After replace broken disk and ceph osd in it, cluster:
ceph health detail
HEALTH_WARN 2 pgs stuck unclean; recovery 60/346857819 degraded (0.000%)
pg 3.884 is stuck unclean for 570722.873270, current state
active+remapped, last acting [143,261,314]
pg 3.154a is stuck unclean for 577659.917066, current state
active+remapped, last acting [85,224,64]
recovery 60/346857819 degraded (0.000%)
What can be wrong?
It is possible this is caused by 'ceph osd reweight-by-utilization' ?
More info:
ceph -v
ceph version 0.67.9 (ba340a97c3dafc9155023da8d515eecc675c619a)
Enabled tunnables:
# begin crush map
tunable choose_local_tries 0
tunable choose_local_fallback_tries 0
tunable choose_total_tries 50
tunable chooseleaf_descend_once 1
df osd:
143 - 78%
261 - 78%
314 - 80%
85 - 76%
224 76%
64 - 75%
ceph osd dump | grep -i pool
pool 0 'data' rep size 3 min_size 1 crush_ruleset 0 object_hash
rjenkins pg_num 64 pgp_num 64 last_change 28459 owner 0
crash_replay_interval 45
pool 1 'metadata' rep size 3 min_size 1 crush_ruleset 1 object_hash
rjenkins pg_num 64 pgp_num 64 last_change 28460 owner 0
pool 2 'rbd' rep size 3 min_size 1 crush_ruleset 2 object_hash
rjenkins pg_num 64 pgp_num 64 last_change 28461 owner 0
pool 3 '.rgw.buckets' rep size 3 min_size 1 crush_ruleset 0
object_hash rjenkins pg_num 8192 pgp_num 8192 last_change 73711 owner
0
pool 4 '.log' rep size 3 min_size 1 crush_ruleset 0 object_hash
rjenkins pg_num 2048 pgp_num 2048 last_change 90517 owner 0
pool 5 '.rgw' rep size 3 min_size 1 crush_ruleset 0 object_hash
rjenkins pg_num 128 pgp_num 128 last_change 72467 owner 0
pool 6 '.users.uid' rep size 3 min_size 1 crush_ruleset 0 object_hash
rjenkins pg_num 8 pgp_num 8 last_change 28465 owner 0
pool 7 '.users' rep size 3 min_size 1 crush_ruleset 0 object_hash
rjenkins pg_num 8 pgp_num 8 last_change 28466 owner 0
pool 8 '.usage' rep size 2 min_size 1 crush_ruleset 0 object_hash
rjenkins pg_num 8 pgp_num 8 last_change 28467 owner
18446744073709551615
pool 9 '.intent-log' rep size 3 min_size 1 crush_ruleset 0 object_hash
rjenkins pg_num 8 pgp_num 8 last_change 28468 owner
18446744073709551615
pool 10 '.rgw.control' rep size 3 min_size 1 crush_ruleset 0
object_hash rjenkins pg_num 8 pgp_num 8 last_change 33485 owner
18446744073709551615
pool 11 '.rgw.gc' rep size 3 min_size 1 crush_ruleset 0 object_hash
rjenkins pg_num 8 pgp_num 8 last_change 33487 owner
18446744073709551615
pool 12 '.rgw.root' rep size 2 min_size 1 crush_ruleset 0 object_hash
rjenkins pg_num 8 pgp_num 8 last_change 44540 owner 0
pool 13 '' rep size 2 min_size 1 crush_ruleset 0 object_hash rjenkins
pg_num 8 pgp_num 8 last_change 46912 owner 0
ceph pg 3.884 query
{ "state": "active+remapped",
"epoch": 160655,
"up": [
143],
"acting": [
143,
261,
314],
"info": { "pgid": "3.884",
"last_update": "160655'111533",
"last_complete": "160655'111533",
"log_tail": "159997'108532",
"last_backfill": "MAX",
"purged_snaps": "[]",
"history": { "epoch_created": 4,
"last_epoch_started": 160261,
"last_epoch_clean": 160261,
"last_epoch_split": 11488,
"same_up_since": 160252,
"same_interval_since": 160260,
"same_primary_since": 160252,
"last_scrub": "155516'107396",
"last_scrub_stamp": "2014-08-06 03:15:18.193611",
"last_deep_scrub": "155516'107293",
"last_deep_scrub_stamp": "2014-08-03 06:45:59.215397",
"last_clean_scrub_stamp": "2014-08-06 03:15:18.193611"},
"stats": { "version": "160655'111533",
"reported_seq": "856860",
"reported_epoch": "160655",
"state": "active+remapped",
"last_fresh": "2014-08-18 23:06:47.068588",
"last_change": "2014-08-17 21:12:29.452628",
"last_active": "2014-08-18 23:06:47.068588",
"last_clean": "2014-08-12 08:44:00.293916",
"last_became_active": "2013-10-25 14:54:55.902442",
"last_unstale": "2014-08-18 23:06:47.068588",
"mapping_epoch": 160258,
"log_start": "159997'108532",
"ondisk_log_start": "159997'108532",
"created": 4,
"last_epoch_clean": 160261,
"parent": "0.0",
"parent_split_bits": 0,
"last_scrub": "155516'107396",
"last_scrub_stamp": "2014-08-06 03:15:18.193611",
"last_deep_scrub": "155516'107293",
"last_deep_scrub_stamp": "2014-08-03 06:45:59.215397",
"last_clean_scrub_stamp": "2014-08-06 03:15:18.193611",
"log_size": 3001,
"ondisk_log_size": 3001,
"stats_invalid": "0",
"stat_sum": { "num_bytes": 2750235192,
"num_objects": 12015,
"num_object_clones": 0,
"num_object_copies": 0,
"num_objects_missing_on_primary": 0,
"num_objects_degraded": 0,
"num_objects_unfound": 0,
"num_read": 708045,
"num_read_kb": 39418032,
"num_write": 120983,
"num_write_kb": 2383937,
"num_scrub_errors": 0,
"num_shallow_scrub_errors": 0,
"num_deep_scrub_errors": 0,
"num_objects_recovered": 44904,
"num_bytes_recovered": 7915543525,
"num_keys_recovered": 0},
"stat_cat_sum": {},
"up": [
143],
"acting": [
143,
261,
314]},
"empty": 0,
"dne": 0,
"incomplete": 0,
"last_epoch_started": 160261},
"recovery_state": [
{ "name": "Started\/Primary\/Active",
"enter_time": "2014-08-17 21:12:29.452429",
"might_have_unfound": [],
"recovery_progress": { "backfill_target": -1,
"waiting_on_backfill": 0,
"backfill_pos": "0\/\/0\/\/-1",
"backfill_info": { "begin": "0\/\/0\/\/-1",
"end": "0\/\/0\/\/-1",
"objects": []},
"peer_backfill_info": { "begin": "0\/\/0\/\/-1",
"end": "0\/\/0\/\/-1",
"objects": []},
"backfills_in_flight": [],
"pull_from_peer": [],
"pushing": []},
"scrub": { "scrubber.epoch_start": "0",
"scrubber.active": 0,
"scrubber.block_writes": 0,
"scrubber.finalizing": 0,
"scrubber.waiting_on": 0,
"scrubber.waiting_on_whom": []}},
{ "name": "Started",
"enter_time": "2014-08-17 21:12:28.436021"}]}
---
Regards
Dominik
2014-08-17 21:57 GMT+02:00 Dominik Mostowiec <dominikmostowiec at gmail.com>:
> Hi,
> After ceph osd out ( 1 osd ) cluster stopped rebalancing on
> 10621 active+clean, 2 active+remapped, 1 active+degraded+remapped;
>
> My crushmap is clean, there is not 'empty' device's.
> grep device /tmp/crush1.txt | grep -v osd | grep -v '^#' | wc -l
> 0
>
> Can You help me with this?
>
> "up": [
> 73],
> "acting": [
> 73,
> 102],
> I have only one copy of this PG ?
>
> More info:
> --
> ceph health detail
> HEALTH_WARN 1 pgs degraded; 3 pgs stuck unclean; recovery
> 12008/346501095 degraded (0.003%)
> pg 3.884 is stuck unclean for 478441.392837, current state
> active+remapped, last acting [143,261,314]
> pg 3.154a is stuck unclean for 485378.436630, current state
> active+remapped, last acting [85,224,64]
> pg 3.cc7 is stuck unclean for 116231.803324, current state
> active+degraded+remapped, last acting [73,102]
> pg 3.cc7 is active+degraded+remapped, acting [73,102]
> recovery 12008/346501095 degraded (0.003%)
> --
> ceph pg dump | grep 3.cc7
> dumped all in format plain
> 3.cc7 12014 0 12012 0 2845541648 3870 3870
> active+degraded+remapped 2014-08-17 21:08:04.155348
> 160273'273322 160273:1044675 [73] [73,102]159997'270388
> 2014-08-13 05:23:48.386184 159997'270388 2014-08-13
> 05:23:48.386184
> --
> grep '3.cc7' /var/log/ceph/ceph-osd.73.log
> 2014-08-17 21:06:47.494511 7f788a625700 20 osd.73 160241 kicking pg 3.cc7
> 2014-08-17 21:06:47.494513 7f788a625700 30 osd.73 pg_epoch: 160241
> pg[3.cc7( v 160241'273320 (155516'269452,160241'273320]
> local-les=160026 n=12016 ec=4 les/c 160026/160026
> 160024/160025/153162) [73]/[73,102] r=0 lpr=160025 mlcod 160241'273319
> active+degraded+remapped] lock
> 2014-08-17 21:06:47.494522 7f788a625700 10 osd.73 pg_epoch: 160241
> pg[3.cc7( v 160241'273320 (155516'269452,160241'273320]
> local-les=160026 n=12016 ec=4 les/c 160026/160026
> 160024/160025/153162) [73]/[73,102] r=0 lpr=160025 mlcod 160241'273319
> active+degraded+remapped] on_shutdown
> 2014-08-17 21:06:47.494530 7f788a625700 10 osd.73 pg_epoch: 160241
> pg[3.cc7( v 160241'273320 (155516'269452,160241'273320]
> local-les=160026 n=12016 ec=4 les/c 160026/160026
> 160024/160025/153162) [73]/[73,102] r=0 lpr=160025 mlcod 160241'273319
> active+degraded+remapped] clear_primary_state
> 2014-08-17 21:06:47.494541 7f788a625700 10 osd.73 pg_epoch: 160241
> pg[3.cc7( v 160241'273320 (155516'269452,160241'273320]
> local-les=160026 n=12016 ec=4 les/c 160026/160026
> 160024/160025/153162) [73]/[73,102] r=0 lpr=160025 luod=0'0 mlcod 0'0
> active+degraded+remapped] cancel_recovery
> 2014-08-17 21:06:47.494548 7f788a625700 10 osd.73 pg_epoch: 160241
> pg[3.cc7( v 160241'273320 (155516'269452,160241'273320]
> local-les=160026 n=12016 ec=4 les/c 160026/160026
> 160024/160025/153162) [73]/[73,102] r=0 lpr=160025 luod=0'0 mlcod 0'0
> active+degraded+remapped] clear_recovery_state
> 2014-08-17 21:07:00.758061 7f9819814700 1 osd.73 pg_epoch: 160244
> pg[3.cc7( v 160241'273320 (155516'269452,160241'273320]
> local-les=160026 n=12016 ec=4 les/c 160026/160026
> 160244/160244/160244) [73]/[73,102] r=0 lpr=160244 pi=160025-160243/2
> lcod 0'0 mlcod 0'0 remapped] state<Start>: transitioning to Primary
> 2014-08-17 21:07:51.121028 7f9819814700 1 osd.73 pg_epoch: 160246
> pg[3.cc7( v 160241'273320 (155516'269452,160241'273320]
> local-les=160245 n=12016 ec=4 les/c 160245/160245
> 160244/160246/160244) [73] r=0 lpr=160246 pi=160244-160245/1 lcod 0'0
> mlcod 0'0 inactive] state<Start>: transitioning to Primary
> 2014-08-17 21:08:02.995105 7f9818011700 1 osd.73 pg_epoch: 160248
> pg[3.cc7( v 160241'273320 (155516'269452,160241'273320]
> local-les=160247 n=12016 ec=4 les/c 160247/160247
> 160244/160248/160244) [73]/[73,102] r=0 lpr=160248 pi=160246-160247/1
> lcod 0'0 mlcod 0'0 remapped] state<Start>: transitioning to Primary
> --
> grep '3.cc7' /var/log/ceph/ceph-osd.102.log
> 2014-08-17 21:06:47.554359 7f630df7a700 1 osd.102 pg_epoch: 160242
> pg[3.cc7( v 160241'273320 (155516'269452,160241'273320]
> local-les=160026 n=12016 ec=4 les/c 160026/160026
> 160242/160242/160242) []/[102] r=0 lpr=160242 pi=158292-160241/12 lcod
> 160241'273319 mlcod 0'0 remapped] state<Start>: transitioning to
> Primary
> 2014-08-17 21:07:00.772420 7f630b775700 1 osd.102 pg_epoch: 160244
> pg[3.cc7( v 160241'273320 (155516'269452,160241'273320]
> local-les=160243 n=12016 ec=4 les/c 160243/160243
> 160244/160244/160244) [73]/[73,102] r=1 lpr=160244 pi=160242-160243/1
> lcod 160241'273319 remapped NOTIFY] state<Start>: transitioning to
> Stray
> 2014-08-17 21:07:50.832077 7f62f878a700 20 osd.102 160245 kicking pg 3.cc7
> 2014-08-17 21:07:50.832079 7f62f878a700 30 osd.102 pg_epoch: 160245
> pg[3.cc7( v 160241'273320 (155516'269452,160241'273320]
> local-les=160245 n=12016 ec=4 les/c 160245/160245
> 160244/160244/160244) [73]/[73,102] r=1 lpr=160244 pi=160242-160243/1
> luod=0'0 lcod 160241'273319 active+remapped] lock
> 2014-08-17 21:07:50.832089 7f62f878a700 10 osd.102 pg_epoch: 160245
> pg[3.cc7( v 160241'273320 (155516'269452,160241'273320]
> local-les=160245 n=12016 ec=4 les/c 160245/160245
> 160244/160244/160244) [73]/[73,102] r=1 lpr=160244 pi=160242-160243/1
> luod=0'0 lcod 160241'273319 active+remapped] on_shutdown
> 2014-08-17 21:07:50.832099 7f62f878a700 10 osd.102 pg_epoch: 160245
> pg[3.cc7( v 160241'273320 (155516'269452,160241'273320]
> local-les=160245 n=12016 ec=4 les/c 160245/160245
> 160244/160244/160244) [73]/[73,102] r=1 lpr=160244 pi=160242-160243/1
> luod=0'0 lcod 160241'273319 active+remapped] clear_primary_state
> 2014-08-17 21:07:50.832109 7f62f878a700 10 osd.102 pg_epoch: 160245
> pg[3.cc7( v 160241'273320 (155516'269452,160241'273320]
> local-les=160245 n=12016 ec=4 les/c 160245/160245
> 160244/160244/160244) [73]/[73,102] r=1 lpr=160244 pi=160242-160243/1
> luod=0'0 lcod 160241'273319 active+remapped] cancel_recovery
> 2014-08-17 21:07:50.832117 7f62f878a700 10 osd.102 pg_epoch: 160245
> pg[3.cc7( v 160241'273320 (155516'269452,160241'273320]
> local-les=160245 n=12016 ec=4 les/c 160245/160245
> 160244/160244/160244) [73]/[73,102] r=1 lpr=160244 pi=160242-160243/1
> luod=0'0 lcod 160241'273319 active+remapped] clear_recovery_state
> 2014-08-17 21:08:02.979471 7f3d54953700 1 osd.102 pg_epoch: 160248
> pg[3.cc7( v 160241'273320 (155516'269452,160241'273320]
> local-les=160245 n=12016 ec=4 les/c 160245/160245
> 160244/160248/160244) [73]/[73,102] r=1 lpr=160248 pi=160242-160247/3
> lcod 0'0 remapped NOTIFY] state<Start>: transitioning to Stray
> --
> ceph pg 3.cc7 query:
> { "state": "active+degraded+remapped",
> "epoch": 160273,
> "up": [
> 73],
> "acting": [
> 73,
> 102],
> "info": { "pgid": "3.cc7",
> "last_update": "160273'273322",
> "last_complete": "160273'273322",
> "log_tail": "155516'269452",
> "last_backfill": "MAX",
> "purged_snaps": "[]",
> "history": { "epoch_created": 4,
> "last_epoch_started": 160249,
> "last_epoch_clean": 160249,
> "last_epoch_split": 11503,
> "same_up_since": 160244,
> "same_interval_since": 160248,
> "same_primary_since": 160244,
> "last_scrub": "159997'270388",
> "last_scrub_stamp": "2014-08-13 05:23:48.386184",
> "last_deep_scrub": "159997'270388",
> "last_deep_scrub_stamp": "2014-08-13 05:23:48.386184",
> "last_clean_scrub_stamp": "2014-08-13 05:23:48.386184"},
> "stats": { "version": "160273'273322",
> "reported_seq": "1044675",
> "reported_epoch": "160273",
> "state": "active+degraded+remapped",
> "last_fresh": "2014-08-17 21:25:34.935269",
> "last_change": "2014-08-17 21:08:04.155348",
> "last_active": "2014-08-17 21:25:34.935269",
> "last_clean": "2014-08-16 13:20:49.883438",
> "last_became_active": "2013-10-25 13:05:26.849618",
> "last_unstale": "2014-08-17 21:25:34.935269",
> "mapping_epoch": 160246,
> "log_start": "155516'269452",
> "ondisk_log_start": "155516'269452",
> "created": 4,
> "last_epoch_clean": 160249,
> "parent": "0.0",
> "parent_split_bits": 0,
> "last_scrub": "159997'270388",
> "last_scrub_stamp": "2014-08-13 05:23:48.386184",
> "last_deep_scrub": "159997'270388",
> "last_deep_scrub_stamp": "2014-08-13 05:23:48.386184",
> "last_clean_scrub_stamp": "2014-08-13 05:23:48.386184",
> "log_size": 3870,
> "ondisk_log_size": 3870,
> "stats_invalid": "0",
> "stat_sum": { "num_bytes": 2845541648,
> "num_objects": 12014,
> "num_object_clones": 0,
> "num_object_copies": 0,
> "num_objects_missing_on_primary": 0,
> "num_objects_degraded": 0,
> "num_objects_unfound": 0,
> "num_read": 723032,
> "num_read_kb": 24658206,
> "num_write": 118401,
> "num_write_kb": 2360009,
> "num_scrub_errors": 0,
> "num_shallow_scrub_errors": 0,
> "num_deep_scrub_errors": 0,
> "num_objects_recovered": 55614,
> "num_bytes_recovered": 10782825899,
> "num_keys_recovered": 0},
> "stat_cat_sum": {},
> "up": [
> 73],
> "acting": [
> 73,
> 102]},
> "empty": 0,
> "dne": 0,
> "incomplete": 0,
> "last_epoch_started": 160249},
> "recovery_state": [
> { "name": "Started\/Primary\/Active",
> "enter_time": "2014-08-17 21:08:04.154871",
> "might_have_unfound": [],
> "recovery_progress": { "backfill_target": -1,
> "waiting_on_backfill": 0,
> "backfill_pos": "0\/\/0\/\/-1",
> "backfill_info": { "begin": "0\/\/0\/\/-1",
> "end": "0\/\/0\/\/-1",
> "objects": []},
> "peer_backfill_info": { "begin": "0\/\/0\/\/-1",
> "end": "0\/\/0\/\/-1",
> "objects": []},
> "backfills_in_flight": [],
> "pull_from_peer": [],
> "pushing": []},
> "scrub": { "scrubber.epoch_start": "0",
> "scrubber.active": 0,
> "scrubber.block_writes": 0,
> "scrubber.finalizing": 0,
> "scrubber.waiting_on": 0,
> "scrubber.waiting_on_whom": []}},
> { "name": "Started",
> "enter_time": "2014-08-17 21:08:02.995104"}]}
>
>
> --
> Regards
> Dominik
--
Pozdrawiam
Dominik
