- Jul 28, 2016
-
-
Morris Jette authored
-
Morris Jette authored
Add support for setting the SLURM_JOB_ACCOUNT, SLURM_JOB_QOS and SLURM_JOB_RESERVAION environment variables are set for the srun command. Document the same environment variables for the salloc, sbatch and srun commands in their man pages. bug 2945
-
Morris Jette authored
Document that the SLURM_JOB_ACCOUNT and SLURM_JOB_QOS environment variables are set for the srun command in its man page. bug 2945
-
Morris Jette authored
Partially revert commit 4f8c62c1 salloc does not set SLURM_JOB_ACCOUNT or SLURM_JOB_QOS
-
Morris Jette authored
-
Morris Jette authored
Document that the SLURM_JOB_ACCOUNT and SLURM_JOB_QOS environment variables are set for the salloc and sbatch commands in their man pages. bug 2945
-
- Jul 27, 2016
-
-
Morris Jette authored
-
Morris Jette authored
Document that persistent burst buffers can not be created or destroyed using the salloc or srun --bb options. bug 2404
-
Brian Christiansen authored
Missed in b5bba34c
-
Morris Jette authored
This patch builds upon commit 0c27392b, adding calls to the new function so the slurmctld daemon will log reasons for jobs failing to start. bug 1828
-
Morris Jette authored
Add new RPC (REQUEST_EVENT_LOG) so that slurmd and slurmstepd can log events through the slurmctld daemon. bug 1828
-
Danny Auble authored
-
Danny Auble authored
on batch script completes.
-
Danny Auble authored
-
Morris Jette authored
-
Danny Auble authored
code change.
-
Morris Jette authored
-
- Jul 26, 2016
-
-
Brian Christiansen authored
-
Brian Christiansen authored
-
Morris Jette authored
-
Morris Jette authored
-
Danny Auble authored
-
Morris Jette authored
The problem only exists on a subset of KNL models, those with 68 cores. bug 2941
-
Danny Auble authored
-
Danny Auble authored
-
Brian Christiansen authored
-
Brian Christiansen authored
-
Brian Christiansen authored
-
Brian Christiansen authored
And make it a pointer on the job_record struct.
-
Brian Christiansen authored
Lost after rebase.
-
Brian Christiansen authored
- Only ask if cluster is being assigned to a different federation. - Show that cluster is already part of federation and don't add cluster to list of updates. - Don't send updates if nothing to change (after finding that clusters are already part of federations).
-
Brian Christiansen authored
-
Brian Christiansen authored
-
Brian Christiansen authored
New jobs will get job IDs within the new range. Even though the pre-existing large jobid-jobs will have federated jobids, they will be treated as local jobs.
-
Brian Christiansen authored
-
Brian Christiansen authored
Fix by allocating slurm_msg_ts and freeing instead of using local variables.
-
Brian Christiansen authored
-
Brian Christiansen authored
-
Brian Christiansen authored
Display local cluster first and don't show persistconn. $ scontrol show fed Federation: f1 Self: fed1:127.0.0.1:31002 ID:1 FedState:ACTIVE Weight:0 Sibling: fed2:127.0.0.1:32002 ID:2 FedState:ACTIVE Weight:0 PersistConn:Connected Sibling: fed3:127.0.0.1:33002 ID:3 FedState:ACTIVE Weight:0 PersistConn:Connected
-
Brian Christiansen authored
Appends federation related columns to default format options.
-