From owner-freebsd-questions@FreeBSD.ORG Tue Mar 15 22:22:55 2011 Return-Path: Delivered-To: freebsd-questions@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id C2AF81065672 for ; Tue, 15 Mar 2011 22:22:55 +0000 (UTC) (envelope-from freebsd@edvax.de) Received: from mx02.qsc.de (mx02.qsc.de [213.148.130.14]) by mx1.freebsd.org (Postfix) with ESMTP id 7F2498FC1B for ; Tue, 15 Mar 2011 22:22:55 +0000 (UTC) Received: from r55.edvax.de (port-92-195-175-53.dynamic.qsc.de [92.195.175.53]) by mx02.qsc.de (Postfix) with ESMTP id 0F4491E166; Tue, 15 Mar 2011 23:22:53 +0100 (CET) Received: from r55.edvax.de (localhost [127.0.0.1]) by r55.edvax.de (8.14.2/8.14.2) with SMTP id p2FMMrI2002380; Tue, 15 Mar 2011 23:22:53 +0100 (CET) (envelope-from freebsd@edvax.de) Date: Tue, 15 Mar 2011 23:22:52 +0100 From: Polytropon To: Adam Vande More Message-Id: <20110315232252.c3114070.freebsd@edvax.de> In-Reply-To: References: <8a6023db5a3d4c8b34161f7ee0af29bb.squirrel@wtp1.ath.cx> <201103151041.56373.erich@alogreentechnologies.com> <5ab7e13805185464a4adf0c5d326671e.squirrel@wtp1.ath.cx> <20110315215907.f8a08352.freebsd@edvax.de> Organization: EDVAX X-Mailer: Sylpheed 2.4.7 (GTK+ 2.12.1; i386-portbld-freebsd7.0) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Cc: freebsd_user@guice.ath.cx, freebsd-questions@freebsd.org Subject: Re: IDE -- mount partitions for better performance X-BeenThere: freebsd-questions@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: Polytropon List-Id: User questions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 15 Mar 2011 22:22:55 -0000 On Tue, 15 Mar 2011 17:07:20 -0500, Adam Vande More wrote: > Your statement about master being faster than a slave is simply not true for > almost every scenario when using devices with same capabilites. All > master/slave really controls is enumeration, and shouldn't effect > performance in and of itself. Other variables can effect that of course, > like using a slower device as an ATA Device-1 with a faster Device-0. Even > that example isn't ubiquitous as many, maybe most controllers are able to > support mixed devices each in their fastest mode. My statement originates back from individual experience in settings where disks with different capabilities (esp. very old + very new disk), as well as disk drive and an optical drive with limited speed. > The whole IDE device contention really isn't much of a bottle neck in this > scenario. It's only a big factor when there's *a lot* of simultaneous IO > going to both, say dumping one disk to another. That's true: When copying (or moving) data from one disk to the other master->master seems to be faster than master->slave (same line), if I remember correctly. > The highest preforming setup in something like this is likely to be > something along the lines of a 4-way /boot gmirror, and a 4-way gstripe with > a smaller stripe size eg 32k across the remaining usable space. If you > aggregate your disk IO in this manner, IDE channel contention shouldn't be > much of a bottleneck. A good advice, I haven't thought of that (never tried, but sounds achievable). -- Polytropon Magdeburg, Germany Happy FreeBSD user since 4.0 Andra moi ennepe, Mousa, ...