From owner-cvs-all Mon Jan 29 1:51:59 2001 Delivered-To: cvs-all@freebsd.org Received: from feral.com (feral.com [192.67.166.1]) by hub.freebsd.org (Postfix) with ESMTP id 1E1D237B6A0; Mon, 29 Jan 2001 01:51:32 -0800 (PST) Received: from beppo (beppo [192.67.166.79]) by feral.com (8.9.3/8.9.3) with ESMTP id BAA04731; Mon, 29 Jan 2001 01:51:03 -0800 Date: Mon, 29 Jan 2001 01:51:04 -0800 (PST) From: Matthew Jacob Reply-To: mjacob@feral.com To: Poul-Henning Kamp Cc: Matt Dillon , John Baldwin , cvs-all@FreeBSD.org, cvs-committers@FreeBSD.org, Mikhail Teterin Subject: Re: workaround for broken mfs using vn. (was Re: cvs commit: src/sys/i386/conf GENERIC ) In-Reply-To: <19702.980761282@critter> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-cvs-all@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG On Mon, 29 Jan 2001, Poul-Henning Kamp wrote: > In message , Matthew Jacob writes: > > >> >Yeah, err, but mdconfig panics for me.... > >> > >> details ? > > > >What's a matter- didn't read mail I sent already? How annoying.... > > You previous email didn't show "mdconfig panics" it showed the kernel > panic'ing. > > Sometimes precision is a good thing :-) Hmm!! Well, you've stunned me with clever rhetoric. It quacks && stinks like a duck, Poul. It's a dead duck. This panic certainly occurs under no other filesystem I can find. But I'll leave it to you to decide things are peachy. I say they isn't. I sure as hell am not going to enable using mdconfig(8) as a replacement for MFS. It's only because I really want to see DEVFS move forward that I'm seething with amusement instead of pissing rage over our usual moe, larry && curly antics... :-)... > > Considering the state of -current, I'm not sure I see your trace > as an obvious indication of anything, but if I can reproduce it > tonight I'll try to see what I can find. > > What's "lmdd" ? Larry McVoy's dd- out of lmbench. I find it handier to use than dd because I don't have to give it a source of /dev/zero- and it has all sorts of bells and whistles- hell, it's even good at doing memory bandwidth testing: 2x200MHz older PPro: remler.nas.nasa.gov > lmdd 255370.19 MB in 3.62 seconds (70578.0187 MB/sec) 170Mhz Ultra1 Solaris: sun520 > lmdd ^C157099.02 MB in 2.79 seconds (56356.6797 MB/sec) 333 MHz Alpha 600 (NetBSD) poseur.nas.nasa.gov > lmdd ^C296471.36 MB in 2.98 seconds (99601.9453 MB/sec) and so on... At any rate- nothing special about it. I was just using it to see how quick a fill of this new MFS replacment would take. As in: poseur.nas.nasa.gov > df /tmp Filesystem 1024-blocks Used Avail Capacity Mounted on mfs:122 169351 1 160882 0% /tmp poseur.nas.nasa.gov > lmdd of=/tmp/foo 157.03 MB in 18.94 seconds (8.2895 MB/sec) Jan 29 01:48:27 poseur /netbsd: uid 7865 on /tmp: file system full (which is about the speed of the actual backing store, yawn...) -matt To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe cvs-all" in the body of the message