Actions
Bug #13493
closedosd: for ec, cascading crash during recovery if one shard is corrupted
Status:
Duplicate
Priority:
Normal
Assignee:
David Zafman
Category:
EC Pools
Target version:
-
% Done:
0%
Source:
Community (dev)
Tags:
Backport:
Regression:
No
Severity:
3 - minor
Reviewed:
Affected Versions:
ceph-qa-suite:
Component(RADOS):
OSD
Pull request ID:
Crash signature (v1):
Crash signature (v2):
Description
For EC pool, during recovery, if there is one shard corrupted, it would cascade crash the OSDs until the PG is down (as once the primary is crashed, the secondary would become primary and start recovering, and then crash when recovering the object).
Updated by Greg Farnum almost 7 years ago
- Project changed from Ceph to RADOS
- Category set to EC Pools
- Assignee changed from Guang Yang to David Zafman
- Component(RADOS) OSD added
I suspect this is being resolved by David's work on EIO handling?
Updated by David Zafman almost 7 years ago
- Is duplicate of Bug #13937: osd/ECBackend.cc: 201: FAILED assert(res.errors.empty()) added
Updated by David Zafman almost 7 years ago
- Status changed from In Progress to Duplicate
Actions