Hi,
I have Ceph Pacific 16.2.9 with CephFS and 4 MDS (2 active, 2 standby-reply)
==========
RANK STATE MDS ACTIVITY DNS INOS DIRS CAPS
0 active mds3 Reqs: 31 /s 162k 159k 69.5k 177k
1 active mds1 Reqs: 4 /s 31.0k 28.7k 10.6k 20.7k
1-s standby-replay mds2 Evts: 35 /s 23.3k 17.7k 264 0
0-s standby-replay mds4 Evts: 49 /s 173k 159k 69.5k 0
POOL TYPE USED AVAIL
upload_hdd_metadata metadata 1421M 4101G
upload_hdd_data data 915G 6151G
MDS version: ceph version 16.2.9
(4c3647a322c0ff5a1dd2344e039859dcbd28c830) pacific (stable)
In MDS logs which handles rank 0 are a lot of error messages:
022-06-15T12:19:53.600+0200 7f3bb3130700 0 mds.0.cache
handle_find_ino_reply failed with -116 on #0x20008559a07, retrying
2022-06-15T12:19:53.600+0200 7f3bb3130700 0 mds.0.cache
handle_find_ino_reply failed with -116 on #0x20008559a07, retrying
2022-06-15T12:19:53.600+0200 7f3bb3130700 0 mds.0.cache
handle_find_ino_reply failed with -116 on #0x20008559a07, retrying
2022-06-15T12:19:53.600+0200 7f3bb3130700 0 mds.0.cache
handle_find_ino_reply failed with -116 on #0x20008559a07, retrying
2022-06-15T12:19:53.600+0200 7f3bb3130700 0 mds.0.cache
handle_find_ino_reply failed with -116 on #0x20008559a07, retrying
2022-06-15T12:19:53.600+0200 7f3bb3130700 0 mds.0.cache
handle_find_ino_reply failed with -116 on #0x20008559a07, retrying
2022-06-15T12:19:53.600+0200 7f3bb3130700 0 mds.0.cache
handle_find_ino_reply failed with -116 on #0x20008559a07, retrying
2022-06-15T12:19:53.600+0200 7f3bb3130700 0 mds.0.cache
handle_find_ino_reply failed with -116 on #0x20008559a07, retrying
2022-06-15T12:19:53.600+0200 7f3bb3130700 0 mds.0.cache
handle_find_ino_reply failed with -116 on #0x20008559a07, retrying
2022-06-15T12:19:53.604+0200 7f3bb3130700 0 mds.0.cache
handle_find_ino_reply failed with -116 on #0x20008559a07, retrying
It appears on any MDS that keeps rank 0.
I tried to find what this error means and how to handle it, but no luck.
To me it looks like MDS cannot find path to inode, is ti correct? How
can I fix ?
Thanks
_______________________________________________
ceph-users mailing list -- ceph-users@xxxxxxx
To unsubscribe send an email to ceph-users-leave@xxxxxxx