Feature #15589: Ceph status outputs mds slow request summary for better monitoring - CephFS - Ceph

Actions

Copy link

Feature #15589

closed

Ceph status outputs mds slow request summary for better monitoring

Added by Zhi Zhang about 8 years ago. Updated over 7 years ago.

Status:

Resolved

Priority:

Normal

Assignee:

Category:

Target version:

% Done:

Source:

Community (dev)

Tags:

Backport:

Reviewed:

Affected Versions:

Component(FS):

Labels (FS):

Pull request ID:

Description

Currently ceph status or ceph health won't output mds slow request summary. It is not very friendly and timely for ops engineer to identify slow requests on mds or monitor mds status.

So we add such feature to output mds slow request summary via ceph status, ceph health and ceph health detail. This will also benefit ops engineer to monitor mds status.

[ceph@xxx ~]$ ceph -s
    cluster 8dd227cf-5397-4a62-9e03-2accdc976bd7
     health HEALTH_WARN
            mds0: 7 slow requests are blocked > 30 sec
     ...

[ceph@xxx ~]$ ceph health detail
HEALTH_WARN mds0: 7 slow requests are blocked > 30 sec
mds0: 7 slow requests are blocked > 30 sec

[ceph@xxx ~]$ ceph health       
HEALTH_WARN mds0: 11 slow requests are blocked > 30 sec