From owner-freebsd-stable@FreeBSD.ORG Fri Jun 15 22:33:54 2012 Return-Path: Delivered-To: freebsd-stable@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id F40B9106566B for ; Fri, 15 Jun 2012 22:33:53 +0000 (UTC) (envelope-from byshenknet@byshenk.net) Received: from portland1.byshenk.net (portland1.byshenk.net [69.168.54.16]) by mx1.freebsd.org (Postfix) with ESMTP id C7C488FC12 for ; Fri, 15 Jun 2012 22:33:53 +0000 (UTC) Received: from portland1.byshenk.net (localhost [127.0.0.1]) by portland1.byshenk.net (8.14.5/8.14.5) with ESMTP id q5FMGLnv014789; Fri, 15 Jun 2012 15:16:21 -0700 (PDT) (envelope-from byshenknet@portland1.byshenk.net) Received: (from byshenknet@localhost) by portland1.byshenk.net (8.14.5/8.14.5/Submit) id q5FMGL0W014788; Fri, 15 Jun 2012 15:16:21 -0700 (PDT) (envelope-from byshenknet) Date: Fri, 15 Jun 2012 15:16:21 -0700 From: Greg Byshenk To: Kurt Jaeger Message-ID: <20120615221621.GS1768@portland1.byshenk.net> References: <20120608144621.GA74475@home.opsec.eu> <201206091527.q59FRTeg069656@lurza.secnetix.de> <20120615172028.GU5335@home.opsec.eu> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20120615172028.GU5335@home.opsec.eu> User-Agent: Mutt/1.4.2.3i X-Spam-Status: No, score=-1.0 required=5.0 tests=ALL_TRUSTED autolearn=unavailable version=3.3.2 X-Spam-Checker-Version: SpamAssassin 3.3.2 (2011-06-06) on portland1.byshenk.net Cc: freebsd-stable@freebsd.org Subject: Re: Experience with Intel SATA and fbsd 8.3-amd64 ? X-BeenThere: freebsd-stable@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Production branch of FreeBSD source code List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 15 Jun 2012 22:33:54 -0000 On Fri, Jun 15, 2012 at 07:20:28PM +0200, Kurt Jaeger wrote: > > Kurt Jaeger wrote: > > > I have a problem with some host: If I put heavy IO load on that > > > system, write errors happen, and then it crashes. > > > > What kind of write errors, exactly? What messages do you > > get on the console? > > g_vfs_done():ada0s1f[WRITE(offset=50699862016, length=16384)]error = 2 > 2 > g_vfs_done():ada0s1f[WRITE(offset=50699862016, length=16384)]error = 22 > g_vfs_done():ada0s1e[WRITE(offset=44693307392, length=16384)]error = 22 > g_vfs_done():ada0s1e[WRITE(offset=44693211136, length=2048)]error = 5 > > > It's also worth mentioning that such problems could also > > be caused by bad RAM, or even by the power supply (though > > the latter is unlikely in this case, I think). > > Well, the device was probably a bit on the cheap side (ALLNET FW9000). Could it be a device problem? I've seen that type of error (including a crash in the end) when a device can't handle DMA. Disabling DMA solved the problem for me. -- greg byshenk - gbyshenk@byshenk.net - Leiden, NL - Portland, OR USA