I've not been able to reproduce an issue with exactly same version of
your cluster.
./ceph -v
ceph version 10.2.5 (c461ee19ecbc0c5c330aca20f7392c9a00730367)
./rados df | grep cephfs
cephfs_data_a 409600 100 0 0
0 0 0 100 409600
./rados -p cephfs_data_a ls | wc -l
100
If you could reproduce an issue and let us share procedure, that would
be definitely help.
Will try again.
On Tue, Feb 7, 2017 at 2:01 AM, Florent B <florent@xxxxxxxxxxx> wrote:
> On 02/06/2017 05:49 PM, Shinobu Kinjo wrote:
>> How about *pve01-rbd01*?
>>
>> * rados -p pve01-rbd01 ls | wc -l
>>
>> ?
>
> # rados -p pve01-rbd01 ls | wc -l
> 871
>
> # ceph df
> GLOBAL:
> SIZE AVAIL RAW USED %RAW USED
> 5173G 5146G 27251M 0.51
> POOLS:
> NAME ID USED %USED MAX AVAIL OBJECTS
> data 0 0 0 2985G 0
> metadata 1 59178k 0 2985G 114
> pve01-rbd01 5 2572M 0.08 2985G 852
> cephfs01 6 39059k 0 2985G 120
Can you do just `df -h` on your box mounting cephfs or `ceph -s` on
your one of the MON hosts?
>
>
> And I saw there's a huge difference between data "used" and "raw used" :
> 27251M is not the sum of all pools (including copies)
_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
