Section: New Software and Platforms

DfAnalyzer

Dataflow Analysis

Keywords: Data management - Monitoring - Runtime Analysis

Functional Description: DfAnalyzer is a tool for monitoring, debugging, steering, and analysis of dataflows while being generated by scientific applications. It works by capturing strategic domain data, registering provenance and execution data to enable queries at runtime. DfAnalyzer provides lightweight dataflow monitoring components to be invoked by high performance applications. It can be plugged in scripts, or Spark applications, in the same way users already plug visualization library components.

• Participants: Vitor Sousa Silva, Daniel De Oliveira, Marta Mattoso and Patrick Valduriez

• Partners: COPPE/UFRJ - Uff

• Contact: Patrick Valduriez

• Publication: DfAnalyzer: Runtime Dataflow Analysis of Scientific Applications using Provenance

• URL: https://github.com/vssousa/dfanalyzer-spark