diff --git a/doc/man/man1/salloc.1 b/doc/man/man1/salloc.1 index 4da4bddb9982885a4ec492f680ac32edc81b7788..07b2eabcefed541a983963c34f52dec6842f4f31 100644 --- a/doc/man/man1/salloc.1 +++ b/doc/man/man1/salloc.1 @@ -1,4 +1,4 @@ -.TH "salloc" "1" "SLURM 1.3" "April 2008" "SLURM Commands" +.TH "salloc" "1" "SLURM 1.3" "May 2008" "SLURM Commands" .SH "NAME" .LP salloc \- Obtain a SLURM job allocation (a set of nodes), execute a command, and then release the allocation when the command is finished. @@ -352,12 +352,13 @@ partition, the job will be rejected. .TP \fB\-n\fR, \fB\-\-ntasks\fR[=]<\fInumber\fR> -salloc does not launch tasks, it requests an allocation of resources and submits -a batch script. However this \-\-tasks option advizes the SLURM controller -that job steps run within this allocation will launch a maximum of \fInumber\fR -tasks. This option, possibly with collaboration with the \-\-cpus\-per\-task -option, will directly impact the number of processors granted to the job -allocation. +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 +that the \fB\-\-cpus\-per\-task\fR option will change this default. .TP \fB\-\-nice\fR[=]<\fIadjustment\fR> @@ -392,7 +393,7 @@ or \fISelectType=CR_Socket_Memory\fR is configured. .TP \fB\-\-ntasks\-per\-node\fR=\fIntasks\fR Request that no more than \fIntasks\fR be invoked on each node. -This is similiar to using \fB\-\-cpus\-per\-task\fR=\fIncpus\fR +This is similar to using \fB\-\-cpus\-per\-task\fR=\fIncpus\fR but does not require knowledge of the actual number of cpus on each node. In some cases, it is more convenient to be able to request that no more than a specific number of ntasks be invoked @@ -558,7 +559,7 @@ SLURM will normally allocate a TORUS if possible for a given geometry. 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 partions on +of nodes having 2 x 3 x 4 = 24 nodes (actually base partitions on Blue Gene). .TP @@ -668,7 +669,8 @@ The block name on Blue Gene systems only. .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 speficied in its command line parameters salloc will ignore most signals. salloc will not exit or release the allocation until the command exits. The noteable exception is SIGHUP; a HUP signal will cause salloc to release the allocation and exit without waiting for the command to finish. +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 diff --git a/doc/man/man1/sbatch.1 b/doc/man/man1/sbatch.1 index e73830f66e400fbbdc4d187426a23a0725cf501c..18e38369b1a697f9e017a8fc1c8c8c2a497c8b60 100644 --- a/doc/man/man1/sbatch.1 +++ b/doc/man/man1/sbatch.1 @@ -1,4 +1,4 @@ -.TH "sbatch" "1" "SLURM 1.3" "April 2008" "SLURM Commands" +.TH "sbatch" "1" "SLURM 1.3" "May 2008" "SLURM Commands" .SH "NAME" .LP sbatch \- Submit a batch script to SLURM. @@ -10,7 +10,7 @@ sbatch [\fIoptions\fP] \fIscript\fP [\fIargs\fP...] sbatch submits a batch script to SLURM. The batch script may be given to sbatch through a file name on the command line, or if no file name is specified, sbatch will read in a script from standard input. The batch script may contain -options preceeded with "#SBATCH" before any executable commands in the script. +options preceded with "#SBATCH" before any executable commands in the script. sbatch exits immediately after the script is successfully transferred to the SLURM controller and assigned a SLURM job ID. The batch script is not @@ -375,12 +375,13 @@ partition, the job will be rejected. .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. However this \-\-tasks option advizes the SLURM controller -that job steps run within this allocation will launch a maximum of \fInumber\fR -tasks. This option, possibly with collaboration with the \-\-cpus\-per\-task -option, will directly impact the number of processors granted to the job -allocation. +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 +that the \fB\-\-cpus\-per\-task\fR option will change this default. .TP \fB\-\-nice\fR[=]<\fIadjustment\fR> diff --git a/doc/man/man1/srun.1 b/doc/man/man1/srun.1 index ff87c5ec1089d3e17a3e053dba6349aabdee10c9..a4575a9a5ef6bf6ec5b995298661e0600f8c7b76 100644 --- a/doc/man/man1/srun.1 +++ b/doc/man/man1/srun.1 @@ -1,6 +1,6 @@ .\" $Id$ .\" -.TH SRUN "1" "April 2008" "srun 1.3" "slurm components" +.TH SRUN "1" "May 2008" "srun 1.3" "slurm components" .SH "NAME" srun \- run parallel jobs @@ -594,9 +594,11 @@ and without delaying the initiation of the job. .TP \fB\-n\fR, \fB\-\-ntasks\fR=\fIntasks\fR -Specify the number of processes to run. Request that \fBsrun\fR -allocate \fIntasks\fR processes. The default is one process per -node, but note that the \fB\-c\fR parameter will change this default. +Specify the number of tasks to run. Request that \fBsrun\fR +allocate resouces 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