From owner-freebsd-current Mon Mar 25 20:53:08 1996 Return-Path: owner-current Received: (from root@localhost) by freefall.freebsd.org (8.7.3/8.7.3) id UAA10056 for current-outgoing; Mon, 25 Mar 1996 20:53:08 -0800 (PST) Received: from wiley.csusb.edu (wiley.csusb.edu [139.182.2.2]) by freefall.freebsd.org (8.7.3/8.7.3) with SMTP id UAA10051 Mon, 25 Mar 1996 20:53:05 -0800 (PST) Received: (from rmallory@localhost) by wiley.csusb.edu (8.6.11/8.6.11) id UAA06712; Mon, 25 Mar 1996 20:57:17 -0800 From: Rob Mallory Message-Id: <199603260457.UAA06712@wiley.csusb.edu> Subject: nocacheflush=true (was Re: Adaptec 1542B and 1522 on current kernels) To: current@freefall.FreeBSD.org Date: Mon, 25 Mar 1996 20:57:17 -0800 (PST) Cc: gibbs@freefall.FreeBSD.org, dyson@freefall.FreeBSD.org In-Reply-To: <199603251315.IAA25614@dyson.iquest.net> from "John S. Dyson" at Mar 25, 96 08:15:59 am X-Mailer: ELM [version 2.4 PL22] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-current@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk > > > Certainly not to dispute problems that some people have been having, but > using the bt driver with the BT545S, I had *extremely* stable SCSI subsystem > operation. My machine was a 486/66 non-write back (early CPU.) I wonder > if some MBs don't support cache invalidation properly? ^^^^^ ^^^^^^^^^^^^^^^^^^ This is why Solaris X86 ships with "set nocacheflush=false" as default. in /etc/system you set it to 'true' to get better performance. It is doccumented in the admin/hardware answerbook for slowaris-X86. I dont know what they are doing, but on a 486/66 with a working cache, I did notice a difference when doing the above. -- Rob Mallory [rmalory@csusb.edu]