From owner-freebsd-mobile Tue Mar 13 4: 1:59 2001 Delivered-To: freebsd-mobile@freebsd.org Received: from hugo10.ka.punkt.de (kagate.punkt.de [194.77.232.254]) by hub.freebsd.org (Postfix) with ESMTP id 3537337B737; Tue, 13 Mar 2001 04:01:53 -0800 (PST) (envelope-from hausen@punkt.de) Received: (from ry93@localhost) by hugo10.ka.punkt.de (8.9.3/8.9.3) id NAA88345; Tue, 13 Mar 2001 13:01:45 +0100 (CET) (envelope-from ry93) From: "Patrick M. Hausen" Message-Id: <200103131201.NAA88345@hugo10.ka.punkt.de> Subject: Re: Disk I/O problem in 4.3-BETA In-Reply-To: from Pete French at "Mar 13, 2001 11:51:11 am" To: pfrench@firstcallgroup.co.uk (Pete French) Date: Tue, 13 Mar 2001 13:01:45 +0100 (CET) Cc: bright@wintelcom.net, Helge.Oldach@de.origin-it.com, mobile@FreeBSD.ORG, oberman@es.net, sos@freebsd.dk, stable@FreeBSD.ORG X-Mailer: ELM [version 2.4ME+ PL54 (25)] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-mobile@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Hi all! Pete wrote: > All very interesting, but a small point has been forgotten > hasnt it ? The way I read this thread is that until recentlly > write-caching was enabled by default and has now been disabled (hence > the original obseravtion of disc performance dropping). > > I havent noticed that FreeBSD has a bad reputation for loss of data > in the event of am power outage, and my own experience backs this up. > As so many people appear to have been running it this way by default until > now you might have though that if it were a serious problem in reality then > people would have noticed by now ? Well, there are a great number of people running Linux with async mounts, who haven't experienced loss of data either. And they will happily tell you that living fast and loose was the way it's meant to be and, BTW, it gives much better performance ... The point in Kirk's work on softupdates was to provide a way to live "almost asynchronously" while _guaranteeing_ filesystem meta data consistency. This guarantee is lost with WC enabled, so you might as well mount async and join the "fast and loose" crowd. Only recently was softupdates included in the GENERIC kernel, so my impression is that because softupdates is now kind of default, the problem with WC popped up and was solved in the "do the right thing [tm]" manner. You are free to reenable WC any time you like. HTH, Patrick -- --- WEB ISS GmbH - Scheffelstr. 17a - 76135 Karlsruhe - 0721/9109-0 --- ------ Patrick M. Hausen - Technical Director - hausen@punkt.de ------- "Two men say, they're Jesus - one of 'em must be wrong." (Dire Straits) > > -pete. > > To Unsubscribe: send mail to majordomo@FreeBSD.org > with "unsubscribe freebsd-stable" in the body of the message > To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-mobile" in the body of the message