An information exploration tool for performance analysis of Java programs

Abstract

The diagnosis of performance and memory problems can require the analysis of large and complex data sets describing a program's execution. An analysis tool must help the user both find the right organization of the data to uncover useful information, and work with the data through a lengthy and unpredicatable discovery process. In this paper we present Jinsight EX, a tool for analyzing Java performance, that adopts techniques that have been successfully used to explore large data sets in other application domains, and adapts them specifically to the needs of program execution analysis. We introduce execution slices, a high-level organizing abstraction that the user may define and then easily reuse in various settings. We illustrate techniques that allow the user to perform a range of common analysis tasks and to structure a longer analysis process, using this abstraction. We present the tool, its implementation and initial experience of its use.