Bug #48611
Bug #48417: unfound EC objects in sepia's LRC after upgrade
osd: Delay sending info to new backfill peer resetting last_backfill until backfill actually starts
% Done:
0%
Source:
Tags:
Backport:
pacific, octopus
Regression:
No
Severity:
3 - minor
Reviewed:
Affected Versions:
ceph-qa-suite:
Component(RADOS):
Pull request ID:
Crash signature (v1):
Crash signature (v2):
Description
This should be relatively harmless as any osd with lb=MIN wouldn’t have been sent any real IOs anyway. Might be analogous to how we ask peers to rollback during log based recovery. Code changes will mostly go into PeeringState::activate(), see https://tracker.ceph.com/issues/48417#note-8.
Related issues
History
#1 Updated by Neha Ojha about 3 years ago
- Backport set to pacific, octopus, nautilus
#2 Updated by Deepika Upadhyay about 3 years ago
- Assignee set to Deepika Upadhyay
#3 Updated by Deepika Upadhyay over 2 years ago
- Status changed from New to Pending Backport
- Pull request ID set to 40593
#4 Updated by Deepika Upadhyay over 2 years ago
- Backport changed from pacific, octopus, nautilus to pacific, octopus
since nautilus has reached EOL removed it
#5 Updated by Deepika Upadhyay over 2 years ago
- Copied to Backport #51522: pacific: osd: Delay sending info to new backfill peer resetting last_backfill until backfill actually starts added
#6 Updated by Deepika Upadhyay over 2 years ago
- Copied to Backport #51523: octopus: osd: Delay sending info to new backfill peer resetting last_backfill until backfill actually starts added
#8 Updated by Backport Bot over 2 years ago
- Copied to Backport #51525: octopus: osd: Delay sending info to new backfill peer resetting last_backfill until backfill actually starts added
#9 Updated by Loïc Dachary over 2 years ago
- Status changed from Pending Backport to Resolved
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are in status "Resolved" or "Rejected".