An Extensible I/O Performance Analysis Framework for Distributed Environments

Abstract

As distributed systems increase in both popularity and scale, it becomes increasingly important to understand as well as to systematically identify performance anomalies and potential opportunities for optimization. However, large scale distributed systems are often complex and non-deterministic due to hardware and software heterogeneity and configurable runtime options that may boost or diminish performance. It is therefore important to be able to disseminate and present the information gleaned from a local system under a common evaluation methodology so that such efforts can be valuable in one environment and provide general guidelines for other environments. Evaluation methodologies can conveniently be encapsulated inside of a common analysis framework that serves as an outer layer upon which appropriate experimental design and relevant workloads (benchmarking and profiling applications) can be supported.

In this paper we present ExPerT, an Extensible Performance Toolkit. ExPerT defines a flexible framework from which a set of benchmarking, tracing, and profiling applications can be correlated together in a unified interface. The framework consists primarily of two parts: an extensible module for profiling and benchmarking support, and a unified data discovery tool for information gathering and parsing. We include a case study of disk I/O performance in virtualized distributed environments which demonstrates the flexibility of our framework for selecting benchmark suite, creating experimental design, and performing analysis.