Tracing and Characterization of NT-based System Workloads

Trace-driven simulation is commonly used by the computer architecture research community to pursue answers to a wide variety of architectural design issues. Traces taken from benchmark execution (e.g., SPEC, Bytemark, SPLASH) have been studied extensively to optimize the design of pipelines, branch predictors, and especially cache memories. Today’s computer designs have been optimized based on the characteristics of these benchmarks. As applications become more dependent on services and APIs provided by the hosting operating system, the overall application performance becomes more dependent on efficient operating system interaction. It has been acknowledged that operating system overhead can greatly affect the benefits provided by a new design feature. The reason why the operating system interaction has, for the most part, been ignored in past architectural studies is the lack of available tools that can generate kernel-laden traces. In this contribution we describe the ongoing efforts to capture operating system rich traces on the DEC Alpha platform. We will describe the current version of the PatchWrx toolset, originally developed by Richard Sites. This tool allows us to obtain trace information of application and operating system activity, while introducing minimal overhead. We will describe the current version of the tool, and demonstrate its capabilities by characterizing a number of applications. We will also contrast the fundamental differences between using simple benchmark programs, versus studying application based programs. This paper demonstrates that for real applications (MS CD Player, MS Visual C/C++, FX!32, etc.), the operating system execution can dominate the overall execution time of the application, contributing significantly to the contents of any captured trace.