On Thu, Apr 26, 2018 at 09:27:18AM +0900, Christian Balzer wrote:
:> The scrubs do impact performance which does mean I'm over capacity as
:> I should be able to scrub and not impact production, but there's still
:> a fair amount of capacity used during scrubbing that doesn't seem used
:> outside.
:>
:To be fair, most clusters can't do full throttle deep scrubs w/o impacting
:things, but with appropriately tuned down parameters (same for recovery)
:they are fine.
:Also with bluestore the need for deep scrubs is somewhat diminished IMHO,
:doing it less frequently and limiting it to low usage times is something
:to consider.
I'm spread to 42days
"osd_deep_scrub_interval": "3628800.000000",
and tuned down priority
"osd_max_scrubs": "1",
"osd_scrub_priority": "5",
"osd_scrub_sleep": "0.100000",
and limiting hours
"osd_scrub_begin_hour": "20",
"osd_scrub_end_hour": "2",
:> But looking harder the only answer may be "buy hardware" which is
:> valid answer.
:>
:More and/or better HW, yes.
So yeah, I think I'm just at the end of the tether :) And now I feel I
can prove that to the people with the purse strings.
So now the more smaller/faster disks -vs- weird tricks with using SSD
primaries and HDD replicas. Since writes are OK and I can't afford to
go all SSD I'm entertaining this but I don't like the weirdness to
messign around with crush map and primary afinity to make it so. Or
splitting pools so special things get special storage, or a million
other things. But that's several more threads.
Thanks all,
-Jon
_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
