diff --git a/doc/html/multi_cluster.shtml b/doc/html/multi_cluster.shtml index f7516630a2819df15447771d512f274c2be5638b..d80a1b7b97c3609868b89217e5bd2c0e345e633f 100644 --- a/doc/html/multi_cluster.shtml +++ b/doc/html/multi_cluster.shtml @@ -2,46 +2,47 @@ <h1>Multi-Cluster Operation</h1> -<p>A cluster is comprised of all the nodes managed by a single -slurmctld. SLURM v2.2 offers the ability to target commands to other +<p>A cluster is comprised of all the nodes managed by a single slurmctld +daemon. SLURM version 2.2 offers the ability to target commands to other clusters instead of, or in addition to, the local cluster on which the command is invoked. When this behavior is enabled, users can submit jobs to one or many clusters and receive status from those remote clusters.</p> -For example, +<p>For example:</p> <PRE> juser@dawn> squeue -M dawn,dusk CLUSTER: dawn - JOBID PARTITION NAME USER ST TIME NODES BP_LIST(REASON) -1076897 pdebug myJob juser R 5:04:10 128 dawn001[8-15] -1076898 pdebug myJob juser R 5:04:10 128 dawn001[16-23] -1076899 pdebug myJob juser R 5:04:10 128 dawn001[24-31] +JOBID PARTITION NAME USER ST TIME NODES BP_LIST(REASON) +76897 pdebug myJob juser R 4:10 128 dawn001[8-15] +76898 pdebug myJob juser R 4:10 128 dawn001[16-23] +16899 pdebug myJob juser R 4:10 128 dawn001[24-31] CLUSTER: dusk - JOBID PARTITION NAME USER ST TIME NODES BP_LIST(REASON) -1001950 pdebug aJob juser R 4:20 128 dusk000[0-15] -1001949 pdebug aJob juser R 5:01 128 dusk000[48-63] -1001946 pdebug aJob juser R 6:35 128 dusk000[32-47] -1001945 pdebug aJob juser R 6:36 128 dusk000[16-31] +JOBID PARTITION NAME USER ST TIME NODES BP_LIST(REASON) +11950 pdebug aJob juser R 4:20 128 dusk000[0-15] +11949 pdebug aJob juser R 5:01 128 dusk000[48-63] +11946 pdebug aJob juser R 6:35 128 dusk000[32-47] +11945 pdebug aJob juser R 6:36 128 dusk000[16-31] </PRE> -<p>Many of the slurm client commands now offer the "-M, --clusters=" +<p>Many of the SLURM client commands now offer the "-M, --clusters=" option and the ability to specify a comma separated list of clusters. When <b>sbatch</b> is invoked with a cluster list, SLURM will submit -the job to the cluster which meets the job's specifications and can -run the job at the earliest time.</p> +the job to the cluster which meets the job's specifications and is expected +to begin the job at the earliest time.</p> <h2>Multi-Cluster Configuration</h2> <p>The multi-cluster functionality requires the use of the slurmDBD. The AccountingStorageType in the slurm.conf file must be set to the accounting_storage/slurmdbd plugin and the MUNGE or authentication keys must be installed to allow each cluster to communicate with the -slurmDBD. See <a href="accounting.html">accounting</a> for -details.</p> +slurmDBD. Note that MUNGE can be configured to use different keys for +communications within a cluster and across clusters if desired. +See <a href="accounting.html">accounting</a> for details.</p> -<p>Once configured, slurm commands specifying the "-M, --clusters=" +<p>Once configured, SLURM commands specifying the "-M, --clusters=" option will become active for all of the clusters listed by the <b>"sacctmgr show clusters"</b> command.</p>