Hi,
After a major crash in which we lost few osds, we are stucked with
incomplete pgs.
At first, peering was blocked with peering_blocked_by_history_les_bound.
Thus we set osd_find_best_info_ignore_history_les true for all osds
involved in the pg and set the primary osd down to force repeering.
It worked for one pg which is in a replica 3 pool, but for the 2 others
pgs which are in a erasurce coding (3+2) pool, it didn't worked... and
the pgs are still incomplete.
We know that we will have data lost, but we would like to minimize it
and save as much as possible. Also because this pg is part of the data
pool of a cephfs filesystem and it seems that files are spread among a
lot of pgs and loosing objects in a pg of the datapool means the loss of
a huge number of files !
According to https://www.spinics.net/lists/ceph-devel/msg41665.html
a way would be to :
- stop each osd involved in that pg
- export the shards with ceph-objectstore-tool
- compare the size of the shards and select the biggest one
(alternatively maybe we can also look at the num_objects returned by
ceph pg query ?)
- Mark it as complete
- restart the osd
- Wait for recover and finally get rid of the missing objects with ceph
pg 10.2 mark_unfound_lost delete
But on this other source
https://github.com/TheJJ/ceph-cheatsheet/blob/master/README.md or here
https://medium.com/opsops/recovering-ceph-from-reduced-data-availability-3-pgs-inactive-3-pgs-incomplete-b97cbcb4b5a1
it's suggested to remove the other parts (but I am not sure these
threads are really related to EC pools).
Could you confirm that we could follow this procedure (or correct it or
suggests anything else) ?
Thanks for your advices.
F.
PS: Here is a part of the ceph pg 10.2 query return :
"state": "incomplete",
"snap_trimq": "[]",
"snap_trimq_len": 0,
"epoch": 434321,
"up": [
78,
105,
90,
4,
41
],
"acting": [
78,
105,
90,
4,
41
],
"info": {
"pgid": "10.2s0",
"state": "incomplete",
"last_peered": "2020-04-22 09:58:42.505638",
"last_became_peered": "2020-04-20 11:06:07.701833",
"num_objects": 161314,
"num_objects_missing_on_primary": 0,
"num_objects_missing": 0,
"num_objects_degraded": 0,
"num_objects_misplaced": 0,
"num_objects_unfound": 0,
"num_objects_dirty": 161314,
"num_objects_recovered": 1290285,
"peer_info": [
"peer": "4(3)",
"pgid": "10.2s3",
"state": "active+undersized+degraded+remapped+backfilling",
"last_peered": "2020-04-25 13:25:12.860435",
"last_became_peered": "2020-04-22 10:45:45.520125",
"num_objects": 162869,
"num_objects_missing_on_primary": 0,
"num_objects_missing": 0,
"num_objects_degraded": 85071,
"num_objects_misplaced": 0,
"num_objects_unfound": 0,
"num_objects_dirty": 162869,
"num_objects_recovered": 1368082,
"peer": "9(2)",
"pgid": "10.2s2",
"state": "down",
"last_peered": "2020-04-25 13:25:12.860435",
"last_became_peered": "2020-04-22 10:45:45.520125",
"num_objects": 162869,
"num_objects_missing_on_primary": 0,
"num_objects_missing": 0,
"num_objects_degraded": 0,
"num_objects_misplaced": 0,
"num_objects_unfound": 0,
"num_objects_dirty": 162869,
"num_objects_recovered": 1368082,
"peer": "41(4)",
"pgid": "10.2s4",
"state": "unknown",
"last_peered": "0.000000",
"last_became_peered": "0.000000",
"num_objects": 0,
"num_objects_missing_on_primary": 0,
"num_objects_missing": 0,
"num_objects_degraded": 0,
"num_objects_misplaced": 0,
"num_objects_unfound": 0,
"num_objects_dirty": 0,
"num_objects_recovered": 0,
"peer": "46(4)",
"pgid": "10.2s4",
"state": "down",
"last_peered": "2020-04-25 13:25:12.860435",
"last_became_peered": "2020-04-22 10:45:45.520125",
"num_objects": 162869,
"num_objects_missing_on_primary": 0,
"num_objects_missing": 0,
"num_objects_degraded": 0,
"num_objects_misplaced": 0,
"num_objects_unfound": 0,
"num_objects_dirty": 162869,
"num_objects_recovered": 1368082,
"peer": "52(3)",
"pgid": "10.2s3",
"state": "unknown",
"last_peered": "0.000000",
"last_became_peered": "0.000000",
"num_objects": 0,
"num_objects_missing_on_primary": 0,
"num_objects_missing": 0,
"num_objects_degraded": 0,
"num_objects_misplaced": 0,
"num_objects_unfound": 0,
"num_objects_dirty": 0,
"num_objects_recovered": 0,
"peer": "69(0)",
"pgid": "10.2s0",
"state": "unknown",
"last_peered": "0.000000",
"last_became_peered": "0.000000",
"num_objects": 84063,
"num_objects_missing_on_primary": 0,
"num_objects_missing": 78807,
"num_objects_degraded": 0,
"num_objects_misplaced": 0,
"num_objects_unfound": 0,
"num_objects_dirty": 84063,
"num_objects_recovered": 0,
"peer": "90(2)",
"pgid": "10.2s2",
"state": "down",
"last_peered": "0.000000",
"last_became_peered": "0.000000",
"num_objects": 0,
"num_objects_missing_on_primary": 0,
"num_objects_missing": 0,
"num_objects_degraded": 0,
"num_objects_misplaced": 0,
"num_objects_unfound": 0,
"num_objects_dirty": 0,
"num_objects_recovered": 0,
"peer": "105(1)",
"pgid": "10.2s1",
"state": "incomplete",
"last_peered": "0.000000",
"last_became_peered": "0.000000",
"num_objects": 0,
"num_objects_missing_on_primary": 0,
"num_objects_missing": 0,
"num_objects_degraded": 0,
"num_objects_misplaced": 0,
"num_objects_unfound": 0,
"num_objects_dirty": 0,
"num_objects_recovered": 0,
"recovery_state": [
"peering_blocked_by": []
"agent_state": {}
_______________________________________________
ceph-users mailing list -- ceph-users@xxxxxxx
To unsubscribe send an email to ceph-users-leave@xxxxxxx
