From owner-freebsd-stable@FreeBSD.ORG Thu Feb 8 23:38:03 2007 Return-Path: X-Original-To: freebsd-stable@freebsd.org Delivered-To: freebsd-stable@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 1DFF516A40A for ; Thu, 8 Feb 2007 23:38:03 +0000 (UTC) (envelope-from erikt@midgard.homeip.net) Received: from ch-smtp01.sth.basefarm.net (ch-smtp01.sth.basefarm.net [80.76.149.212]) by mx1.freebsd.org (Postfix) with ESMTP id A05CF13C49D for ; Thu, 8 Feb 2007 23:38:02 +0000 (UTC) (envelope-from erikt@midgard.homeip.net) Received: from c83-253-29-241.bredband.comhem.se ([83.253.29.241]:63493 helo=falcon.midgard.homeip.net) by ch-smtp01.sth.basefarm.net with smtp (Exim 4.63) (envelope-from ) id 1HFIq1-0000fd-4w for freebsd-stable@freebsd.org; Fri, 09 Feb 2007 00:38:01 +0100 Received: (qmail 40080 invoked from network); 9 Feb 2007 00:37:58 +0100 Received: from owl.midgard.homeip.net (10.1.5.7) by falcon.midgard.homeip.net with SMTP; 9 Feb 2007 00:37:58 +0100 Received: (qmail 59781 invoked by uid 1001); 9 Feb 2007 00:37:58 +0100 Date: Fri, 9 Feb 2007 00:37:58 +0100 From: Erik Trulsson To: Freddie Cash Message-ID: <20070208233758.GA59681@owl.midgard.homeip.net> Mail-Followup-To: Freddie Cash , freebsd-stable@freebsd.org References: <00ad01c74b65$79db1710$0c00a8c0@Artem> <45CBA15F.4090408@bit0.com> <200702081451.58355.fcash@ocis.net> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <200702081451.58355.fcash@ocis.net> User-Agent: Mutt/1.5.13 (2006-08-11) X-Scan-Result: No virus found in message 1HFIq1-0000fd-4w. X-Scan-Signature: ch-smtp01.sth.basefarm.net 1HFIq1-0000fd-4w 802796f43cace02894cd9ac7170ac915 Cc: freebsd-stable@freebsd.org Subject: Re: What is a good choice of sata-ii raid controller for freebsd? 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: Thu, 08 Feb 2007 23:38:03 -0000 On Thu, Feb 08, 2007 at 02:51:58PM -0800, Freddie Cash wrote: > On Thursday 08 February 2007 02:17 pm, Mike Andrews wrote: > > Jaime Bozza wrote: > > > Everyone has their reasons - I liked the RAID 6 feature, plus the OOB > > > management of Areca, plus my history with 3ware wasn't good. :( > > > > For what it's worth, 3Ware's latest PCI-E cards (9650 series) now > > support RAID 6. The updated twa driver that supports them hasn't yet > > been merged into FreeBSD (see kern/106488 which I filed 2 months ago) > > but you can download either the source or the binary for it from 3Ware > > that works just fine. The updated 3dm2 for it did make it into the > > Ports tree. > > > > Driver annoyances aside, my 9650SE is considerably faster than my 9500S > > Not all that surprising, since the 9500-series use PATA-133 chipsets with > SATA-PATA bridges, and the 9550+ uses a native 3G SATA chipset. Even > though the 9500s are listed as 1.5G SATA parts, you'll never get better > than ATA-133 speeds out of them. Which is quite irrelevant since there are no SATA-disks which actually can use more speed than that. (The fastest SATA-disks currently available -- Western Digital's Raptor series has a maximum transfer rate of just under 90 MB/s. Most disks are significantly slower than that.) The 133 MB/s one can get out of ATA-133 is quite enough for that (and not all that much less than the 150MB/s that normal SATA provides. (Some SATA devices also provide a 300MB/s transfer speed, but since no disks can keep up with that it does not make all that much of a difference in practice.)) Just about all reviews that have compared both controllers and disks with and without SATA-PATA bridges have come to the conclusion that those bridges do not cause any measurable drop in performance over their native-SATA counterparts. The only real drawback with using SATA-PATA bridges is that you cannot get support for the optional SATA features like NCQ. (But not all native-SATA solutions support those features either.) > > We didn't realise that when we ordered our first pair of Escalade 9500S > 4-port cards. Thankfully, just after they arrived and before we put in > the mass-order, the 9550SX was released and we've standardised on them. The 9550SX should be a bit faster than the 9500S and the 9650SE faster still, but that is for other reasons. (Faster processor for handling the parity calculations for RAID-5, faster memory on the card, being able to do more operations in parallell, etc.) -- Erik Trulsson ertr1013@student.uu.se