Hi, I need help for deploying jewel OSDs on CentOS 7. Following the guide, I have successfully run OSD daemons but all of them are down according to `ceph -s`: 15/15 in osds are down
No errors in /var/log/ceph/ceph-osd.1.log, it just stoped at these lines and never made progress: 2016-05-09 01:32:03.187802 7f35acb4a700 0 osd.0 100 crush map has features 2200130813952, adjusting msgr requires for clients 2016-05-09 01:32:03.187841 7f35acb4a700 0 osd.0 100 crush map has features 2200130813952 was 2199057080833, adjusting msgr requires for mons 2016-05-09 01:32:03.187859 7f35acb4a700 0 osd.0 100 crush map has features 2200130813952, adjusting msgr requires for osds ceph health details shows: osd.0 is down since epoch 0, last address :/0 Why the address is :/0? Am I configuring it wrong? I've followed the OSD troubleshooting guide but with no luck. And the network seems good, since the ports are telnet-able, and I can do ceph -s on the OSD machine. ceph.conf: [global] fsid = fad5f8d4-f5f6-425d-b035-a018614c0664 mon osd full ratio = .75 mon osd nearfull ratio = .65 auth cluster required = cephx auth service requried = cephx auth client required = cephx mon initial members = mon_vm_1,mon_vm_2,mon_vm_3 mon host = 10.3.1.94,10.3.1.95,10.3.1.96 [mon.a] host = mon_vm_1 mon addr = 10.3.1.94 [mon.b] host = mon_vm_2 mon addr = 10.3.1.95 [mon.c] host = mon_vm_3 mon addr = 10.3.1.96 [osd] osd journal size = 10240 osd pool default size = 3 osd pool default min size = 2 osd pool default pg num = 512 osd pool default pgp num = 512 osd crush chooseleaf type = 1 osd journal = /ceph_journal/$id
_______________________________________________ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com