From owner-freebsd-current@FreeBSD.ORG Tue Jul 20 06:49:39 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 288A716A4CE for ; Tue, 20 Jul 2004 06:49:39 +0000 (GMT) Received: from av1-1-sn4.m-sp.skanova.net (av1-1-sn4.m-sp.skanova.net [81.228.10.116]) by mx1.FreeBSD.org (Postfix) with ESMTP id DFDA143D62 for ; Tue, 20 Jul 2004 06:49:38 +0000 (GMT) (envelope-from daniel_k_eriksson@telia.com) Received: by av1-1-sn4.m-sp.skanova.net (Postfix, from userid 502) id 1D13037E55; Tue, 20 Jul 2004 08:49:38 +0200 (CEST) Received: from smtp2-2-sn4.m-sp.skanova.net (smtp2-2-sn4.m-sp.skanova.net [81.228.10.182]) by av1-1-sn4.m-sp.skanova.net (Postfix) with ESMTP id 0F7D937E4B for ; Tue, 20 Jul 2004 08:49:38 +0200 (CEST) Received: from gadget (h130n1fls11o822.telia.com [213.64.66.130]) by smtp2-2-sn4.m-sp.skanova.net (Postfix) with ESMTP id EC31237E44 for ; Tue, 20 Jul 2004 08:49:37 +0200 (CEST) From: "Daniel Eriksson" To: Date: Tue, 20 Jul 2004 08:49:42 +0200 Organization: Home Message-ID: MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable X-Priority: 3 (Normal) X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook, Build 10.0.6626 Importance: Normal In-Reply-To: X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2800.1441 Subject: RE: HEADS UP [Re: thread+preemption stability improvement] 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: Tue, 20 Jul 2004 06:49:39 -0000 > I have set aside some time on the server (normally a busy=20 > production-type > server) to try a few different configs (SHED_ULE instead of SHED_4BSD, > turning off apic, removing polling) to see if any of them=20 > will have any > impact. I have just tried a number of different combinations of sheduler, acpi, apic, polling, ... No matter what I do, the only way to prevent errors like the one below = seems to be to run with preemption turned off. Interrupt storm detected on "irq20: atapci4"; throttling interrupt = source ad20: FAILURE - already active DMA on this device ad20: setting up DMA failed See my recent mail on this list entitled "Kernel preemption leads to = SATA instability (how to debug?)" for machine configuration and further information. /Daniel Eriksson