[Bug 2064843] Re: Gluster 11.1 brick SEGFAULT

[Nick O'Connor]

** Description changed:

  [ Impact ]
  
   * Users experience brick SEGFAULTs under certain not-yet-understood
  scenarios. Some reports include a high percentage of small file I/O. I
  encountered the issue roughly every hour with Minio backed by GlusterFS
  on ZFS.
  
   * This bug introduces an increased risk of data loss or corruption
  depending on the user's configuration and timing of brick crashes.
  
   * Core dumps from multiple users revealed that the SEGFAULTs are caused
  by a stack overflow when namespaced inodes are destroyed.
  
- * The patch removes the recursive call to inode_unref when a namespaced
+  * The patch removes the recursive call to inode_unref when a namespaced
  inode is destroyed.
  
  [ Test Plan ]
  
   * The triggers for the issue are not well understood. I have compiled
- the patch into version 11.1-4build3 of glusterfs and it resolved the
+ the patch against version 11.1-4build3 of glusterfs and it resolved the
  issue on my system.
  
  [ Where problems could occur ]
  
   * It's conceivable that this patch introduces undesired behavior when
  inodes are destroyed, however I highly doubt this scenario as
- __inode_destroy (private function) did not call inode_unref (public
- function) before the change which introduced the bug.
+ __inode_destroy was not recursive before the change which introduced the
+ bug.
  
  [ Other Info ]
  
   * PR which introduced the bug: https://github.com/gluster/glusterfs/pull/1763
   * PR which added this patch: https://github.com/gluster/glusterfs/pull/4302
   * Issue discussion: https://github.com/gluster/glusterfs/issues/4295

-- 
You received this bug notification because you are a member of Ubuntu
Sponsors, which is subscribed to the bug report.
https://bugs.launchpad.net/bugs/2064843

Title:
  Gluster 11.1 brick SEGFAULT

Status in glusterfs package in Ubuntu:
  Triaged
Status in glusterfs source package in Noble:
  Triaged
Status in glusterfs source package in Oracular:
  Triaged

Bug description:
  [ Impact ]

   * Users experience brick SEGFAULTs under certain not-yet-understood
  scenarios. Some reports include a high percentage of small file I/O. I
  encountered the issue roughly every hour with Minio backed by
  GlusterFS on ZFS.

   * This bug introduces an increased risk of data loss or corruption
  depending on the user's configuration and timing of brick crashes.

   * Core dumps from multiple users revealed that the SEGFAULTs are
  caused by a stack overflow when namespaced inodes are destroyed.

   * The patch removes the recursive call to inode_unref when a
  namespaced inode is destroyed.

  [ Test Plan ]

   * The triggers for the issue are not well understood. I have compiled
  the patch against version 11.1-4build3 of glusterfs and it resolved
  the issue on my system.

  [ Where problems could occur ]

   * It's conceivable that this patch introduces undesired behavior when
  inodes are destroyed, however I highly doubt this scenario as
  __inode_destroy was not recursive before the change which introduced
  the bug.

  [ Other Info ]

   * PR which introduced the bug: https://github.com/gluster/glusterfs/pull/1763
   * PR which added this patch: https://github.com/gluster/glusterfs/pull/4302
   * Issue discussion: https://github.com/gluster/glusterfs/issues/4295

To manage notifications about this bug go to:
https://bugs.launchpad.net/ubuntu/+source/glusterfs/+bug/2064843/+subscriptions