On Wed, Mar 11, 2015 at 1:21 PM, LOPEZ Jean-Charles <jelopez@xxxxxxxxxx> wrote:
> Hi Florent
>
> What are the « rules » for stripe_unit & object_size ? -> stripe_unit *
> stripe_count = object_size
>
> So in your case set stripe_unit = 2
>
> JC
>
>
> On 11 Mar 2015, at 19:59, Florent B <florent@xxxxxxxxxxx> wrote:
>
> Hi all,
>
> I'm testing CephFS with Giant and I have a problem when I set these attrs :
>
> setfattr -n ceph.dir.layout.stripe_unit -v "65536" pool_cephfs01/
> setfattr -n ceph.dir.layout.stripe_count -v "1" pool_cephfs01/
> setfattr -n ceph.dir.layout.object_size -v "1310720" pool_cephfs01/
> setfattr -n ceph.dir.layout.pool -v "cephfs01" pool_cephfs01/
>
> When a client writes files in pool_cephfs01/, It got "failed: Transport
> endpoint is not connected (107)" and these errors on MDS :
>
> 10.111.0.6:6801/41706 >> 10.111.17.118:0/9384 pipe(0x5e3a580 sd=27 :6801 s=2
> pgs=2 cs=1 l=0 c=0x6a8d1e0).fault, server, going to standby
>
> When I set stripe_unit=1048576 & object_size=1048576, it seems working.
>
> What are the "rules" for stripe_unit & object_size ?
"stripe_unit * stripe_count = object_size" is definitely not correct.
The current rules are:
- object_size is a multiple of stripe_unit
- stripe_unit (and consequently object_size) is 64k-aligned
- stripe_count is at least 1 (i.e. at least 1 object in an object set)
However, the above layout is pretty bogus - there is basically no
striping going on, so it's probably a bug in the way it's handled.
Thanks,
Ilya
_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
