DragonFly BSD
DragonFly users List (threaded) for 2006-07
[Date Prev][Date Next]  [Thread Prev][Thread Next]  [Date Index][Thread Index]

Re: What would you like in DF 1.8?

From: Oliver Fromme <check+j2lq6000rsupybt3@xxxxxxxxxx>
Date: 18 Jul 2006 14:22:47 GMT

Michel wrote:
 > Steve O'Hara-Smith wrote:
 > > Well since all of that can be obtained elsewhere I would be very
 > > happy to see it stacked behind the clustering behaviour that Matt has
 > > already outlined as the primary goal because that *cannot* be obtained
 > > elsewhere.
 > I must be dreaming, what are running all those high performance clusters
 > which appear in the Top500, and are supposed to be based on Linux?
 > Perhaps something like
 > http://openssi.org/cgi-bin/view?page=features.html
 > I could not swear it, but from memory it is more than 5 years and perhaps
 > much more than functional solutions exist for Linux, with all kernel hooks
 > and much more than  have been proposed here. Not to mention older
 > distributed computing projects like amoeba by Tanenbaum. And by the way,
 > who has the money to run such clusters, besides big corporations and 
 > big academic labs? How much does cost Myrinet and other Infiniband hardware
 > necessary to ensure low enough latency so that distributed computing has
 > a small chance of being a realistic proposition? The present and foreseable
 > future of affordable computing is multiprocessor machines, with perhaps up
 > to 32 virtual processors (Sun machines). Being scalable on such hardware is
 > a realistic goal, Solaris does it, Linux does it, both using traditional
 > solutions. Maybe Dragonfly can do it with innovative solutions.

I'm not sure I understand correctly.  Are you saying that
SMP should be high priority, instead of clustering and SSI?
In that case I think it doesn't make sense.

SMP and clustering complement each other, and also have
much in common.  Therefore it doesn't make sense to neglect
one because of the other.  Each of them has advantages
as well as disadvantages, and they will co-exist for the
foreseable future.

I think that many of the concepts (and much of the code)
required for efficient SMP will be valuable for clustering
as well, and vice versa.

Besides, you don't need a Top500 multi-billion dollar setup
in order to benefit from clustering.  Even if you only have
two PCs, you will benefit from it.

Personally, if I had to pick hardware for a small reliable
server (e.g. small company), I would certainly prefer an
SSI cluster of two UP machines over a single SMP machine.
The _only_ problem with that is that there's currently no
open-source UNIX system (preferably BSD) that supports such
an SSI cluster.  That's what Matt Dillon intents to change.

Best regards

Oliver Fromme,  secnetix GmbH & Co. KG, Marktplatz 29, 85567 Grafing
Dienstleistungen mit Schwerpunkt FreeBSD: http://www.secnetix.de/bsd

Any opinions expressed in this message may be personal to the author
and may not necessarily reflect the opinions of secnetix in any way.

[Date Prev][Date Next]  [Thread Prev][Thread Next]  [Date Index][Thread Index]