Hi Giuseppe,
There are likely one or two clients whose op is blocking the reconnect/replay.
If you increase debug_mds perhaps you can find the guilty client and
disconnect it / block it from mounting.
Or for a more disruptive recovery you can try this "Deny all reconnect
to clients " option:
http
Hi David,
Thanks a lot for your reply.
Yes we have heavy load from clients on the same subtree. We have multiple MDSs
that were setup with the hope to distribute the load among them, but this is
not really happening, in moments of high load we see most of the load on one
MDS.
We don't use pinnin
Hi Guiseppe,
Wouldn't you have clients who heavily load the MDS with concurrent access
on the same trees ?
Perhaps, also, look at the stability of all your clients (even if there are
many) [dmesg -T, ...]
How are your 4 active MDS configured (pinning?) ?
Probably nothing to do but normal for 2