5

Minimum Cost Benchmarking Approaches

In this chapter, we present our minimum cost benchmarking approaches for the applications in the cloud. The benchmark is the theoretical minimum application cost in the cloud, which is also the best trade-off between computation and storage. As introduced in Section 4.3, we use a cost rate to represent this trade-off (i.e. SCR). Benchmarking is the process of finding the minimum value of this cost rate (i.e. the SCR with the minimum cost storage strategy of the DDG). Due to the complex dependencies among the data sets in the cloud, the DDG is a DAG. Hence calculating the minimum cost benchmark is a seemingly NP-hard problem based on the cost model introduced in Section 4.3. Furthermore, the application cost ...

Get Computation and Storage in the Cloud now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.