From owner-cvs-all Tue Jun 27 17:51:47 2000 Delivered-To: cvs-all@freebsd.org Received: from florence.pavilion.net (florence.pavilion.net [212.74.0.25]) by hub.freebsd.org (Postfix) with ESMTP id 8FD4037B652; Tue, 27 Jun 2000 17:51:36 -0700 (PDT) (envelope-from joe@pavilion.net) Received: from genius.systems.pavilion.net (genesis.tao.org.uk [194.242.131.254]) by florence.pavilion.net (8.9.3/8.8.8) with ESMTP id BAA42638; Wed, 28 Jun 2000 01:51:31 +0100 (BST) (envelope-from joe@pavilion.net) Received: by genius.systems.pavilion.net (Postfix, from userid 100) id 1BC1A12547; Wed, 28 Jun 2000 01:52:47 +0100 (BST) Date: Wed, 28 Jun 2000 01:52:47 +0100 From: Josef Karthauser To: Matthew Jacob Cc: Akinori -Aki- MUSHA , andrews@technologist.com, mckusick@FreeBSD.org, cvs-committers@FreeBSD.org, cvs-all@FreeBSD.org Subject: Re: cvs commit: src/sys/contrib/softupdates softdep.h ffs_softdep.c Message-ID: <20000628015247.H19558@pavilion.net> References: <20000628012956.B19558@pavilion.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.2i In-Reply-To: ; from mjacob@feral.com on Tue, Jun 27, 2000 at 05:38:11PM -0700 X-NCC-RegID: uk.pavilion Organisation: Pavilion Internet plc, Lees House, 21-23 Dyke Road, Brighton, England Phone: +44-845-333-5000 Fax: +44-845-333-5001 Mobile: +44-403-596893 Sender: owner-cvs-all@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG On Tue, Jun 27, 2000 at 05:38:11PM -0700, Matthew Jacob wrote: > > There were in fact, more issues at one point with readahead in UFS than in > Softupdates code under SMP (I had it sysctl'd off for 3.3). As far as I know, > this problem went at last 6 months ago- I think this was a Matt Dillon effort. Was it fixed in RELENG_3? > Your comments are a bit unfair. *You* haven't been running the currently > released product with Softupdates. You have excellent reasons to be concerned > because of your previous experience, but your statement of "A number of times > this year I've lost whole filesystems on an SMP..." is misleading at best. :) Understood. I've not trying to be scaremongering. What I was trying to do was elicit a response like your first paragraph, i.e. "yes, there were some SMP related problems, should be fixed now :)" On one hand I'm being a bit meladramitic, on the other other hand the ccd/SU event cost two people (one of them myself) 7 hours of beauty sleep and my customers over 4 hours of downtime, and the second, / appearing in lost+found, cost 3 hours - hence I'm reacting a bit more emotionally about it than I should. > Your reference to a friend should be made clearer. I'll track him down and see what's what. He was building a 4.0 machine a few weeks ago (may have been 5 weeks...) > I'm not trying to defend SOFTUPDATES/SMP or anything (which work fine for me, > btw, on most of my filesystems) but I believe that your statements could be a > bit more clearer to try and assist all of us to see whether there is a problem > and how to fix it. Anything I can do to help would be great. As it turns out I've got a spare SMP machine sitting on the bench, but it's only got a couple of drives (different sizes) so I can't test ccd or vinum with SU/SMP. I guess that Matt Dillon's probably got a pretty extensive set of system thrash scripts. Joe To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe cvs-all" in the body of the message