[LU-2036] sanity.sh test_76: fails with lod/osp (inodes are not purged as expected) Created: 27/Sep/12 Updated: 18/Oct/17 Resolved: 18/Mar/13 |
|
| Status: | Resolved |
| Project: | Lustre |
| Component/s: | None |
| Affects Version/s: | Lustre 2.4.0 |
| Fix Version/s: | None |
| Type: | Bug | Priority: | Minor |
| Reporter: | Alex Zhuravlev | Assignee: | WC Triage |
| Resolution: | Duplicate | Votes: | 0 |
| Labels: | None | ||
| Issue Links: |
|
||||||||||||||||
| Severity: | 3 | ||||||||||||||||
| Rank (Obsolete): | 4198 | ||||||||||||||||
| Description |
|
OSP objects are not removed immediately, so ll_d_iput() in unlink path finds extent locks and do not reset nlink to 0 leaving the inode in the cache. we need to figure out another way to purge inode... on MDS corresponding inode does get nlink=0 only if the inode is actually being destroyed (orphans get nlink=1 being on PENDING/). this zero nlink propagated to the client can be a signal for ELC on the client ? |
| Comments |
| Comment by Andreas Dilger [ 18/Mar/13 ] |
|
This was landed with http://review.whamcloud.com/4087 (commit 5165cdd4b063d). |
| Comment by Andreas Dilger [ 18/Mar/13 ] |
|
To be clear - problem landed to master with LOD/OSP, but has not been fixed. Closing this as a duplicate of |
| Comment by Patrick Farrell (Inactive) [ 18/Oct/17 ] |
|
This appears to be fixed by: Test passes with that patch, fails without it. |