[ Please keep all correspondence on the list. ] That's a very short log. Please add "debug ms = 1", "debug mds = 20", and "debug journaler = 20" to your MDS ceph.conf and then restart the MDS server. Wait for a while and send *that* log over. :) -Greg Software Engineer #42 @ http://inktank.com | http://ceph.com On Fri, Apr 26, 2013 at 4:44 PM, MinhTien MinhTien <tientienminh080590@xxxxxxxxx> wrote: > Hi Gregory Farnum > > I remained in that condition. > > MDS stanby but not active. > > ceph -w > health HEALTH_WARN 36 pgs peering; 36 pgs stuck inactive; 107 pgs stuck > unclean; nodown flag(s) set > monmap e2: 2 mons at {0=172.30.33.2:6789/0,1=172.30.33.5:6789/0}, > election epoch 602, quorum 0,1 0,1 > osdmap e3487: 8 osds: 8 up, 8 in > pgmap v333385: 640 pgs: 28 active, 529 active+clean, 43 active+replay, 3 > active+clean+replay, 36 peering, 1 active+clean+scrubbing+deep; 20945 GB > data, 20979 GB used, 83437 GB / 107 TB avail > mdsmap e822: 1/1/1 up {0=1=up:replay}, 1 up:standby > Please see if you have time > > > On Sat, Apr 27, 2013 at 2:40 AM, Gregory Farnum <greg@xxxxxxxxxxx> wrote: >> >> Got a log? I don't have time for a dive but it could be something >> simple we can fix with a config switch, if you're lucky. >> -Greg >> Software Engineer #42 @ http://inktank.com | http://ceph.com >> >> >> On Thu, Apr 25, 2013 at 7:49 PM, MinhTien MinhTien >> <tientienminh080590@xxxxxxxxx> wrote: >> > Hi all, >> > >> > I use ceph 0.56.4, when I restart ceph services, mds not active, I >> > rebooted >> > several times, but mds still not active. >> > e707: 1/1/1 up {0=1=up:replay}, 1 up:standby >> > >> > -- >> > Bui Minh Tien >> > >> > _______________________________________________ >> > ceph-users mailing list >> > ceph-users@xxxxxxxxxxxxxx >> > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com >> > > > > > > -- > Bui Minh Tien _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |