Skip to content
Snippets Groups Projects
Select Git revision
  • slurm_metricq default protected
1 result
Search by author
  • Any Author
  • Andreas Gocht Andreas Gocht gocht--tu-dresden.de
  • Christian von Elm s4367864--tu-dresden.de
  • Daniel Hackenberg Daniel Hackenberg hackenbe--tu-dresden.de
  • Florian Mros Florian Mros flmr799e--tu-dresden.de
  • Franz Höpfner Franz Höpfner s1406784--tu-dresden.de
  • Hannes Tröpgen s9105947--tu-dresden.de
  • Lars Jitschin Lars Jitschin jitschin--tu-dresden.de
  • Mario Bielert Mario Bielert s9242987--tu-dresden.de
  • Markus Velten Markus Velten s3414584--tu-dresden.de
  • Robert Schöne rschoene--tu-dresden.de
  • Tessa Todorowski Tessa Todorowski teto519f--tu-dresden.de
  • Thomas Ilsche Thomas Ilsche tilsche--tu-dresden.de
12 authors
  1. May 26, 2015
  3. May 23, 2015
  5. May 22, 2015
  7. May 21, 2015
  9. May 20, 2015
  11. May 19, 2015
  13. May 18, 2015
  15. May 16, 2015
  17. May 15, 2015
  19. May 14, 2015
  21. May 13, 2015
  23. May 12, 2015
  25. May 11, 2015
    • Morris Jette's avatar
      Explain job option of --mem=0 means all memory · c0d6edc9
      Morris Jette authored 
      This is a special case. This change documents the way Slurm has
always worked.
      c0d6edc9
    • Morris Jette's avatar
      Purge old step data on job requeue · beecc7b0
      Morris Jette authored 
      Make sure that old step data is purged when a job is requeued.
Without this logic, if a job terminates abnormally then old step
data may be left in slurmctld. If the job is then requeued and
started on a different node, referencing that old job step data
can result in abnormal events. One specific failure mode is if
the job is requeued on a node with a different number of cores,
and the step terminated RPC arrives later, the job and step
bitmaps of allocated cores can differ in size generating an
abort.
bug 1660
      beecc7b0
  27. May 08, 2015
Nutzungsbedingungen | Datenschutzerklärung | Barrierefreiheitserklärung