tmp

[zhanglu]

5-12-23 06:22:21.512 UTC [26] LOG: database system was interrupted; last known up at 2025-12-23 06:21:21 UTC
2025-12-23 06:22:21.950 UTC [26] LOG: database system was not properly shut down; automatic recovery in progress
2025-12-23 06:22:21.954 UTC [26] LOG: redo starts at 18/9B999808
2025-12-23 06:22:21.955 UTC [26] LOG: invalid record length at 18/9BA06F18: wanted 24, got 0
2025-12-23 06:22:21.955 UTC [26] LOG: redo done at 18/9BA06EF0
2025-12-23 06:22:21.955 UTC [26] LOG: last completed transaction was at log time 2025-12-23 06:22:20.084128+00
2025-12-23 06:22:22.075 UTC [1] LOG: database system is ready to accept connections

[zhanglu]

cluster:
id: 807d820b-5c5b-451c-9f52-41b93d5d905a
health: HEALTH_ERR
1 MDSs report oversized cache
1 MDSs are read only
2 MDSs behind on trimming
full ratio(s) out of order
Low space hindering backfill (add storage if this doesn't resolve itself): 10 pgs backfill_toofull
94 pgs not deep-scrubbed in time
69 pgs not scrubbed in time

services:
mon: 3 daemons, quorum bm,bo,bp (age 13d)
mgr: b(active, since 2w), standbys: a
mds: 1/1 daemons up, 1 hot standby
osd: 51 osds: 51 up (since 13d), 51 in (since 2w); 67 remapped pgs

data:
volumes: 1/1 healthy
pools: 4 pools, 2097 pgs
objects: 279.98M objects, 306 TiB
usage: 619 TiB used, 82 TiB / 701 TiB avail
pgs: 3748313/601598194 objects misplaced (0.623%)
2024 active+clean
57 active+remapped+backfilling
10 active+remapped+backfill_toofull
6 active+clean+scrubbing+deep

io:
client: 1.2 MiB/s rd, 100 KiB/s wr, 183 op/s rd, 19 op/s wr
recovery: 52 MiB/s, 37 objects/s

[zhanglu]

cluster:
id: 807d820b-5c5b-451c-9f52-41b93d5d905a
health: HEALTH_ERR
1 MDSs report oversized cache
1 MDSs are read only
2 MDSs behind on trimming
full ratio(s) out of order
Low space hindering backfill (add storage if this doesn't resolve itself): 10 pgs backfill_toofull
94 pgs not deep-scrubbed in time
69 pgs not scrubbed in time

services:
mon: 3 daemons, quorum bm,bo,bp (age 13d)
mgr: b(active, since 2w), standbys: a
mds: 1/1 daemons up, 1 hot standby
osd: 51 osds: 51 up (since 13d), 51 in (since 2w); 67 remapped pgs

data:
volumes: 1/1 healthy
pools: 4 pools, 2097 pgs
objects: 279.98M objects, 306 TiB
usage: 619 TiB used, 82 TiB / 701 TiB avail
pgs: 3748313/601598194 objects misplaced (0.623%)
2024 active+clean
57 active+remapped+backfilling
10 active+remapped+backfill_toofull
6 active+clean+scrubbing+deep

io:
client: 1.2 MiB/s rd, 100 KiB/s wr, 183 op/s rd, 19 op/s wr
recovery: 52 MiB/s, 37 objects/s

[zhanglu]

Image:         registry.k8s.io/sig-storage/csi-node-driver-registrar:v2.5.1
Image:         quay.io/cephcsi/cephcsi:v3.7.2
Image:         registry.k8s.io/sig-storage/csi-node-driver-registrar:v2.5.1
Image:         quay.io/cephcsi/cephcsi:v3.7.2
Image:         registry.k8s.io/sig-storage/csi-node-driver-registrar:v2.5.1
Image:         quay.io/cephcsi/cephcsi:v3.7.2
Image:         registry.k8s.io/sig-storage/csi-node-driver-registrar:v2.5.1
Image:         quay.io/cephcsi/cephcsi:v3.7.2
Image:         registry.k8s.io/sig-storage/csi-node-driver-registrar:v2.5.1
Image:         quay.io/cephcsi/cephcsi:v3.7.2
Image:         registry.k8s.io/sig-storage/csi-attacher:v4.0.0
Image:         registry.k8s.io/sig-storage/csi-snapshotter:v6.1.0
Image:         registry.k8s.io/sig-storage/csi-resizer:v1.6.0
Image:         registry.k8s.io/sig-storage/csi-provisioner:v3.3.0
Image:         quay.io/cephcsi/cephcsi:v3.7.2
Image:         registry.k8s.io/sig-storage/csi-attacher:v4.0.0
Image:         registry.k8s.io/sig-storage/csi-snapshotter:v6.1.0
Image:         registry.k8s.io/sig-storage/csi-resizer:v1.6.0
Image:         registry.k8s.io/sig-storage/csi-provisioner:v3.3.0
Image:         quay.io/cephcsi/cephcsi:v3.7.2
Image:         registry.k8s.io/sig-storage/csi-node-driver-registrar:v2.5.1
Image:         quay.io/cephcsi/cephcsi:v3.7.2
Image:         registry.k8s.io/sig-storage/csi-node-driver-registrar:v2.5.1
Image:         quay.io/cephcsi/cephcsi:v3.7.2
Image:         registry.k8s.io/sig-storage/csi-node-driver-registrar:v2.5.1
Image:         quay.io/cephcsi/cephcsi:v3.7.2
Image:         registry.k8s.io/sig-storage/csi-node-driver-registrar:v2.5.1
Image:         quay.io/cephcsi/cephcsi:v3.7.2
Image:         registry.k8s.io/sig-storage/csi-node-driver-registrar:v2.5.1
Image:         quay.io/cephcsi/cephcsi:v3.7.2
Image:         registry.k8s.io/sig-storage/csi-node-driver-registrar:v2.5.1
Image:         quay.io/cephcsi/cephcsi:v3.7.2
Image:         registry.k8s.io/sig-storage/csi-provisioner:v3.3.0
Image:         registry.k8s.io/sig-storage/csi-resizer:v1.6.0
Image:         registry.k8s.io/sig-storage/csi-attacher:v4.0.0
Image:         registry.k8s.io/sig-storage/csi-snapshotter:v6.1.0
Image:         quay.io/cephcsi/cephcsi:v3.7.2
Image:         registry.k8s.io/sig-storage/csi-provisioner:v3.3.0
Image:         registry.k8s.io/sig-storage/csi-resizer:v1.6.0
Image:         registry.k8s.io/sig-storage/csi-attacher:v4.0.0
Image:         registry.k8s.io/sig-storage/csi-snapshotter:v6.1.0
Image:         quay.io/cephcsi/cephcsi:v3.7.2
Image:         registry.k8s.io/sig-storage/csi-node-driver-registrar:v2.5.1
Image:         quay.io/cephcsi/cephcsi:v3.7.2
Image:         registry.k8s.io/sig-storage/csi-node-driver-registrar:v2.5.1
Image:         quay.io/cephcsi/cephcsi:v3.7.2
Image:         registry.k8s.io/sig-storage/csi-node-driver-registrar:v2.5.1
Image:         quay.io/cephcsi/cephcsi:v3.7.2
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         rook/ceph:v1.10.8
Image:         quay.io/cephcsi/cephcsi:v3.7.2
Image:         rook/ceph:v1.10.8
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         rook/ceph:v1.10.8
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         rook/ceph:v1.10.8
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         rook/ceph:v1.10.8
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5
Image:         rook/ceph:v1.10.8
Image:         quay.io/ceph/ceph:v17.2.5
Image:         quay.io/ceph/ceph:v17.2.5

[zhanglu]

Image:          quay.io/calico/kube-controllers:v3.16.5
Image:         quay.io/calico/cni:v3.16.5
Image:         quay.io/calico/cni:v3.16.5
Image:          quay.io/calico/node:v3.16.5
Image:         quay.io/calico/cni:v3.16.5
Image:         quay.io/calico/cni:v3.16.5
Image:          quay.io/calico/node:v3.16.5
Image:         quay.io/calico/cni:v3.16.5
Image:         quay.io/calico/cni:v3.16.5
Image:          quay.io/calico/node:v3.16.5
Image:         quay.io/calico/cni:v3.16.5
Image:         quay.io/calico/cni:v3.16.5
Image:          quay.io/calico/node:v3.16.5
Image:         quay.io/calico/cni:v3.16.5
Image:         quay.io/calico/cni:v3.16.5
Image:          quay.io/calico/node:v3.16.5
Image:         quay.io/calico/cni:v3.16.5
Image:         quay.io/calico/cni:v3.16.5
Image:          quay.io/calico/node:v3.16.5
Image:         quay.io/calico/cni:v3.16.5
Image:         quay.io/calico/cni:v3.16.5
Image:          quay.io/calico/node:v3.16.5
Image:         k8s.gcr.io/coredns:1.7.0
Image:         k8s.gcr.io/coredns:1.7.0
Image:         k8s.gcr.io/coredns:1.7.0
Image:         k8s.gcr.io/coredns:1.7.0
Image:         k8s.gcr.io/coredns:1.7.0
Image:         k8s.gcr.io/coredns:1.7.0
Image:         k8s.gcr.io/cpa/cluster-proportional-autoscaler-amd64:1.8.3
Image:         k8s.gcr.io/kube-apiserver:v1.19.7
Image:         k8s.gcr.io/kube-apiserver:v1.19.7
Image:         k8s.gcr.io/kube-controller-manager:v1.19.7
Image:         k8s.gcr.io/kube-controller-manager:v1.19.7
Image:         k8s.gcr.io/kube-proxy:v1.19.7
Image:         k8s.gcr.io/kube-proxy:v1.19.7
Image:         k8s.gcr.io/kube-proxy:v1.19.7
Image:         k8s.gcr.io/kube-proxy:v1.19.7
Image:         k8s.gcr.io/kube-proxy:v1.19.7
Image:         k8s.gcr.io/kube-proxy:v1.19.7
Image:         k8s.gcr.io/kube-proxy:v1.19.7
Image:         k8s.gcr.io/kube-scheduler:v1.19.7
Image:         k8s.gcr.io/kube-scheduler:v1.19.7
Image:          docker.io/library/nginx:1.19
Image:          docker.io/library/nginx:1.19
Image:          docker.io/library/nginx:1.19
Image:          docker.io/library/nginx:1.19
Image:          docker.io/library/nginx:1.19
Image:         k8s.gcr.io/dns/k8s-dns-node-cache:1.16.0
Image:         k8s.gcr.io/dns/k8s-dns-node-cache:1.16.0
Image:         k8s.gcr.io/dns/k8s-dns-node-cache:1.16.0
Image:         k8s.gcr.io/dns/k8s-dns-node-cache:1.16.0
Image:         k8s.gcr.io/dns/k8s-dns-node-cache:1.16.0
Image:         k8s.gcr.io/dns/k8s-dns-node-cache:1.16.0
Image:         k8s.gcr.io/dns/k8s-dns-node-cache:1.16.0
Image:          nvcr.io/nvidia/k8s-device-plugin:v0.17.1
Image:          nvcr.io/nvidia/k8s-device-plugin:v0.17.1
Image:          nvcr.io/nvidia/k8s-device-plugin:v0.17.1
Image:          nvcr.io/nvidia/k8s-device-plugin:v0.17.1
Image:          nvcr.io/nvidia/k8s-device-plugin:v0.17.1
Image:          nvcr.io/nvidia/k8s-device-plugin:v0.17.1
Image:          nvcr.io/nvidia/k8s-device-plugin:v0.17.1
Image:         csiplugin/snapshot-controller:v4.0.0

[zhanglu]

docker save registry.k8s.io/sig-storage/csi-node-driver-registrar:v2.5.1 -o csi-node-driver-registrar.tar
docker save quay.io/cephcsi/cephcsi:v3.7.2 -o cephcsi.tgar
docker save registry.k8s.io/sig-storage/csi-attacher:v4.0.0 -o csi-attacher.tar
docker save registry.k8s.io/sig-storage/csi-snapshotter:v6.1.0 -o csi-snapshotter.tar
docker save registry.k8s.io/sig-storage/csi-resizer:v1.6.0 -o csi-resizer.tar
docker save registry.k8s.io/sig-storage/csi-provisioner:v3.3.0 -o csi-provisioner.tar
docker save quay.io/ceph/ceph:v17.2.5 -o ceph1.tar
docker save rook/ceph:v1.10.8 -o ceph.tar

docker save quay.io/calico/kube-controllers:v3.16.5 -o kube-controllers.tar
docker save quay.io/calico/cni:v3.16.5 -o cni.tar
docker save quay.io/calico/node:v3.16.5 -o node.tar
docker save k8s.gcr.io/coredns:1.7.0 -o coredns.tar
docker save k8s.gcr.io/cpa/cluster-proportional-autoscaler-amd64:1.8.3 -o cluster-proportional-autoscaler-amd64.tar
docker save k8s.gcr.io/kube-apiserver:v1.19.7 -o apiserver.tar
docker save k8s.gcr.io/kube-controller-manager:v1.19.7 -o manager.tar
docker save k8s.gcr.io/kube-proxy:v1.19.7 -o proxy.tar
docker save k8s.gcr.io/kube-scheduler:v1.19.7 -o scheduler.tar
docker save docker.io/library/nginx:1.19 -o ngins.tar
docker save k8s.gcr.io/dns/k8s-dns-node-cache:1.16.0 -o cache.tar
docker save nvcr.io/nvidia/k8s-device-plugin:v0.17.1 -o plugin.tar
docker save csiplugin/snapshot-controller:v4.0.0 -o controller.tar

[zhanglu]

docker load < csi-node-driver-registrar.tar
docker load < cephcsi.tgar
docker load <csi-attacher.tar
docker load < csi-snapshotter.tar
docker load < csi-resizer.tar
docker load < csi-provisioner.tar
docker load <-o ceph1.tar
docker load < -o ceph.tar

docker load < kube-controllers.tar
docker load < cni.tar
docker load < node.tar
docker load < coredns.tar
docker load < cluster-proportional-autoscaler-amd64.tar
docker load < -o apiserver.tar
docker load < manager.tar
docker load < proxy.tar
docker load < scheduler.tar
docker load < ngins.tar
docker load < cache.tar
docker load < plugin.tar
docker load <controller.tar

[zhanglu]

cluster:
id: 807d820b-5c5b-451c-9f52-41b93d5d905a
health: HEALTH_ERR
full ratio(s) out of order
Low space hindering backfill (add storage if this doesn't resolve itself): 5 pgs backfill_toofull
178 pgs not deep-scrubbed in time
117 pgs not scrubbed in time

services:
mon: 3 daemons, quorum bm,bo,bp (age 39h)
mgr: a(active, since 39h), standbys: b
mds: 1/1 daemons up, 1 hot standby
osd: 51 osds: 51 up (since 109m), 51 in (since 109m); 59 remapped pgs

data:
volumes: 1/1 healthy
pools: 4 pools, 2097 pgs
objects: 279.97M objects, 306 TiB
usage: 617 TiB used, 84 TiB / 701 TiB avail
pgs: 5001255/601565087 objects misplaced (0.831%)
2028 active+clean
54 active+remapped+backfilling
10 active+clean+scrubbing+deep
5 active+remapped+backfill_toofull

io:
client: 338 KiB/s rd, 8.8 MiB/s wr, 175 op/s rd, 7 op/s wr
recovery: 65 MiB/s, 49 objects/s

[zhanglu]

datasource:
# SQLite 数据库文件：项目根目录自动生成 cromwell_log.db（对应你的数据库名）
url: jdbc:sqlite:/home/genostack/workspace/CromwellStatus/cromwell_log.db
# SQLite 无用户名密码，留空
username:
password:
driver-class-name: org.sqlite.JDBC
initialization-mode: always # 开启自动执行脚本
schema: classpath:schema.sql # 建表脚本路径

[zhanglu]

ID HOST USED AVAIL WR OPS WR DATA RD OPS RD DATA STATE
0 node1 8480G 2468G 0 0 0 0 exists,up
1 node1 9556G 1392G 20 3438k 18 4128k exists,up
2 node1 8933G 2015G 36 1188k 8 1328k exists,up
3 node1 8795G 2153G 0 0 0 0 exists,up
4 node1 9250G 1698G 0 0 0 0 exists,up
5 node1 8957G 1991G 0 0 0 0 exists,up
6 node1 8772G 2176G 0 2563 0 0 exists,up
7 node2 9247G 1701G 1 7584 0 0 exists,up
8 node2 9939G 1009G 0 0 7 20.2k exists,up
9 node2 9352G 1596G 0 0 0 0 exists,up
10 node2 9.87T 838G 0 2563 0 0 exists,up
11 node2 9656G 1292G 0 0 0 0 exists,up
12 node2 9678G 1270G 0 0 0 0 exists,up
13 node2 9558G 1390G 0 2563 0 0 exists,up
14 node3 9945G 1003G 0 0 0 0 exists,up
15 node3 9762G 1186G 0 0 0 0 exists,up
16 node3 9231G 1717G 0 0 0 0 exists,up
17 node3 9239G 1709G 0 2902 0 0 exists,up
18 node3 9668G 1280G 0 2563 0 0 exists,up
19 node3 9551G 1397G 0 721k 0 0 exists,up
20 node3 9859G 1089G 0 0 0 0 exists,up
21 node8 16.1T 2062G 18 1638k 7 831k exists,up
22 node7 13.1T 1450G 2 1638k 9 844k exists,up
23 node7 12.8T 1780G 0 0 0 0 exists,up
24 node7 13.2T 1283G 0 89.7k 0 0 exists,up
25 node7 12.8T 1731G 0 2563 0 0 exists,up
26 node7 13.4T 1119G 0 0 0 0 exists,up
27 node5 12.5T 2039G 0 2563 0 0 exists,up
28 node5 12.4T 2160G 0 0 0 0 exists,up
29 node5 12.9T 1658G 4 27.4k 0 0 exists,up
30 node5 12.7T 1887G 34 6468k 21 6494k exists,up
31 node5 12.8T 1781G 0 0 0 0 exists,up
32 node5 12.2T 2337G 0 0 0 0 exists,up
33 node5 12.5T 2022G 3 819k 9 842k exists,up
34 node6 13.1T 1443G 0 12.1k 0 0 exists,up
35 node6 12.6T 1935G 0 0 0 0 exists,up
36 node6 13.0T 1527G 1 592k 0 0 exists,up
37 node6 12.5T 2095G 0 195 0 0 exists,up
38 node6 12.8T 1731G 0 0 0 0 exists,up
39 node6 13.4T 1174G 0 2563 0 0 exists,up
40 node6 13.0T 1557G 15 2928k 19 3797k exists,up
41 node8 16.4T 1814G 1 2563 7 832k exists,up
42 node8 15.6T 2574G 0 819 0 0 exists,up
43 node8 15.8T 2346G 0 0 0 0 exists,up
44 node8 16.2T 1979G 76 1524k 9 852k exists,up
45 node8 15.8T 2403G 0 0 0 0 exists,up
46 node8 15.8T 2405G 8 2515k 10 2478k exists,up
47 node8 16.1T 2057G 1 8408 0 0 exists,up
48 node8 16.7T 1448G 0 0 0 0 exists,up
49 node8 15.3T 2888G 0 0 0 0 exists,up
50 node8 16.1T 2045G 0 0 0 0 exists,up

[zhanglu]

[root@node1 prod]# kubectl get pod -n genostack-base-dev
NAME READY STATUS RESTARTS AGE
postgres-7cffc9f66-6ngfr 0/1 ContainerCreating 0 17m
postgres-7cffc9f66-fqmzm 0/1 Terminating 0 27m
redis-bd7c6cbb4-gtdz9 1/1 Running 0 30d

[zhanglu]

Resource Requests Limits

---

cpu 46867m (41%) 58400m (52%)
memory 242859107584 (28%) 315783595264 (37%)
ephemeral-storage 0 (0%) 0 (0%)
hugepages-1Gi 0 (0%) 0 (0%)
hugepages-2Mi 0 (0%) 0 (0%)
Events:
Type Reason Age From Message

---

Normal NodeReady 8m (x252 over 16h) kubelet Node node1 status is now: NodeReady
Normal NodeNotReady 59s (x254 over 16h) kubelet Node node1 status is now: NodeNotReady

[zhanglu]

ps -eo pid,stat,cmd | grep -E '^.+ D'

[zhanglu]

[root@node1 account]# ps -eo pid,stat,cmd | grep -E '^.+ D'
382513 Ds /opt/gitlab/embedded/bin/postgres -D /var/opt/gitlab/postgresql/data
382518 Ds postgres: autovacuum launcher process
382519 Ds postgres: stats collector process
385554 D svlogd -tt /var/log/gitlab/redis
385557 D svlogd -tt /var/log/gitlab/sidekiq
385704 D svlogd -tt /var/log/gitlab/node-exporter
385705 D svlogd -tt /var/log/gitlab/gitlab-monitor
385707 D svlogd -tt /var/log/gitlab/prometheus
385722 Ds postgres: gitlab-psql postgres [local] SELECT
385926 D tail --follow=name --retry /var/log/gitlab/nginx/error.log /var/log/gitlab/nginx/current /var/log/gitlab/nginx/gitlab_error.log /var/log/gitlab/nginx/access.log /var/log/gitlab/nginx/gitlab_access.log /var/log/gitlab/prometheus/current /var/log/gitlab/prometheus/state /var/log/gitlab/postgresql/current /var/log/gitlab/postgresql/state /var/log/gitlab/redis/current /var/log/gitlab/redis/state /var/log/gitlab/alertmanager/current /var/log/gitlab/alertmanager/state /var/log/gitlab/redis-exporter/current /var/log/gitlab/redis-exporter/state /var/log/gitlab/gitlab-shell/gitlab-shell.log /var/log/gitlab/sidekiq/current /var/log/gitlab/sidekiq/state /var/log/gitlab/gitlab-monitor/current /var/log/gitlab/gitlab-monitor/state /var/log/gitlab/sshd/current /var/log/gitlab/gitlab-workhorse/current /var/log/gitlab/gitlab-workhorse/state /var/log/gitlab/unicorn/unicorn_stderr.log /var/log/gitlab/unicorn/current /var/log/gitlab/unicorn/unicorn_stdout.log /var/log/gitlab/unicorn/state /var/log/gitlab/gitaly/current /var/log/gitlab/gitaly/state /var/log/gitlab/postgres-exporter/current /var/log/gitlab/postgres-exporter/state /var/log/gitlab/node-exporter/current /var/log/gitlab/node-exporter/state /var/log/gitlab/gitlab-rails/production.log /var/log/gitlab/gitlab-rails/gitlab-rails-db-migrate-2023-02-21-09-56-26.log /var/log/gitlab/gitlab-rails/application.log /var/log/gitlab/gitlab-rails/grpc.log /var/log/gitlab/gitlab-rails/production_json.log /var/log/gitlab/gitlab-rails/api_json.log /var/log/gitlab/logrotate/current /var/log/gitlab/logrotate/state

[zhanglu]

SELECT count(*) FROM "METADATA_ENTRY";
SELECT * FROM "METADATA_ENTRY" where "WORKFLOW_EXECUTION_UUID" = 'e845ff2e-95ba-4108-bec5-7b8ece2fe76d' ;
SELECT * FROM "METADATA_ENTRY" where "WORKFLOW_EXECUTION_UUID" = 'e1ae68d6-8c6d-4f91-b970-06e65e57c564' ;

[zhanglu]

http://192.168.30.202:31237/api/workflows/v1/70d9a7f6-33c9-4ef4-80bf-62e7af9cc662/metadata

[zhanglu]

6e362360-32d0-4311-8d9f-a1a2ed5b61c2
e845ff2e-95ba-4108-bec5-7b8ece2fe76d
e1ae68d6-8c6d-4f91-b970-06e65e57c564

[zhanglu]

select "WORKFLOW_EXECUTION_UUID" , "WORKFLOW_NAME", "WORKFLOW_STATUS" from "WORKFLOW_METADATA_SUMMARY_ENTRY" where "WORKFLOW_STATUS" = 'Running';

[zhanglu]

[root@node3 cephfs_data]# ps -eo pid,stat,cmd | grep -E '^.+ D'
647454 D sync
773495 D sync
777729 D /usr/bin/mount -o bind,remount /proc/7817/fd/50 /var/lib/kubelet/pods/ce2112de-6092-400b-8d1f-ff9c7f0feb60/volume-subpaths/data/cromwell/0
807143 D sync
831541 D sync
862778 D sync
923295 D sync
925182 D sync
1120488 D sync
1137925 D sync
1438346 D sync
1685722 D /usr/bin/mount -o bind,remount /proc/7817/fd/54 /var/lib/kubelet/pods/01c428af-c57a-4159-93ce-4e57c73ed85b/volume-subpaths/data/cromwell/0
1698130 D sync
1699192 D sync
1729571 D sync
1729918 D sync
1916667 D sync
1957175 D sync
3327874 S+ grep --color=auto -E ^.+ D
3402901 DNs (coredump)
3883466 D+ rm -rf ./5b9c9af2-49ab-4cd3-bbe9-637c131ef344 ./ff853c49-720c-442a-b5bf-fb50c63736c2 ./4dba7671-4615-4ce8-8083-09c1b6a3b895 ./a00fd097-cd21-4561-9dcc-2bb9b66d58fa ./2ca5d416-7398-43f4-b368-68e790abaf95 ./f7f4938d-0b2a-4e95-9f6c-0b9e3c442ef6 ./5958823a-cb9b-4556-a30d-4142eba696c7 ./8281f2d8-fcb9-4508-853d-be96fe10535e ./0ee9f259-014c-44e1-9453-f2af6f423c06 ./4fbe43e5-4018-434f-a6fd-61ba3ebc69e6 ./03a22cb6-5ca6-4b58-8f32-b95988a4605c ./58ade6fd-845a-4ee5-bebd-b0dce6cfdac5 ./4b8fde55-6387-4fd3-9092-d4c19c44ab9c ./aed461b9-dfff-4fc1-b089-f33b2673b1c5 ./7a932a56-0a47-42d4-893b-d0435a2edc1c ./57ff22a3-5fa4-4d77-94b7-71011cb6238e ./e8c72d7c-1d92-4d3c-8702-f4cf50ea2ee2 ./93a9de1b-7be3-40ba-9e9e-3364b67b202d ./e3d77188-3693-4f7f-81e7-8688b4b01dec ./8bf3777b-361c-46c1-9328-c9f3d5cc2822 ./eaf418dc-01b3-4bc0-b272-d2ba3f2493ce ./1c24a9f4-2e97-44c8-af0a-85db7e374956 ./77b44fc3-2f4b-480b-b01a-d57a1395fe1e ./f2fd7fe2-3903-437b-a40f-2e812dc35201 ./a862e7a9-99e2-4c31-82ba-3e87c0421354 ./b16de460-9245-41d5-8b69-444e95e549a0 ./815801ee-1ded-46db-933a-0decd35d5fe4 ./75f6352d-2080-40dc-9ac5-ce4c6566e0c2 ./9ef6a0eb-1d37-4966-b7e1-1ffc4b9abc22 ./d97f36bd-6805-4bfa-a386-0b90bb42d8cd ./345b403e-45e2-4e09-9b99-23b1b3c7f33c ./c5ef2a0e-2868-4e09-9c26-cf5357f60448 ./b0b9b6c3-bcb6-479f-83c5-429e306ff1ad ./4ec53f20-4f2c-430c-a332-7736584b26c7 ./02ac4847-d640-4312-a761-e7fd01d45c27 ./53630622-fa7f-4cf6-91b2-12768883af6f ./e1660f00-841f-4899-a4b2-c2451edf2b36 ./07de3f21-1de8-4326-9bf7-5774a2791eaa ./97914a70-2fe4-4c1f-a326-adebe8222df0 ./695f925d-723b-4446-b9b1-11dfa642f065
3911819 D sync
3948171 D sync

[zhanglu]

SELECT "METADATA_KEY", COUNT()
FROM "METADATA_ENTRY"
WHERE "WORKFLOW_EXECUTION_UUID" = 'e886888f-c972-4932-a9a4-187525877ea0'
GROUP BY "METADATA_KEY"
ORDER BY COUNT() DESC
LIMIT 20;

DELETE FROM "METADATA_ENTRY"
WHERE "WORKFLOW_EXECUTION_UUID" = '32d44941-c654-4163-b01e-aa41a0cc597a'
AND "METADATA_KEY" = 'vmStartTime'

          METADATA_KEY              |  count  

----------------------------------------+---------
vmStartTime | 2023761
executionStatus | 9
stderr | 6
stdout | 6
commandLine | 6
start | 4
callRoot | 3
backend | 3
callCaching:effectiveCallCachingMode | 3
runtimeAttributes:failOnStderr | 3
runtimeAttributes:maxRetries | 3
tes_stderr | 3
runtimeAttributes:docker | 3
status | 3
backendStatus | 3
runtimeAttributes:continueOnReturnCode | 3
runtimeAttributes:preemptible | 3
jobId | 3
callCaching:allowResultReuse | 3
tes_stdout | 3