Prediction-based auto-scaling of scientific workflows

Open Access
Authors
Publication date 2011
Host editors
  • B. Schulze
  • O. Rana
  • E. Madeira
Book title Proceedings of the 9th International Workshop on Middleware for Grids, Clouds and e-Science: MGC 2011, co-located with ACM/IFIP/USENIX 12th International Middleware Conference, December 12-16, 2011, Lisbon, Portugal
ISBN
  • 9781450310680
Event 9th International Workshop on Middleware for Grids, Clouds and e-Science
Pages (from-to) 1
Publisher New York, NY: ACM
Organisations
  • Faculty of Science (FNWI) - Informatics Institute (IVI)
Abstract
In this paper we propose a novel method for auto-scaling data-centric workflow tasks. Scaling is achieved through a prediction mechanism where the input data load on each task within a workflow is used to compute the estimated task execution time. Through load prediction, the framework can take informed decisions on scaling multiple workflow tasks independently to improve overall throughput and reduce workflow bottlenecks. This method was implemented in the WS-VLAM workflow system and with an image analyses workflow we show that this technique achieves faster data processing rates and reduces overall workflow makespan.
Document type Conference contribution
Language English
Published at https://doi.org/10.1145/2089002.2089003
Downloads
Permalink to this page
Back