application exit codes can be
distiguished from those generated by SLURM. SLURM_EXIT_ERROR specifies the
exit code when a SLURM error occurs. SLURM_EXIT_IMMEDIATE specifies the
exit code when the --immediate option is specified and resources are not
available. Any other non-zero exit code would be that of the application
run by SLURM.
-- Added a Quality of Service (QOS) html page.
-- In sched/wiki2, JOBWILLRUN command, add support for identification of
preemptable and preempted jobs (both new and old format of commands are
supported).
-- Remove contribs/python/hostlist files. Download the materials as needed
directly from http://www.nsc.liu.se/~kent/python-hostlist.
-- BLUEGENE - Preemption now works on bluegene systems
-- For salloc, sbatch and srun commands, ignore _maximum_ values for
--sockets-per-node, --cores-per-socket and --threads-per-core options.
Remove --mincores, --minsockets, --minthreads options (map them to
minimum values of -sockets-per-node, --cores-per-socket and
--threads-per-core for now).
Loading
Loading full blame...