You must have a quorum or MORE than 50% of your monitors functioning for the cluster to function. With one of two you only have 50% which isn't enough and stops i/o. Sent from my iPad > On Oct 11, 2013, at 11:28 PM, "飞" <duron800@xxxxxx> wrote: > > hello, I am a new user of ceph, > I have built a ceph testing Environment for block storage, > I have 2 osd and 2 monitor,In addition to failover test, other tests are normal. > when I perform failover test, if I stop one osd , the cluster is OK, > but if I stop one monitor , the cluster have entire die , why ? thank you. > > my configure file : > ; global > [global] > ; enable secure authentication > ; auth supported = cephx > > auth cluster required = none > auth service required = none > auth client required = none > > mon clock drift allowed = 3 > > ; monitors > ; You need at least one. You need at least three if you want to > ; tolerate any node failures. Always create an odd number. > [mon] > mon data = /home/ceph/mon$id > ; some minimal logging (just message traffic) to aid debugging > debug ms = 1 > [mon.0] > host = sheepdog1 > mon addr = 192.168.0.19:6789 > > [mon.1] > mon data = /var/lib/ceph/mon.$id > host = sheepdog2 > mon addr = 192.168.0.219:6789 > > ; mds > ; You need at least one. Define two to get a standby. > [mds] > ; where the mds keeps it's secret encryption keys > keyring = /home/ceph/keyring.mds.$id > [mds.0] > host = sheepdog1 > ; osd > ; You need at least one. Two if you want data to be replicated. > ; Define as many as you like. > [osd] > ; This is where the btrfs volume will be mounted. > osd data = /home/ceph/osd.$id > osd journal = /home/ceph/osd.$id/journal > osd journal size = 512 > ; working with ext4 > filestore xattr use omap = true > > ; solve rbd data corruption > filestore fiemap = false > > [osd.0] > host = sheepdog1 > osd data = /var/lib/ceph/osd/diskb > osd journal = /var/lib/ceph/osd/diskb/journal > [osd.2] > host = sheepdog2 > osd data = /var/lib/ceph/osd/diskc > osd journal = /var/lib/ceph/osd/diskc/journal > > _______________________________________________ > ceph-users mailing list > ceph-users@xxxxxxxxxxxxxx > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |