Le 15 oct. 2014 à 11:48, Roman <[email protected]> a écrit : > Pascal, > > Here is my latest installation: > > cluster 204986f6-f43c-4199-b093-8f5c7bc641bb > health HEALTH_WARN 192 pgs degraded; 192 pgs stuck unclean; recovery > 20/40 objects degraded (50.000%) > monmap e1: 2 mons at > {ceph02=192.168.33.142:6789/0,ceph03=192.168.33.143:6789/0}, election epoch > 4, quorum 0,1 ceph02,ceph03 > mdsmap e4: 1/1/1 up {0=ceph02=up:active} > osdmap e8: 2 osds: 2 up, 2 in > pgmap v14: 192 pgs, 3 pools, 1884 bytes data, 20 objects > 68796 kB used, 6054 MB / 6121 MB avail > 20/40 objects degraded (50.000%) > 192 active+degraded > > > host ceph01 - admin > host ceph02 - mon.ceph02 + osd.1 (sdb, 8G) + mds > host ceph03 - mon.ceph03 + osd.0 (sdb, 8G) > > $ ceph osd tree > # id weight type name up/down reweight > -1 0 root default > -2 0 host ceph03 > 0 0 osd.0 up 1 > -3 0 host ceph02 > 1 0 osd.1 up 1 >
I'm not sure, but i think something is wrong during the installation, all weights are equal at all levels of your map. See http://docs.ceph.com/docs/master/rados/operations/crush-map/ Check the rulset id #0 (all your pool uses this ruleset). If you have something like this : rule data { ruleset 0 type replicated min_size 1 max_size 10 step take default step chooseleaf firstn 0 type host step emit } and if i understand the mechanism, for a good replication placement, ceph will need two OSDs on two different nodes. Maybe, 0 as weight is a wrong value ? After deploying a similar configuration, i have : # id weight type name up/down reweight -1 2 root default -2 1 host econome-7 1 1 osd.1 up 1 -3 1 host econome-18 0 1 osd.0 up 1 Pascal > > $ ceph osd dump > epoch 8 > fsid 204986f6-f43c-4199-b093-8f5c7bc641bb > created 2014-10-15 13:39:05.986977 > modified 2014-10-15 13:40:45.644870 > flags > pool 0 'data' replicated size 2 min_size 1 crush_ruleset 0 object_hash > rjenkins pg_num 64 pgp_num 64 last_change 1 flags hashpspool > crash_replay_interval 45 stripe_width 0 > pool 1 'metadata' replicated size 2 min_size 1 crush_ruleset 0 object_hash > rjenkins pg_num 64 pgp_num 64 last_change 1 flags hashpspool stripe_width 0 > pool 2 'rbd' replicated size 2 min_size 1 crush_ruleset 0 object_hash > rjenkins pg_num 64 pgp_num 64 last_change 1 flags hashpspool stripe_width 0 > max_osd 2 > osd.0 up in weight 1 up_from 4 up_thru 4 down_at 0 last_clean_interval > [0,0) 192.168.33.143:6800/2284 192.168.33.143:6801/2284 > 192.168.33.143:6802/2284 192.168.33.143:6803/2284 exists,up > dccd6b99-1885-4c62-864b-107bd9ba0d84 > osd.1 up in weight 1 up_from 8 up_thru 0 down_at 0 last_clean_interval > [0,0) 192.168.33.142:6800/2399 192.168.33.142:6801/2399 > 192.168.33.142:6802/2399 192.168.33.142:6803/2399 exists,up > 4d4adf4b-ae8e-4e26-8667-c952c7fc4e45 > > Thanks, > Roman > >> Hello, >> >>> osdmap e10: 4 osds: 2 up, 2 in >> >> >> What about following commands : >> # ceph osd tree >> # ceph osd dump >> >> You have 2 OSDs on 2 hosts, but 4 OSDs seems to be debined in your crush map. >> >> Regards, >> >> Pascal >> >> Le 15 oct. 2014 à 11:11, Roman <[email protected]> a écrit : >> >>> Hi ALL, >>> >>> I've created 2 mon and 2 osd on Centos 6.5 (x86_64). >>> >>> I've tried 4 times (clean centos installation) but always have health: >>> HEALTH_WARN >>> >>> Never HEALTH_OK always HEALTH_WARN! :( >>> >>> # ceph -s >>> cluster d073ed20-4c0e-445e-bfb0-7b7658954874 >>> health HEALTH_WARN 192 pgs degraded; 192 pgs stuck unclean >>> monmap e1: 2 mons at >>> {ceph02=192.168.0.142:6789/0,ceph03=192.168.0.143:6789/0}, election epoch >>> 4, quorum 0,1 ceph02,ceph03 >>> osdmap e10: 4 osds: 2 up, 2 in >>> pgmap v15: 192 pgs, 3 pools, 0 bytes data, 0 objects >>> 68908 kB used, 6054 MB / 6121 MB avail >>> 192 active+degraded >>> >>> What am I doing wrong??? >>> >>> ----------- >>> >>> host: 192.168.0.141 - admin >>> host: 192.168.0.142 - mon.ceph02 + osd.0 (/dev/sdb, 8G) >>> host: 192.168.0.143 - mon.ceph03 + osd.1 (/dev/sdb, 8G) >>> >>> ceph-deploy version 1.5.18 >>> >>> [global] >>> osd pool default size = 2 >>> ----------- >>> >>> Thanks, >>> Roman. >>> _______________________________________________ >>> ceph-users mailing list >>> [email protected] >>> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com >> >> -- >> Pascal Morillon >> University of Rennes 1 >> IRISA, Rennes, France >> SED >> Offices : E206 (Grid5000), D050 (SED) >> Phone : +33 2 99 84 22 10 >> [email protected] >> Twitter @pmorillon >> xmpp: [email protected] >> http://www.grid5000.fr >> > -- Pascal Morillon University of Rennes 1 IRISA, Rennes, France SED Offices : E206 (Grid5000), D050 (SED) Phone : +33 2 99 84 22 10 [email protected] Twitter @pmorillon xmpp: [email protected] http://www.grid5000.fr
smime.p7s
Description: S/MIME cryptographic signature
_______________________________________________ ceph-users mailing list [email protected] http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
