Nephele Streaming: Stream Processing Under QoS Constraints At Scale

TL;DR

This paper introduces Nephele Streaming, a scalable stream processing approach that ensures QoS constraints are met, significantly reducing latency while maintaining throughput in large-scale data processing environments.

Contribution

It presents a novel distributed scheme for detecting QoS violations and optimizing job execution in parallel data processing frameworks, demonstrated with Nephele.

Findings

Latency improved by at least 13 times

High throughput preserved under QoS constraints

Effective detection and correction of QoS violations

Abstract

The ability to process large numbers of continuous data streams in a near-real-time fashion has become a crucial prerequisite for many scientific and industrial use cases in recent years. While the individual data streams are usually trivial to process, their aggregated data volumes easily exceed the scalability of traditional stream processing systems. At the same time, massively-parallel data processing systems like MapReduce or Dryad currently enjoy a tremendous popularity for data-intensive applications and have proven to scale to large numbers of nodes. Many of these systems also provide streaming capabilities. However, unlike traditional stream processors, these systems have disregarded QoS requirements of prospective stream processing applications so far. In this paper we address this gap. First, we analyze common design principles of today's parallel data processing frameworks and identify those principles that provide degrees of freedom in trading off the QoS goals latency and throughput. Second, we propose a highly distributed scheme which allows these frameworks to detect violations of user-defined QoS constraints and optimize the job execution without manual interaction. As a proof of concept, we implemented our approach for our massively-parallel data processing framework Nephele and evaluated its effectiveness through a comparison with Hadoop Online. For an example streaming application from the multimedia domain running on a cluster of 200 nodes, our approach improves the processing latency by a factor of at least 13 while preserving high data throughput when needed.