adequate
adequate
adequate
adequate
 

JPPF, java, parallel computing, distributed computing, grid computing, parallel, distributed, cluster, grid, cloud, open source, android, .net
JPPF

The open source
grid computing
solution

 Home   About   Features   Download   Documentation   Forums 
July 22, 2018, 09:06:04 AM *
Welcome,
Please login or register.

Login with username, password and session length
Advanced search  
News: New users, please read this message. Thank you!
  Home Help Search Login Register  
Pages: [1]   Go Down

Author Topic: Maximum resource utilization with unlimited task pool  (Read 49 times)

calkuta2

  • JPPF Padawan
  • *
  • Posts: 1
Maximum resource utilization with unlimited task pool
« on: April 03, 2018, 11:00:14 PM »

Hello,

I am implementing a steady-state genetic algorithm, meaning that we have an essentially unlimited number of tasks.  Assuming operation on a local node + slave nodes, what we would like to do is keep each slave node busy working on evaluating a candidate solution.  We also would like each task to be processed immediately upon completion, followed by the assignment of another task to the unoccupied node.  This process would continue indefinitely.

Is this possible?  The problem we are currently encountering is that we are sending out groups of tasks in a job, and as the job nears completion many available threads are being unutilized until the job returns and we send out another job.

We would also like to achieve this same scheme on a grid of nodes running slave nodes, which I assume would be straightforward once establishing it for the case of a local node + slave nodes.

Thanks kindly for any help.

Ricky
Logged
Pages: [1]   Go Up
 
JPPF Powered by SMF 2.0 RC5 | SMF © 2006–2011, Simple Machines LLC Get JPPF at SourceForge.net. Fast, secure and Free Open Source software downloads