From owner-freebsd-current Wed Feb 5 0:54:18 2003 Delivered-To: freebsd-current@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id F0F1137B401; Wed, 5 Feb 2003 00:54:16 -0800 (PST) Received: from critter.freebsd.dk (critter.freebsd.dk [212.242.86.163]) by mx1.FreeBSD.org (Postfix) with ESMTP id 185B043FD3; Wed, 5 Feb 2003 00:54:16 -0800 (PST) (envelope-from phk@freebsd.org) Received: from critter.freebsd.dk (localhost [127.0.0.1]) by critter.freebsd.dk (8.12.6/8.12.6) with ESMTP id h158sEYu035260; Wed, 5 Feb 2003 09:54:14 +0100 (CET) (envelope-from phk@freebsd.org) To: Brad Knowles Cc: "Greg 'groggy' Lehey" , current@freebsd.org Subject: Re: Preview: GEOMs statistics code. From: phk@freebsd.org In-Reply-To: Your message of "Wed, 05 Feb 2003 09:22:55 +0100." Date: Wed, 05 Feb 2003 09:54:14 +0100 Message-ID: <35259.1044435254@critter.freebsd.dk> Sender: owner-freebsd-current@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.ORG In message , Brad Knowles writes: >At 8:26 AM +0100 2003/02/05, phk@freebsd.org wrote: > My understanding was that a disk is 100% busy, if the heads are >constantly moving to and fro, and there is no period of time when >they aren't being yanked around. In other words, it would be 100% if >there is always at least one outstanding request. Works for me, I'll try if I can instrument that cheaply. > What is your time resolution on this sort of thing? Iostat can >only report in periods as small as one update per second, so I would >hope that you could measure these quantities on a much more frequent >basis, thus being able to make a useful calculation of average values >over that period of time. I currently use binuptime() which means that the resolution is whatever the system provides, which means better than 1 microsecond on all current platforms. The counters are updated in real time, so it's up to you how often you read them. >> For truly trying to understand our disk-I/O load, tracelogs will >> be needed (And I fear they will show a lot of interesting phenomena). > > Hmm. I'd like to learn more about this tracelog concept. Can >you provide any pointers? Well, "tracelog" is simply my word for the concept of recording each and every transaction and run it through some kind of analysis afterwards. -- Poul-Henning Kamp | UNIX since Zilog Zeus 3.20 phk@FreeBSD.ORG | TCP/IP since RFC 956 FreeBSD committer | BSD since 4.3-tahoe Never attribute to malice what can adequately be explained by incompetence. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-current" in the body of the message