From owner-freebsd-cluster Fri Jan 10 13:29:45 2003 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 0B2B037B401 for ; Fri, 10 Jan 2003 13:29:44 -0800 (PST) Received: from vps.vitalit.com (vps.vitalit.com [64.105.194.69]) by mx1.FreeBSD.org (Postfix) with ESMTP id 5A26B43F18 for ; Fri, 10 Jan 2003 13:29:43 -0800 (PST) (envelope-from car@vitalit.com) Received: from LAPTOP (gso167-138-145.triad.rr.com [24.167.138.145]) by vps.vitalit.com (8.12.3/8.12.3) with SMTP id h0ALTVhQ091199 for ; Fri, 10 Jan 2003 16:29:31 -0500 (EST) (envelope-from car@vitalit.com) Message-ID: <000901c2b8ef$57e4eb70$0201000a@LAPTOP> From: "Rouzer, Charles A (Chuck)" To: Subject: freebsd cluster target market Date: Fri, 10 Jan 2003 16:29:17 -0500 MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 6.00.2720.3000 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2600.0000 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 Is it fair to say that FreeBSD Clustering may gain adoption more quickly if designed for the hosting market as that seems to be its target market? These functions would also benefit other cluster applications. Seamless process migration could be a great benefit for this area. Next in line would probably be a more appropriate network file system. Can anyone offer the status of any ports or work done to provide these clustering abilities? We had one other besides myself join the #freebsd-cluster IRC channel. Maybe if things pick up around here it will grow one day. ;-) I understand some have restricted or costly Internet access. -- Chuck Rouzer Vital Information Technology, Inc. http://www.vitalit.com http://www.vitalserver.com To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-cluster" in the body of the message From owner-freebsd-cluster Fri Jan 10 15:18:13 2003 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 6B41037B401 for ; Fri, 10 Jan 2003 15:18:11 -0800 (PST) Received: from web14207.mail.yahoo.com (web14207.mail.yahoo.com [216.136.173.71]) by mx1.FreeBSD.org (Postfix) with SMTP id 2A82643E4A for ; Fri, 10 Jan 2003 15:18:11 -0800 (PST) (envelope-from temac@yahoo.com) Message-ID: <20030110231811.98794.qmail@web14207.mail.yahoo.com> Received: from [12.22.62.13] by web14207.mail.yahoo.com via HTTP; Fri, 10 Jan 2003 15:18:11 PST Date: Fri, 10 Jan 2003 15:18:11 -0800 (PST) From: Thomas McIntyre Subject: Re: freebsd cluster target market To: car@vitalit.com Cc: freebsd-cluster@FreeBSD.ORG MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii 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 Rouzer, Charles A (Chuck) said: > Is it fair to say that FreeBSD Clustering may gain adoption more quickly if designed for the hosting market as that seems to be its target market? I'm not in that market, so I can't really say, but my interests always come back to roughly the same thing. Something like a cluster of web servers running over a clustered database. Everything should be minimized, requires minimal servers, zero specialized hardware, and runs without X windows. The above specs might supply a general model for the business motivations behind clustering. For everything to be attractive, it needs to meet 2 core requirements: 1) Vips w/ load balancing. 2) Robust shared storage. There's a third requirement that often gets a lot of jawboning: 3) Application state replication, preferably in memory. But I think the first two are the key here. The third has an somewhat higher cost/benifit ratio, is insufficiently general, and often can faked by writing state to shared storage. --- So, in context, here's requirements 1 and 2: Two secured RELEASE machines running apache and mysql. The entry point for both applications are vips. The front end is active/active. The back end can be active/passive. I want to later expand vertically (run only a single application per machine) as well as horizontally (add more load balanced boxes). I don't want any special Cisco or F5 hardware or detached switched storage. I don't want to mount anything (particularly databases) over NFS, and I don't want data living on a single node. Of the above, the shared nothing storage is the trickiest. Something like a synchronous write, with a timeout that blows out one node if it takes too long. Robust and configurable semantics like software raid 1 on a single machine. Otherwise, there's three obvious routes: A) Buy a hardware load balancer with sticky sessions and a fibre switch for detached storage. If we really want to waste $$$, we go for a middleware server that hot replicates its internal state. b) On the cheap use something like two active/passive stovepipe systems with application level replication and scripting to keep data in two places. c) Forget the clustering and use tape backups. Nothing gets the grand prize, but it would be great if this project could. --- Apologies in advance if I'm behind the curve, or have only repackaged prior threads. Regards, Tom McIntyre __________________________________________________ Do you Yahoo!? Yahoo! Mail Plus - Powerful. Affordable. Sign up now. http://mailplus.yahoo.com To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-cluster" in the body of the message From owner-freebsd-cluster Fri Jan 10 15:25:57 2003 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 61BC937B401 for ; Fri, 10 Jan 2003 15:25:56 -0800 (PST) Received: from malasada.lava.net (malasada.lava.net [64.65.64.17]) by mx1.FreeBSD.org (Postfix) with ESMTP id E697043F1E for ; Fri, 10 Jan 2003 15:25:55 -0800 (PST) (envelope-from cliftonr@lava.net) Received: by malasada.lava.net (Postfix, from userid 102) id 3D63E17A320; Fri, 10 Jan 2003 13:25:50 -1000 (HST) Date: Fri, 10 Jan 2003 13:25:50 -1000 From: Clifton Royston To: "Rouzer, Charles A (Chuck)" Cc: freebsd-cluster@FreeBSD.ORG Subject: Re: freebsd cluster target market Message-ID: <20030110132550.A18143@lava.net> Mail-Followup-To: "Rouzer, Charles A (Chuck)" , freebsd-cluster@FreeBSD.ORG References: <000901c2b8ef$57e4eb70$0201000a@LAPTOP> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.2.5.1i In-Reply-To: <000901c2b8ef$57e4eb70$0201000a@LAPTOP>; from car@vitalit.com on Fri, Jan 10, 2003 at 04:29:17PM -0500 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 On Fri, Jan 10, 2003 at 04:29:17PM -0500, Rouzer, Charles A (Chuck) wrote: > Is it fair to say that FreeBSD Clustering may gain adoption more quickly > if designed for the hosting market as that seems to be its target market? > These functions would also benefit other cluster applications. > > Seamless process migration could be a great benefit for this area. > > Next in line would probably be a more appropriate network file system. > > Can anyone offer the status of any ports or work done to provide these > clustering abilities? Really the thing that would appeal to me is a clustered solution that works for very highly reliable and indefinitely scalable mail delivery (SMTP) and user mailbox access (POP/IMAP.) This is one of the hardest, klunkiest, most expensive problems to solve right now. Note that this requires that N servers can engage in concurrent read/write access to the same file system while it remains coherent across all of them. The best available solution at present seems to be a load-balancer in front of a cluster of servers running appropriately chosen MTA and POP/IMAP daemons, accessing user mail-stores in maildir format on high-end NFS servers (NFS appliance type, e.g. NetApp) which are configured in pairs for fail-over. The kind of stuff talked about in Ward Christensen or Brad Knowles' papers. This is pretty expensive to build due to the NFS component. At a SWAG, it's $100K-200K and up from there for just a few servers' worth of cluster. Hosting of dynamic web content is very similar in problem space. Hosting of static content is easy by comparison, because you can simply replicate the data. -- Clifton -- Clifton Royston -- LavaNet Systems Architect -- cliftonr@lava.net "If you ride fast enough, the Specialist can't catch you." "What's the Specialist?" Samantha says. "The Specialist wears a hat," says the babysitter. "The hat makes noises." She doesn't say anything else. Kelly Link, _The Specialist's Hat_ To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-cluster" in the body of the message