A study of tracing overhead on a high-performance linux cluster

Authors:
Kathryn Mohror;Karen L. Karavanic
Affiliations:
Portland State University, Portland, OR;Portland State University, Portland, OR
Venue:
Proceedings of the 12th ACM SIGPLAN symposium on Principles and practice of parallel programming
Year:
2007

Citing 3
Cited 1

Semicoarsening Multigrid on Distributed Memory Machines

SIAM Journal on Scientific Computing
Integrating Database Technology with Comparison-based Parallel Performance Diagnosis: The PerfTrack Performance Experiment Management Tool

SC '05 Proceedings of the 2005 ACM/IEEE conference on Supercomputing
The Tau Parallel Performance System

International Journal of High Performance Computing Applications

A performance tuning methodology with compiler support

Scientific Programming - Large-Scale Programming Tools and Environments

Quantified Score

Hi-index	0.00

Visualization

Abstract

Our goal in this work was to identify and quantify the overheads of tracing parallel applications. We investigate several different sources of overhead related to tracing: trace instrumentation, periodic writing of trace files to disk, differing trace buffer sizes, system changes, and increasing numbers of processors in the target application. We encountered overheads as large as 26.7% for writing the trace file to disk. We found that buffer sizes can make a difference in the overheads, and that differences in system software can also contribute to the level of the perturbation. Our results show that the overhead of instrumentation correlates strongly with the number of events, while the overhead of writing the trace buffer increases with increasing numbers of processors.