kirancodes.me
To Proof Maintenance & Beyond!
FSE 2019

Symbolic execution-driven extraction of the parallel execution plans of Spark applications

Luciano Baresi, Giovanni Denaro, Giovanni Quattrocchi

PDFDOI 10.1145/3338906.3338973dblp

Abstract

The execution of Spark applications is based on the execution order and parallelism of the different jobs, given data and available resources. Spark reifies these dependencies in a graph that we refer to as the (parallel) execution plan of the application. All the approaches that have studied the estimation of the execution times and the dynamic provisioning of resources for this kind of applications have always assumed that the execution plan is unique, given the computing resources at hand. This assumption is at least simplistic for applications that include conditional branches or loops and limits the precision of the prediction techniques.

BibTeX
@inproceedings{Baresi-al:FSE19,
  author    = {Luciano Baresi and
               Giovanni Denaro and
               Giovanni Quattrocchi},
  title     = {Symbolic execution-driven extraction of the parallel execution plans of Spark applications},
  booktitle = {{ESEC/SIGSOFT} {FSE}},
  pages     = {246--256},
  publisher = {{ACM}},
  year      = {2019},
}

Related papers