Hello,
I have a luminous (12.2.1) cluster with 3 nodes for cephfs (no rbd or rgw) and we hit the "X clients failing to respond to cache pressure" message.
I have 3 mds servers active.
Is this something I have to worry about ?
here some information about the cluster :
> root@iccluster054:~# ceph --cluster container -s
> cluster:
> id: a294a95a-0baa-4641-81c1-7cd70fd93216
> health: HEALTH_WARN
> 3 clients failing to respond to cache pressure
>
> services:
> mon: 3 daemons, quorum iccluster041.iccluster.epfl.ch,iccluster042.iccluster.epfl.ch,iccluster054.iccluster.epfl.ch
> mgr: iccluster042(active), standbys: iccluster054
> mds: cephfs-3/3/3 up {0=iccluster054.iccluster.epfl.ch=up:active,1=iccluster041.iccluster.epfl.ch=up:active,2=iccluster042.iccluster.epfl.ch=up:active}
> osd: 18 osds: 18 up, 18 in
>
> data:
> pools: 3 pools, 544 pgs
> objects: 2357k objects, 564 GB
> usage: 2011 GB used, 65055 GB / 67066 GB avail
> pgs: 544 active+clean
>
> root@iccluster041:~# ceph --cluster container daemon mds.iccluster041.iccluster.epfl.ch perf dump mds
> {
> "mds": {
> "request": 193508283,
> "reply": 192815355,
> "reply_latency": {
> "avgcount": 192815355,
> "sum": 457371.475011160,
> "avgtime": 0.002372069
> },
> "forward": 692928,
> "dir_fetch": 1717132,
> "dir_commit": 43521,
> "dir_split": 4197,
> "dir_merge": 4244,
> "inode_max": 2147483647,
> "inodes": 11098,
> "inodes_top": 7668,
> "inodes_bottom": 3404,
> "inodes_pin_tail": 26,
> "inodes_pinned": 143,
> "inodes_expired": 1386234444,
> "inodes_with_caps": 87,
> "caps": 239,
> "subtrees": 15,
> "traverse": 195425369,
> "traverse_hit": 192867085,
> "traverse_forward": 692723,
> "traverse_discover": 476,
> "traverse_dir_fetch": 1714684,
> "traverse_remote_ino": 0,
> "traverse_lock": 6,
> "load_cent": 19465322425,
> "q": 0,
> "exported": 1211,
> "exported_inodes": 845556,
> "imported": 1082,
> "imported_inodes": 1209280
> }
> }
> root@iccluster041:~# ceph --cluster container daemon mds.iccluster041.iccluster.epfl.ch perf dump mds
> {
> "mds": {
> "request": 193508283,
> "reply": 192815355,
> "reply_latency": {
> "avgcount": 192815355,
> "sum": 457371.475011160,
> "avgtime": 0.002372069
> },
> "forward": 692928,
> "dir_fetch": 1717132,
> "dir_commit": 43521,
> "dir_split": 4197,
> "dir_merge": 4244,
> "inode_max": 2147483647,
> "inodes": 11098,
> "inodes_top": 7668,
> "inodes_bottom": 3404,
> "inodes_pin_tail": 26,
> "inodes_pinned": 143,
> "inodes_expired": 1386234444,
> "inodes_with_caps": 87,
> "caps": 239,
> "subtrees": 15,
> "traverse": 195425369,
> "traverse_hit": 192867085,
> "traverse_forward": 692723,
> "traverse_discover": 476,
> "traverse_dir_fetch": 1714684,
> "traverse_remote_ino": 0,
> "traverse_lock": 6,
> "load_cent": 19465322425,
> "q": 0,
> "exported": 1211,
> "exported_inodes": 845556,
> "imported": 1082,
> "imported_inodes": 1209280
> }
> }
> root@iccluster054:~# ceph --cluster container daemon mds.iccluster054.iccluster.epfl.ch perf dump mds
> {
> "mds": {
> "request": 267620366,
> "reply": 255792944,
> "reply_latency": {
> "avgcount": 255792944,
> "sum": 42256.407340600,
> "avgtime": 0.000165197
> },
> "forward": 11827411,
> "dir_fetch": 183,
> "dir_commit": 2607,
> "dir_split": 27,
> "dir_merge": 19,
> "inode_max": 2147483647,
> "inodes": 3740,
> "inodes_top": 2517,
> "inodes_bottom": 1149,
> "inodes_pin_tail": 74,
> "inodes_pinned": 143,
> "inodes_expired": 2103018,
> "inodes_with_caps": 57,
> "caps": 272,
> "subtrees": 8,
> "traverse": 267626346,
> "traverse_hit": 255796915,
> "traverse_forward": 11826902,
> "traverse_discover": 77,
> "traverse_dir_fetch": 30,
> "traverse_remote_ino": 0,
> "traverse_lock": 0,
> "load_cent": 26824996745,
> "q": 3,
> "exported": 1319,
> "exported_inodes": 2037400,
> "imported": 418,
> "imported_inodes": 7347
> }
> }
--
Yoann Moulin
EPFL IC-IT
_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
