Dear everyone,

Update, on Friday we decided to apply blunt force to the problem (this 
still being a prototype cluster for the time being) and started 
rebooting nodes, one by one, again. After the second rebooted node had 
come back online the misplaced percentage jumped by about 10 percent but 
we finally began to see 'ceph -s' report recovery traffic - and when I 
checked this morning all PGs were back to normal.

Just in case this is helps anyone figure out what did happen, so that we 
can avoid this / fix it faster in the future:

* CRUSH: we do group our hosts into buckets corresponding to the server 
rooms they are located in (of which there are three). Apart from that, 
nothing non-default;

* EC pools - yes, we have got some of these. See below.

* pool and CRUSH-rule details:

pool 1 '.mgr' replicated size 3 min_size 2 crush_rule 6 object_hash 
rjenkins pg_num 1 pgp_num 1 autoscale_mode on last_change 545 flags 
hashpspool stripe_width 0 pg_num_max 32 pg_num_min 1 application mgr 
read_balance_score 50.00

pool 2 'cephfs.fs1.meta' replicated size 3 min_size 2 crush_rule 6 
object_hash rjenkins pg_num 16 pgp_num 16 autoscale_mode on last_change 
548 lfor 0/0/153 flags hashpspool stripe_width 0 pg_autoscale_bias 4 
pg_num_min 16 recovery_priority 5 application cephfs read_balance_score 3.02

pool 3 'cephfs.fs1.data' replicated size 3 min_size 2 crush_rule 6 
object_hash rjenkins pg_num 1024 pgp_num 1024 autoscale_mode on 
last_change 38714 lfor 0/0/201 flags hashpspool,selfmanaged_snaps,bulk 
stripe_width 0 application cephfs read_balance_score 1.08

pool 4 '.nfs' replicated size 3 min_size 2 crush_rule 6 object_hash 
rjenkins pg_num 32 pgp_num 32 autoscale_mode on last_change 546 lfor 
0/0/233 flags hashpspool stripe_width 0 application nfs 
read_balance_score 2.99

pool 5 'cephfs.fs1.repl1' replicated size 3 min_size 2 crush_rule 6 
object_hash rjenkins pg_num 512 pgp_num 512 autoscale_mode on 
last_change 38714 lfor 0/0/264 flags hashpspool,selfmanaged_snaps,bulk 
stripe_width 0 application cephfs read_balance_score 1.13

pool 8 '.rgw.root' replicated size 3 min_size 2 crush_rule 6 object_hash 
rjenkins pg_num 32 pgp_num 32 autoscale_mode on last_change 20219 lfor 
0/0/569 flags hashpspool stripe_width 0 application rgw 
read_balance_score 4.52

pool 9 'default.rgw.log' replicated size 3 min_size 2 crush_rule 6 
object_hash rjenkins pg_num 32 pgp_num 32 autoscale_mode on last_change 
20221 lfor 0/0/571 flags hashpspool stripe_width 0 application rgw 
read_balance_score 2.99

pool 10 'default.rgw.control' replicated size 3 min_size 2 crush_rule 6 
object_hash rjenkins pg_num 32 pgp_num 32 autoscale_mode on last_change 
20226 lfor 0/0/571 flags hashpspool stripe_width 0 application rgw 
read_balance_score 4.49

pool 11 'default.rgw.meta' replicated size 3 min_size 2 crush_rule 6 
object_hash rjenkins pg_num 32 pgp_num 32 autoscale_mode on last_change 
20231 lfor 0/0/573 flags hashpspool stripe_width 0 pg_autoscale_bias 4 
application rgw read_balance_score 2.99

pool 15 '.smb' replicated size 3 min_size 2 crush_rule 6 object_hash 
rjenkins pg_num 32 pgp_num 32 autoscale_mode on last_change 20233 lfor 
0/0/6089 flags hashpspool stripe_width 0 application smb 
read_balance_score 4.50

pool 16 'cephfs.fs1.ec1' erasure profile isa_rsv_4p2_host_hdd size 6 
min_size 5 crush_rule 4 object_hash rjenkins pg_num 128 pgp_num 128 
autoscale_mode on last_change 38714 lfor 0/0/9461 flags 
hashpspool,ec_overwrites,selfmanaged_snaps,bulk stripe_width 16384 
fast_read 1 application cephfs

Where the relevant CRUSH rules are:
* 4 - erasure, on hard drives only, host-level failure domain
* 6 - replicated, on NVMe drives only, room-level failure domain
-- 
MS
_______________________________________________
ceph-users mailing list -- [email protected]
To unsubscribe send an email to [email protected]

Reply via email to