From owner-freebsd-scsi Mon Mar 12 15: 7:49 2001 Delivered-To: freebsd-scsi@freebsd.org Received: from fw.wintelcom.net (ns1.wintelcom.net [209.1.153.20]) by hub.freebsd.org (Postfix) with ESMTP id 7445237B719; Mon, 12 Mar 2001 15:07:46 -0800 (PST) (envelope-from bright@fw.wintelcom.net) Received: (from bright@localhost) by fw.wintelcom.net (8.10.0/8.10.0) id f2CN6Ne24881; Mon, 12 Mar 2001 15:06:23 -0800 (PST) Date: Mon, 12 Mar 2001 15:06:23 -0800 From: Alfred Perlstein To: Bruce Evans Cc: Soren Schmidt , Kevin Oberman , scsi@FreeBSD.ORG, gibbs@FreeBSD.ORG Subject: Re: Disk I/O problem in 4.3-BETA Message-ID: <20010312150623.D18351@fw.wintelcom.net> References: <20010312132922.Y18351@fw.wintelcom.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.2.5i In-Reply-To: ; from bde@zeta.org.au on Tue, Mar 13, 2001 at 09:17:47AM +1100 X-all-your-base: are belong to us. Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org * Bruce Evans [010312 14:18] wrote: > On Mon, 12 Mar 2001, Alfred Perlstein wrote: > > > > > Mr ATA, is there no ATA command to "syncronize cache" like in SCSI? > > > > > > Yes, there is, and the ATA driver even uses it, the problem is WHEN > > > to use it. I originally made it flush the cache if a write contained > > > the BIO_ORDERED bit, but that doesn't work with softupdates.. > > > If somebody can come up with a way to tell me when I need to flush > > > the write cache, then I'll happily add that.. > > > > Justin, I've heard that SCSI knows when to send sync-cache commands > > to the disks, how does the driver know when to do this based on > > the bio request? > > > > It'd be nice to get this fixed for 4.3 because I've noticed terrible > > perf for laptops because of the complete lack of write caching... :( > > I just put "options ATA_ENABLE_WC" in all my config files. Changing > the default for write caching from enabled to disabled in rev.1.92 of > ata_disk.c was a huge pessimisation, but it is probably currently > required for soft updates. I don't use soft updates ... Afaik it's also required by normal non-async mounts. Basically if you let the disk lie about write completetion you might as well be running fully async. -- -Alfred Perlstein - [bright@wintelcom.net|alfred@freebsd.org] Daemon News Magazine in your snail-mail! http://magazine.daemonnews.org/ To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message