From owner-freebsd-stable Mon Feb 11 14: 8:17 2002 Delivered-To: freebsd-stable@freebsd.org Received: from smtp1.sentex.ca (smtp1.sentex.ca [199.212.134.4]) by hub.freebsd.org (Postfix) with ESMTP id 9619337B402 for ; Mon, 11 Feb 2002 14:08:13 -0800 (PST) Received: from simoeon.sentex.net (pyroxene.sentex.ca [199.212.134.18]) by smtp1.sentex.ca (8.11.6/8.11.6) with ESMTP id g1BM88d68438; Mon, 11 Feb 2002 17:08:08 -0500 (EST) (envelope-from mike@sentex.net) Message-Id: <5.1.0.14.0.20020211160732.04c12890@marble.sentex.ca> X-Sender: mdtpop@marble.sentex.ca X-Mailer: QUALCOMM Windows Eudora Version 5.1 Date: Mon, 11 Feb 2002 17:01:44 -0500 To: sos@freebsd.dk From: Mike Tancsa Subject: Re: RocketRaid133 Cc: stable@FreeBSD.ORG In-Reply-To: <200202111756.g1BHuKS59263@freebsd.dk> References: <5.1.0.14.0.20020211120456.024ca010@marble.sentex.ca> Mime-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1"; format=flowed Content-Transfer-Encoding: quoted-printable Sender: owner-freebsd-stable@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.ORG At 06:56 PM 2/11/02 +0100, S=F8ren Schmidt wrote: >It seems Mike Tancsa wrote: > > Hi, > > it seems HighPoint has created their own drivers for the 372 based IDE= =20 > raid > > cards. These *seem* to have a bit more guts and features in them than= the > > previous cards. Has anyone worked with them ? The previous drives with= the > > ar driver are OK but had limited functionality-- especially when= compared > > with the 3ware card which sadly they do not make any more (the 6200 I > > mean). Does anyone have these newer Highpoint cards in production ? Are > > they any good? > >We already support the hpt372, and I've just added support for the >hpt374 to -current. STABLE doesnt yet see it as an AR capable device. But the KLD provided by= =20 them at http://www.highpoint-tech.com/FreeBSD_v13_370_372.zip works exactly as advertised. I just installed it with the 4.5R ISO and all= =20 worked well using RAID1 and RAID0. The Raid 1 performance was OK, but not=20 as great an improvement as the 3ware shows. I seem to recall a noticeable=20 difference between a single drive on UDMA 66, versus that same drive in a=20 RAID1 config (as well as of course RAID0) Simple bonnie numbers -------Sequential Output-------- ---Sequential Input--=20 --Random-- -Per Char- --Block--- -Rewrite-- -Per Char- --Block---=20 --Seeks--- Machine MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU /sec= %CPU ad0 500 27996 68.3 27833 29.5 13531 15.6 25261 92.7 31253 14.7 195.0 = 1.0 da0 R1 500 29811 73.2 28939 32.8 13157 16.9 25611 95.0 29396 22.5 209.4 = 1.4 da0 R0 500 45427 94.0 47434 49.7 17556 23.0 21718 80.3 44401 33.8 198.6 = 1.5 R0=3DRaid 0 R1=3DRaid 1 ad0 is a UDMA 100 Fujitsu 7200 RPM drive of which I put in 2 in the=20 controller. I am a little surprised that the Random seeks would not be=20 that much better. dmesg shows it as da0 at hpt37x20 bus 0 target 0 lun 0 da0: Fixed Direct Access SCSI-2 device da0: 58821MB (120466945 512 byte sectors: 255H 63S/T 7498C) Mounting root from ufs:/dev/da0s1a Note, I had to upgrade the BIOS for it to work with my oldish 810 chipset=20 board. But once I did that everything worked as it should. I will try out=20 the GUI management stuff later tonight and try and see how it works with a= =20 failed drive tomorrow before I ship the card out. ---Mike To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-stable" in the body of the message