-
Bug
-
Resolution: Fixed
-
Minor
-
Lustre 2.7.0
-
None
-
3
-
15959
An OST of the soak cluster has many messages like this:
LustreError: 21300:0:(ldlm_lockd.c:1306:ldlm_handle_enqueue0()) ### delayed lvb init failed (rc -2) ns: filter-soaked-OST0040_UUID lock: ffff88036263f700/0x948ed57201b0714b lrc: 2/0,0 mode: --/PR res: [0x23ac2:0x0:0x0].0 rrc: 1 type: EXT [0->0] (req 0->0) flags: 0x40000000000000 nid: local remote: 0x541a4e3a52c14473 expref: -99 pid: 21300 timeout: 0 lvb_type: 0
I think it is due to "rm -rf" running in parallel on several clients against the same tree. In any case, we should not fill logs with such errors if they are expected in some legitimate races.
- is related to
-
LU-12659 change log level for "lvbo_init failed" back to CERROR
-
- Open
-