client: track (and forward to MDS) average read/write/metadata latency
Client already tracks cumulative read/write/metadata latencies. However, average latencies are much more useful to the user.
Start tracking average latencies and forward to the MDS for displaying in `perf stats` command (and `cephfs-top` utility).
(kclient also needs to start sending these metrics).
- Copied to Feature #48621: kclient: track (and forward to MDS) average read/write/metadata latency added
Xiubo suggested that the client also sends min/max and stddev.
- Status changed from New to In Progress
- Assignee set to Venky Shankar
- Target version changed from v16.0.0 to v17.0.0
- Status changed from In Progress to Fix Under Review
- Pull request ID set to 41397
- Target version deleted (
- Status changed from Fix Under Review to Resolved
- Status changed from Resolved to Pending Backport
- Target version set to v18.0.0
- Backport set to pacific,quincy
- Copied to Backport #57439: pacific: client: track (and forward to MDS) average read/write/metadata latency added
- Copied to Backport #57440: quincy: client: track (and forward to MDS) average read/write/metadata latency added
- Tags set to backport_processed
Also available in: Atom