- 03 Dec, 2013 2 commits
-
-
Danny Auble authored
-
Danny Auble authored
-
- 02 Dec, 2013 22 commits
-
-
Morris Jette authored
-
Morris Jette authored
Conflicts: NEWS doc/man/man5/cgroup.conf.5
-
Morris Jette authored
Add a check to make sure that the job completion RPC from a slurmstepd match that node that the batch job is running on. This would not be the case of for a job started on a node if that node's slurmd fails, but the slurmstepd keeps running. The job could then be requeued and generate a completion RPC from both slurmstepd daemons (one per node). This logic will ignore the job complete RPC from the node NOT currently running the batch job.
-
Morris Jette authored
-
David Bigagli authored
-
Morris Jette authored
Fix race condition on batch job termination that could result in a job exit code of 0xfffffffe if the slurmd on node zero registers its active jobs at the same time that slurmstepd is recording the job's exit code. but 535
-
Danny Auble authored
-
Danny Auble authored
-
Morris Jette authored
-
David Bigagli authored
-
David Bigagli authored
-
Danny Auble authored
-
Danny Auble authored
-
Danny Auble authored
-
Danny Auble authored
-
Danny Auble authored
-
Jason Sollom authored
-
Danny Auble authored
-
Danny Auble authored
-
Danny Auble authored
-
Danny Auble authored
This is needed primarily for native Cray systems to avoid hitting their LDAP or NIS server from every node in their system. This can also provide a more scalable model for other systems as well.
-
Morris Jette authored
-
- 29 Nov, 2013 10 commits
-
-
Morris Jette authored
-
Morris Jette authored
-
Morris Jette authored
Conflicts: src/plugins/proctrack/cgroup/proctrack_cgroup.c
-
Morris Jette authored
There was already cgroup locking in the version 14.03 code base using different variable names and slighly different logic from that in commit 3f6d9e36. This commit is a variant of that commit in order to make the logic in version 2.6 match that of our next release (logic which is already pretty well tested). bug 447
-
Morris Jette authored
proctrack/cgroup - Add locking to prevent race condition where one job step is ending for a user or job at the same time another job stepsis starting and the user or job container is deleted from under the starting job step. bug 447
-
Morris Jette authored
-
Morris Jette authored
Conflicts: NEWS src/common/gres.h src/slurmctld/node_scheduler.c
-
Morris Jette authored
This eliminates some now redundant arrays and variable copying introduced in commit 74d1a4b4 bug 525
-
David Bigagli authored
Substantial performance improvement for systems with Shared=YES or FORCE and large numbers of running jobs (replace bubble sort with quick sort). Bug 525
-
David Bigagli authored
Remove trailing spaces No changes in logic
-
- 27 Nov, 2013 6 commits
-
-
David Bigagli authored
-
Morris Jette authored
Original code worked only for Cray systems. For other systems it set gres_alloc to the total number of each GRES allocated on each node to any job
-
Morris Jette authored
-
Morris Jette authored
-
Jason Bacon authored
-
Morris Jette authored
-