Workload Characterization for Capacity Planning and Performance Management in IaaS Cloud

Effective characterization of workload could be used to drive Capacity Planning and Performance Management in IaaS Cloud. There are different workload metrics (e.g. CPU, memory usage, throughput, response time) which could be modeled along with relationships between them. Similarly, we could model relationships across a set of workloads. Analyzing and characterizing this would enable decision making for various scenarios such as migration, re-provisioning, load balancing, resource management, initial placement. In this paper, we study workload running in IaaS cloud and categorize into patterns, based on their behavioral characteristics. We define different types of behavioral patterns and outline statistical techniques to be used in determining these patterns. We present initial results for development workload data collected in the lab.