IBM High Performance Computing Cluster Health Check

The health lifecycle methodology

This chapter describes the requirement for a methodology to address the entire lifecycle of the compute environment components. This chapter guides you through the different phases of a cluster’s life, and gives suggestions based on the experiences of the authors.

This chapter covers the following topics:

•Why a methodology is necessary

•The health lifecycle methodology

•Practical application of the health lifecycle methodology

3.1 Why a methodology is necessary

Due to the complexity, interdependence, and magnitude ...