Skip to content
GitLab
  1. 08 Nov, 2019 2 commits
    • Michael Hinton's avatar
      Fix issues with --gpu-bind while using cgroups · 5b13fbb3
      Michael Hinton authored 
      CUDA_VISIBLE_DEVICES was not being set to the correct GPU indexes when
cgroups were being used. These issues were exhibited with at least the
map_gpu and mask_gpu binding options.

The issue was that usable_gres is a bitmask of GRESs in the step's
cgroup, but bit_test() was looking at bit i, which is the index of the
global gres_list (not constrained by cgroups).

Bug 7509
      5b13fbb3
    • Felip Moll's avatar
      Fix regression on update from older versions with DefMemPerCPU · 6abe1e75
      Felip Moll authored 
      In 19.05 JOB_MEM_SET flag was added along with a conditional check on
this flag that changed the pn_min_memory when validating job limits.
This caused that after an upgrade, PD jobs in earlier versions didn't
have this flag and the memory was incorrectly set when their limits were
checked before starting. The patch here addresses this issue adding this
flag to jobs from an older protocol version when loading the state
files.

Bug 8011
      6abe1e75
  3. 07 Nov, 2019 1 commit
    • Marshall Garey's avatar
      Allow coordinators to delete users. · 0d579734
      Marshall Garey authored 
      Previously, coordinators could delete specific associations, but could
not delete users. Allow coordinators to delete users if the users are
only part of accounts that the coordinator is over.

Bug 7413.
      0d579734
  5. 31 Oct, 2019 5 commits
  7. 29 Oct, 2019 1 commit
  9. 28 Oct, 2019 2 commits
  11. 25 Oct, 2019 2 commits
    • Albert Gil's avatar
      Enforce PART_NODES if only Partition is specified · c8ce5a53
      Albert Gil authored 
      Bug 7490
      c8ce5a53
    • Marshall Garey's avatar
      Avoid abort in dev-build · fe945037
      Marshall Garey authored 
      If not enforcing QOS, it's possible to submit a job without a qos. If
submitting such a job to multiple partitions where at least one has a
qos, slurmctld would abort in a development build. A non-development
build didn't segfault only because _find_qos_part doesn't dereference
the NULL pointer. Prevent the abort.

Bug 7171
      fe945037
  13. 24 Oct, 2019 1 commit
  15. 23 Oct, 2019 1 commit
  17. 22 Oct, 2019 2 commits
    • Gavin Howard's avatar
      Fix abort initializing a configuration without acct_gather.conf. · a301635f
      Gavin Howard authored 
      Previous logic would only call s_p_hashtbl_create() to create the hashtable
when the file acct_gather.conf could be successfully stat()'d. This lead to
a subsequent attempt to pack the non-created hashtable into a buffer which
triggered the abort.

This makes it so the hashtable is uncondtionally created no matter if the
file is missing.

Bug 7893.
      a301635f
    • Michael Hinton's avatar
      auth/munge - truncate FQDN to shortname for AllocNodes. · 50eaa012
      Michael Hinton authored 
      gethostbyaddr() can potentially return a fully-qualified domain name,
which breaks backwards compatibility with the shortname AllocNodes
expected pre 19.05.

Bug 7653.
      50eaa012
  19. 21 Oct, 2019 2 commits
  21. 18 Oct, 2019 1 commit
  23. 16 Oct, 2019 2 commits
  25. 15 Oct, 2019 2 commits
  27. 11 Oct, 2019 1 commit
  29. 09 Oct, 2019 1 commit
  31. 08 Oct, 2019 2 commits
  33. 07 Oct, 2019 1 commit
  35. 04 Oct, 2019 3 commits
  37. 03 Oct, 2019 2 commits
  39. 02 Oct, 2019 3 commits
  41. 01 Oct, 2019 3 commits