Grid 5000 CPU Load Performance
Monitoring by SBLOMARS
 

 

Experiment Description:

 

 

Algorithms Description:

 

The following graphs compare three scheduling algorithms performance in several nodes beloging to Grid5000 testbed.

The total amount of nodes performing this experiment were 74. They have heterogenous architectures wich thier description are available on: www.grid5000.fr

Every node was running a processor generator application to simulate processor load. Each scheduling algorithm was working along 120 minutes (2hrs) receiving 30 jobs every 60 seconds. On every node were also running a background processes generator. It was running randomly for the whole experiment (6hrs)

 

BLOMERS: This algorithm is part of the PhD thesis by Edgar Magaña. It is based on a Genetic Algorithm and SBLOMARS monitoring agents. This algorithms selects the nodes whose processor threshold is not more than 50%.

Round-robin: This algorithm schedules every job received to the next available node from a list of nodes available. Once the list has been complete, this approach sends the next job to the first node of the list and goes on. Then, it generates several cicles per scheduling.

Least Used: This algorithm schedules based on the average of the least used node. Based on the statistics generated per SBLOMARS monitoring agents it selects the least used in average and send the next job received.

 

Created by Edgar Magaña