A Tale of Two Data-Intensive Paradigms: Applications, Abstractions, and Architectures

TL;DR

This paper compares high-performance computing and Hadoop paradigms for data-intensive applications, analyzing their architectures, workloads, and performance, and proposes using 'Big Data Ogres' as benchmarks for evaluation.

Contribution

It introduces a common framework and terminology for analyzing both paradigms, and presents a semi-quantitative methodology using K-means clustering as a benchmark.

Findings

Architectural similarities despite software differences

Performance insights from K-means clustering experiments

'Big Data Ogres' as a potential benchmarking suite

Abstract

Scientific problems that depend on processing large amounts of data require overcoming challenges in multiple areas: managing large-scale data distribution, co-placement and scheduling of data with compute resources, and storing and transferring large volumes of data. We analyze the ecosystems of the two prominent paradigms for data-intensive applications, hereafter referred to as the high-performance computing and the Apache-Hadoop paradigm. We propose a basis, common terminology and functional factors upon which to analyze the two approaches of both paradigms. We discuss the concept of "Big Data Ogres" and their facets as means of understanding and characterizing the most common application workloads found across the two paradigms. We then discuss the salient features of the two paradigms, and compare and contrast the two approaches. Specifically, we examine common implementation/approaches of these paradigms, shed light upon the reasons for their current "architecture" and discuss some typical workloads that utilize them. In spite of the significant software distinctions, we believe there is architectural similarity. We discuss the potential integration of different implementations, across the different levels and components. Our comparison progresses from a fully qualitative examination of the two paradigms, to a semi-quantitative methodology. We use a simple and broadly used Ogre (K-means clustering), characterize its performance on a range of representative platforms, covering several implementations from both paradigms. Our experiments provide an insight into the relative strengths of the two paradigms. We propose that the set of Ogres will serve as a benchmark to evaluate the two paradigms along different dimensions.