Hi,
were you able to resolve that situation in the meantime? If not, I
would probably try to 'umount -l' and see if that helps. If not, you
can check if the client is still blacklisted:
ceph osd blocklist ls (or blacklist)
If it's still blocklisted, you could try to remove it:
ceph osd blocklist clear
If it isn't blocklisted you could try to add it to the blocklist and
try to clear the stale mount. But there are situations where a reboot
is unavoidable, you might have run into such a situation.
Regards,
Eugen
Zitat von zxcs <zhuxiongcs@xxxxxxx>:
Hi, Experts,
we have an cephfs cluster 16.2.* run with multi active mds, and we
have some old machine run with ubuntu 16.04 , so we mount these
client using ceph-fuse.
After a full mds process restart, all of these old ubuntu 16.04
clients cannot connect to ceph , `ls -lrth` or `df -hT` hang on the
client node.
and we can see mds log said `evicting unresponsive client *** after
waiting ** seconds during restart`
also checking the client node, no ceph-fuse process, (ps -ef | grep
ceph or ps -ef | grep fuse).
but there is a remount process (ps -ef | grep mount) in the client node.
root 176516 1 0 01:38 ? 00:00:00 mount -i -o remount /data
cannot kill this process using `sudo kill -9 176516`.
we really need experts help us how to save this client out of hang.
we cannot restart this client node due to there are some other
critical service.
Thanks a ton.
zx
_______________________________________________
ceph-users mailing list -- ceph-users@xxxxxxx
To unsubscribe send an email to ceph-users-leave@xxxxxxx
_______________________________________________
ceph-users mailing list -- ceph-users@xxxxxxx
To unsubscribe send an email to ceph-users-leave@xxxxxxx
