Date: Tue, 19 Nov 2002 05:22:40 -0800 From: Luigi Rizzo <rizzo@icir.org> To: Alexander Langer <alex@big.endian.de> Cc: freebsd-ipfw@FreeBSD.ORG Subject: Re: ipfw2 on SMP Message-ID: <20021119052240.B59522@xorpc.icir.org> In-Reply-To: <20021119105904.GK4666@fump.kawo2.rwth-aachen.de>; from alex@big.endian.de on Tue, Nov 19, 2002 at 11:59:04AM %2B0100 References: <20021119105904.GK4666@fump.kawo2.rwth-aachen.de>
next in thread | previous in thread | raw e-mail | index | archive | help
all the network stack is still under Giant so the second CPU won't help much in the lower levels of the stack (including ipfw2 and bridging). DEVICE_POLLING being incompatible with SMP is an orthogonal issue. cheers luigi On Tue, Nov 19, 2002 at 11:59:04AM +0100, Alexander Langer wrote: > HI! > > Does ipfw2 (box does use DEVICE_POLLING) on -CURRENT benefit from 2 CPUs? > > We have quite the same incoming / outgoing traffic here, but I don't > know the actual design of ipfw2 or the bridging-code, so I > wondered if that would benefit from a 2nd CPU, or if the CPUs lock > theirselves to the inefficiency. > > Comments? Stats? Already doing this somewhere? :) > > Thanks > > Alex > > > To Unsubscribe: send mail to majordomo@FreeBSD.org > with "unsubscribe freebsd-ipfw" in the body of the message To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-ipfw" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20021119052240.B59522>