- 29 Apr, 2019 40 commits
-
-
Nate Rini authored
Bug 6513
-
Nate Rini authored
Bug 6513
-
Tim Wickberg authored
CID 197758.
-
Tim Wickberg authored
I believe job cannot be NULL here, but the flow through this function is messy, and relies on some external setup that has not been documented with xassert()s. Put this in for now as a stop-gap; this code should be refactored at a later point.
-
Brian Christiansen authored
-
Brian Christiansen authored
-
Tim Wickberg authored
Bug 6632.
-
Tim Wickberg authored
-
Matt Ezell authored
The slurmsmwd cannot be build as part of a Cray Aries build at this time, so should not be bundled alongside it. Add this separate build option to make it easier to package independently of the main installation. Bug 6632.
-
Matt Ezell authored
The --disable-native-cray option was used to revert back to Cray/ALPS mode, and does not do anything at this point. So reuse the spec option to actual disable ("Native") Cray Aries builds. Bug 6632.
-
Brian Christiansen authored
when one offset passes and other fails. Bug 6892
-
Nate Rini authored
Bug 6513.
-
Brian Christiansen authored
Bug 6513
-
Brian Christiansen authored
Bug 6513 First offset is good but second is bad -- didn't request task count. $ cat etc/job_submit.lua function slurm_job_submit(job_desc, part_list, submit_uid) slurm.log_user("submit1\nstuff") slurm.log_user("submit2") slurm.log_user("submit3") -- slurm.log_user("case 0") if job_desc.num_tasks == slurm.NO_VAL or job_desc.num_tasks == nil then slurm.log_user("Batch submit error: Must specify either number of nodes or number of tasks!") -- reject the job return slurm.ERROR end return slurm.SUCCESS end function slurm_job_modify(job_desc, job_rec, part_list, modify_uid) slurm.log_user("modify1") slurm.log_user("modify2") slurm.log_user("modify3") return slurm.SUCCESS end slurm.log_user("initialized") return slurm.SUCCESS $ sbatch -Ablah2 -n1 --wrap="hostname" : -J asdfl sbatch: error: 0: initialized sbatch: error: 0: submit1 sbatch: error: 0: stuff sbatch: error: 0: submit2 sbatch: error: 0: submit3 sbatch: error: submit1 sbatch: error: stuff sbatch: error: submit2 sbatch: error: submit3 sbatch: error: Batch submit error: Must specify either number of nodes or number of tasks! sbatch: error: Batch job submission failed: Unspecified error $ sbatch -Ablah2 -n1 --wrap="hostname" : -J asdfl sbatch: error: 0: initialized sbatch: error: 0: submit1 sbatch: error: 0: stuff sbatch: error: 0: submit2 sbatch: error: 0: submit3 sbatch: error: 1: submit1 sbatch: error: 1: stuff sbatch: error: 1: submit2 sbatch: error: 1: submit3 sbatch: error: 1: Batch submit error: Must specify either number of nodes or number of tasks! sbatch: error: Batch job submission failed: Unspecified error srun already handles this
-
Nate Rini authored
Was dumping this: $ srun -A test7.21-account.1 --qos test7.21-qos.1 -n5 : -n3 : -n1 /bin/true srun: error: 0: submit1 srun: error: submit2 srun: error: submit3 srun: error: Unable to allocate resources: Invalid account or account/partition combination specified Will now dump this: $ srun -A test7.21-account.1 --qos test7.21-qos.1 -n5 : -n3 : -n1 /bin/true srun: error: 0: initialized srun: error: 0: submit1 srun: error: 0: submit2 srun: error: 0: submit3 srun: error: Unable to allocate resources: Invalid account or account/partition combination specified Bug 6513.
-
Nate Rini authored
Bug 6895.
-
Brian Christiansen authored
Bug 6895
-
Brian Christiansen authored
Bug 6895
-
Daniel Letai authored
And require the compute nodes to have an identical installation version to avoid issues with mismatched libraries. Bug 6598.
-
Daniel Letai authored
And require the compute nodes to have an identical installation version to avoid issues with mismatched libraries. Bug 6598.
-
Boris Karasev authored
PMIX_VAL_SET will not be supported in PMIx v4 or later. This commit changes the use of the old (and non-standard) PMIX_VAL_SET macro to the standardized PMIX_INFO_LOAD (which is used within a new internal PMIXP_KVP_ADD macro). Bug 6624.
-
Marshall Garey authored
Bug 6824.
-
Marshall Garey authored
PrologFlags=x11 is incompatible with proctracktype=proctrack/linuxproc because linuxproc cannot kill processes not owned by the user, and root owns processes spawned for handling x11 forwarding. When using PrologFlags=contain, it is recommended to use proctrack/cgroup or proctrack/cray because contain is mostly useful for pam_slurm_adopt which requires proctrack/cgroup or proctrack/cray. Bug 6824.
-
Marshall Garey authored
Commit f293a763 caused slurmctld to fatal when proctrack/cray and PrologFlags=Contain are both in slurm.conf. proctrack/cray should be allowed with PrologFlags=contain. Bug 6824.
-
Boris Karasev authored
This commit changes the logic of selecting a type of collective. The Tree-based algorithm will be selected when fence with an empty data contribution, which allows for improved fence performance. Bug 6637.
-
Dominik Bartkiewicz authored
Bug 6411.
-
Dominik Bartkiewicz authored
Any srun command launched within a shell under pam_slurm_adopt's control will automatically use the job's allocation now. Bug 6411.
-
Dominik Bartkiewicz authored
-
Danny Auble authored
-
Tim Wickberg authored
Should fix build errors with 'make contrib'.
-
Brian Christiansen authored
Continuation of 36c30487 Bug 6782
-
Tim Wickberg authored
Bug 6633.
-
Brian Christiansen authored
-
Brian Christiansen authored
Bug 6920
-
Brian Christiansen authored
Bug 6290
-
Brian Christiansen authored
-
Brian Christiansen authored
Bug 6791
-
Brian Christiansen authored
Bug 6791
-