From owner-freebsd-net Thu Oct 4 10: 3:33 2001 Delivered-To: freebsd-net@freebsd.org Received: from iguana.aciri.org (iguana.aciri.org [192.150.187.36]) by hub.freebsd.org (Postfix) with ESMTP id 640BB37B405 for ; Thu, 4 Oct 2001 10:03:28 -0700 (PDT) Received: (from rizzo@localhost) by iguana.aciri.org (8.11.3/8.11.1) id f94H0ZQ45166; Thu, 4 Oct 2001 10:00:35 -0700 (PDT) (envelope-from rizzo) From: Luigi Rizzo Message-Id: <200110041700.f94H0ZQ45166@iguana.aciri.org> Subject: Re: How to increase TCP and UDP buffers (for IPv4/IPv6) In-Reply-To: <5.1.0.14.0.20011004122716.0408d470@marble.sentex.ca> from Mike Tancsa at "Oct 4, 2001 12:38:19 pm" To: mike@sentex.net (Mike Tancsa) Date: Thu, 4 Oct 2001 10:00:35 -0700 (PDT) Cc: rizzo@aciri.org, freebsd-net@freebsd.org X-Mailer: ELM [version 2.4ME+ PL43 (25)] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-net@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org > I guess in my case, the load average is general 0.00, but that is just > measuring userland activity no ? Is there a way to allocate more CPU to yes... "top" should tell you how much time you spend in kernel space, though, and that could be an indication. > measuring userland activity no ? Is there a way to allocate more CPU to > the kernel for routing ? The box in question has some 100,000 routes, so I no, currently the kernel will use up to 100% of the CPU for that task. > dont think I can implement fast_forwarding-- or am I thinking of something > else? fast_forwarding helps in the sense that it bypasses the queue and calls directly ip_input at interrupt time. The fact that it also uses a cache for routes is only an optimization. I am not sure how bad would it be to add code for full route lookups in ipflow_fastforwarding, i might try and have a look at this in a week or two once i am done with some (partly related) work i am doing. > Also, will removing ipv6 from the kernel make it more efficient acting as a > router ? probably not much, i guess it is just an additional entry in a switch() statement... cheers luigi ----------------------------------+----------------------------------------- Luigi RIZZO, luigi@iet.unipi.it . ACIRI/ICSI (on leave from Univ. di Pisa) http://www.iet.unipi.it/~luigi/ . 1947 Center St, Berkeley CA 94704 Phone: (510) 666 2927 ----------------------------------+----------------------------------------- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-net" in the body of the message