Thanks Patrick,
is this the bug you are referring to
https://tracker.ceph.com/issues/42515 ?
We also see performance issues mainly on metadata operations like finding file stats
operations , however mds perf dump shows no sign of any latencies . could this bug cause
any performance issues ? here is the perf dump metrics .
https://pastebin.com/178anAe1
do you see any clue in this that could cause slow down in such operations ? our metadara
pool has around 1.7 GB of data I gave mds cache 3 GB , I am not sure where to check how
much used in the 3 GB or what is hit and miss count/ration in cache .
We have huge cluster , there is definitely not enough IO that could saturate actual disk
capacity so it is definitely MDS , not sure what to check here to pin point the issues.
Could you point me where I can start to go deep in troubleshooting this ?
Thanks,
Uday.