Not logged in.

Contribution Details

Type Conference or Workshop Paper
Scope Discipline-based scholarship
Published in Proceedings Yes
Title Workload Scheduling in Distributed Stream Processors using Graph Partitioning
Organization Unit
Authors
  • Lorenz Fischer
  • Abraham Bernstein
Presentation Type paper
Item Subtype Original Work
Refereed Yes
Status Published in final form
Language
  • English
Event Title 2015 IEEE International Conference on Big Data (IEEE BigData 2015)
Event Type conference
Event Location Santa Clara, CA, USA
Event Start Date October 29 - 2015
Event End Date November 1 - 2015
Publisher IEEE Computer Society
Abstract Text With ever increasing data volumes, large compute clusters that process data in a distributed manner have become prevalent in industry. For distributed stream processing platforms (such as Storm) the question of how to distribute workload to available machines, has important implications for the overall performance of the system. We present a workload scheduling strategy that is based on a graph partitioning algorithm. The scheduler is application agnostic: it collects the communication behavior of running applications and creates the schedules by partitioning the result- ing communication graph using the METIS graph partitioning software. As we build upon graph partitioning algorithms that have been shown to scale to very large graphs, our approach can cope with topologies with millions of tasks. While the experiments in this paper assume static data loads, our approach could also be used in a dynamic setting. We implemented our proposed algorithm for the Storm stream processing system and evaluated it on a commodity cluster with up to 80 machines. The evaluation was conducted on four different use cases – three using synthetic data loads and one application that processes real data. We compared our algorithm against two state-of-the-art sched- uler implementations and show that our approach offers sig- nificant improvements in terms of resource utilization, enabling higher throughput at reduced network loads. We show that these improvements can be achieved while maintaining a balanced workload in terms of CPU usage and bandwidth consumption across the cluster. We also found that the performance advantage increases with message size, providing an important insight for stream-processing approaches based on micro-batching.
Other Identification Number merlin-id:12370
PDF File Download from ZORA
Export BibTeX
EP3 XML (ZORA)