Skip site navigation (1)Skip section navigation (2)
Date:      Fri, 2 Mar 2012 22:11:23 +1100
From:      Peter Jeremy <peterjeremy@acm.org>
To:        Luke Marsden <luke-lists@hybrid-logic.co.uk>
Cc:        freebsd-fs@freebsd.org, Alexander Leidinger <Alexander@Leidinger.net>
Subject:   Re: Another ZFS ARC memory question
Message-ID:  <20120302111123.GA40708@server.vk2pj.dyndns.org>
In-Reply-To: <1330683366.3819.20.camel@pow>
References:  <1330081612.13430.39.camel@pow> <20120227181436.GA49667@server.vk2pj.dyndns.org> <20120301142826.GG97848@zxy.spb.ru> <20120302102509.Horde.6uPSdpjmRSRPUJH1lHEHc3A@webmail.leidinger.net> <1330683366.3819.20.camel@pow>

next in thread | previous in thread | raw e-mail | index | archive | help

--17pEHd4RhPHOinZp
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
Content-Transfer-Encoding: quoted-printable

[Cc list pruned]

On 2012-Mar-02 10:16:06 +0000, Luke Marsden <luke-lists@hybrid-logic.co.uk>=
 wrote:
>We are presently working around it by limiting arc_max to 4G on our 24G
>RAM production boxes (which seems like a massive waste of performance)
>and by doing very careful/aggressive application level management of
>memory usage to ensure stability (limits.conf didn't work for us, so we
>rolled our own).  A better solution would be welcome, though, so that we
>can utilise all the free memory we're presently keeping around as a
>safety margin - ideally it would be used as ARC cache.

Have you tried increasing vm.v_cache_min to cover your spikes?

>1.  Is it expected that with a 4G limited arc_max value that we should
>see wired memory usage around 7-8G?  I understand that the kernel has to
>use some memory, but really 3-4G of non-ARC data?

Yes, that sounds possible.

>2.  We have some development machines with only 3G of RAM.  Previously
>they had no arc_max set and were left to tune themselves.  They were
>quite unstable.  Now we've set arc_max to 256M but things have got
>worse: we've seen a disk i/o big performance hit (untarring a ports
>tarball now takes 20 minutes), and wired memory usage is up around
>2.5GB, the machines are swapping a lot, and crashing more frequently.

That's stress-testing ZFS more than anything else.  You definitely
can't use those results as a guide to tune your production boxes
(other than what not to do).  That said, I have 3.5GB in my $work
desktop (running 8.2-stable from about a month ago) and don't have
any stability issues with either it or a buildbox with 2GB RAM.

>Follows is arc_summary.pl from one of the troubled dev machines showing
>the ARC using 500% of the memory it should be.  Also uname follows.  My
>second question is: have there been fixes between 8.2-RELEASE and
>8.3-BETA1 or 9.0-RELEASE which solve this ARC over-usage problem?

There definitely have been some commits to ensure that arc_max is
treated much more as a hard limit but I can't quickly find them so
I'm not sure if they pre- or post-date 8.2-RELEASE.

--=20
Peter Jeremy

--17pEHd4RhPHOinZp
Content-Type: application/pgp-signature

-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.18 (FreeBSD)

iEYEARECAAYFAk9QqtsACgkQ/opHv/APuIfWmgCfW+tqI1+n5qV9b5dWZ4F2aK/M
khEAoKqIgtv3M7cmbCQ0RBRrIJpSEfwj
=DgVI
-----END PGP SIGNATURE-----

--17pEHd4RhPHOinZp--



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20120302111123.GA40708>