I agree with Maged that perhaps not enough osds were able to report the osd as down to the mons. Setting that variable will make sure that any 1 osd can report any other osd as down. I usually prefer seeing that value to at least 1 more than a single host so that a networking event on a single note can't mark every osd in the cluster down.
You can also many mark osds down with `ceph osd down 4`.
On Wed, Jan 31, 2018, 3:20 PM Maged Mokhtar <mmokhtar@xxxxxxxxxxx> wrote:
try setting:
mon_osd_min_down_reporters = 1
_______________________________________________
On 2018-01-31 20:46, Steven Vacaroaia wrote:
Hi,Why is ceph osd tree reports that osd.4 is up when the server on which osd.4 is running is actually down ??Any help will be appreciated[root@osd01 ~]# ping -c 2 osd02PING osd02 (10.10.30.182) 56(84) bytes of data.From osd01 (10.10.30.181) icmp_seq=1 Destination Host UnreachableFrom osd01 (10.10.30.181) icmp_seq=2 Destination Host Unreachable[root@osd01 ~]# ceph osd treeID CLASS WEIGHT TYPE NAME STATUS REWEIGHT PRI-AFF-9 0 root ssds-10 0 host osd01-ssd-11 0 host osd02-ssd-12 0 host osd04-ssd-1 4.22031 root default-3 1.67967 host osd010 hdd 0.55989 osd.0 down 0 1.000003 hdd 0.55989 osd.3 down 0 1.000006 hdd 0.55989 osd.6 up 1.00000 1.00000-5 1.67967 host osd021 hdd 0.55989 osd.1 down 1.00000 1.000004 hdd 0.55989 osd.4 up 1.00000 1.000007 hdd 0.55989 osd.7 down 1.00000 1.00000-7 0.86096 host osd042 hdd 0.28699 osd.2 down 0 1.000005 hdd 0.28699 osd.5 down 1.00000 1.000008 hdd 0.28699 osd.8 down 1.00000 1.00000[root@osd01 ~]# ceph tell osd.4 bench^CError EINTR: problem getting command descriptions from osd.4[root@osd01 ~]# ceph osd dfID CLASS WEIGHT REWEIGHT SIZE USE AVAIL %USE VAR PGS0 hdd 0.55989 0 0 0 0 0 0 03 hdd 0.55989 0 0 0 0 0 0 06 hdd 0.55989 1.00000 573G 16474M 557G 2.81 0.84 01 hdd 0.55989 1.00000 573G 16516M 557G 2.81 0.84 04 hdd 0.55989 1.00000 573G 16465M 557G 2.80 0.84 07 hdd 0.55989 1.00000 573G 16473M 557G 2.81 0.84 02 hdd 0.28699 0 0 0 0 0 0 05 hdd 0.28699 1.00000 293G 16466M 277G 5.47 1.63 08 hdd 0.28699 1.00000 293G 16461M 277G 5.47 1.63 0TOTAL 2881G 98857M 2784G 3.35MIN/MAX VAR: 0.84/1.63 STDDEV: 1.30[root@osd01 ~]# ceph osd df treeID CLASS WEIGHT REWEIGHT SIZE USE AVAIL %USE VAR PGS TYPE NAME-9 0 - 0 0 0 0 0 - root ssds-10 0 - 0 0 0 0 0 - host osd01-ssd-11 0 - 0 0 0 0 0 - host osd02-ssd-12 0 - 0 0 0 0 0 - host osd04-ssd-1 4.22031 - 2881G 98857M 2784G 3.35 1.00 - root default-3 1.67967 - 573G 16474M 557G 2.81 0.84 - host osd010 hdd 0.55989 0 0 0 0 0 0 0 osd.03 hdd 0.55989 0 0 0 0 0 0 0 osd.36 hdd 0.55989 1.00000 573G 16474M 557G 2.81 0.84 0 osd.6-5 1.67967 - 1720G 49454M 1671G 2.81 0.84 - host osd021 hdd 0.55989 1.00000 573G 16516M 557G 2.81 0.84 0 osd.14 hdd 0.55989 1.00000 573G 16465M 557G 2.80 0.84 0 osd.47 hdd 0.55989 1.00000 573G 16473M 557G 2.81 0.84 0 osd.7-7 0.86096 - 587G 32928M 555G 5.47 1.63 - host osd042 hdd 0.28699 0 0 0 0 0 0 0 osd.25 hdd 0.28699 1.00000 293G 16466M 277G 5.47 1.63 0 osd.58 hdd 0.28699 1.00000 293G 16461M 277G 5.47 1.63 0 osd.8TOTAL 2881G 98857M 2784G 3.35MIN/MAX VAR: 0.84/1.63 STDDEV: 1.30
_______________________________________________
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
_______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
