Also check if you have a half-upgraded cluster and have set “auth_allow_insecure_global_id_reclaim” to false. If that is the case, revert this option to true. 发件人: 峰<mailto:286204879@xxxxxx> 发送时间: 2021年8月3日 15:37 收件人: ceph-users<mailto:ceph-users@xxxxxxx> 主题: 100.000% pgs unknown Hello, my ceph cluster has crashed, please help me! #ceph -s cluster: id: 5e1d9b55-9040-494a-9011-d73469dabe1a health: HEALTH_WARN 1 filesystem is degraded 1 MDSs report slow metadata IOs 27 osds down 7 hosts (28 osds) down 1 root (28 osds) down Reduced data availability: 1760 pgs inactive services: mon: 3 daemons, quorum ceph-m-51,ceph-m-52,ceph-m-53 (age 24h) mgr: ceph-m-51(active, since 4h) mds: cephfs:1/1 {0=ceph-m-51=up:replay} 2 up:standby osd: 30 osds: 2 up (since 24h), 29 in (since 24h) data: pools: 7 pools, 1760 pgs objects: 0 objects, 0 B usage: 0 B used, 0 B / 0 B avail pgs: 100.000% pgs unknown 1760 unknown #ceph osd tree ID CLASS WEIGHT TYPE NAME STATUS REWEIGHT PRI-AFF -25 2.18320 root cache-ssd -22 2.18320 host ceph-node-47 24 ssd 1.09160 osd.24 up 1.00000 1.00000 25 ssd 1.09160 osd.25 up 1.00000 1.00000 -1 27.44934 root default -28 3.58989 host ceph-node-110 26 hdd 0.90970 osd.26 down 0.79999 1.00000 27 hdd 0.90970 osd.27 down 0.79999 1.00000 28 hdd 0.90970 osd.28 down 0.79999 1.00000 29 hdd 0.86079 osd.29 down 0.79999 1.00000 -3 14.55475 host ceph-node-54 0 hdd 3.63869 osd.0 down 0 1.00000 1 hdd 3.63869 osd.1 down 1.00000 1.00000 2 hdd 3.63869 osd.2 down 1.00000 1.00000 3 hdd 3.63869 osd.3 down 1.00000 1.00000 -5 1.76936 host ceph-node-55 4 hdd 0.45479 osd.4 down 0.50000 1.00000 5 hdd 0.45479 osd.5 down 0.50000 1.00000 6 hdd 0.45479 osd.6 down 0.50000 1.00000 7 hdd 0.40500 osd.7 down 0.50000 1.00000 -7 2.22427 host ceph-node-56 8 hdd 0.90970 osd.8 down 0.50000 1.00000 9 hdd 0.45479 osd.9 down 0.50000 1.00000 10 hdd 0.45479 osd.10 down 0.50000 1.00000 11 hdd 0.40500 osd.11 down 0.50000 1.00000 -9 1.77036 host ceph-node-57 12 hdd 0.45479 osd.12 down 0.50000 1.00000 13 hdd 0.45479 osd.13 down 0.50000 1.00000 14 hdd 0.45479 osd.14 down 0.50000 1.00000 15 hdd 0.40599 osd.15 down 0.50000 1.00000 -11 1.77036 host ceph-node-58 16 hdd 0.45479 osd.16 down 0.50000 1.00000 17 hdd 0.45479 osd.17 down 0.50000 1.00000 18 hdd 0.45479 osd.18 down 0.50000 1.00000 19 hdd 0.40599 osd.19 down 0.50000 1.00000 -13 1.77036 host ceph-node-59 20 hdd 0.45479 osd.20 down 0.50000 1.00000 21 hdd 0.45479 osd.21 down 0.50000 1.00000 22 hdd 0.45479 osd.22 down 0.50000 1.00000 23 hdd 0.40599 osd.23 down 0.50000 1.00000 #ceph fs dump e110784 enable_multiple, ever_enabled_multiple: 0,0 compat: compat={},rocompat={},incompat={1=base v0.20,2=client writeable ranges,3=default file layouts on dirs,4=dir inode in separate object,5=mds uses versioned encoding,6=dirfrag is stored in omap,8=no anchor table,9=file layout v2,10=snaprealm v2} legacy client fscid: 1 Filesystem 'cephfs' (1) fs_name cephfs epoch 110784 flags 32 created 2020-09-18 11:05:47.190096 modified 2021-08-03 15:33:04.379969 tableserver 0 root 0 session_timeout 60 session_autoclose 300 max_file_size 1099511627776 min_compat_client -1 (unspecified) last_failure 0 last_failure_osd_epoch 18808 compat compat={},rocompat={},incompat={1=base v0.20,2=client writeable ranges,3=default file layouts on dirs,4=dir inode in separate object,5=mds uses versioned encoding,6=dirfrag is stored in omap,8=no anchor table,9=file layout v2,10=snaprealm v2} max_mds 1 in 0 up {0=554577} failed damaged stopped data_pools [13] metadata_pool 14 inline_data disabled balancer standby_count_wanted 1 [mds.ceph-m-51{0:554577} state up:replay seq 37643 addr [v2:192.168.221.51:6800/1640891715,v1:192.168.221.51:6801/1640891715]] Standby daemons: [mds.ceph-m-52{-1:554746} state up:standby seq 2 addr [v2:192.168.221.52:6800/1652218221,v1:192.168.221.52:6801/1652218221]] [mds.ceph-m-53{-1:554789} state up:standby seq 2 addr [v2:192.168.221.53:6800/1236333507,v1:192.168.221.53:6801/1236333507]] dumped fsmap epoch 110784 When I start osd, the error message:“ 8月 03 15:05:16 ceph-node-54 ceph-osd[101387]: 2021-08-03 15:05:16.337 7f4ac0702700 -1 monclient(hunting): handle_auth_bad_method server allowed_methods [2] but i only support [2] 8月 03 15:05:16 ceph-node-54 ceph-osd[101387]: 2021-08-03 15:05:16.337 7f4abff01700 -1 monclient(hunting): handle_auth_bad_method server allowed_methods [2] but i only support [2] 8月 03 15:05:16 ceph-node-54 ceph-osd[101387]: failed to fetch mon config (--no-mon-config to skip) ” Every osd is like this! I exported the crush map and found no abnormalities. How can I fix it next? _______________________________________________ ceph-users mailing list -- ceph-users@xxxxxxx To unsubscribe send an email to ceph-users-leave@xxxxxxx _______________________________________________ ceph-users mailing list -- ceph-users@xxxxxxx To unsubscribe send an email to ceph-users-leave@xxxxxxx