Application Profiler

Pepperdata® Application Profiler analyzes all Hadoop and Spark jobs running on the cluster and provides developers with technical insights on how each job performed. Application Profiler improves MapReduce and Spark developer productivity and increases cluster efficiency based on clear recommendations on how to modify workloads and configurations.

Application Profiler provides performance feedback to the Code, Build, Test, and Release phases of the DevOps cycle.

Benefits for Devs

  • Actionable recommendations for tuning jobs
  • Validate tuning changes made to applications with a before and after comparison
  • Highlights worst performing phases of jobs

Benefits for Managers

  • Improve DevOps productivity
  • Reduce time to market

Benefits for Ops

  • Visualize resource usage by host, user, application, job, and tasks for quick troubleshooting

  • Reduce burden from developers

  • Codify best practices as heuristics for developers

Application Profiler provides detailed information on which stages of their data pipelines consume what type of resources, including a simple visual understanding of bottlenecks and tuning efficiency suggestions.

Application Profiler and Open Source

Application Profiler incorporates technology from the Dr. Elephant open source project. Application Profiler has the same capabilities as Dr. Elephant, but is enterprise ready and enables simplified deployment, scaling, and maintenance.

Application Profiler also minimizes performance impact and operational overhead on the cluster by storing performance data and running analysis for job tuning recommendations in a cloud-hosted service provided by Pepperdata. The Application Profiler user interface is integrated into the Pepperdata dashboard, making it easy to search and compare jobs.

Application Profiler is integrated with the other Pepperdata products to provide an end-to-end solution, combining overall cluster awareness (monitoring, troubleshooting, and alerting) with deep recommendations for improving the performance of individual jobs.

Works With All Big Data Distributions

Application Profiler works with all Big Data distributions including Apache, Cloudera, Hortonworks, MapR, and IBM, with support for both MapReduce and Spark. Pepperdata supports clusters running on-premise and in the cloud.