[ceph-users] Is object name used by CRUSH algorithm?

Gregory Farnum gfarnum at redhat.com
Mon Oct 1 10:39:00 PDT 2018


On Thu, Sep 27, 2018 at 12:08 PM Jin Mao <jin at tower-research.com> wrote:

> I am running luminous and the objects were copied from Isilon with a long
> and similar prefix in path like /dir1/dir2/dir3/yyyy/mm/dd. The objects are
> copied to various buckets like bucket_YYYYMMDD/dir1/dir2/dir3/yyyy/mm/dd.
> This setup minimize some internal code change when moving from NFS to
> object store.
>
> I heard that CRUSH may NOT evenly balance OSDs if there are many common
> leading characters in the object name? However, I couldn't find any
> evidence to support this.
>
> Does anyone know further details about this?
>

CRUSH does use the object name as an input to generate a hashed value, but
it's not a stable hash and having common prefixes should not be an issue.

Also since you're going through RGW there's quite a bit more happening to
the object names, so I wouldn't worry about it.


>
> Thank you.
>
> Jin.
> _______________________________________________
> ceph-users mailing list
> ceph-users at lists.ceph.com
> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.ceph.com/pipermail/ceph-users-ceph.com/attachments/20181001/d8a66a77/attachment.html>


More information about the ceph-users mailing list