I think you'll find the "ceph df" command more useful -- in recent
versions that is pretty smart about reporting the effective space
available for each pool.
John
On Fri, Feb 6, 2015 at 3:38 PM, pixelfairy <pixelfairy@xxxxxxxxx> wrote:
> heres output of 'ceph -s' from a kvm instance running as a ceph node.
> all 3 nodes are monitors, each with 6 4gig osds.
>
> mon_osd_full ratio: .611
> mon_osd_nearfull ratio: .60
>
> whats 23689MB used? is that a buffer because of mon_osd_full ratio?
>
> is there a way to query a pool for how much usable space is really
> available to clients? for example, in this case, 3 nodes, 6osds, 4G
> each = 72G, so with a replica size of 3, id like to see something that
> says close 20G available, 1.7G in use.
>
> ceph3:~# ceph -s
> cluster 2198abdb-2669-438a-8673-fc4f226a226c
> health HEALTH_OK
> monmap e1: 3 mons at
> {ceph1=172.21.0.31:6789/0,ceph2=172.21.0.32:6789/0,ceph3=172.21.0.33:6789/0},
> election epoch 16, quorum 0,1,2 ceph1,ceph2,ceph3
> osdmap e104: 18 osds: 18 up, 18 in
> pgmap v5557: 600 pgs, 1 pools, 1694 MB data, 432 objects
> 23689 MB used, 49858 MB / 73548 MB avail
> 600 active+clean
> _______________________________________________
> 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
