[LU-5632] ldlm_lock_addref()) ASSERTION( lock != ((void *)0) ) Created: 16/Sep/14 Updated: 19/Sep/14 Resolved: 19/Sep/14 |
|
| Status: | Resolved |
| Project: | Lustre |
| Component/s: | None |
| Affects Version/s: | Lustre 2.4.2 |
| Fix Version/s: | Lustre 2.5.0 |
| Type: | Bug | Priority: | Major |
| Reporter: | Christopher Morrone | Assignee: | Niu Yawei (Inactive) |
| Resolution: | Duplicate | Votes: | 0 |
| Labels: | None | ||
| Environment: |
Lustre 2.4.2-14chaos (see github.com/chaos/lustre) |
||
| Issue Links: |
|
||||||||||||
| Severity: | 3 | ||||||||||||
| Rank (Obsolete): | 15756 | ||||||||||||
| Description |
|
We had an MDS crash with the following assertion: ldlm_lock.c:770:ldlm_lock_addref()) ASSERTION( lock != ((void *)0) ) The previous few minutes contained many lock timeouts and some node reconnections. The backtrace for the mdt_02_049 that hit the assertion was: ldlm_lock_addref mdt_reint_open mdt_reconstruct_open mdt_reconstruct mdt_reint_internal mdt_intent_reint mdt_intent_policy ldlm_lock_enqueue ldlm_handle_enqueue0 mdt_enqueue mdt_handle_common mds_regular_handle ptlrpc_server_handle_request ptlrpc_main We were running lustre version 2.4.2-14chaos (see github.com/chaos/lustre). We cannot provide logs or crash dumps from this system. |
| Comments |
| Comment by Peter Jones [ 16/Sep/14 ] |
|
Niu Could you please comment? Thanks Peter |
| Comment by Niu Yawei (Inactive) [ 17/Sep/14 ] |
|
This is caused by the flaw patch of |
| Comment by Andreas Dilger [ 19/Sep/14 ] |
|
Should be fixed for 2.4 with Oleg's patch from |