From owner-freebsd-hackers Wed Jan 1 15:20:26 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.4/8.8.4) id PAA29521 for hackers-outgoing; Wed, 1 Jan 1997 15:20:26 -0800 (PST) Received: from news1.gtn.com (news1.gtn.com [192.109.159.3]) by freefall.freebsd.org (8.8.4/8.8.4) with ESMTP id PAA29502 for ; Wed, 1 Jan 1997 15:20:20 -0800 (PST) Received: (from uucp@localhost) by news1.gtn.com (8.7.2/8.7.2) with UUCP id AAA04314; Thu, 2 Jan 1997 00:16:01 +0100 (MET) Received: (from andreas@localhost) by klemm.gtn.com (8.8.4/8.8.2) id AAA18565; Thu, 2 Jan 1997 00:09:41 +0100 (MET) Message-ID: Date: Thu, 2 Jan 1997 00:09:40 +0100 From: andreas@klemm.gtn.com (Andreas Klemm) To: jfieber@indiana.edu (John Fieber) Cc: hackers@FreeBSD.org Subject: Re: New motherboard breaks tape drive References: X-Mailer: Mutt 0.55-PL15 Mime-Version: 1.0 In-Reply-To: ; from "John Fieber" on Dec 31, 1996 14:02:35 -0500 Sender: owner-hackers@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk John Fieber writes: > I have an Archive Viper 150 tape drive that has served me well > for many years. I have never had difficulty getting the maximum > performance of about 100K/second writing speed from it... > > ...until upgrade my old 486DX33 motherboard to a Pentium 100 > (ASUS). Now the tape drive will no longer stream and typical > writing speed has dropped to about 50K/second. > > My first thought was something with the new SCSI controller (ASUS > SC200) was the problem so I put my old Adaptec 1542C in, but the > result was the same (I even tried putting the drive alone on the > bus). I tried team, but it didn't help. > > I'm fishing for where to look next. Ideas? Did you upgrade only the board or did you additionally a - FreeBSD release change - FreeBSD kernel recompile How is your kernel config file. What's the SC200 ? PCI controller ? AHA 2940 compatible or what ? I get about 300-600 KB/sec throughput using dump and a TDC 4222, which uses data compression. I'm getting these numbers with -current and 2.2-Release (Beta of today). BTW: My numbers depend heavily on filesystem fragmentation. BTW, did you try team from the ports collection ? team(1) - parallel pipe, allows asynchronous io This can be used to speedup data throughput for tar and dump and friends ;-) Andreas /// -- andreas@klemm.gtn.com /\/\___ Wiechers & Partner Datentechnik GmbH Andreas Klemm ___/\/\/ Support Unix -- andreas.klemm@wup.de pgp p-key http://www-swiss.ai.mit.edu/~bal/pks-toplev.html >>> powered by <<< ftp://sunsite.unc.edu/pub/Linux/system/Printing/aps-491.tgz >>> FreeBSD <<<