|
Neohapsis is currently accepting applications for employment. For more information, please visit our website www.neohapsis.com or email hr@neohapsis.com |
Re: 3.6 squid/pf performance tested
From: Niall O'Higgins (niallo
netsoc.ucd.ie)
Date: Thu Jan 27 2005 - 13:40:14 CST
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
On Thu, Jan 27, 2005 at 11:16:43AM -0800, Karsten McMinn wrote:
> I nominated
> OpenBSD+squid/pf for the job. Stripped kernel, squid compiled
> transparent with a large amount of file descriptors, 2nics running in
> bridge mode, separate webserver behind one of the nics.
Stripping or otherwise messing with the GENERIC kernel sounds like a bad idea,
but maybe you have your reasons.
Squid handling moderate load on OpenBSD/amd64 GENERIC kernel can cause
panics due to high degrees of memory fragmentation. Previously, one would
have to tweak MAX_KMAPENT to avoid this panic, but Brad recently
committed a fix for this to -current.
I haven't been able to test a snap on our Squid box yet (we're
planning to do it soonish), but 3.7 looks like it will allow us to run a proper
GENERIC kernel again.
Thanks for the work guys, OpenBSD just keeps on getting better.
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]