From owner-freebsd-hackers Tue Mar 4 22:19:45 2003 Delivered-To: freebsd-hackers@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 9DCCA37B405; Tue, 4 Mar 2003 22:19:43 -0800 (PST) Received: from garple.migus.org (pcp243391pcs.howard01.md.comcast.net [68.55.83.143]) by mx1.FreeBSD.org (Postfix) with ESMTP id 5CB0C43FAF; Tue, 4 Mar 2003 22:19:42 -0800 (PST) (envelope-from adam@migus.org) Received: from migus.org (a1ppna9as80qy5ih@garple.migus.org [192.168.4.4]) by garple.migus.org (8.12.6/8.12.6) with SMTP id h256Je4t010441; Wed, 5 Mar 2003 01:19:41 -0500 (EST) (envelope-from adam@migus.org) Received: from 192.168.4.2 (SquirrelMail authenticated user adam) by mail.migus.org with HTTP; Wed, 5 Mar 2003 01:19:41 -0500 (EST) Message-ID: <49978.192.168.4.2.1046845181.squirrel@mail.migus.org> Date: Wed, 5 Mar 2003 01:19:41 -0500 (EST) Subject: RE: Disk scheduling in FreeBSD From: "Adam Migus" To: In-Reply-To: <20030228125613.A711@odysseus.silby.com> References: <20030228125613.A711@odysseus.silby.com> X-Priority: 3 Importance: Normal Cc: , , , X-Mailer: SquirrelMail (version 1.2.8) MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit X-Spam-Status: No, hits=-5.8 required=5.7 tests=AWL,IN_REP_TO,QUOTED_EMAIL_TEXT,REFERENCES, SPAM_PHRASE_00_01,TO_BE_REMOVED_REPLY version=2.41 Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.ORG Mike, I don't have the test, but I've built a generic performance testing framework for FreeBSD over the past couple of months that would make running such a test trivial. I'd post a link but the page has no permanent home yet. When it gets one I can follow it up with a link. For now, the application called "boot_tester" allows the user to run a set of commands (usually performance tests) on boot. The framework optionally creates a new filesystem work area and outputs in a standard format. The commands are run for n iterations (one per boot) over an array of kernels. If used with the diskless testbed setup I've started developing to use with it, running tests over arbitrary worlds as well as kernels is trivial and can be automated. If anyone's interested, contact me. Like I said, I'll put up a link when I get a home for the pages. > > On Fri, 28 Feb 2003, Paul Robinson wrote: > >> Well, I'm just a hanger-on without a commit bit, so I'll >> work on making it production ready in the next few weeks, >> post up a patch and if somebody wants to commit it, great. >> At the moment it's all based on 4.3-RELEASE and isn't really >> production ready. It does look worth doing though. > > Make an easy to run testbench which should show the > performance > improvements / disadvantages of a new IO scheduler first; > that's really the first step. > > Mike "Silby" Silbersack > > > To Unsubscribe: send mail to majordomo@FreeBSD.org > with "unsubscribe freebsd-hackers" in the body of the message -- Adam Migus - Research Scientist Network Associates Laboratories (http://www.nailabs.com) TrustedBSD (http://www.trustedbsd.org) FreeBSD (http://www.freebsd.org) To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message