On 13-07-15 14:07, alberto ayllon wrote: > On 13-07-15 13:12, alberto ayllon wrote: >> Maybe this can help to get the origin of the problem. >> >> If I run ceph pg dump, and the end of the response i get: >> > > What does 'ceph osd tree' tell you? > > It seems there is something wrong with your CRUSHMap. > > Wido > > > Thanks for your answer Wido. > > Here is the output of ceph osd tree; > > # ceph osd tree > ID WEIGHT TYPE NAME UP/DOWN REWEIGHT PRIMARY-AFFINITY > -1 0 root default > -2 0 host ceph01 > 0 0 osd.0 up 1.00000 1.00000 > 3 0 osd.3 up 1.00000 1.00000 > 6 0 osd.6 up 1.00000 1.00000 > -3 0 host ceph02 > 1 0 osd.1 up 1.00000 1.00000 > 4 0 osd.4 up 1.00000 1.00000 > 7 0 osd.7 up 1.00000 1.00000 > -4 0 host ceph03 > 2 0 osd.2 up 1.00000 1.00000 > 5 0 osd.5 up 1.00000 1.00000 > 8 0 osd.8 up 1.00000 1.00000 > > The weights are allo zero (0) of all the OSDs. How big are the disks? I think they are very tiny , eg <10GB? You probably want a bit bigger disks to test with. Or set the weight manually of each OSD: $ ceph osd crush reweight osd.X 1 Wido >> >> osdstatkbusedkbavailkbhb inhb out >> 03668851949085231596[1,2,3,4,5,6,7,8][] >> 13400451975925231596[][] >> 23400451975925231596[1][] >> 33400451975925231596[0,1,2,4,5,6,7,8][] >> 43400451975925231596[1,2][] >> 53400451975925231596[1,2,4][] >> 63400451975925231596[0,1,2,3,4,5,7,8][] >> 73400451975925231596[1,2,4,5][] >> 83400451975925231596[1,2,4,5,7][] >> sum3087204677564447084364 >> >> >> Please someone can help me? >> >> >> >> 2015-07-13 11:45 GMT+02:00 alberto ayllon <albertoayllonces at > gmail.com <http://gmail.com> >> <mailto:albertoayllonces <mailto:albertoayllonces> at gmail.com > <http://gmail.com>>>: >> >> Hello everybody and thanks foryour help. >> >> Hello, I'm newbie in CEPH, I'm trying to install a CEPHcluster with >> test purpose. >> >> I had just installed a CEPH cluster with three VMs (ubuntu 14.04), >> each one has one mon daemon and three OSDs, also each server has 3 > disk. >> Cluster has only one poll (rbd) with pg and pgp_num = 280, and "osd >> pool get rbd size = 2". >> >> I made cluster's installation with ceph-deploy, ceph version is >> "0.94.2" >> >> I think cluster's OSDs are having peering problems, because if Irun >> ceph status, it returns: >> >> # ceph status >> cluster d54a2216-b522-4744-a7cc-a2106e1281b6 >> health HEALTH_WARN >> 280 pgs degraded >> 280 pgs stuck degraded >> 280 pgs stuck unclean >> 280 pgs stuck undersized >> 280 pgs undersized >> monmap e3: 3 mons at >> > {ceph01=172.16.70.158:6789/0,ceph02=172.16.70.159:6789/0,ceph03=172.16.70.160:6789/0 > <http://172.16.70.158:6789/0,ceph02=172.16.70.159:6789/0,ceph03=172.16.70.160:6789/0> >> > <http://172.16.70.158:6789/0,ceph02=172.16.70.159:6789/0,ceph03=172.16.70.160:6789/0>} >> election epoch 38, quorum 0,1,2 ceph01,ceph02,ceph03 >> osdmap e46: 9 osds: 9 up, 9 in >> pgmap v129: 280 pgs, 1 pools, 0 bytes data, 0 objects >> 301 MB used, 45679 MB / 45980 MB avail >> 280 active+undersized+degraded >> >> And for all pgs, the command "ceph pg map X.yy"returns something like: >> >> osdmap e46 pg 0.d7 (0.d7) -> up [0] acting [0] >> >> As I know "Acting Set" and "Up Set" must have the same value, but as >> they are equal to 0, there are not defined OSDs to >> stores pgs replicas, and I think this is why all pg are in >> "active+undersized+degraded" state. >> >> Has anyone any idea of what I have to do for "Active Set" and "Up >> Set" reaches correct values. >> >> >> Thanks a lot! >> >> >> >> >> _______________________________________________ >> ceph-users mailing list >> ceph-users at lists.ceph.com <http://lists.ceph.com> >> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com >> > > > > _______________________________________________ > ceph-users mailing list > ceph-users@xxxxxxxxxxxxxx > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com > _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |