It's not stable at Firely for kvstore. But for the master branch, it's should be no existing/known bug. On Fri, Oct 24, 2014 at 7:41 PM, Andrey Korolyov <andrey@xxxxxxx> wrote: > Hi, > > during recovery testing on a latest firefly with leveldb backend we > found that the OSDs on a selected host may crash at once, leaving > attached backtrace. In other ways, recovery goes more or less smoothly > for hours. > > Timestamps shows how the issue is correlated between different > processes on same node: > > core.ceph-osd.25426.node01.1414148261 > core.ceph-osd.25734.node01.1414148263 > core.ceph-osd.25566.node01.1414148345 > > The question is about kv backend state in Firefly - is it considered > stable enough to run production test against it or we should better > move to giant/master for this? > > Thanks! > > _______________________________________________ > ceph-users mailing list > ceph-users@xxxxxxxxxxxxxx > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com > -- Best Regards, Wheat _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |