This is just the output if it fails to connect to the first monitor it tries (in this case, the one that isn't running). If you let it run for a while it should time out after 15 seconds or something, pick a different monitor, and succeed. -Greg Software Engineer #42 @ http://inktank.com | http://ceph.com On Mon, Jul 14, 2014 at 2:27 PM, Lukac, Erik <Erik.Lukac at br.de> wrote: > Hi Guys, > > I am using ceph firefly on a three-node-cluster (all of them are storage-servers AND monitors) with rhel 6.5. Right now I've updated ceph from version from 0.80.2 to 0.80.3. > But during update something strange happened. After having updated node2 I stopped ceph (osd and mon) on node 1. Then I ran "ceph -s" on node2 and recieved this message: > root at node2:/# ceph -s > 2014-07-14 23:11:46.922824 7f2090663700 0 -- :/1020989 >> 10.65.201.241:6789/0 pipe(0x7f208c021410 sd=3 :0 s=1 pgs=0 cs=0 l=1 c=0x7f208c021680).fault > This also happened on node3 while node1 was updating: > root at node3:/#ceph -s > 2014-07-14 23:11:32.542985 7f57121fc700 0 -- :/1023519 >> 10.65.201.241:6789/0 pipe(0x7f5714021410 sd=3 :0 s=1 pgs=0 cs=0 l=1 c=0x7f5714021680).fault > > > After having updated node1 "ceph -s" worked fine. > This didnt happen while updating node2 and node3. > > Maybe it is a bug... maybe not but I think it is worth to be reported. > > If you have some more questions... tell me ;) > > Bye > > Erik > -------------------------------------------------------------------------------------------------- > Bayerischer Rundfunk; Rundfunkplatz 1; 80335 M?nchen > Telefon: +49 89 590001; E-Mail: info at BR.de; Website: http://www.BR.de > _______________________________________________ > ceph-users mailing list > ceph-users at lists.ceph.com > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com