From owner-freebsd-current Tue Feb 17 03:02:19 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id DAA27152 for freebsd-current-outgoing; Tue, 17 Feb 1998 03:02:19 -0800 (PST) (envelope-from owner-freebsd-current@FreeBSD.ORG) Received: from silvia.HIP.Berkeley.EDU (ala-ca34-51.ix.netcom.com [207.93.143.179]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id DAA27146 for ; Tue, 17 Feb 1998 03:02:17 -0800 (PST) (envelope-from asami@vader.cs.berkeley.edu) Received: (from asami@localhost) by silvia.HIP.Berkeley.EDU (8.8.8/8.6.9) id DAA06837; Tue, 17 Feb 1998 03:02:07 -0800 (PST) Date: Tue, 17 Feb 1998 03:02:07 -0800 (PST) Message-Id: <199802171102.DAA06837@silvia.HIP.Berkeley.EDU> To: brian@worldcontrol.com CC: freebsd-current@FreeBSD.ORG In-reply-to: <19980217025443.51503@top.worldcontrol.com> (brian@worldcontrol.com) Subject: Re: softupdates4 ruins performance of my wide drive 8-) From: asami@FreeBSD.ORG (Satoshi Asami) Sender: owner-freebsd-current@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG * SEAGATE ST43400N 5400rpm SCSI2-FAST avg(r/w)seek 10/11ms * (8 bit interface drive, tag enabled) * SEAGATE ST15150W 7200rpm SCSI2-FAST-WIDE avg(r/w)seek 8/9ms * (16 bit interface drive, tag enabled) * So all the extra expense of the wide controller and wide drive bought * me 6 minutes or a 4.5% improvement. With only one drive, it shouldn't make any difference whether the drive is narrow or wide or ultra or ultra-wide. There is no contention for the bus, and the actual data transfer time over the SCSI bus is so small compared to the rest of the work that has to be done. What you are seeing here in improment is actually caused by the seek time and rotational latency difference. When you have at least 3 or 4 drives, then the bus type will start making the difference. Satoshi To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-current" in the body of the message