Details
-
Bug
-
Resolution: Unresolved
-
Major
-
None
-
Lustre 2.12.2
-
lustre servers using ZFS 0.8.1+
-
3
-
9223372036854775807
Description
The fix for LU-12510 was only a temporary work around. Currently Lustre manages the zrlock directly but this can collide with ZFS doing with the same thing which can lead to dead locks. The proper fix it so use the ZFS lock management functions provided by ZFS. https://github.com/zfsonlinux/zfs/pull/9027 landed a patch to export the needed functions for Lustre to use. This ticket will track the proper locking implementation.
Attachments
Issue Links
- mentioned in
-
Page No Confluence page found with the given URL.
-
Page No Confluence page found with the given URL.
-
Page No Confluence page found with the given URL.
-
Page No Confluence page found with the given URL.
-
Page No Confluence page found with the given URL.
-
Page Loading...
-
Page Loading...
-
Page Loading...
-
Page Loading...
-
Page Loading...
-
Page Loading...
-
Page Loading...
-
Page Loading...
-
Page Loading...
-
Page Loading...
-
Page Loading...
-
Page Loading...
-
Page Loading...
-
Page Loading...
-
Page Loading...
-
Page Loading...
-
Page Loading...
-
Page Loading...
-
Page Loading...
-
Page Loading...
-
Page Loading...
-
Page Loading...
"James Simmons <jsimmons@infradead.org>" uploaded a new patch: https://review.whamcloud.com/c/fs/lustre-release/+/55821
Subject: LU-12607 osd-zfs: use proper locking for dnodes
Project: fs/lustre-release
Branch: master
Current Patch Set: 1
Commit: bea303930c81351f4e742f804887e445686cc34a