A Community Databank for Performance Tracefiles
نویسندگان
چکیده
Tracefiles provide a convenient record of the behavior of HPC programs, but are not generally archived because of their storage requirements. This has hindered the developers of performance analysis tools, who must create their own tracefile collections in order to test tool functionality and usability. This paper describes a shared databank where members of the HPC community can deposit tracefiles for use in studying the performance characteristics of HPC platforms as well as in tool development activities. We describe how the Tracefile Testbed was designed and implemented to facilitate flexible searching and retrieval of tracefiles. A Web-based interface provides a convenient mechanism for browsing and downloading collections of tracefiles and tracefile segments based on a variety of characteristics. The paper discusses the key implementation challenges.
منابع مشابه
The Tracefile Testbed - A Community Repository for Identifying and Retrieving HPC Performance Data
HPC programmers utilise tracefiles, which record program behaviour in great detail, as the basis for many performance analysis activities. The lack of generally accessible tracefiles has forced programmers to develop their own testbeds in order to study the basic performance characteristics of the platforms they use. Because tracefiles serve as input to performance analysis and performance pred...
متن کاملThe controlled logical clock--a global time for trace-based software monitoring of parallel applications in workstation clusters
Event tracing and monitoring of parallel applications are difficult if each processor has its own unsynchronized clock. A survey is given on several strategies to generate a global time, and their limits are discussed. The controlled logical clock is a new method based on Lamport’s logical clock and provides a method to modify inexact timestamps of tracefiles. The new timestamps guarantee the c...
متن کاملAutomatic Structure Extraction from MPI Applications Tracefiles
The process of obtaining useful message passing applications tracefiles for performance analysis in supercomputers is a large and tedious task. When using hundreds or thousands of processors, the tracefile size can grow up to 10 or 20 GB. It is clear that analyzing or even storing these large traces is a problem. The methodology we have developed and implemented performs an automatic analysis t...
متن کاملPrivacy transformations for databank
The term databank implies a centralized collection of dara-to wnic1f a number -of users have access. A computerized databank system consists of the data files, the associated computer facility, a management structure, and a user community. Several classes of databank systems can be defined on the basis of the nature of the organization supported by the databank, and its activity; the nature of ...
متن کاملVirgil: A Databank of Links between GDB and GenBank
This paper focuses on a speci c type of information frequently used by researchers in Genetics: links between genome objects. It emphasizes the fact that, at present, links are not su ciently characterized and describes our work to address this problem: the design of a prototype databank to store links between genome databases. Because this global repository is of concern for many people, we we...
متن کامل