Re: problem readding an osd

Greg <itooo@xxxxxxxxx> · Mon, 06 May 2013 19:47:09 +0200



    Le 06/05/2013 19:23, Glen Aidukas a
      écrit :

    
        Hello, 
         
        I think this is a newbe question but I
          tested everything and, yes I FTFM as best I could.
         
        I’m evaluating ceph and so I setup a
          cluster of 4 nodes.  The nodes are KVM virtual machines named
          ceph01 to ceph04 all running Ubuntu 12.04.2 LTS each with a
          single osd named osd.1 though osd.4 respective to the host
          they were running on.  Each host also has a 1TB disk for ceph
          to use ‘/dev/vdb1’.
         
        After some work I was able to get the
          cluster up and running and even mounted it on a test client
          host (named ceph00).  I ran into issues when I was testing a
          failure.  I shut off ceph02 and watched via (ceph –w) it
          recover and move the data around.  At this point all is fine.
         
        When I turned the host back on, it did not
          auto reconnect.  I expected this.  I then send through many
          attempts to re add it but all failed.
         
        Here is an output from:  ceph osd tree
         
        #
            id    weight  type name       up/down reweight
        -1     
            4       root default
        -3     
            4               rack unknownrack
        -2     
            1                       host ceph01
        1      
            1                               osd.1   up      1
        -4     
            1                       host ceph02
        2      
            1                               osd.2   down    0
        -5     
            1                       host ceph03
        3      
            1                               osd.3   up      1
        -6     
            1                       host ceph04
        4      
            1                               osd.4   up      1
        -7     
            0               rack unkownrack
         
        ceph
            -s
          
            health HEALTH_WARN 208 pgs peering; 208 pgs stuck inactive;
            208 pgs stuck unclean; 1/4 in osds are down
          
            monmap e1: 1 mons at {a=10.30.20.81:6789/0}, election epoch
            1, quorum 0 a
          
            osdmap e172: 4 osds: 3 up, 4 in
           
            pgmap v1970: 960 pgs: 752 active+clean, 208 peering; 5917 MB
            data, 61702 MB used, 2854 GB / 3068 GB avail
          
            mdsmap e39: 1/1/1 up {0=a=up:active}
         
        While I’m able to get it to be in the ‘in’
          state, I cant seem to bring it up.
         
        Any ideas on how to fix this?
         

    Glen,

    
    try to bring up your OSD daemon with -d switch, this will probably
    give you some information. (alternatively look in the logs)

    
    Cheers,

  
_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com