[LU-11581] Not all changelog entries are returned to userspace Created: 29/Oct/18 Updated: 06/Aug/19 Resolved: 26/Mar/19 |
|
| Status: | Resolved |
| Project: | Lustre |
| Component/s: | None |
| Affects Version/s: | Lustre 2.10.1 |
| Fix Version/s: | None |
| Type: | Bug | Priority: | Minor |
| Reporter: | Olaf Weber | Assignee: | WC Triage |
| Resolution: | Duplicate | Votes: | 0 |
| Labels: | changelog | ||
| Environment: |
Lustre 2.10 based virtual cluster |
||
| Issue Links: |
|
||||||||
| Epic/Theme: | changelog | ||||||||
| Severity: | 2 | ||||||||
| Rank (Obsolete): | 9223372036854775807 | ||||||||
| Description |
|
In a Lustre 2.10+ based cluster I have observed a problem where some changelog entries are not returned to userspace. Which entries are dropped is not consistent across attempts to read them. I can reproduce this by doing the following:
What I have observed is that I got different output files from lfs changelog every single time. Changelog records that are absent in one of the output files are present in another and vice versa. At no point were all entries that should be in the on-disk log returned. In my (admittedly CPU-starved) virtual cluster the drop rate was approximately 1 entry per 16000 records, but in a test like above having a few million on-disk records is required to consistently see the problem. Notes:
|
| Comments |
| Comment by John Hammond [ 29/Oct/18 ] |
|
I agree that this is likely to due |
| Comment by Peter Jones [ 29/Oct/18 ] |
|
John Can you please advise? Thanks Peter |
| Comment by Olaf Weber [ 06/Aug/19 ] |
|
We have now seen this issue on systems running 2.7 based code. Out of order records do seem to play a part, but the 2.10+ mechanism for returning records to userspace does not appear to be the culprit. |