Hello, my cluster didn't have MDS. I recommended add "ceph osd set noout" before shutdown OSD daemons. I've done those operation tomorrow and my cluster working again. Пятница, 7 апреля 2017, 13:47 +05:00 от TYLin <[email protected]>: > >Hi all, > >We’re trying to stop and then restart our ceph cluster. Our steps are as >following: > >stop cluster: >stop mds -> stop osd -> stop mon > >restart cluster: >start mon -> start osd -> start mds > >Our cluster will stuck in cephfs degraded and mds is replaying journal. After >restart mds again, cluster status becomes HEALTH_OK. What is the correct (or >recommend) steps to stop/restart cluster? > >Thanks, >Tim >_______________________________________________ >ceph-users mailing list >[email protected] >http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
_______________________________________________ ceph-users mailing list [email protected] http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
