Date: Tue, 24 Jul 2001 17:10:32 +0100 From: Paul Robinson <paul@akita.co.uk> To: Bob Bishop <rb@gid.co.uk> Cc: freebsd-cluster@FreeBSD.ORG Subject: Re: Is this list dead? Message-ID: <20010724171032.A60915@jake.akitanet.co.uk> In-Reply-To: <4.3.2.7.2.20010724164231.00bdb960@gid.co.uk>; from rb@gid.co.uk on Tue, Jul 24, 2001 at 05:02:03PM %2B0100 References: <4.3.2.7.2.20010724155503.00be2100@gid.co.uk> <20010724154545.D34017@jake.akitanet.co.uk> <4.3.2.7.2.20010724155503.00be2100@gid.co.uk> <20010724163537.A54445@jake.akitanet.co.uk> <4.3.2.7.2.20010724164231.00bdb960@gid.co.uk>
next in thread | previous in thread | raw e-mail | index | archive | help
On Jul 24, Bob Bishop <rb@gid.co.uk> wrote: > http://www.xrefer.com/entry/632785 > > "Hide one's light under a bushel: > Show extreme modesty [etc]" I still think it's strange. Thanks for explaining though. > Easy: it hasn't climbed high enough up anyone's todo list for it to > actually get fixed. Hmmmm. Well, who knows where my evenings will lead me over the next month or so then. It seems like an interesting (and valuable) thing to work on. If you're into that sort of thing. :-) > I suspect (with little supporting evidence) that this is partly due to the > different ways people are using clusters in diverse applications. For > instance, a lot of the academic work is directed at microdecomposition via > message passing, distributed shared memory or what have you. We on the > other hand are currently doing some environmental modelling work > characterised by large numbers of 30hr runs of a fat nasty FORTRAN program > on assorted datasets. Clusters are appropriate in both cases, but different > infrastructures are appropriate. Indeed. I actually want to think about things at a slightly higher level than that. For me a cluster is a redundant bunch of SQL servers that gives high-availability. Bit of load-balancing thrown in there, etc. > One indicator I don't much like is that there doesn't seem to be much > cluster-related software among the thousands of ports in the ports collection. The reason I started this thread was because over on -isp people were talking about vrrpd which is in ports. The idea being that you have a primary server and when it dies, your backup takes over. Then conversation led to load balancing, and then to clustering, and now we're here.... ;-) Like I said over on -isp, I hope to have some time to put into looking at high-level clustering soon with FBSD. I was just wondering if anybody else was playing with it or doing anything with clustering as a whole with FBSD. -- Paul Robinson ,--------------------------------------- Technical Director @ Akita | A computer lets you make more mistakes PO Box 604, Manchester, M60 3PR | than any other invention with the T: +44 (0) 161 228 6388 (F:6389)| possible exceptions of handguns and | Tequila - Mitch Ratcliffe `----- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-cluster" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20010724171032.A60915>