Bug 2116551 - How to determine excessive crc error rate [NEEDINFO]
Summary: How to determine excessive crc error rate
Keywords:
Status: ASSIGNED
Alias: None
Product: Red Hat OpenShift Data Foundation
Classification: Red Hat Storage
Component: ceph-monitoring
Version: 4.11
Hardware: Unspecified
OS: Unspecified
unspecified
high
Target Milestone: ---
: ---
Assignee: Juan Miguel Olmo
QA Contact: Neha Berry
URL:
Whiteboard:
Depends On:
Blocks:
TreeView+ depends on / blocked
 
Reported: 2022-08-08 19:34 UTC by Jenifer Abrams
Modified: 2023-08-09 16:37 UTC (History)
12 users (show)

Fixed In Version:
Doc Type: If docs needed, set a value
Doc Text:
Clone Of:
Environment:
Last Closed:
Embargoed:
jolmomar: needinfo? (jdurgin)
jolmomar: needinfo? (nojha)

Attachments (Terms of Use)

Comment 2 Nitin Goyal 2022-08-09 04:56:42 UTC 
It looks like it has to be done on the rook side, Moving it to rook.
Comment 3 Travis Nielsen 2022-08-09 22:31:12 UTC 
Perhaps there is already a metric being collected related to the crc error rate. 
Paul, are you aware of any related metric or this would need to be a new metric?
Comment 4 Paul Cuzner 2022-08-10 03:56:21 UTC 
No. The current osd perf schema includes 3 crc cache related metrics only - nothing that would be useful to indicate CRC issues in the data path. 

Sounds like it would likely be a new metric exposed within the osd perf counter scheme.

Josh, thoughts?
Comment 18 Juan Miguel Olmo 2023-04-05 07:53:31 UTC 
Moved to ODF 4.14.0 because we need to evaluate how to get and impact of the new crc errors perf counters requested
Comment 19 Jenifer Abrams 2023-05-31 21:38:18 UTC 
Could this be considered a ceph health warn issue, similar to the discussion in: https://issues.redhat.com/browse/RHSTOR-3276 ?
Note You need to log in before you can comment on or make changes to this bug.