From owner-freebsd-stable Mon Apr 20 08:04:41 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id IAA09286 for freebsd-stable-outgoing; Mon, 20 Apr 1998 08:04:41 -0700 (PDT) (envelope-from owner-freebsd-stable@FreeBSD.ORG) Received: from lepton.nuc.net (root@lepton.nuc.net [204.49.61.5]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id PAA09216 for ; Mon, 20 Apr 1998 15:04:21 GMT (envelope-from wheelman@nuc.net) Received: from electron (dhcp1.nuc.net [204.49.61.15]) by lepton.nuc.net (8.8.8/8.7.3) with SMTP id KAA06918; Mon, 20 Apr 1998 10:03:55 -0500 (CDT) From: "Jaime Bozza" To: "Mike Smith" , "Berend de Boer" Cc: Subject: RE: best sd0 flags ? (was wdc0) Date: Mon, 20 Apr 1998 10:01:32 -0500 Message-ID: <000801bd6c6d$34866560$0f3d31cc@electron.nuc.net> MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Priority: 3 (Normal) X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook 8.5, Build 4.71.2173.0 In-Reply-To: <199804200531.WAA04185@antipodes.cdrom.com> X-MimeOLE: Produced By Microsoft MimeOLE V4.72.3110.0 Importance: Normal Sender: owner-freebsd-stable@FreeBSD.ORG Precedence: bulk > As Bruce mentioned, you should use the raw device: > > azaria# dd if=/dev/sd1 of=/dev/null bs=1m count=20 > 20+0 records in > 20+0 records out > 20971520 bytes transferred in 9.182458 secs (2283868 bytes/sec) > azaria# dd if=/dev/rsd1 of=/dev/null bs=1m count=20 > 20+0 records in > 20+0 records out > 20971520 bytes transferred in 2.571084 secs (8156684 bytes/sec) > > for a similar configuration (DCAS34330UW, PII/337, AHA2940UW) I decided to try the same thing. Always been curious about the performance. %dd if=/dev/sd0 of=/dev/null bs=1m count=20 20+0 records in 20+0 records out 20971520 bytes transferred in 4.835489 secs (4337001 bytes/sec) %dd if=/dev/rsd0 of=/dev/null bs=1m count=20 20+0 records in 20+0 records out 20971520 bytes transferred in 2.201617 secs (9525508 bytes/sec) I did it a few times, and have seen slightly higher and slightly lower. 9M seems to be about an average for me. That particular system is a SEAGATE ST34555W 0930 (Seagate Hawk), Pentium 133, Adaptec 2940W (Not a(n) UW, though the drive is an UltraWide) Another system with a 2940UW/P5-133/SEAGATE ST15150W 0011 (One of the original Seagate Barracudas!) meson# dd if=/dev/sd0 of=/dev/null bs=1m count=20 20+0 records in 20+0 records out 20971520 bytes transferred in 8.065788 secs (2600058 bytes/sec) meson# dd if=/dev/rsd0 of=/dev/null bs=1m count=20 20+0 records in 20+0 records out 20971520 bytes transferred in 3.049587 secs (6876839 bytes/sec) Jaime Bozza Nucleus Communications, Inc. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-stable" in the body of the message