We're sorry but this page doesn't work properly without JavaScript enabled. Please enable it to continue.
Feedback

Graphing tools for scheduler tracing

Formal Metadata

Title
Graphing tools for scheduler tracing
Title of Series
Number of Parts
542
Author
Contributors
License
CC Attribution 2.0 Belgium:
You are free to use, adapt and copy, distribute and transmit the work or content in adapted or unchanged form for any legal purpose as long as the work is attributed to the author in the manner specified by the author or licensor.
Identifiers
Publisher
Release Date
Language

Content Metadata

Subject Area
Genre
Abstract
Understanding scheduler behavior can be important for understanding application performance. In this talk, we present some tools that we have developed to help understand scheduling behavior on highly multicore machines. The tools to be presented enable 1) obtaining a graph showing what tasks are running on what cores, with a variety of coloring schemes, 2) detecting overload situations, and 3) stepping through a recorded execution. All tools rely on traces collected using trace-cmd. The tools make it possible to get an overview of the execution, as well as to study specific execution intervals.