Date: Mon, 07 Jun 2010 22:48:46 +0300 From: Mikolaj Golub <to.my.trociny@gmail.com> To: Olaf Seibert <O.Seibert@cs.ru.nl> Cc: Pyun YongHyeon <pyunyh@gmail.com>, freebsd-stable@freebsd.org Subject: Re: nfe0 loses network connectivity (8.0-RELEASE-p2) Message-ID: <86mxv6wrmp.fsf@kopusha.home.net> In-Reply-To: <20100607140611.GX883@twoquid.cs.ru.nl> (Olaf Seibert's message of "Mon, 7 Jun 2010 16:06:11 %2B0200") References: <20100527131310.GS883@twoquid.cs.ru.nl> <20100527174211.GC1211@michelle.cdnetworks.com> <20100607140611.GX883@twoquid.cs.ru.nl>
next in thread | previous in thread | raw e-mail | index | archive | help
On Mon, 7 Jun 2010 16:06:11 +0200 Olaf Seibert wrote: OS> I do get the impression there is a mbuf leak somehow. On a much older OS> file server (FreeBSD 6.1, serves a bit of NFS but has no ZFS) the mbuf OS> cluster useage is much lower, despite a longer uptime: OS> 256/634/890/25600 mbuf clusters in use (current/cache/total/max) OS> Also, it shows signs that measures are taken in case of mbuf shortage: OS> 2259806/466391/598621 requests for mbufs denied (mbufs/clusters/mbuf+clusters) OS> 1016 calls to protocol drain routines OS> whereas the FreeBSD 8.0 machine has zero or very low numbers: OS> 0/3956/1959 requests for mbufs denied (mbufs/clusters/mbuf+clusters) OS> 0 calls to protocol drain routines OS> and useage keeps growing: OS> 26122/1782/27904/32768 mbuf clusters in use (current/cache/total/max) It looks like the issue that has been fixed in STABLE. http://www.freebsd.org/cgi/query-pr.cgi?pr=kern/144330 -- Mikolaj Golub
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?86mxv6wrmp.fsf>