The Workings of Typical Cluster Management Software - 5

The Workings of Typical Cluster Management Software - 5

Fault Tolerance

• The master scheduler is also tasked with the responsibility of ensuring that jobs complete successfully.

• It does this by monitoring jobs until they successfully finish.

• If a job fails, due to problems other than an application runtime error, it will reschedule the job to run again.

Previous slide

Next slide

Back to the first slide

View Graphic Version