[ceph-users] Bluestore osd_max_backfills

Scottix scottix at gmail.com
Wed Nov 8 12:54:11 PST 2017


When I add in the next hdd i'll try the method again and see if I just
needed to wait longer.

On Tue, Nov 7, 2017 at 11:19 PM Wido den Hollander <wido at 42on.com> wrote:

>
> > Op 7 november 2017 om 22:54 schreef Scottix <scottix at gmail.com>:
> >
> >
> > Hey,
> > I recently updated to luminous and started deploying bluestore osd
> nodes. I
> > normally set osd_max_backfills = 1 and then ramp up as time progresses.
> >
> > Although with bluestore it seems like I wasn't able to do this on the fly
> > like I used to with XFS.
> >
> > ceph tell osd.* injectargs '--osd-max-backfills 5'
> >
> > osd.34: osd_max_backfills = '5'
> > osd.35: osd_max_backfills = '5' rocksdb_separate_wal_dir = 'false' (not
> > observed, change may require restart)
> > osd.36: osd_max_backfills = '5'
> > osd.37: osd_max_backfills = '5'
> >
> > As I incorporate more bluestore osds not being able to control this is
> > going to drastically affect recovery speed and with the default as 1, on
> a
> > big rebalance, I would be afraid restarting a bunch of osd.
> >
>
> Are you sure the backfills are really not increasing? If you re-run the
> command, what does it output?
>
> I've seen this as well, but the backfills seemed to increase anyway.
>
> Wido
>
> > Any advice in how to control this better?
> >
> > Thanks,
> > Scott
> > _______________________________________________
> > 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/20171108/e97fefd8/attachment.html>


More information about the ceph-users mailing list