Bug #58366
closedCrimson: unable to initialize pool for rbd due to inactive pgs
0%
Description
While trying to test Crimson-osd on DSAL lab cluster, it was observed that once OSDs were brought up and OSD pool was created, 31 pgs remained in inactive state and eventually progressed into unknown state. Due to pgs being unavailable, association of pool for rbd application is not possible
The issue is not reproducible with Quincy build on the same lab setup.
Crimson image - https://shaman.ceph.com/repos/ceph/main/aa49dee4e60f69d68f1c8252eef8f1c6cd991c08/crimson/267610/
Cephadm shell -
[root@dell-r730-043 /]# cephadm shell Inferring fsid 129128f4-816f-11ed-ae0e-801844e02b40 Inferring config /var/lib/ceph/129128f4-816f-11ed-ae0e-801844e02b40/mon.dell-r730-043.dsal.lab.eng.rdu2.redhat.com/config Using ceph image with id 'd92233276102' and tag 'aa49dee4e60f69d68f1c8252eef8f1c6cd991c08-crimson' created on 2022-12-13 16:56:05 +0000 UTC quay.ceph.io/ceph-ci/ceph@sha256:7b703795d72ebf9fb6e9c28a88f6b50d10161225951107951541631dd2640a1b [ceph: root@dell-r730-043 /]# ceph -v ceph version 18.0.0-1417-gaa49dee4 (aa49dee4e60f69d68f1c8252eef8f1c6cd991c08) reef (dev)
ceph status shows a Health warning (Reduced data availability: 31 pgs inactive) and the pgs status as inactive
[ceph: root@dell-r730-043 /]# ceph -s cluster: id: 129128f4-816f-11ed-ae0e-801844e02b40 health: HEALTH_WARN Reduced data availability: 31 pgs inactive services: mon: 3 daemons, quorum dell-r730-043.dsal.lab.eng.rdu2.redhat.com,dell-r730-006,dell-r730-026 (age 5d) mgr: dell-r730-043.dsal.lab.eng.rdu2.redhat.com.bhyhhe(active, since 5d), standbys: dell-r730-006.efjfln osd: 9 osds: 9 up (since 5d), 9 in (since 5d) data: pools: 2 pools, 33 pgs objects: 0 objects, 0 B usage: 53 MiB used, 900 GiB / 900 GiB avail pgs: 93.939% pgs unknown 31 unknown 2 active+clean progress: Global Recovery Event (0s) [............................]
DSAL Lab setup -
HOST ADDR LABELS STATUS dell-r730-006.dsal.lab.eng.rdu2.redhat.com 10.1.8.16 crash alertmanager mon mgr osd node-exporter dell-r730-026.dsal.lab.eng.rdu2.redhat.com 10.1.8.36 crash osd mon node-exporter dell-r730-043.dsal.lab.eng.rdu2.redhat.com 10.1.8.53 _admin crash alertmanager mon mgr prometheus osd grafana installer node-exporter 3 hosts in cluster
Ceph OSDs up and running -
[ceph: root@dell-r730-043 /]# ceph osd tree ID CLASS WEIGHT TYPE NAME STATUS REWEIGHT PRI-AFF -1 0.87918 root default -2 0.29306 host dell-r730-006 2 0.09769 osd.2 up 1.00000 1.00000 3 0.09769 osd.3 up 1.00000 1.00000 6 0.09769 osd.6 up 1.00000 1.00000 -4 0.29306 host dell-r730-026 0 0.09769 osd.0 up 1.00000 1.00000 5 0.09769 osd.5 up 1.00000 1.00000 7 0.09769 osd.7 up 1.00000 1.00000 -3 0.29306 host dell-r730-043 1 0.09769 osd.1 up 1.00000 1.00000 4 0.09769 osd.4 up 1.00000 1.00000 8 0.09769 osd.8 up 1.00000 1.00000
Ceph Health Details -
[ceph: root@dell-r730-043 /]# ceph health detail HEALTH_WARN Reduced data availability: 31 pgs inactive [WRN] PG_AVAILABILITY: Reduced data availability: 31 pgs inactive pg 2.1 is stuck inactive for 5d, current state unknown, last acting [] pg 2.2 is stuck inactive for 5d, current state unknown, last acting [] pg 2.3 is stuck inactive for 5d, current state unknown, last acting [] pg 2.4 is stuck inactive for 5d, current state unknown, last acting [] pg 2.5 is stuck inactive for 5d, current state unknown, last acting [] pg 2.6 is stuck inactive for 5d, current state unknown, last acting [] pg 2.7 is stuck inactive for 5d, current state unknown, last acting [] pg 2.8 is stuck inactive for 5d, current state unknown, last acting [] pg 2.9 is stuck inactive for 5d, current state unknown, last acting [] pg 2.a is stuck inactive for 5d, current state unknown, last acting [] pg 2.b is stuck inactive for 5d, current state unknown, last acting [] pg 2.c is stuck inactive for 5d, current state unknown, last acting [] pg 2.d is stuck inactive for 5d, current state unknown, last acting [] pg 2.e is stuck inactive for 5d, current state unknown, last acting [] pg 2.f is stuck inactive for 5d, current state unknown, last acting [] pg 2.10 is stuck inactive for 5d, current state unknown, last acting [] pg 2.11 is stuck inactive for 5d, current state unknown, last acting [] pg 2.12 is stuck inactive for 5d, current state unknown, last acting [] pg 2.13 is stuck inactive for 5d, current state unknown, last acting [] pg 2.14 is stuck inactive for 5d, current state unknown, last acting [] pg 2.15 is stuck inactive for 5d, current state unknown, last acting [] pg 2.16 is stuck inactive for 5d, current state unknown, last acting [] pg 2.17 is stuck inactive for 5d, current state unknown, last acting [] pg 2.18 is stuck inactive for 5d, current state unknown, last acting [] pg 2.19 is stuck inactive for 5d, current state unknown, last acting [] pg 2.1a is stuck inactive for 5d, current state unknown, last acting [] pg 2.1b is stuck inactive for 5d, current state unknown, last acting [] pg 2.1c is stuck inactive for 5d, current state unknown, last acting [] pg 2.1d is stuck inactive for 5d, current state unknown, last acting [] pg 2.1e is stuck inactive for 5d, current state unknown, last acting [] pg 2.1f is stuck inactive for 5d, current state unknown, last acting []
Ceph ps stats -
[ceph: root@dell-r730-043 /]# ceph pg stat 33 pgs: 31 unknown, 2 active+clean; 0 B data, 53 MiB used, 900 GiB / 900 GiB avail
Ceph pg dump stats -
[ceph: root@dell-r730-043 /]# ceph pg dump_stuck PG_STAT STATE UP UP_PRIMARY ACTING ACTING_PRIMARY 2.e unknown [] -1 [] -1 2.d unknown [] -1 [] -1 2.c unknown [] -1 [] -1 2.b unknown [] -1 [] -1 2.a unknown [] -1 [] -1 2.9 unknown [] -1 [] -1 2.8 unknown [] -1 [] -1 2.7 unknown [] -1 [] -1 2.6 unknown [] -1 [] -1 2.5 unknown [] -1 [] -1 2.3 unknown [] -1 [] -1 2.1 unknown [] -1 [] -1 2.2 unknown [] -1 [] -1 2.4 unknown [] -1 [] -1 2.f unknown [] -1 [] -1 2.1b unknown [] -1 [] -1 2.1c unknown [] -1 [] -1 2.1a unknown [] -1 [] -1 2.1d unknown [] -1 [] -1 2.1f unknown [] -1 [] -1 2.1e unknown [] -1 [] -1 2.19 unknown [] -1 [] -1 2.18 unknown [] -1 [] -1 2.17 unknown [] -1 [] -1 2.16 unknown [] -1 [] -1 2.15 unknown [] -1 [] -1 2.14 unknown [] -1 [] -1 2.13 unknown [] -1 [] -1 2.12 unknown [] -1 [] -1 2.11 unknown [] -1 [] -1 2.10 unknown [] -1 [] -1 ok
Ceph Config Dump -
[ceph: root@dell-r730-043 /]# ceph config dump WHO MASK LEVEL OPTION VALUE RO global basic container_image quay.ceph.io/ceph-ci/ceph@sha256:7b703795d72ebf9fb6e9c28a88f6b50d10161225951107951541631dd2640a1b * global basic log_to_file true mon advanced auth_allow_insecure_global_id_reclaim false mon advanced public_network 10.1.8.0/22 * mgr advanced mgr/cephadm/container_init True * mgr advanced mgr/cephadm/migration_current 5 * mgr advanced mgr/dashboard/ALERTMANAGER_API_HOST http://host.containers.internal:9093 * mgr advanced mgr/dashboard/GRAFANA_API_SSL_VERIFY false * mgr advanced mgr/dashboard/GRAFANA_API_URL https://host.containers.internal:3000 * mgr advanced mgr/dashboard/PROMETHEUS_API_HOST http://host.containers.internal:9095 * mgr advanced mgr/dashboard/ssl_server_port 8443 * mgr advanced mgr/orchestrator/orchestrator cephadm osd host:dell-r730-006 basic osd_memory_target 29262227456 osd host:dell-r730-026 basic osd_memory_target 30693042176 osd host:dell-r730-043 basic osd_memory_target 28187644586 osd advanced osd_memory_target_autotune true
Ceph pg dump attached
Ceph /var/logs - https://drive.google.com/file/d/1bVTcnDwnVHZCtvuz1V55Hisz0-MTGzuz/view?usp=share_link
Files
Updated by Samuel Just over 1 year ago
It doesn't look like pool id 2 actually maps to any osds. Can you attach the osdmap?
Updated by Nitzan Mordechai over 1 year ago
- Assignee set to Nitzan Mordechai
@Harsh Kumar, can you also attach logs with DEBUG messages?
as Sam mention, it doesn't looks like any of the pgs from poolid 2 are mapped.
Updated by Harsh Kumar over 1 year ago
Hey Nitzan, Sam,
Apologies for the delay, I had a hard time restoring my DSAL lab setup to the above ceph cluster configuration.
I couldn't find a recent crimson image off of reef build, so I instead used a crimson image off of quincy build, however, I way able to reproduce the issue with this build as well.
[ceph: root@dell-r730-043 /]# ceph -s cluster: id: 7a245c9c-9016-11ed-a78e-801844e02b40 health: HEALTH_WARN Failed to apply 1 service(s): prometheus Reduced data availability: 31 pgs inactive services: mon: 3 daemons, quorum dell-r730-043.dsal.lab.eng.rdu2.redhat.com,dell-r730-026,dell-r730-006 (age 44h) mgr: dell-r730-043.dsal.lab.eng.rdu2.redhat.com.nbllxz(active, since 2d), standbys: dell-r730-006.jxqbih osd: 9 osds: 9 up (since 44h), 9 in (since 44h) data: pools: 2 pools, 33 pgs objects: 2 objects, 449 KiB usage: 100 MiB used, 900 GiB / 900 GiB avail pgs: 93.939% pgs unknown 31 unknown 2 active+clean progress: Global Recovery Event (20h) [=...........................] (remaining: 4w) [ceph: root@dell-r730-043 /]# ceph -v ceph version 17.2.5-624-ga112c1c7 (a112c1c71fab41e0cb0b3bb2cc58e9792caa32cb) quincy (stable)
OSD map summary -
[ceph: root@dell-r730-043 /]# ceph osd dump epoch 37 fsid 7a245c9c-9016-11ed-a78e-801844e02b40 created 2023-01-09T12:10:28.248287+0000 modified 2023-01-10T12:11:28.073432+0000 flags sortbitwise,recovery_deletes,purged_snapdirs,pglog_hardlimit crush_version 8 full_ratio 0.95 backfillfull_ratio 0.9 nearfull_ratio 0.85 require_min_compat_client luminous min_compat_client jewel require_osd_release quincy stretch_mode_enabled false pool 1 '.mgr' replicated size 3 min_size 2 crush_rule 0 object_hash rjenkins pg_num 1 pgp_num 1 autoscale_mode on last_change 16 flags hashpspool stripe_width 0 pg_num_max 32 pg_num_min 1 application mgr pool 2 'rbd' replicated size 3 min_size 2 crush_rule 0 object_hash rjenkins pg_num 32 pgp_num 1 pgp_num_target 32 autoscale_mode on last_change 34 lfor 0/0/34 flags hashpspool stripe_width 0 max_osd 9 osd.0 up in weight 1 up_from 11 up_thru 0 down_at 0 last_clean_interval [0,0) v2:10.1.8.53:6802/2115189942 v2:10.1.8.53:6803/2115189942 exists,up de67cb44-edfd-4082-83ea-e6a87aef4c3c osd.1 up in weight 1 up_from 11 up_thru 24 down_at 0 last_clean_interval [0,0) v2:10.1.8.36:6801/1664737338 v2:10.1.8.36:6800/1664737338 exists,up c725c525-dd09-4fad-a577-8a18489c48de osd.2 up in weight 1 up_from 13 up_thru 34 down_at 0 last_clean_interval [0,0) v2:10.1.8.53:6807/441164187 v2:10.1.8.53:6806/441164187 exists,up ee9fb0ae-4603-4640-b17d-b058ce65c3c4 osd.3 up in weight 1 up_from 13 up_thru 0 down_at 0 last_clean_interval [0,0) v2:10.1.8.36:6804/729704151 v2:10.1.8.36:6805/729704151 exists,up dd1f2bcf-6ba3-4188-a447-4f05e69f7e8c osd.4 up in weight 1 up_from 19 up_thru 0 down_at 0 last_clean_interval [0,0) v2:10.1.8.53:6811/3933002731 v2:10.1.8.53:6810/3933002731 exists,up eb1d84eb-1caf-4cb5-a00c-703a085eda2c osd.5 up in weight 1 up_from 18 up_thru 0 down_at 0 last_clean_interval [0,0) v2:10.1.8.36:6808/410057933 v2:10.1.8.36:6809/410057933 exists,up 872e488e-1cfa-4fbb-9865-e5b2e53912df osd.6 up in weight 1 up_from 24 up_thru 0 down_at 0 last_clean_interval [0,0) v2:10.1.8.16:6801/2634977743 v2:10.1.8.16:6800/2634977743 exists,up 006169f7-e79b-4d3f-ab0d-5bc82529c614 osd.7 up in weight 1 up_from 27 up_thru 0 down_at 0 last_clean_interval [0,0) v2:10.1.8.16:6804/3089609507 v2:10.1.8.16:6805/3089609507 exists,up e33a1271-6975-4eb3-a44a-7054a0528ba1 osd.8 up in weight 1 up_from 29 up_thru 0 down_at 0 last_clean_interval [0,0) v2:10.1.8.16:6808/3765740467 v2:10.1.8.16:6809/3765740467 exists,up c9741a00-acd2-43aa-a7ef-086d1f07f6fc
ceph osd tree -
[ceph: root@dell-r730-043 /]# ceph osd tree ID CLASS WEIGHT TYPE NAME STATUS REWEIGHT PRI-AFF -1 0.87918 root default -4 0.29306 host dell-r730-006 6 0.09769 osd.6 up 1.00000 1.00000 7 0.09769 osd.7 up 1.00000 1.00000 8 0.09769 osd.8 up 1.00000 1.00000 -3 0.29306 host dell-r730-026 1 0.09769 osd.1 up 1.00000 1.00000 3 0.09769 osd.3 up 1.00000 1.00000 5 0.09769 osd.5 up 1.00000 1.00000 -2 0.29306 host dell-r730-043 0 0.09769 osd.0 up 1.00000 1.00000 2 0.09769 osd.2 up 1.00000 1.00000 4 0.09769 osd.4 up 1.00000 1.00000
Please let me know if you need access to the cluster for further investigation
I will attach the requested logs shortly.
Updated by Nitzan Mordechai over 1 year ago
Harsh, please attach the logs with debug level
Updated by Harsh Kumar over 1 year ago
Nitzan Mordechai wrote:
Harsh, please attach the logs with debug level
Hi Nitzan,
Please find the logs for the current cluster setup here - https://drive.google.com/file/d/1x2MLvSRlK1AWOYHAuRreTAMmCK0zn8xU/view?usp=share_link
Updated by Nitzan Mordechai over 1 year ago
It appears that autoscaler is on, which cause the issue to happen.