Date: Mon, 12 May 2008 22:49:27 +0200 From: Mel <fbsd.questions@rachie.is-a-geek.net> To: freebsd-questions@freebsd.org Cc: Aminuddin Abdullah <amin.scg@gmail.com> Subject: Re: Panic String: kmem_malloc(4096): kmem_map too small: 335544320 total allocated Message-ID: <200805122249.27906.fbsd.questions@rachie.is-a-geek.net> In-Reply-To: <48284371.02578c0a.17c4.1aed@mx.google.com> References: <20080412200816.A820110656B1@hub.freebsd.org> <48284371.02578c0a.17c4.1aed@mx.google.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Monday 12 May 2008 15:16:48 Aminuddin Abdullah wrote:
> I have 5 servers running almost at 70mbit/sec and each one of them will
> crash/reboot after more than 24 hours. The most it can stay up is 48 hours.
>
> How do I increase this memory from the default 320MB?
After some digging it looks like vm.kmem_size* are the loader tunables you're
looking for. See loader(8) for a description.
However, does it make sense to have this much kernel memory? What is it caused
by? mbufs? If you dump netstat -m periodically from cron, is that where the
memory is going?
--
Mel
Problem with today's modular software: they start with the modules
and never get to the software part.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200805122249.27906.fbsd.questions>