Actions
Bug #50801
closedcephfs-top should show average instead of cumulative latency
Status:
Duplicate
Priority:
Normal
Assignee:
-
Category:
-
Target version:
-
% Done:
0%
Source:
Tags:
Backport:
Regression:
No
Severity:
3 - minor
Reviewed:
Affected Versions:
ceph-qa-suite:
Component(FS):
cephfs-top
Labels (FS):
Pull request ID:
Crash signature (v1):
Crash signature (v2):
Description
I was playing with cephfs-top today and noticed that the read/write latency fields are in seconds, but the numbers were really large. Patrick mentioned that it's actually a cumulative latency metric instead of an average one.
I'll assert that a cumulative latency is not a terribly useful metric, as it's not clear what you'd compare it to and it depends on uptime, etc. Average latency seems like might be a more useful metric.
Updated by Venky Shankar almost 3 years ago
- Status changed from New to Duplicate
Duplicate of #48619
Actions