From owner-freebsd-current@FreeBSD.ORG Sat Dec 25 03:11:39 2004 Return-Path: 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 347DF16A4CE for ; Sat, 25 Dec 2004 03:11:39 +0000 (GMT) Received: from relay02.pair.com (relay02.pair.com [209.68.5.16]) by mx1.FreeBSD.org (Postfix) with SMTP id A096743D1D for ; Sat, 25 Dec 2004 03:11:38 +0000 (GMT) (envelope-from silby@silby.com) Received: (qmail 27929 invoked from network); 25 Dec 2004 03:11:37 -0000 Received: from unknown (HELO localhost) (unknown) by unknown with SMTP; 25 Dec 2004 03:11:37 -0000 X-pair-Authenticated: 209.68.2.70 Date: Fri, 24 Dec 2004 21:11:36 -0600 (CST) From: Mike Silbersack To: current@freebsd.org Message-ID: <20041224210649.D72855@odysseus.silby.com> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed X-Mailman-Approved-At: Sat, 25 Dec 2004 17:35:12 +0000 Subject: Disk access SOLVES sound stutter! X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 25 Dec 2004 03:11:39 -0000 My laptop has built-in sound: pcm0: port 0x1000-0x10ff mem 0xd0001000-0xd0001fff irq 5 at device 6.0 on pci0 pcm0: pcm0: [GIANT-LOCKED] I haven't played with it much, but I started doing so again recently. The sound quality is rather poor when the system is idle, it sounds as if it's playing too slowly. However, while there is disk activity going on (start Konqueror, OO, opening my huge inbox, etc), the sound is perfect. systat -vm shows this to be due to interrupt rates. Although irq 5 is not shared with anything else, disk activity causes the interrupt rate for irq 5 to increase from ~79 per second to ~84 per second. This is a 6.0-current UP system. 4BSD scheduler, preemption enabled. Any clue as to why this might be happening? Sounds like something very interesting going on in some low level system somewhere. :) BTW, mpg123 and xmms were both used for testing, with and without X running; results always seem to fix the above profile. Mike "Silby" Silbersack