My monitors are suddenly not starting up properly, or at all. Using latest Debian release from ceph.com/debian-cuttlefish wheezy
One (mon.7 ip ending in .190) starts but says things like this in the logs:
1 mon.7@0(probing) e3 discarding message mon_subscribe({monmap=0+,osdmap=796}) and sending client elsewhere
1 mon.7@0(probing) e3 discarding message auth(proto 0 25 bytes epoch 0) v1 and sending client elsewhere
1 mon.7@0(probing) e3 discarding message auth(proto 0 34 bytes epoch 0) and sending client elsewhere
Another (mon.8 ip ending in .191) starts but says this in the logs:
0 -- x.x.x.191:6789/0 >> x.x.x.197:0/2400174543 pipe(0x92028c0 sd=660 :6789 s=0 pgs=0 cs=0 l=0).accept peer addr is really x.x.x.197:0/2400174543 (socket is x.x.x.197:55263/0)
0 -- x.x.x.191:6789/0 >> x.x.x.197:0/2400174543 pipe(0x9200e00 sd=804 :6789 s=0 pgs=0 cs=0 l=0).accept peer addr is really x.x.x.197:0/2400174543 (socket is x.x.x.197:55267/0)
0 -- x.x.x.191:6789/0 >> x.x.x.197:0/2400174543 pipe(0x9207dc0 sd=881 :6789 s=0 pgs=0 cs=0 l=0).accept peer addr is really x.x.x.197:0/2400174543 (socket is x.x.x.197:55269/0)
And the last one (mon.4 ip ending in .197) won't start, with this in the logs:
-1 obtain_monmap unable to find a monmap
0 mon.4 does not exist in monmap, will attempt to join an existing cluster
1 mon.4@-1(probing) e0 preinit fsid 00000000-0000-0000-0000-000000000000
-1 mon.4@-1(probing) e0 error: cluster_uuid file exists with value '167cc337-e3a3-4df0-8fe8-be84cce7f4f0', != our uuid 00000000-0000-0000-0000-000000000000
Machine with ip ending in .197 is a client, the only one at the moment. The other two are osd's.
Previously, all 3 were working although one of them (normally, but not always mon.4) would be marked down whenever I wasn't looking...
Any hints?
Thanks
James
_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
