1. 02 Mar, 2017 1 commit
  2. 28 Feb, 2017 1 commit
  3. 25 Feb, 2017 1 commit
  4. 24 Feb, 2017 2 commits
  5. 23 Feb, 2017 1 commit
  6. 20 Feb, 2017 22 commits
  7. 18 Jan, 2017 4 commits
  8. 12 Jan, 2017 2 commits
  9. 14 Dec, 2016 2 commits
    • Ilya Dryomov's avatar
      libceph: always signal completion when done · c297eb42
      Ilya Dryomov authored
      r_safe_completion is currently, and has always been, signaled only if
      on-disk ack was requested.  It's there for fsync and syncfs, which wait
      for in-flight writes to flush - all data write requests set ONDISK.
      
      However, the pool perm check code introduced in 4.2 sends a write
      request with only ACK set.  An unfortunately timed syncfs can then hang
      forever: r_safe_completion won't be signaled because only an unsafe
      reply was requested.
      
      We could patch ceph_osdc_sync() to skip !ONDISK write requests, but
      that is somewhat incomplete and yet another special case.  Instead,
      rename this completion to r_done_completion and always signal it when
      the OSD client is done with the request, whether unsafe, safe, or
      error.  This is a bit cleaner and helps with the cancellation code.
      Reported-by: default avatarYan, Zheng <zyan@redhat.com>
      Signed-off-by: default avatarIlya Dryomov <idryomov@gmail.com>
      c297eb42
    • Yan, Zheng's avatar
      ceph: avoid creating orphan object when checking pool permission · 80e80fbb
      Yan, Zheng authored
      Pool permission check needs to write to the first object. But for
      snapshot, head of the first object may have already been deleted.
      Skip the check for snapshot inode to avoid creating orphan object.
      
      Link: http://tracker.ceph.com/issues/18211Signed-off-by: default avatarYan, Zheng <zyan@redhat.com>
      80e80fbb
  10. 12 Dec, 2016 4 commits