Date: Fri, 04 Jun 2004 07:50:25 +0900 From: Jun Kuriyama <kuriyama@imgsrc.co.jp> To: Frode Nordahl <frode@nordahl.net> Cc: freebsd-current@freebsd.org Subject: Re: [HEADS-UP] mbuma is in the tree Message-ID: <7mn03k5k9a.wl@black3.imgsrc.co.jp> In-Reply-To: <29C3F4DB-B474-11D8-A18D-000A95A9A574@nordahl.net> References: <20040531215101.GA60299@freefall.freebsd.org> <29C3F4DB-B474-11D8-A18D-000A95A9A574@nordahl.net>
next in thread | previous in thread | raw e-mail | index | archive | help
At Wed, 2 Jun 2004 09:07:46 +0000 (UTC),
Frode Nordahl wrote:
> I'm running two NFS servers on 5.2.1-RELEASE (with the old mbuf code
> obviously), and I see the problem with leakage here. Don't know a way
> to reproduce it yet, but it happends over time. This happends both on a
> UP and a SMP machine.
>
> After more than a month of uptime, the mbuf map starts to get eaten up.
>
> Is there any way to look at the mbuf cache while the system is running
> to see what is in there?
It looks your host2 has normal value of mbuf usage. Is there the
difference of apprication with these hosts?
I'm using net-snmp and mrtg to collect statistics of mbuf/mbufc
usage. If you can find any trends (increasing at specific time period
or so), it would be help for further debugging.
---- mrtg.cfg
Target[mbuf]:hrStorageUsed.1&hrStorageUsed.4:public@server
MaxBytes1[mbuf]: 40960
MaxBytes2[mbuf]: 20480
Options[mbuf]: gauge,nopercent,growright
Title[mbuf]: Number of mbufs in use
YLegend[mbuf]: mbufs
ShortLegend[mbuf]:
LegendI[mbuf]: mbufs in use
LegendO[mbuf]: mbuf clusters in use
PageTop[mbuf]: <H1>Number of mbufs in use</H1>
--
Jun Kuriyama <kuriyama@imgsrc.co.jp> // IMG SRC, Inc.
<kuriyama@FreeBSD.org> // FreeBSD Project
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?7mn03k5k9a.wl>