From owner-freebsd-net@FreeBSD.ORG Sun Oct 16 04:21:51 2005 Return-Path: X-Original-To: net@freebsd.org Delivered-To: freebsd-net@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 86F0E16A420 for ; Sun, 16 Oct 2005 04:21:51 +0000 (GMT) (envelope-from wollman@khavrinen.csail.mit.edu) Received: from khavrinen.csail.mit.edu (khavrinen.csail.mit.edu [128.30.28.20]) by mx1.FreeBSD.org (Postfix) with ESMTP id C154C43D49 for ; Sun, 16 Oct 2005 04:21:50 +0000 (GMT) (envelope-from wollman@khavrinen.csail.mit.edu) Received: from khavrinen.csail.mit.edu (localhost.csail.mit.edu [127.0.0.1]) by khavrinen.csail.mit.edu (8.13.1/8.13.4) with ESMTP id j9G4Lk1b047015 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=OK CN=khavrinen.csail.mit.edu issuer=Client+20CA); Sun, 16 Oct 2005 00:21:48 -0400 (EDT) (envelope-from wollman@khavrinen.csail.mit.edu) Received: (from wollman@localhost) by khavrinen.csail.mit.edu (8.13.1/8.13.4/Submit) id j9G4LjB6047012; Sun, 16 Oct 2005 00:21:45 -0400 (EDT) (envelope-from wollman) From: Garrett Wollman MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Message-ID: <17233.54617.89368.645866@khavrinen.csail.mit.edu> Date: Sun, 16 Oct 2005 00:21:45 -0400 To: Bruce Evans In-Reply-To: <20051016135234.T86712@delplex.bde.org> References: <17231.43525.446450.161986@grasshopper.cs.duke.edu> <13600.1129298731@critter.freebsd.dk> <17231.50841.442047.622878@grasshopper.cs.duke.edu> <20051015092141.F1403@epsplex.bde.org> <20051015194738.C66245@fledge.watson.org> <20051016135234.T86712@delplex.bde.org> X-Mailer: VM 7.17 under 21.4 (patch 17) "Jumbo Shrimp" XEmacs Lucid X-Greylist: Sender DNS name whitelisted, not delayed by milter-greylist-1.6 (khavrinen.csail.mit.edu [127.0.0.1]); Sun, 16 Oct 2005 00:21:48 -0400 (EDT) X-Spam-Status: No, score=0.0 required=5.0 tests=none version=3.0.2 X-Spam-Checker-Version: SpamAssassin 3.0.2 (2004-11-16) on khavrinen.csail.mit.edu Cc: net@freebsd.org Subject: Re: Call for performance evaluation: net.isr.direct (fwd) X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 16 Oct 2005 04:21:51 -0000 < said: > Probably the problem is largest for latency, especially in benchmarks. > Latency benchmarks probably have to start cold, so they have no chance > of queue lengths > 1, so there must be a context switch per packet and > may be 2. It has frequently been proposed that one of the deficiencies of the sockets model is that too much work must take place in interrupt context. Several alternatives have been suggested, including user-mode protocol processing (e.g., Exokernel) and event-driven receive (can't think of an example here from the literature). In an alternate universe with truly pervasive threading, one might require an application to "donate" a thread to protocol processing -- effectively combining the two approaches I mentioned -- which would be the way to "win" such latency benchmarks. (The application donating the processing power is then also able to donate its memory.) -GAWollman