- 18 Jul, 2012 8 commits
-
-
Morris Jette authored
-
https://github.com/SchedMD/slurmjette authored
-
jette authored
-
Morris Jette authored
This corrects a bug introduced in commit 952401ec The NODE_CR_RESV value is being stored in a job as an 8-bit variable, so we can not use a value of 10000 for an exclusive node allocation. It's value was reduced to 250, which will be the maximum number of jobs that can be run on any node. Problem demonstrated by "salloc -N1 --exclusive" allocating the job only one CPU on the node rather than all CPUs on the node.
-
Morris Jette authored
-
Morris Jette authored
Fixing problems with core based reservations and jobs using exclusive flag
-
alejluther authored
'exclusive' flag
-
https://github.com/SchedMD/slurmalejluther authored
Conflicts: src/api/reservation_info.c src/common/node_select.c src/common/node_select.h src/plugins/sched/backfill/backfill.c src/plugins/sched/builtin/builtin.c src/plugins/sched/wiki2/job_will_run.c src/plugins/select/bluegene/select_bluegene.c src/plugins/select/cons_res/dist_tasks.c src/plugins/select/cons_res/job_test.c src/plugins/select/cons_res/select_cons_res.c src/plugins/select/cray/other_select.c src/plugins/select/cray/other_select.h src/plugins/select/cray/select_cray.c src/plugins/select/linear/select_linear.c src/scontrol/create_res.c src/slurmctld/job_scheduler.c src/slurmctld/node_scheduler.c src/slurmctld/reservation.c src/slurmctld/reservation.h src/slurmctld/slurmctld.h
-
- 17 Jul, 2012 16 commits
-
-
Morris Jette authored
-
Morris Jette authored
This corresponds to commit dd2dce54 from Mark Grondona's work in squeue, but applied to the sview command.
-
Morris Jette authored
Slurm 2.4 minor fixes
-
Morris Jette authored
-
Morris Jette authored
-
Morris Jette authored
-
Morris Jette authored
-
Rod Schultz authored
-
Morris Jette authored
-
Morris Jette authored
-
Morris Jette authored
-
Morris Jette authored
Batch job will have environment variable set: "SLURM_CPU_FREQ_REQ=0" and this will be loaded and reported as an invalid value by srun.
-
Morris Jette authored
-
Morris Jette authored
-
Morris Jette authored
-
Rod Schultz authored
-
- 16 Jul, 2012 7 commits
-
-
Morris Jette authored
-
Morris Jette authored
This addresses trouble ticket 85
-
Morris Jette authored
-
Don Albert authored
-
Morris Jette authored
-
Morris Jette authored
-
Morris Jette authored
-
- 13 Jul, 2012 9 commits
-
-
Danny Auble authored
runjob_mux
-
Morris Jette authored
-
Morris Jette authored
-
Morris Jette authored
-
Danny Auble authored
is always set when sending or receiving a message.
-
Tim Wickberg authored
-
Mark A. Grondona authored
Set SLURM_CONF in default prolog/epilog environment instead of only in spank prolog/epilog environment. This change fixes a potential hang during spank prolog/epilog execution due to the possibility of memory allocation after fork(2) and before exec(2) when invoking slurmstepd spank prolog|epilog. This also has the benefit that SLURM commands used in prolog and epilog scripts will use the correct slurm.conf file.
-
Mark A. Grondona authored
If exec_wait_child_wait_for_parent() fails for any reason, it is safer to abort immediately rather than proceed to execute the user's job.
-
Mark A. Grondona authored
On a failure of fork(2), slurmstepd would print an error and exit, possibly leaving previously forked children waiting. Ensure a better cleanup by killing all active children on fork failure before exiting slurmstepd.
-