Performance Evaluation: Metrics, Models and Benchmarks

This book constitutes the refereed proceedings of the SPEC International Performance Evaluation Workshop, SIPEW 2008, held in Darmstadt, Germany, in June 2008. The 17 revised full papers presented together with 3 keynote talks were carefully reviewed and selected out of 39 submissions for inclusion in the book. The papers are organized in topical sections on models for software performance engineering; benchmarks and workload characterization; Web services and service-oriented architectures; power and performance; and profiling, monitoring and optimization.

Keynotes. - Scheduling for Server Farms: Approaches and Open Problems. - SAP Standard Application Benchmarks - IT Benchmarks with a Business Focus. - The Relationship of Performance Models to Data. - Models for Software Performance Engineering. - Extracting Response Times from Fluid Analysis of Performance Models. - Approximate Solution of a PEPA Model of a Key Distribution Centre. - A Model Transformation from the Palladio Component Model to Layered Queueing Networks. - Model-Driven Generation of Performance Prototypes. - Benchmarks and Workload Characterization. - SCALASCA Parallel Performance Analyses of SPEC MPI2007 Applications. - Generating Probabilistic and Intensity-Varying Workload for Web-Based Software Systems. - Comparison of the SPEC CPU Benchmarks with 499 Other Workloads Using Hardware Counters. - Tuning Topology Generators Using Spectral Distributions. - Performance, Benchmarking and Sizing in Developing Highly Scalable Enterprise Software. - Web Services and Service-Oriented Architectures. - Phase-Type Approximations for Message Transmission Times in Web Services Reliable Messaging. - A Framework for Simulation Models of Service-Oriented Architectures. - Model-Driven Performability Analysis of Composite Web Services. - Power and Performance. - Dynamic Server Allocation for Power and Performance. - Workload Characterization of the SPECpower_ssj2008 Benchmark. - Profiling, Monitoring and Optimization. - Trace-Context Sensitive Performance Profiling for Enterprise Software Applications. - Performance Monitoring and Analysis of a Large Online Transaction Processing System. - Speeding up STL Set/Map Usage in C++ Applications.