Hi, I'm testing ceph 0.67.3 (408cd61584c72c0d97b774b3d8f95c6b1b06341a) under load. My configuration has 2 mds, 3 mon and 16 osd - mon and mds are on separate servers, osd distributed on 8 servers
3 servers with several processes read and write via libcephfs. Restart of active mds leads to infinite rejoin and complete inaccessibility of the cephfs. It seems related to the bug http://tracker.ceph.com/issues/4637 -- Kind regards, Serge Slipchenko
_______________________________________________ ceph-users mailing list [email protected] http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
