From owner-freebsd-current@FreeBSD.ORG Mon Dec 19 22:19:11 2005 Return-Path: X-Original-To: freebsd-current@freebsd.org 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 3465A16A420; Mon, 19 Dec 2005 22:19:11 +0000 (GMT) (envelope-from jd@ugcs.caltech.edu) Received: from lira.ugcs.caltech.edu (lira.ugcs.caltech.edu [131.215.176.118]) by mx1.FreeBSD.org (Postfix) with ESMTP id 6361C43D64; Mon, 19 Dec 2005 22:19:10 +0000 (GMT) (envelope-from jd@ugcs.caltech.edu) Received: by lira.ugcs.caltech.edu (Postfix, from userid 3640) id 203416B002; Mon, 19 Dec 2005 14:19:08 -0800 (PST) Received: from localhost (localhost [127.0.0.1]) by lira.ugcs.caltech.edu (Postfix) with ESMTP id C27525300A; Mon, 19 Dec 2005 14:19:08 -0800 (PST) Date: Mon, 19 Dec 2005 14:19:08 -0800 (PST) From: Jon Dama To: Matthias Andree In-Reply-To: <20051219215551.GA7362@merlin.emma.line.org> Message-ID: References: <20051213151908.GA26821@crodrigues.org> <20051216151228.GA34670@crodrigues.org> <20051217141647.GC27992@merlin.emma.line.org> <2b22951e0512172355k36a579f4i42dd72562a3530ed@mail.gmail.com> <20051218092523.GA4694@merlin.emma.line.org> <2b22951e0512191348t227c9354i36d6a4a87e7d5698@mail.gmail.com> <20051219215551.GA7362@merlin.emma.line.org> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Cc: freebsd-fs@freebsd.org, "Cai, Quanqing" , freebsd-current@freebsd.org Subject: Re: XFS (read-only) support committed to CURRENT X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.5 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: Mon, 19 Dec 2005 22:19:11 -0000 > On the downside, ext3fs and write caches don't mix well, unless you have > battery backup units sitting on your RAID controllers (I do, and > switching this MegaRAID - RAID5 on 2+1 - to writeback mode improved > write speed by a factor of 5 - no database loads though). This an issue that Kirk has been looking into. Ideally the problem will go away completely when both request barriers and NCQ are implemented. (The latter for people with high-end SATA drives and the former for the rest of the consumers of ATA). -Jon