Changing sending email address as something was wrong with my last one. Still OP here.
Cluster is generally healthy. Not running out of storage space or pools filling up. As mentioned in the original post, one RGW is able to come online. I've cross-compared about every file permission, config file, keyring, etc between the working RGW and all other non working RGWs, and nothing seems to allow them to rejoin the cluster.
ceph -s
[root@host ceph]# ceph -s
cluster:
id: <id>
health: HEALTH_WARN
601 large omap objects
502 pgs not deep-scrubbed in time
1 pgs not scrubbed in time
services:
mon: 3 daemons, quorum <mon1>,<mon2>,<mon3> (age 28h)
mgr: <mgr1>(active, since 28h), standbys: <mgr2>, <mgr3>
osd: 130 osds: 130 up (since 3d), 130 in
rgw: 1 daemon active (<rgw1>)
task status:
data:
pools: 7 pools, 4288 pgs
objects: 926.15M objects, 88 TiB
usage: 397 TiB used, 646 TiB / 1.0 PiB avail
pgs: 4258 active+clean
30 active+clean+scrubbing+deep
io:
client: 340 KiB/s rd, 280 KiB/s wr, 370 op/s rd, 496 op/s wr
ceph df:
RAW STORAGE:
CLASS SIZE AVAIL USED RAW USED %RAW USED
hdd 763 TiB 450 TiB 313 TiB 313 TiB 41.04
ssd 279 TiB 196 TiB 80 TiB 84 TiB 29.95
TOTAL 1.0 PiB 646 TiB 394 TiB 397 TiB 38.07
POOLS:
POOL ID PGS STORED OBJECTS USED %USED MAX AVAIL
.rgw.root 51 32 172 KiB 98 14 MiB 0 177 TiB
zone.rgw.control 60 32 0 B 8 0 B 0 177 TiB
zone.rgw.meta 61 32 11 MiB 34.04k 5.0 GiB 0 177 TiB
zone.rgw.log 62 32 508 GiB 438.39k 508 GiB 0.09 177 TiB
zone.rgw.buckets.data 63 4096 88 TiB 925.20M 361 TiB 40.47 177 TiB
zone.rgw.buckets.index 64 32 890 GiB 469.31k 890 GiB 0.16 177 TiB
zone.rgw.buckets.non-ec 66 32 3.7 MiB 610 3.7 MiB 0 177 TiB
_______________________________________________
ceph-users mailing list -- ceph-users@xxxxxxx
To unsubscribe send an email to ceph-users-leave@xxxxxxx
