From owner-freebsd-cluster Tue Jul 9 2: 8:53 2002 Delivered-To: freebsd-cluster@freebsd.org Received: from mx1.FreeBSD.org (mx1.FreeBSD.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id B0F9537B400 for ; Tue, 9 Jul 2002 02:08:50 -0700 (PDT) Received: from yello.shallow.net (yello.shallow.net [203.18.243.120]) by mx1.FreeBSD.org (Postfix) with ESMTP id 1911843E3B for ; Tue, 9 Jul 2002 02:08:50 -0700 (PDT) (envelope-from joshua@shallow.net) Received: by yello.shallow.net (Postfix, from userid 1001) id CE3412A6B; Tue, 9 Jul 2002 19:08:42 +1000 (EST) Date: Tue, 9 Jul 2002 19:08:42 +1000 From: Joshua Goodall To: Derek Barrett Cc: freebsd-cluster@FreeBSD.ORG Subject: Re: SPREAD clusters Message-ID: <20020709090842.GB34919@roughtrade.net> References: <20020709083759.11726.qmail@graffiti.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20020709083759.11726.qmail@graffiti.net> User-Agent: Mutt/1.5.1i Sender: owner-freebsd-cluster@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.ORG I already maintain a FreeBSD Spread port plus associated libraries: ports/net/spread (including perl & java lib) ports/net/py-spreadmodule (python lib) ports/net/p5-Spread-Session (OO perl lib) There's also a protocol decode and Spread-daemon-hacking on my personal site for it at http://www.roughtrade.net/spread/ You can use this stuff now to build Spread-based application clusters now, if you like. Spread gives you reliable, ordered messaging and process-group membership information, from which can be derived lock management, shared-state, flailover etc. It is, however, totally incompatible with Andy Sporner's existing work. It suffers from a basic problem; if you want to cluster at kernel level, doing it with a userland communications daemon is going to fail (because having the kernel block on userland is Bad :)) I have an architectural direction that will result in a FreeBSD clustering technique rather different from Andy's, based on the technologies that Spread also uses, but no interest in collaborating on it yet. Joshua On Tue, Jul 09, 2002 at 04:37:59PM +0800, Derek Barrett wrote: > Hi everybody, > > I picked this up from another mailing list. > > There is a toolkit over at Johns Hopkins University called > SPREAD, which has been implemented to clustered applications such as > Apache-SSL and Postgres-R. > > "Spread is designed to encapsulate the challenging aspects of asynchronous networks and enable the construction of scalable distributed applications, allowing application builders to focus on the differentiating components of their application. " > > Maybe this code would work in conjunction with Andy's code, as > part of the "Phase 2" project. > > Derek > > > -- > _______________________________________________ > Get your free email from http://www.graffiti.net > > Powered by Outblaze > > To Unsubscribe: send mail to majordomo@FreeBSD.org > with "unsubscribe freebsd-cluster" in the body of the message -- "Running makeworld fast is important to me. Anything longer than 5-10 minutes is too long, since it is not reasonable to check every commit using makeworld if it takes longer." - Bruce Evans, ultimate guardian of build stability. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-cluster" in the body of the message