Bug 2282097

Summary:	[IBM Support][ODF][4.11] Active MDS stuck in up:clientreplay state
Product:	[Red Hat Storage] Red Hat OpenShift Data Foundation	Reporter:	Kritik Sachdeva <ksachdev>
Component:	ceph	Assignee:	Dhairya Parmar <dparmar>
ceph sub component:	CephFS	QA Contact:	Elad <ebenahar>
Status:	ASSIGNED ---	Docs Contact:
Severity:	low
Priority:	unspecified	CC:	amk, assingh, bniver, dparmar, gsitlani, muagarwa, sostapov, vshankar
Version:	4.11	Flags:	ksachdev: needinfo- ksachdev: needinfo- dparmar: needinfo? (muagarwa)
Target Milestone:	---
Target Release:	---
Hardware:	All
OS:	All
Whiteboard:
Fixed In Version:		Doc Type:	If docs needed, set a value
Doc Text:		Story Points:	---
Clone Of:
Clones:	2311741 2311743 (view as bug list)		Environment:
Last Closed:		Type:	Bug
Regression:	---	Mount Type:	---
Documentation:	---	CRM:
Verified Versions:		Category:	---
oVirt Team:	---	RHEL 7.3 requirements from Atomic Host:
Cloudforms Team:	---	Target Upstream Version:
Embargoed:
Bug Depends On:
Bug Blocks:	2311741, 2311743, 2345561

Description Kritik Sachdeva 2024-05-21 08:22:30 UTC

Description of problem (please be detailed as possible and provide log
snippests):

We got a case where an active MDS is stuck at the up:clientreplay state and in the logs we were seeing the unhandled messages related to client_metrics. 

However, we do found a few trackers where an MDS stuck in up:clientreplay state but no diagnostic was available for the below one.
  - Additionally, there is no downstream BZ for this tracker as well.

https://tracker.ceph.com/issues/56577

We did collected the debug_mds 20 & debug_ms 1 logs from the active MDS for an RCA, and need help to confirm if we are hitting issue as mentioned in the tracker.

Version of all relevant components (if applicable): ODF 4.11 + Ceph version 5.3z5


Does this issue impact your ability to continue to work with the product
(please explain in detail what is the user impact)? No


Is there any workaround available to the best of your knowledge? Currently, issue has been resolved by restarting the active MDS pod.


Rate from 1 - 5 the complexity of the scenario you performed that caused this
bug (1 - very simple, 5 - very complex)? 1


Actual results:


Expected results:


Additional info:

We found one more tracker for the similar symptoms but that is already fixed in the version customer is using i.e 5.3z5
- https://tracker.ceph.com/issues/61523