From owner-freebsd-questions@FreeBSD.ORG Wed Jun 22 16:12:47 2005 Return-Path: X-Original-To: freebsd-questions@freebsd.org Delivered-To: freebsd-questions@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 482A116A41C for ; Wed, 22 Jun 2005 16:12:47 +0000 (GMT) (envelope-from jim.mozley@exponential-e.net) Received: from mx1.exponential-e.net (ixbl-sun-02.exponential-e.net [62.244.177.19]) by mx1.FreeBSD.org (Postfix) with ESMTP id 09F8B43D4C for ; Wed, 22 Jun 2005 16:12:46 +0000 (GMT) (envelope-from jim.mozley@exponential-e.net) Received: from 62-244-182-25.cust.exponential-e.net ([62.244.182.25]:34892 helo=[127.0.0.1]) by mx1.exponential-e.net with esmtp (Exim 4.43) id 1Dl7qH-0000Uj-CI for freebsd-questions@freebsd.org; Wed, 22 Jun 2005 16:12:45 +0000 Message-ID: <42B98DFD.3050400@exponential-e.net> Date: Wed, 22 Jun 2005 17:12:45 +0100 From: Jim Mozley User-Agent: Mozilla Thunderbird 1.0.2 (Windows/20050317) X-Accept-Language: en-us, en MIME-Version: 1.0 To: freebsd-questions@freebsd.org References: In-Reply-To: Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Antivirus: avast! (VPS 0525-2, 22/06/2005), Outbound message X-Antivirus-Status: Clean Subject: Re: support for ICH6R controller and Broadcom ethernet X-BeenThere: freebsd-questions@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: User questions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 22 Jun 2005 16:12:47 -0000 scuba@centroin.com.br wrote: > Hi Jim, > > I think it's not a answer to you but here is my recent experience. > I've installed FBSD 5.4 in a box with Intel ICH5R chipset. > It's working, no hangs, no panics, but the disk performance on the > second IDE disk (I'm not using RAID, just simple master/slave setup), is > terrible. > It's like the DMA was not correctly set on the second disk. > I read somewhere, that FreeBSD has full support to ICH5 chipset > but NOT for ICH5"R". > Even when running in "compatibility mode" set on BIOS, the > performance is the same. > > Someone told me the follwing on the performance list: > > "I remember a commit to the ata driver to fix misprogramming of > DMA timing on an Intel chipset for devices and/or channels other than the > first. I'm not sure if 5.4 has the bug or the fix." > > To me it still has the bug. OK thanks for that help. If anyone knows anything more definitive I'd be grateful (no criticism of the helpful reply intended). Thanks, Jim