From owner-freebsd-current@FreeBSD.ORG Sun May 11 15:26:13 2003 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 93A0A37B404 for ; Sun, 11 May 2003 15:26:13 -0700 (PDT) Received: from kyle.tandemedia.com (kyle.tandemedia.com [216.29.169.3]) by mx1.FreeBSD.org (Postfix) with ESMTP id 656B143FE0 for ; Sun, 11 May 2003 15:26:12 -0700 (PDT) (envelope-from rmtodd@servalan.servalan.com) Received: by kyle.tandemedia.com (Postfix, from userid 66) id 9C07D55414; Sun, 11 May 2003 18:26:11 -0400 (EDT) Received: from localhost (1767 bytes) by servalan.servalan.com via sendmail with P:stdio/R:smart_host/T:hacked-uux (sender: ) (ident using unix) id for ; Sun, 11 May 2003 16:24:37 -0500 (CDT) (Smail-3.2.0.114 2001-Aug-6 #1 built 2003-Feb-6) Message-Id: Date: Sun, 11 May 2003 16:24:37 -0500 (CDT) From: rmtodd@servalan.servalan.com (Richard Todd) To: current@freebsd.org References: <1052570246.27195.6.camel@cf.freebsd-services.com> <22333.1052574519@critter.freebsd.dk> <20030511.134504.85393710.imp@bsdimp.com> Subject: Re: Interrupt latency problems 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: Sun, 11 May 2003 22:26:13 -0000 In the freebsd-current mailinglist M. Warner Losh writes: >Actually, this may be a problem in the acpi code. I have at least one >battery that causes my system to 'freeze' for a while. The mouse >interrupts aren't lost, per se, but just deferred too long. That was >before the latest acpi upgrade, and I've not tried the offending >battery since then (I think that the zero length messages are related >to querrying the battery status, but haven't booted windows to find >out for sure). I've been seeing similar things on my system for some time, but with the ACPI thermal code instead of the battery (which I don't have anyway as it's a desktop machine :-). The system every so often freezes for a second or two and, if you're watching closely with top, you see the CPU usage of the acpi_thermal process suddenly jump, e.g., 23 root 0 0 0K 12K nothin 0 34:44 4.15% 4.15% acpi_therma Changing how often the acpi_thermal process runs with the hw.acpi.thermal.polling_rate sysctl affects how often the freeze happens, making it clear that it's that part of the ACPI code that's the culprit. This is on a dual PII/400 system with Tyan Thunder 100GX (S1836DLUAN, IIRC) motherboard, running -current as of early last week: FreeBSD ichotolot.servalan.com 5.1-BETA FreeBSD 5.1-BETA #20: Tue May 6 20:14:14 CDT 2003 rmtodd@ichotolot.servalan.com:/usr/src/sys/i386/compile/ICHOTOLOTSMP i386 I'm not sure if this is before or after the "latest ACPI upgrade" you mention.