My understanding is that the exact same objects would move back to the OSD if weight went 1 -> 0 -> 1 given the same Cluster state and same object names, CRUSH is deterministic so that would be the almost certain result.
On Mon, Jan 15, 2018 at 2:46 PM, lists <lists@xxxxxxxxxxxxx> wrote:
Hi Wes,
On 15-1-2018 20:32, Wes Dillingham wrote:
I dont hear a lot of people discuss using xfs_fsr on OSDs and going over the mailing list history it seems to have been brought up very infrequently and never as a suggestion for regular maintenance. Perhaps its not needed.True, it's just something we've always done on all our xfs filesystems, to keep them speedy and snappy. I've disabled it, and then it doesn't happen.
Perhaps I'll keep it disabled.
But on this last question, about data distribution across OSDs:
In that case, how about reweighting that osd.10 to "0", wait until
all data has moved off osd.10, and then setting it back to "1".
Would this result in *exactly* the same situation as before, or
would it at least cause the data to have spread move better across
the other OSDs?
Would it work like that? Or would setting it back to "1" give me again the same data on this OSD that we started with?
Thanks for your comments,
MJ
_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Respectfully,
Wes Dillingham
Research Computing | Senior CyberInfrastructure Storage Engineer
Harvard University | 38 Oxford Street, Cambridge, Ma 02138 | Room 204
_______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
