Feature #65503: mgr/stats, cephfs-top: provide per volume/sub-volume based performance metrics to monitor / troubleshoot performance issues - CephFS - Ceph

Actions

Copy link

Feature #65503

open

mgr/stats, cephfs-top: provide per volume/sub-volume based performance metrics to monitor / troubleshoot performance issues

Added by Jos Collin 14 days ago. Updated 14 days ago.

Status:

New

Priority:

Normal

Assignee:

Jos Collin

Category:

Administration/Usability

Target version:

Ceph - v20.0.0

% Done:

Source:

Community (dev)

Tags:

Backport:

Reviewed:

Affected Versions:

Component(FS):

cephfs-top

Labels (FS):

Pull request ID:

Description

Reported by BZ: https://bugzilla.redhat.com/show_bug.cgi?id=2275081

Currently the cephfs-top utility only displays client performance metrics. However during slow downs and latency from high amounts of IO in the customer's environment it is difficult to tell what share/workload is causing it. CephFS top doesn't report enough data other than per client IO to tell where the problem stems from. Thus the customer requires per volume/sub-volume based performance metrics to monitor / troubleshoot performance issues.

This needs to be introduced at the mgr/stats first and then display it in the cephfs-top.