Still celebrating National IT Professionals Day with 3 months of free Premium Membership. Use Code ITDAY17

x
?
Solved

Parallel Processing

Posted on 1999-06-26
5
Medium Priority
?
281 Views
Last Modified: 2010-04-21
Can FreeBSD perform parallel processing, i.e. perform a job by multiple machine ?

If yes, how can I do it ?

Andrew
0
Comment
Question by:andrewyu
[X]
Welcome to Experts Exchange

Add your voice to the tech community where 5M+ people just like you are talking about what matters.

  • Help others & share knowledge
  • Earn cash & points
  • Learn & ask questions
  • 3
  • 2
5 Comments
 
LVL 14

Accepted Solution

by:
chris_calabrese earned 200 total points
ID: 2011216
FreeBSD can perform parallel processing to the extent that it can schedule multiple threads of execution within the same process across multiple CPU's on the _same_ machine.

It can not schedule multiple threads of the same process across multiple machines (the only systems I can think of that can do this are the newer IRIX releases running on SGI's with HPPI connections and some research systems like Ameoba).

However, that doesn't mean it's impossible to write software that can take advantage of processing across multiple machines.  The simplist way is to write a program that uses remsh()/rsh to spwn processes on other machines.  Another way is to have dedicated services running on a bunch of machines and contact them via RPC's.  Java RMI's are pretty similar to this if you're writing in Java.  Finally, you could use the Yale 'T' system which allows you to distribute programs written in 'T' (a lisp dialect) across multiple machines, even if they're not the same OS or hardware architecture.
0
 

Author Comment

by:andrewyu
ID: 2011217
But, how about different process ? Can FreeBSD distribute the processes into other machines automatically (like NT clustering) ?

So, do you mean that the easiest and best way is use CORBA or RMI (anyway, RPC) ?

Andrew
0
 
LVL 14

Expert Comment

by:chris_calabrese
ID: 2011218
This kind of clustering is almost done on top of some other service like CORBA, RMI, RPC, etc.  I don't know much about NT clustering, but I'd bet it's sitting on top of NT RPC's with some kind of load balancer (hmm, maybe they don't even have a load balancer since they only do 2-way without third-party add-ons).  I don't believe the NT clusters can actually migrate a process running on one machine to another machine (which both IRIX and Ameoba can do, though in the case of IRIX all the machines are running a single coordinated OS kernel and the fact that they're physically seperate boxes is just an interesting side issue).

I've seen lots of solutions to this problem over the years.

Exactly how to do it depends greatly on how you want things to work.  For example, AT&T Research's nmake uses some simple shell scripts that look at rwho statistics to do the balancing part and then calls rsh to do remote compiles.  CORBA and RMI environments have large parts of this stuff built-in.  RPC's also work, but getting the load balancing right isn't so easy.
0
 

Author Comment

by:andrewyu
ID: 2011219
Thank you very much indeed !

But do you mean that the CORBA and RMI have already implement the Load Balancing ?

Andrew
0
 
LVL 14

Expert Comment

by:chris_calabrese
ID: 2011220
No, CORBA and RMI have not implemented load balancing.  However, CORBA aware and RMI aware transaction monitors (such as BEA's Tuxedo) can.
0

Featured Post

Free Tool: Subnet Calculator

The subnet calculator helps you design networks by taking an IP address and network mask and returning information such as network, broadcast address, and host range.

One of a set of tools we're offering as a way of saying thank you for being a part of the community.

Question has a verified solution.

If you are experiencing a similar issue, please ask a related question

Attention: This article will no longer be maintained. If you have any questions, please feel free to mail me. jgh@FreeBSD.org Please see http://www.freebsd.org/doc/en_US.ISO8859-1/articles/freebsd-update-server/ for the updated article. It is avail…
A metadevice consists of one or more devices (slices). It can be expanded by adding slices. Then, it can be grown to fill a larger space while the file system is in use. However, not all UNIX file systems (UFS) can be expanded this way. The conca…
Learn how to find files with the shell using the find and locate commands. Use locate to find a needle in a haystack.: With locate, check if the file still exists.: Use find to get the actual location of the file.:
Learn how to navigate the file tree with the shell. Use pwd to print the current working directory: Use ls to list a directory's contents: Use cd to change to a new directory: Use wildcards instead of typing out long directory names: Use ../ to move…

721 members asked questions and received personalized solutions in the past 7 days.

Join the community of 500,000 technology professionals and ask your questions.

Join & Ask a Question