From f84107d1fa019ba321ba999273a6ecc89c6cfd69 Mon Sep 17 00:00:00 2001 From: Gennaro Oliva <oliva.g@na.icar.cnr.it> Date: Fri, 22 May 2015 15:07:23 -0700 Subject: [PATCH] Man pages fixes. --- doc/man/man1/scontrol.1 | 4 ++++ doc/man/man5/slurm.conf.5 | 4 ++-- 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/doc/man/man1/scontrol.1 b/doc/man/man1/scontrol.1 index 8f032522558..c170a480c2d 100644 --- a/doc/man/man1/scontrol.1 +++ b/doc/man/man1/scontrol.1 @@ -779,11 +779,13 @@ The list of nodes allocated to the job. The NodeIndices expose the internal indices into the node table associated with the node(s) allocated to the job. .TP +.na \fINtasksPerN:B:S:C\fP= <tasks_per_node>:<tasks_per_baseboard>:<tasks_per_socket>:<tasks_per_core> Specifies the number of tasks to be started per hardware component (node, baseboard, socket and core). Unconstrained values may be shown as "0" or "*". +.ad .TP \fIPreemptTime\fP Time at which job was signaled that it was selected for preemption. @@ -796,10 +798,12 @@ Time the job ran prior to last suspend. \fIReason\fP The reason job is not running: e.g., waiting "Resources". .TP +.na \fIReqB:S:C:T\fP= <baseboard_count>:<socket_per_baseboard_count>:<core_per_socket_count>:<thread_per_core_count> Specifies the count of various hardware components requested by the job. Unconstrained values may be shown as "0" or "*". +.ad .TP \fISecsPreSuspend\fP=<seconds> If the job is suspended, this is the run time accumulated by the job diff --git a/doc/man/man5/slurm.conf.5 b/doc/man/man5/slurm.conf.5 index ab624031937..5f308676034 100644 --- a/doc/man/man5/slurm.conf.5 +++ b/doc/man/man5/slurm.conf.5 @@ -1283,8 +1283,8 @@ May not exceed 65533. .TP \fBMemLimitEnforce\fR If set to "no" then Slurm will not terminate the job or the job step -if they exceeds the value requested using the --mem-per-cpu option of -salloc/sbatch/srun. This is useful if jobs need to specify --mem-per-cpu +if they exceeds the value requested using the \-\-mem\-per\-cpu option of +salloc/sbatch/srun. This is useful if jobs need to specify \-\-mem\-per\-cpu for scheduling but they should not be terminate if they exceed the estimated value. The default value is 'yes', terminate the job/step if exceed the requested memory. -- GitLab