(1)ceph告警提示:1 slow ops, oldest one blocked for
[root@node143 ~]# ceph -s
cluster:
id: 58a12719-a5ed-4f95-b312-6efd6e34e558
health: HEALTH_WARN
1 slow ops, oldest one blocked for 1416 sec, mon.node142 has slow ops
services:
mon: 2 daemon, quorum node140,node142 (age 8d)
mgr: admin(active, since 8d), standbys: node140
mds: cephfs:1 {0=node140=up:active} 1 up:standby
osd: 22 osds: 22 up (since 23m), 18 in (since 29m)
data:
pools: 5 pools, 768 pgs
objects: 2.65k objects, 9.9 GiB
usage: 53 GiB used, 12 TiB / 12 TiB avail
pgs: 768 active+clean
(2)檢查ntpd服務
[root@node143 ~]# systemctl status ntpd
[root@node143 ~]# systemctl start ntpd #新增的節點沒有啓動ntpd
(3)重啓monitor服務node140 node142 的monitor
[root@node140 ceph]# systemctl restart ceph-mon.target
[root@node140 ceph]# systemctl status ceph-mon.target
[root@node142 ceph]# systemctl restart ceph-mon.target
[root@node142 ceph]# systemctl status ceph-mon.target
(4)檢查集羣已經恢復
[root@node140 ceph]# ceph -s
cluster:
id: 58a12719-a5ed-4f95-b312-6efd6e34e558
health: HEALTH_OK
services:
mon: 2 daemon, quorum node140,node142 (age 3m)
mgr: admin(active, since 8d), standbys: node140
mds: cephfs:1 {0=node140=up:active} 1 up:standby
osd: 22 osds: 22 up (since 31m), 18 in (since 36m)
data:
pools: 5 pools, 768 pgs
objects: 2.65k objects, 9.9 GiB
usage: 53 GiB used, 12 TiB / 12 TiB avail
pgs: 768 active+clean
參考:https://blog.csdn.net/genglei1022/article/details/82461053