Actions
Feature #19862
openmds: add LTTnG tracepoints for each type of MDS operation
Status:
New
Priority:
Normal
Assignee:
-
Category:
-
Target version:
-
% Done:
0%
Source:
Development
Tags:
Backport:
Reviewed:
Affected Versions:
Component(FS):
MDS
Labels (FS):
Pull request ID:
Description
It would be nice to know the latency of different file system operations so we can see which operations:
- scale poorly with more requests
- should be load balanced to another MDS
The latencies would be measured at the MDS, not the client.
Similar to #19362, this would be another step towards more comprehensive performance tracking in the MDS.
Actions