From owner-freebsd-hardware Tue Feb 18 16:45:40 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id QAA15044 for hardware-outgoing; Tue, 18 Feb 1997 16:45:40 -0800 (PST) Received: (from jmb@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id QAA15022; Tue, 18 Feb 1997 16:45:14 -0800 (PST) From: "Jonathan M. Bresler" Message-Id: <199702190045.QAA15022@freefall.freebsd.org> Subject: Re: Motherboard doesn't like tape drive To: jfieber@indiana.edu (John Fieber) Date: Tue, 18 Feb 1997 16:45:13 -0800 (PST) Cc: msmith@atrad.adelaide.edu.au, hardware@freebsd.org In-Reply-To: from "John Fieber" at Feb 18, 97 06:21:12 pm X-Mailer: ELM [version 2.4 PL24] Content-Type: text Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk John Fieber wrote: > > On Wed, 19 Feb 1997, Michael Smith wrote: > > > > The one tunable parameter on the archive viper is the buffer > > > disconnect size. It is currently at 16K (factory default), but > > > can be adjusted between 2K and 32K. Could that be a factor here? > > > > Indeed. Is that the high-water or low-water mark for disconnect? > > >From the manual: > > "The buffer disconnect size sets the maximum number of bytes that > can be sent over the SCSI bus during a single data transfer > phase. During lengthy data transfers, this feature periodically > frees the bus for other operations; thus, the disocnnect size can > affect overall system performance where more than two SCSI > devices must arbitrate for bus time. Optimum disconnect size is > a function of both the number of devices and the speed at which > they independently process data burts." the problem may be that the tape is straved for data, so it stops writing and has to seek before starting to write again. could hte disks be holding the bus for too long? can you change the "buffer disconnect size" on the disks? jmb