[erlang-questions] very large distributed implementation?

Michael Truog mjtruog@REDACTED
Tue Aug 17 03:05:43 CEST 2010


Scalaris probably has been tested with many nodes but you would probably
need to check their IEEE paper, or the presentations
(http://www.onscale.de/scalarix.html).

Cloudi exists but is not meant for 100s of computing nodes
(http://cloudi.org).  The reason is that private clouds with new
hardware would have many cores, so the need for many nodes is reduced.

Any Erlang code that works on 100s or 1000s of nodes is unlikely to use
the distributed Erlang mode because of the heartbeat message that is
used every minute (i.e., so local network backbones that are not
expected to go down).  That means that such Erlang code is likely to
utilize tcp, udp, etc. with custom code that manages consistency.

On 08/16/2010 02:15 PM, Miles Fidelman wrote:
> Our of somewhat less than academic curiousity, are there any good
> examples of very large distributed systems written in Erlang -
> specifically systems consisting of 100s to 1000s of computing nodes?
>
> I'm looking at several applications along the lines of SETI@REDACTED and
> distributed.net, that take the background cycles, from very large
> numbers of machines, and turn them into a gridded processing environent.
>
> It strikes me that Erlang should make a very nice platform for such an
> environment.  I wonder if anyone has actually done anything on this
> scale.
>
> Thanks,
>
> Miles Fidelman
>



More information about the erlang-questions mailing list