[NTLUG:Discuss] Distributed processing

[Bug Hunter]

  mosix (from israel) hands processess off to another machine.

  If you write your code in a certain way, then you can hand off
functionality through sockets and daemons.   

  also see 

http://red.coral.com.mx/ceyusa/projects/xsusockd/

  it is a daemon that executes code on command.

bug

On Wed, 25 Jul 2001, Greg Hewett wrote:

> Greg,
> 
> I work a lot in the fail over type of clusters, and I know that is far from what you are looking at, but I have had some of the same ideas as you.  I know that there is not much out there in the open world, but there are a lot of proects out there that might be able to piece together some of the complicated parts.
> 
> The way that I have suggested my idea, is that sometime the failover clusters and the parallel processing cluster will come together and meet in the middle.  Reading this thread has kinda got me thinking a little more in detail about what you are suggesting.
> 
> Some of the OSS projects I watch are FailSafe (SGI) and linux-ha.org.  Neither comes close to your requirements, but I thought I would mention them.
> 
> Please let me know what you find.  I have been intrested in investing is such a project.
> 
> cya
> greg
> 
> -----Original Message-----
> From: discuss-admin at ntlug.org [mailto:discuss-admin at ntlug.org]On Behalf
> Of Greg Edwards
> Sent: Tuesday, July 17, 2001 8:07 PM
> To: ntlug discuss
> Subject: [NTLUG:Discuss] Distributed processing
> 
> 
> I sent this out last week and was wondering why I never saw it posted. 
> Well I guess I sent it to admin at ntlug.org, sorry:)
> 
> -------- Original Message --------
> Subject: Distributed processing
> Date: Sun, 08 Jul 2001 17:54:36 -0500
> From: Greg Edwards <greg at nas-inet.com>
> Organization: New Age Software, Inc.
> To: ntlug Admin <discuss-admin at ntlug.org>
> 
> I've been searching for tools that will do distibuted processing at the
> function level and haven't had much luck.  There are plenty of
> distributed load managers and parallel processing managers (such as
> Beowolf).  The load managers work at the program level and parallel
> process managers at the calculation level.  Neither of these solutions
> answer my needs and multi-threaded has too many drawbacks for a solution
> here.  What I need is a distribution manager that will pass the load at
> the procedural level.
> 
> What I'm trying to do is run an application farm for interactive web
> applications.  This solution would be usable well beyond web
> applications.  The idea is that during the processing of an application
> rather than a single program using a set of libraries on a single box an
> API would allow the function request to be distributed among N boxes
> that support that function.  Not every box would support every function
> available throughout the farm but every box would have knowledge of
> every function in the farm.