自ceph版本Luminous v12.2.x以后,参数mon_pg_warn_max_per_osd变更为mon_max_pg_per_osd,默认值也从300变更为200,修改该参数后,也由原来的重启ceph-mon服务变为重启ceph-mgr服务。 修复步骤为: 1.修改ceph.conf文件,将mon_max_pg_per_osd设置一个值,注意mon_max_pg_per_osd放在[global]下 2.将修改pu...
ceph -s集群报错too many PGs per OSD 背景 集群状态报错,如下: # ceph -scluster1d64ac80-21be-430e-98a8-b4d8aeb18560healthHEALTH_WARN<--报错的地方toomanyPGsperOSD(912>max300)monmap e1:1monsat{node1=109.105.115.67:6789/0}electionepoch4,quorum0node1osdmap e49: 2 osds:2up,2inflagssortbi...
前提是有多余的可用磁盘。 方法2. 调整每个osd默认PG数,参数为mon_pg_warn_max_per_osd。 # ceph --show-config | grep mon_pg_warn_max_per_osd mon_pg_warn_max_per_osd = 300 2.1 使用ceph tell的方式临时调整这个参数为400: # ceph tell mon.* injectargs --mon_pg_warn_max_per_osd 400 2....
TOO_MANY_PGS¶ The number of PGs in use in the cluster is above the configurable threshold ofmon_max_pg_per_osdPGs per OSD. If this threshold is exceed the cluster will not allow new pools to be created, poolpg_numto be increased, or pool replication to be increased (any of which ...
Ceph: too many PGs per OSD 一、故障现象: 查看ceph的集群状态:too many PGs per OSD (698 > max 300) # ceph -scluster e2ca994a-00c4-477f-9390-ea3f931c5062 health HEALTH_WARN too many PGs per OSD(698>max300)monmap e1:3mons at{hz-01-ops-tc-ceph-02=172.16.2.231:6789/0,hz-01...
too many PGs per OSD (652 > max 300) 《==报错内容 monmap e1: 1 mons at {node241=192.168.2.41:6789/0} election epoch 1, quorum 0 node241 osdmap e408: 5 osds: 5 up, 5 in pgmap v23049: 1088 pgs, 16 pools, 256 MB data, 2889 objects ...
Ceph: too many PGs per OSD 一、故障现象: 查看ceph的集群状态:too many PGs per OSD (698 > max 300) 1 2 3 4 5 6 7 8 9 10 11 12 13 # ceph -s cluster e2ca994a-00c4-477f-9390-ea3f931c5062 health HEALTH_WARN too many PGs per OSD (698 > max 300)...
Ceph是一个PB,EB级别的分布式存储系统,可以提供文件存储,对象存储、和块存储,它可靠性高,易扩展,管理简便,其中对象存储和块存储可以和其他云平台集成。一个Ceph集群中有Monitor节点、MDS节点(用于文件存储)、OSD守护进程。 Ceph组件 Ceph OSD:OSD守护进程,用于存储数据、数据恢复、数据回滚、平衡数据,并通过心跳程序向...
pgs stuck PG处于一些不健康状态的时候,会显示出来 requests are blocked slow requests会警告 osds have slow requests slow requests会警告 recovery 需要recovery的时候会报 at/near target max 使用cache tier的时候会警告 too few PGs per OSD 每个OSD的PG数过少 too many PGs per OSD too many PGs...
too many PGs per OSD 每个OSD的PG数过多 pgp_num pg_num大于pgp_num has many more objects per pg than average (too few pgs?) 每个Pg上的objects数过多 HEALTH_ERR: 集群健康状态描述信息 代表的现象 no osds 部署完就可以看到,运行过程中不会出现 ...