1. 07 Jul, 2015 3 commits
    • Trey Dockendorf's avatar
      Update job's QOS before partition · f2faa213
      Trey Dockendorf authored
      This patch moves the QOS update of an existing job to be before the
      partition update.  This ensures a new QOS value is the value used when
      doing validations against things like a partition's AllowQOS and DenyQOS.
      
      Currently if a two partitions have AllowQOS that do not share any QOS,
      the order of updates prevents a job from being moved from one partition
      to another using something like the following:
      
      scontrol update job=<jobID> partition=<new part> qos=<new qos>
      f2faa213
    • David Bigagli's avatar
    • Morris Jette's avatar
      Correct pack node logic · 0e0c64de
      Morris Jette authored
      Correct task layout with CR_Pack_Node option and more than 1 CPU per task.
      Previous logic would place one task per CPU launch too few tasks.
      bug 1781
      0e0c64de
  2. 06 Jul, 2015 2 commits
    • Morris Jette's avatar
      scheduler/backfill enhancements · edfbabe6
      Morris Jette authored
      Backfill scheduler now considers OverTimeLimit and KillWait configuration
      parameters to estimate when running jobs will exit. Initially the job's
      end time is estimated based upon it's time limit. After the time limit
      is reached, the end time estimate is based upon the OverTimeLimit and
      KillWait configuration parameters.
      bug 1774
      edfbabe6
    • Morris Jette's avatar
      Add backfill scheduler timeout · 7e944220
      Morris Jette authored
      Backfill scheduler: The configured backfill_interval value (default 30
          seconds) is now interpretted as a maximum run time for the backfill
          scheduler. Once reached, the scheduler will build a new job queue and
          start over, even if not all jobs have been tested.
      bub 1774
      7e944220
  3. 30 Jun, 2015 2 commits
  4. 29 Jun, 2015 1 commit
  5. 25 Jun, 2015 1 commit
  6. 24 Jun, 2015 1 commit
  7. 23 Jun, 2015 1 commit
  8. 22 Jun, 2015 3 commits
    • Morris Jette's avatar
      Advanced reservation fixes · a6454176
      Morris Jette authored
      Updates of existing bluegene advanced reservations did not work at all.
      Some multi-core configurations resulting in an abort due to creating
        core_bitmaps for the reservation that only had one bit per node rather
        than one bit per core.
      These bugs were introduced in commit 5f258072
      a6454176
    • David Bigagli's avatar
      Update NEWS · c8545598
      David Bigagli authored
      c8545598
    • David Bigagli's avatar
      Update NEWS · 38007f9b
      David Bigagli authored
      38007f9b
  9. 19 Jun, 2015 1 commit
  10. 15 Jun, 2015 1 commit
  11. 12 Jun, 2015 2 commits
  12. 11 Jun, 2015 1 commit
  13. 10 Jun, 2015 1 commit
  14. 09 Jun, 2015 2 commits
    • David Bigagli's avatar
      Search for user in all groups · 93ead71a
      David Bigagli authored
      93ead71a
    • Morris Jette's avatar
      Fix scheduling inconsistency with GRES · e1a00772
      Morris Jette authored
      1. I submit a first job that uses 1 GPU:
      $ srun --gres gpu:1 --pty bash
      $ echo $CUDA_VISIBLE_DEVICES
      0
      
      2. while the first one is still running, a 2-GPU job asking for 1 task per node
      waits (and I don't really understand why):
      $ srun --ntasks-per-node=1 --gres=gpu:2 --pty bash
      srun: job 2390816 queued and waiting for resources
      
      3. whereas a 2-GPU job requesting 1 core per socket (so just 1 socket) actually
      gets GPUs allocated from two different sockets!
      $ srun -n 1  --cores-per-socket=1 --gres=gpu:2 -p testk --pty bash
      $ echo $CUDA_VISIBLE_DEVICES
      1,2
      
      With this change #2 works the same way as #3.
      bug 1725
      e1a00772
  15. 05 Jun, 2015 1 commit
  16. 04 Jun, 2015 2 commits
  17. 03 Jun, 2015 1 commit
    • Morris Jette's avatar
      switch/cray: Refine PMI_CRAY_NO_SMP_ENV set · ef66b2eb
      Morris Jette authored
      switch/cray: Refine logic to set PMI_CRAY_NO_SMP_ENV environment variable.
      Rather than testing for the task distribution option, test the actual
      task IDs to see fi they are monotonically increasing across all nodes.
      Based upon idea from Brian Gilmer (Cray).
      ef66b2eb
  18. 02 Jun, 2015 3 commits
  19. 01 Jun, 2015 1 commit
  20. 30 May, 2015 1 commit
  21. 29 May, 2015 5 commits
  22. 28 May, 2015 1 commit
  23. 27 May, 2015 1 commit
    • Morris Jette's avatar
      Map job --mem-per-cpu=0 to --mem=0. · 33c77302
      Morris Jette authored
      However, --mem=0 now reflects the appropriate amount of memory in the
      system, --mem-per-cpu=0 hasn't changed.  This allows all the memory to
      be allocated in a cgroup but is not "consumed" and is available for
      other jobs running on the same host.
      Eric Martin, Washington University School of Medicine
      33c77302
  24. 26 May, 2015 1 commit
  25. 22 May, 2015 1 commit