Bug #21426
qa/workunits/fs/snaps/untar_snap_rm.sh: timeout during up:rejoin (thrashing)
Status:
New
Priority:
Normal
Assignee:
-
Category:
Correctness/Safety
Target version:
-
% Done:
0%
Source:
Support
Tags:
Backport:
Regression:
No
Severity:
2 - major
Reviewed:
Affected Versions:
ceph-qa-suite:
fs
Component(FS):
MDS
Labels (FS):
Pull request ID:
Crash signature (v1):
Crash signature (v2):
Description
Related issues
History
#1 Updated by Zheng Yan over 6 years ago
- Priority changed from Urgent to Normal
The mds was busy at opening inodes for reconnected client caps. There are two reason opening inodes took so long.
First, there were about 25000 client caps, probably caused by issue http://tracker.ceph.com/issues/21423.
Second, ms_inject_socket_failures was set to 2500. mds need to sent about 25000 getxattr requests to osd. Each time socket failed, messenger re-sent all these requests, but only about 1000 requests got sent successfully.
#2 Updated by Patrick Donnelly over 6 years ago
- Related to Bug #21423: qa: test_client_pin times out waiting for dentry release from kernel added