Big data presents new challenges to both cluster infrastructure software
and parallel application design. We present a set of software services
and design principles for data intensive computing with petabyte
data sets, named GrayWulf. These services are intended for deployment
on a cluster of commodity servers similar to the well-known Beowulf
clusters. We use the Pan-STARRS system currently under development
as an example of the architecture and principles in action.
%0 Conference Paper
%1 Simmhan:hicss:2009
%A Simmhan, Yogesh
%A Barga, Roger
%A van Ingen, Catharine
%A Nieto-Santisteban, Maria
%A Dobos, Lazslo
%A Li, Nolan
%A Shipway, Michael
%A Szalay, Alexander S.
%A Werner, Sue
%A Heasley, Jim
%B Hawaii International Conference on System Sciences (HICSS)
%D 2009
%I IEEE
%K cloud, data escience, graywulf, hpc, management, msr, panstarrs, peer reviewed trident, workflows,
%P 1-10
%R 10.1109/HICSS.2009.235
%T GrayWulf: Scalable Software Architecture for Data Intensive Computing
%X Big data presents new challenges to both cluster infrastructure software
and parallel application design. We present a set of software services
and design principles for data intensive computing with petabyte
data sets, named GrayWulf. These services are intended for deployment
on a cluster of commodity servers similar to the well-known Beowulf
clusters. We use the Pan-STARRS system currently under development
as an example of the architecture and principles in action.
@inproceedings{Simmhan:hicss:2009,
abstract = {Big data presents new challenges to both cluster infrastructure software
and parallel application design. We present a set of software services
and design principles for data intensive computing with petabyte
data sets, named GrayWulf. These services are intended for deployment
on a cluster of commodity servers similar to the well-known Beowulf
clusters. We use the Pan-STARRS system currently under development
as an example of the architecture and principles in action.},
added-at = {2014-08-13T04:08:36.000+0200},
author = {Simmhan, Yogesh and Barga, Roger and van Ingen, Catharine and Nieto-Santisteban, Maria and Dobos, Lazslo and Li, Nolan and Shipway, Michael and Szalay, Alexander S. and Werner, Sue and Heasley, Jim},
biburl = {https://www.bibsonomy.org/bibtex/2e284962ea1f7bfb15d7a148e25cfae74/simmhan},
booktitle = {Hawaii International Conference on System Sciences (HICSS)},
doi = {10.1109/HICSS.2009.235},
interhash = {24b68fb89ad24f197f4bfa4c6b362c3e},
intrahash = {e284962ea1f7bfb15d7a148e25cfae74},
keywords = {cloud, data escience, graywulf, hpc, management, msr, panstarrs, peer reviewed trident, workflows,},
note = {[CORE A]},
owner = {Simmhan},
pages = {1-10},
publisher = {IEEE},
timestamp = {2014-08-13T04:08:36.000+0200},
title = {GrayWulf: Scalable Software Architecture for Data Intensive Computing},
year = 2009
}