Actions
Feature #49811
closedmds: collect I/O sizes from client for cephfs-top
% Done:
0%
Source:
Development
Tags:
Backport:
pacific
Reviewed:
Affected Versions:
Component(FS):
Client, Common/Protocol, MDS, kceph
Labels (FS):
Pull request ID:
Description
An average is a start but a histogram would be better for this kind of data.
Updated by Xiubo Li about 3 years ago
- Copied to Feature #49913: kclient: collect I/O sizes from client for cephfs-top added
Updated by Xiubo Li about 3 years ago
@Patric, @Jeff Lee
Comparing the iotop/iostat:
We may also need to collect the average IO READ/WRITE speed per-second, make sense ? There already have the latency metrics.
For the IO size I am planing to collect the min/average/max metrics and at the same time the total size should also make sense for us ?
How ahout the rtps/wtps ? For us the {r/w}tps will be READ/WRITE IO requests per second.
Updated by Xiubo Li about 3 years ago
- Status changed from In Progress to Fix Under Review
- Pull request ID set to 40514
Updated by Patrick Donnelly over 2 years ago
- Status changed from Fix Under Review to Pending Backport
Updated by Backport Bot over 2 years ago
- Copied to Backport #53121: pacific: mds: collect I/O sizes from client for cephfs-top added
Updated by Xiubo Li over 2 years ago
- Status changed from Pending Backport to Resolved
Actions