Serious zfs slowdown when mixed with another file system (ufs/msdosfs/etc.).

[Peter Jeremy]

On 2010-Jul-11 11:25:12 -0700, Richard Lee <ricky at csua.berkeley.edu> wrote:
>But when almost all of the memory is taken by disk cache (of non-zfs
>file system), ZFS disks start threshing like mad and the write
>throughput goes down in 1-digit MB/second.

It can go a lot lower than that...

Yes, this is a known problem.  The underlying problem is a disconnect
between the ZFS cache (ARC) and the VM cache used by everything else,
preventing ZFS reclaiming RAM from the VM cache.  For several months,
I was running a regular cron job that was a slightly fancier version
of the perl one-liner.

I have been using the attached arc.patch1 based on a patch written by
Artem Belevich <fbsdlist at src.cx> (see http://pastebin.com/ZCkzkWcs )
for about a month.  I have had reasonable success with it (and junked
my cronjob) but have managed to wedge my system a couple of times
whilst doing zfs send|recv.  Whilst looking at that diff, I just
noticed a nasty signed/unsigned bug that could bite in low memory
conditions and have revised it to arc.patch2 (untested as yet).

Independently, Martin Matuska <mm at FreeBSD.org> committed r209227
that corrects a number of ARC bugs reported on OpenSolaris.  Whilst
this patch doesn't add checks on "inactive" or "cache", some quick
checks suggest it also helps (though I need to do further checks).
See http://people.freebsd.org/~mm/patches/zfs/head-12636.patch

-- 
Peter Jeremy
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 196 bytes
Desc: not available
Url : http://lists.freebsd.org/pipermail/freebsd-stable/attachments/20100712/1a90ab4b/attachment.pgp