Analysis of Linux Scheduling with VAMPIR

نویسندگان

  • Michael Kluge
  • Wolfgang E. Nagel
چکیده

Analyzing the scheduling behavior of an operating system becomes more and more interesting because multichip mainboards and Multi-Core CPUs are available for a wide variety of computer systems. Those system can range from a few CPU cores to thousands of cores. Up to now there is no tool available to visualize the scheduling behavior of a system running Linux. The Linux Kernel has an unique implementation of threads, each thread is treated as a process. In order to be able to analyze scheduling events within the kernel we have developed a method to dump all information needed to analyze process switches between CPUs into files. These data will then be analyzed using the VAMPIR tool. Traditional VAMPIR displays will be reused to visualize scheduling events. This approach allows to follow processes as they switch between CPUs as well as gathering statistical data, for example the the number of process switches.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Scalable Tools for Non-Intrusive Performance Debugging of Parallel Linux Workloads

There are a variety of tools to measure the performance of Linux systems and the applications running on them. However, the resulting performance data is often presented in plain text format or only with a very basic user interface. For large systems with many cores and concurrent threads, it is increasingly difficult to present the data in a clear way for analysis. Moreover, certain performanc...

متن کامل

Performance Prediction in a Grid Environment

Knowing the performance of an application in a Grid environment is an important issue in application development and for scheduling decisions. In this paper we describe the analysis and optimisation of a computationand communication-intensive application from the field of bioinformatics, which was demonstrated at the HPCChallenge of Supercomputing 2002 at Baltimore. This application has been ad...

متن کامل

Vampir: Visualization and Analysis of Mpi Resources

Performance analysis most often is based on the detailed knowledge of program behavior. One option to get this information is tracing. Based on the research tool PARvis, the visualization environment VAMPIR was developed at KFA which now supports the new message passing standard MPI. VAMPIR translates a given trace le into a variety of graphical views, e.g., state diagrams, activity charts, tim...

متن کامل

Dynamic Instrumentation of Large-Scale MPI and OpenMP Applications

In recent years, software infrastructures for the run-time instrumentation of programs have begun to emerge. This paper presents and evaluates prototypes of dynamic instrumentation and dynamic control of instrumentation for parallel mixed MPI/OpenMP applications. An overview of the technology behind these approaches is presented. Prototypes of dynamic instrumentation and dynamic control of inst...

متن کامل

Fitting Linux Device Drivers into an Analyzable Scheduling Framework

API extensions and performance improvements to the Linux operating system now enable it to serve as a platform for a range of embedded real-time applications, using fixed-priority preemptive scheduling. Powerful techniques exist for analytical verification of application timing constraints under this scheduling model. However, when the application is layered over an operating system the operati...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2007