From owner-freebsd-net Mon Jul 26 11:53:55 1999 Delivered-To: freebsd-net@freebsd.org Received: from cs.rice.edu (cs.rice.edu [128.42.1.30]) by hub.freebsd.org (Postfix) with ESMTP id A9D9414CC2 for ; Mon, 26 Jul 1999 11:53:52 -0700 (PDT) (envelope-from aron@cs.rice.edu) Received: (from aron@localhost) by cs.rice.edu (8.9.0/8.9.0) id NAA28030; Mon, 26 Jul 1999 13:53:02 -0500 (CDT) From: Mohit Aron Message-Id: <199907261853.NAA28030@cs.rice.edu> Subject: Re: FreeBSD tuning for webserver performance To: luigi@labinfo.iet.unipi.it (Luigi Rizzo) Date: Mon, 26 Jul 1999 13:53:00 -0500 (CDT) Cc: freebsd-net@freebsd.org, druschel@cs.rice.edu In-Reply-To: <199907261504.RAA00474@labinfo.iet.unipi.it> from "Luigi Rizzo" at Jul 26, 99 05:04:00 pm X-Mailer: ELM [version 2.4 PL25] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-net@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org > > usually backbone routers have (or try, or ought to) some active > queue management techniques such as RED or fair queueing variants > so that per-flow queues are kept short. Try to flood-ping some site > behind a bottleneck while you run a regular ping to the same site > with a separate connection, and you'll see that in many cases the > delay does not increase a lot -- you can even compute the queue > size with this technique using different packet sizes. > Very interesting. I thought that the deployment of intelligent techniques like RED and fair queuing was still rather thin in Internet routers. My impression was that most still do the naive FIFO queuing. - Mohit To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-net" in the body of the message