Advanced MPI scheduling: Difference between revisions

Advanced MPI scheduling (view source)

1 byte removed , 6 years ago

m

no edit summary

cc_staff

176

edits

@@ Line 39: / Line 39: @@
 <!--T:19-->
-You should use <code>--mem=128000M</code> rather than <code>--mem=128G</code> when requesting  whole nodes because a small tranche of memory is reserved to the operating system, and requesting precisely 128GB means the job cannot be scheduled on the plentiful 128GB nodes. The job will not be rejected by Slurm, it will just wait much longer to start than it needs to.
+You should use <code>--mem=128000M</code> rather than <code>--mem=128G</code> when requesting  whole nodes because a small amount of memory is reserved to the operating system, and requesting precisely 128GB means the job cannot be scheduled on the plentiful 128GB nodes. The job will not be rejected by Slurm, it will just wait much longer to start than it needs to.
 ==== Few cores, single node ==== <!--T:6-->