Actions
Bug #22716
closedrbd snap create/rm takes 60s long
Status:
Resolved
Priority:
High
Assignee:
-
Target version:
-
% Done:
0%
Source:
Tags:
Backport:
luminous,jewel
Regression:
No
Severity:
3 - minor
Reviewed:
Affected Versions:
ceph-qa-suite:
Pull request ID:
Crash signature (v1):
Crash signature (v2):
Description
when create snap from an image of huge size, like 64T, it takes for almost 60s in our server enviroment, even if the image exsits without actual data. more harmfully, it stalls the osd holding image header object for 100% cpu usage, impacting client IO drops very much, possibly down to zero.
when rm snap, it also take 60s, which is a long time.
Updated by wb song over 6 years ago
Updated by Jason Dillaman over 6 years ago
- Tracker changed from Feature to Bug
- Status changed from New to Fix Under Review
- Priority changed from Normal to High
- Target version deleted (
v13.0.0) - Backport set to luminous,jewel
- Regression set to No
- Severity set to 3 - minor
Updated by Nathan Cutler over 6 years ago
- Has duplicate Bug #22722: [cls] rbd.object_map_snap_create and rbd.object_map_snap_remove are slow added
Updated by Jason Dillaman over 6 years ago
- Status changed from Fix Under Review to Pending Backport
Updated by Nathan Cutler over 6 years ago
- Copied to Backport #22809: luminous: rbd snap create/rm takes 60s long added
Updated by Nathan Cutler over 6 years ago
- Copied to Backport #22810: jewel: rbd snap create/rm takes 60s long added
Updated by Nathan Cutler about 6 years ago
- Status changed from Pending Backport to Resolved
Actions