Non-stop monitoring and debugging on shared-memory multiprocessors

Abstract

Monitoring and debugging parallel programs is a diflcult activity. There are many situations where the traditional "stop the world, I want to get ofs' approach to debugging is simply unsuitable. Frequently, nonintrusive monitoring of the program execution is more productive in locating sources of error and also in monitoring "correct" programs f o r such purposes as performance measurement and tuning. This paper presents a number of space-and timeefficient tools and techniques to support nonintrusive, non-stop monitoring and debugging of parallel programr running on a shared-memory multiprocessor. The techniques include the use of spy tasks, circular history bufSers, vectors of use bits, and &tu structure audits. Particular emphasis is placed on issues that pertain to parallel computing, such as dealing with concurrent execution, shared memory and data caches.