From owner-freebsd-sparc64@FreeBSD.ORG Fri Oct 31 13:02:30 2008 Return-Path: Delivered-To: freebsd-sparc64@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 2FC60106567A for ; Fri, 31 Oct 2008 13:02:30 +0000 (UTC) (envelope-from mdh_lists@yahoo.com) Received: from web56802.mail.re3.yahoo.com (web56802.mail.re3.yahoo.com [66.196.97.76]) by mx1.freebsd.org (Postfix) with SMTP id C7D248FC14 for ; Fri, 31 Oct 2008 13:02:29 +0000 (UTC) (envelope-from mdh_lists@yahoo.com) Received: (qmail 13067 invoked by uid 60001); 31 Oct 2008 13:02:29 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=X-YMail-OSG:Received:X-Mailer:Date:From:Reply-To:Subject:To:Cc:In-Reply-To:MIME-Version:Content-Type:Message-ID; b=ZgIb3MC01zag90W3dVT5rET/JJ6VLEy4klvD1+XqWmHkx0BVFfJ1g+nRcT/l7mDg3Q/4xwD+vH5/mAqh+vagjTWmtEtPQSVX5hjhu0XSWbrrS5p3A0Bj361HcR94o1034BIWCiLOXNjglQZtUgX9rtdWGchW2Ag4obuQAP3tMq8=; X-YMail-OSG: j7r9n1QVM1nQNBnBxd0.yjIy7o7MGU7MnGmLNYnz5CDWpyg8t6TFuKGTaiVQJZEdLo0vLS9DVjFy3S2Y_NDe2Uu3mbprKrTFjhEprFlfaX8wDWEWVgvpja8q5lQek4_SYSO93GBkViuSubdlYi0Nb5c.CWjo55tEfiXNHLEsOkl1q5GMdHTlMeS3eQpB4A-- Received: from [71.61.220.126] by web56802.mail.re3.yahoo.com via HTTP; Fri, 31 Oct 2008 06:02:28 PDT X-Mailer: YahooMailWebService/0.7.260.1 Date: Fri, 31 Oct 2008 06:02:28 -0700 (PDT) From: mdh To: Mark Linimon In-Reply-To: <20081031124442.GB9102@soaustin.net> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Message-ID: <183638.12752.qm@web56802.mail.re3.yahoo.com> Cc: freebsd-sparc64@freebsd.org Subject: Re: Free Ultra2 in Silicon Valley, USA X-BeenThere: freebsd-sparc64@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: mdh_lists@yahoo.com List-Id: Porting FreeBSD to the Sparc List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 31 Oct 2008 13:02:30 -0000 --- On Fri, 10/31/08, Mark Linimon wrote: > From: Mark Linimon > Subject: Re: Free Ultra2 in Silicon Valley, USA > To: "mdh" > Cc: freebsd-sparc64@freebsd.org, "Steve Rikli" > Date: Friday, October 31, 2008, 8:44 AM > On Fri, Oct 31, 2008 at 05:06:50AM -0700, mdh wrote: > > Perhaps this could augment the package build setup? > > We have a couple of Ultra 5s in the cluster but we > haven't set them up > yet; the belief is that the Ultras are too underpowered to > be of too > much help. (Mostly we have Netra T1s there, with some > e4500s on loan > remotely). A dual CPU Ultra2 is going to be a lot more powerful than an Ultra5. Ultra5's used the U-IIi CPUs which had less, slower cache than did the U-II CPUs which the Ultra2 systems used. A dual CPU Ultra2 will also outperform a T1-105. The T1's came out later, but in terms of CPU performance, the Ultra2 still stacks up, and with 2x400, it'll beat a T1-105 with a single 440 hands down for compiling stuff. E4500's can be relatively beefy. They're the lowest end of the real "high tier" boxes from Sun (some people would argue that the 3500 is, but I've generally avoided 3500's because of the downright whacky under-performing FC setup they use and how fscking hard they are to mount anywhere other than on the floor.) > > If anyone wants to debug the kernel problem on the 4 unused > T1 200s that > would be more helpful :-) (the 105s work correctly; there > is some kind > of race condition on the 200s that mean you can boot them > up if you > breakpoint through the boot process.) OK, this is probably way over my head, but I'll bite - what exactly happens if you don't breakpoint through it? > > However, that machine might be useful for someone as a > ports tinderbox. > (I had considered setting up one of the existing ones to do > that, but there > are other machines I have been working on which are higher > priority.) > > mcl I guess my point is that a dual CPU Ultra2 can be a pretty nice box, certainly one of the best of the era from which it came, and probably one of the better Ultra-II CPU based systems you'll find. I've got one at home which runs my home file server, hooked up to a D1000 array. - mdh