Project

General

Profile

Actions

Bug #64707

open

suites/fsstress.sh hangs on one client - test times out

Added by Venky Shankar 2 months ago. Updated 4 days ago.

Status:
In Progress
Priority:
Normal
Assignee:
Category:
-
Target version:
% Done:

0%

Source:
Tags:
Backport:
quincy,reef,squid
Regression:
No
Severity:
3 - minor
Reviewed:
Affected Versions:
ceph-qa-suite:
Component(FS):
MDS, kceph
Labels (FS):
Pull request ID:
Crash signature (v1):
Crash signature (v2):

Description

https://pulpito.ceph.com/vshankar-2024-03-04_08:26:39-fs-wip-vshankar-testing-20240304.042522-testing-default-smithi/7580951/

Description: fs/upgrade/mds_upgrade_sequence/{bluestore-bitmap centos_9.stream conf/{client mds mon osd} fail_fs/yes overrides/{ignorelist_health ignorelist_upgrade ignorelist_wrongly_marked_down pg-warn syntax} roles tasks/{0-from/quincy 1-volume/{0-create 1-ranks/1 2-allow_standby_replay/no 3-inline/yes 4-verify} 2-client/kclient 3-upgrade-mgr-staggered 4-config-upgrade/{fail_fs} 5-upgrade-with-workload 6-verify}}

client.1 runs to completion, however, fsstress on client.0 times out with the following last few operations

2024-03-04T11:06:15.538 INFO:tasks.workunit.client.0.smithi078.stdout:5/993: creat d15/d64/d4d/d49/dda/ddc/f139 x:0 0 0
2024-03-04T11:06:15.541 INFO:tasks.workunit.client.0.smithi078.stdout:5/994: getdents d15/d2e/d11d 0
2024-03-04T11:06:15.554 INFO:tasks.workunit.client.0.smithi078.stdout:5/995: dread d15/d2e/f9a [0,4194304] 0
2024-03-04T11:06:15.554 INFO:tasks.workunit.client.0.smithi078.stdout:5/996: chown d15/d2e/l12e 14317335 1
2024-03-04T11:06:15.558 INFO:tasks.workunit.client.0.smithi078.stdout:5/997: mknod d15/d40/dbe/dcb/dcc/c13a 0
2024-03-04T11:06:15.558 INFO:tasks.workunit.client.0.smithi078.stdout:5/998: write d15/d40/fe0 [5130847,44776] 0
2024-03-04T11:06:15.560 INFO:tasks.workunit.client.0.smithi078.stdout:5/999: mkdir d15/d64/d4d/d49/d73/d13b 0
2024-03-04T11:06:16.193 INFO:journalctl@ceph.mon.smithi078.smithi078.stdout:Mar 04 11:06:15 smithi078 ceph-mon[29227]: pgmap v48: 65 pgs: 65 active+clean; 3.8
2024-03-04T14:04:14.958 DEBUG:teuthology.orchestra.run:got remote process result: 124
2024-03-04T14:04:14.959 INFO:tasks.workunit:Stopping ['suites/fsstress.sh'] on client.0...
2024-03-04T14:04:14.959 DEBUG:teuthology.orchestra.run.smithi078:> sudo rm -rf -- /home/ubuntu/cephtest/workunits.list.client.0 /home/ubuntu/cephtest/clone.client.0

Interestingly, the kerne ring buffers are empty:

- ./remote/smithi078/syslog/kern.log.gz
- ./remote/smithi175/syslog/kern.log.gz

which should not be the case - there should be something in those, isn't it?


Related issues 2 (2 open0 closed)

Related to CephFS - Bug #50821: qa: untar_snap_rm failure during mds thrashingFix Under ReviewXiubo Li

Actions
Related to CephFS - Fix #52916: mds,client: formally remove inline data supportFix Under ReviewMilind Changire

Actions
Actions

Also available in: Atom PDF