On the Performance of Spark on HPC Systems: Towards a Complete Picture

Abstract

Big Data analytics frameworks (e.g., Apache Hadoop and Apache Spark) have been increasingly used by many companies and research labs to facilitate large-scale data analysis. However, with the growing needs of users and size of data, commodity-based infrastructure will strain under the heavy weight of Big Data. On the other hand, HPC systems offer a rich set of opportunities for Big Data processing. As first steps toward Big Data processing on HPC systems, several research efforts have been devoted to understanding the performance of Big Data applications on these systems. Yet the HPC specific performance considerations have not been fully investigated. In this work, we conduct an experimental campaign to provide a clearer understanding of the performance of Spark, the de facto in-memory data processing framework, on HPC systems. We ran Spark using representative Big Data workloads on Grid'5000 testbed to evaluate how the latency, contention and file system's configuration can influence the application performance. We discuss the implications of our findings and draw attention to new ways (e.g., burst buffers) to improve the performance of Spark on HPC systems.

Spark-DIY: A Framework for Interoperable Spark Operations with High Performance Block-Based Data Models

“…Nonetheless, Big Data and HPC frameworks today remain largely incompatible: programming models and software development tools are inconsistent [5]; trying to mix both models out-of-the-box generates memory overheads and poor scalability in a HPC environment [6]; the disparity between collocated and distributed storage architectures in Big Data and HPC systems, respectively, degrades performance when running Big Data applications on HPC systems [7]; and the usage of merged Big Data models presents limitations, such as high memory consumption and low efficiency in communication between cooperating processes [8].…”