A distributed performance analysis architecture for clusters

Author

Brunst, Holger ; Nagel, Wolfgang E. ; Malony, Allen D.

Author_Institution

Center for High Performance Comput., Dresden Univ. of Technol., Germany

fYear

2003

fDate

1-4 Dec. 2003

Firstpage

73

Lastpage

81

Abstract

The use of a cluster for distributed performance analysis of parallel trace data is discussed. We propose an analysis architecture that uses multiple cluster nodes as a server to execute analysis operations in parallel and communicate to remote clients where performance visualization and user interactions occur. The client-server system developed, VNG, is highly configurable and is shown to perform well for traces of large size, when compared to leading trace visualization systems.

Keywords

client-server systems; file servers; parallel architectures; performance evaluation; workstation clusters; analysis operations; client-server system; distributed performance analysis architecture; multiple cluster nodes; parallel computing; parallel trace data; performance visualization; profiling; remote clients; trace visualization systems; tracing; user interactions; Client-server systems; Computer architecture; Concurrent computing; Data visualization; Distributed computing; File servers; High performance computing; Measurement techniques; Parallel architectures; Parallel processing; Parallel programming; Performance analysis; Prototypes;

fLanguage

English

Publisher

ieee

Conference_Titel

Cluster Computing, 2003. Proceedings. 2003 IEEE International Conference on

Print_ISBN

0-7695-2066-9

Type

conf

DOI

10.1109/CLUSTR.2003.1253301

Filename

1253301