Leveraging Non-Uniform Resources for Parallel Query Processing

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Standard

Leveraging Non-Uniform Resources for Parallel Query Processing. / Mayr, Tobias; Bonnet, Philippe; Gehrke, Johannes; Seshadri, Praveen.

Third IEEE International Symposium on Cluster Computing and the Grid. 2003.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Harvard

Mayr, T, Bonnet, P, Gehrke, J & Seshadri, P 2003, Leveraging Non-Uniform Resources for Parallel Query Processing. in Third IEEE International Symposium on Cluster Computing and the Grid. CCGrid 2003, 29/11/2010. https://doi.org/http://doi.ieeecomputersociety.org/10.1109/CCGRID.2003.1199360

APA

Mayr, T., Bonnet, P., Gehrke, J., & Seshadri, P. (2003). Leveraging Non-Uniform Resources for Parallel Query Processing. In Third IEEE International Symposium on Cluster Computing and the Grid https://doi.org/http://doi.ieeecomputersociety.org/10.1109/CCGRID.2003.1199360

Vancouver

Mayr T, Bonnet P, Gehrke J, Seshadri P. Leveraging Non-Uniform Resources for Parallel Query Processing. In Third IEEE International Symposium on Cluster Computing and the Grid. 2003 https://doi.org/http://doi.ieeecomputersociety.org/10.1109/CCGRID.2003.1199360

Author

Mayr, Tobias ; Bonnet, Philippe ; Gehrke, Johannes ; Seshadri, Praveen. / Leveraging Non-Uniform Resources for Parallel Query Processing. Third IEEE International Symposium on Cluster Computing and the Grid. 2003.

Bibtex

@inproceedings{0bf0d270f39911dcbee902004c4f4f50,
title = "Leveraging Non-Uniform Resources for Parallel Query Processing",
abstract = "Modular clusters are now composed of non- uniform nodes with different CPUs, disks or network cards so that customers can adapt the cluster configuration to the changing technologies and to their changing needs. This challenges dataflow parallelism as the primary load balancing technique of existing parallel database systems. We show in this paper that dataflow parallelism alone is ill suited for modular clusters because running the same operation on different subsets of the data can not fully utilize non-uniform hardware resources. We propose and evaluate new load balancing techniques that blend pipeline parallelism with data parallelism. We consider relational operators as pipelines of fine-grained operations that can be located on different cluster nodes and executed in parallel on different data subsets to best exploit non-uniform resources. We present an experimental study that confirms the feasibility and effectiveness of the new techniques in a parallel execution engine prototype based on the open-source DBMS Predator.",
keywords = "Faculty of Science, query processing, parallel databases",
author = "Tobias Mayr and Philippe Bonnet and Johannes Gehrke and Praveen Seshadri",
year = "2003",
doi = "http://doi.ieeecomputersociety.org/10.1109/CCGRID.2003.1199360",
language = "English",
booktitle = "Third IEEE International Symposium on Cluster Computing and the Grid",
note = "null ; Conference date: 29-11-2010",

}

RIS

TY - GEN

T1 - Leveraging Non-Uniform Resources for Parallel Query Processing

AU - Mayr, Tobias

AU - Bonnet, Philippe

AU - Gehrke, Johannes

AU - Seshadri, Praveen

PY - 2003

Y1 - 2003

N2 - Modular clusters are now composed of non- uniform nodes with different CPUs, disks or network cards so that customers can adapt the cluster configuration to the changing technologies and to their changing needs. This challenges dataflow parallelism as the primary load balancing technique of existing parallel database systems. We show in this paper that dataflow parallelism alone is ill suited for modular clusters because running the same operation on different subsets of the data can not fully utilize non-uniform hardware resources. We propose and evaluate new load balancing techniques that blend pipeline parallelism with data parallelism. We consider relational operators as pipelines of fine-grained operations that can be located on different cluster nodes and executed in parallel on different data subsets to best exploit non-uniform resources. We present an experimental study that confirms the feasibility and effectiveness of the new techniques in a parallel execution engine prototype based on the open-source DBMS Predator.

AB - Modular clusters are now composed of non- uniform nodes with different CPUs, disks or network cards so that customers can adapt the cluster configuration to the changing technologies and to their changing needs. This challenges dataflow parallelism as the primary load balancing technique of existing parallel database systems. We show in this paper that dataflow parallelism alone is ill suited for modular clusters because running the same operation on different subsets of the data can not fully utilize non-uniform hardware resources. We propose and evaluate new load balancing techniques that blend pipeline parallelism with data parallelism. We consider relational operators as pipelines of fine-grained operations that can be located on different cluster nodes and executed in parallel on different data subsets to best exploit non-uniform resources. We present an experimental study that confirms the feasibility and effectiveness of the new techniques in a parallel execution engine prototype based on the open-source DBMS Predator.

KW - Faculty of Science

KW - query processing

KW - parallel databases

U2 - http://doi.ieeecomputersociety.org/10.1109/CCGRID.2003.1199360

DO - http://doi.ieeecomputersociety.org/10.1109/CCGRID.2003.1199360

M3 - Article in proceedings

BT - Third IEEE International Symposium on Cluster Computing and the Grid

Y2 - 29 November 2010

ER -

ID: 3185413