Processing moldable tasks on the grid : late job binding with lightweight user-level overlay

Independent observations and everyday user experience indicate that performance and reliability of large grid infrastructures may suffer from large and unpredictable variations. In this paper we study the impact of the job queuing time on processing of moldable tasks which are commonly found in larg...

Full description

Bibliographic Details
Main Authors: Mościcki, J. T., Lamanna, M., Sloot, Peter M. A., Bubak, Marian
Other Authors: School of Computer Engineering
Format: Journal Article
Language:English
Published: 2013
Online Access:https://hdl.handle.net/10356/96035
http://hdl.handle.net/10220/10124
_version_ 1826118223827828736
author Mościcki, J. T.
Lamanna, M.
Sloot, Peter M. A.
Bubak, Marian
author2 School of Computer Engineering
author_facet School of Computer Engineering
Mościcki, J. T.
Lamanna, M.
Sloot, Peter M. A.
Bubak, Marian
author_sort Mościcki, J. T.
collection NTU
description Independent observations and everyday user experience indicate that performance and reliability of large grid infrastructures may suffer from large and unpredictable variations. In this paper we study the impact of the job queuing time on processing of moldable tasks which are commonly found in large-scale production grids. We use the mean value and variance of makespan as the quality of service indicators. We develop a general task processing model to provide a quantitative comparison between two models: early and late job binding in a user-level overlay applied to the EGEE Grid infrastructure. We find that the late-binding model effectively defines a transformation of the distribution of makespan according to the Central Limit Theorem. As demonstrated by Monte Carlo simulations using real job traces, this transformation allows to substantially reduce the mean value and variance of makespan. For certain classes of applications task granularity may be adjusted such that a speedup of an order of magnitude or more may be achieved. We use this result to propose a general strategy for managing access to resources and optimization of workload based on Ganga and DIANE user-level overlay tools. Key features of this approach include: a late-binding scheduler, an ability to interface to a wide range of distributed systems, an ability to extend and customize the system to cover application-specific scheduling and processing patterns and finally, ease of use and lightweight deployment in the user space. We discuss the impact of this approach for some practical applications where efficient processing of many tasks is required to solve scientific problems.
first_indexed 2024-10-01T04:39:52Z
format Journal Article
id ntu-10356/96035
institution Nanyang Technological University
language English
last_indexed 2024-10-01T04:39:52Z
publishDate 2013
record_format dspace
spelling ntu-10356/960352020-05-28T07:18:33Z Processing moldable tasks on the grid : late job binding with lightweight user-level overlay Mościcki, J. T. Lamanna, M. Sloot, Peter M. A. Bubak, Marian School of Computer Engineering Independent observations and everyday user experience indicate that performance and reliability of large grid infrastructures may suffer from large and unpredictable variations. In this paper we study the impact of the job queuing time on processing of moldable tasks which are commonly found in large-scale production grids. We use the mean value and variance of makespan as the quality of service indicators. We develop a general task processing model to provide a quantitative comparison between two models: early and late job binding in a user-level overlay applied to the EGEE Grid infrastructure. We find that the late-binding model effectively defines a transformation of the distribution of makespan according to the Central Limit Theorem. As demonstrated by Monte Carlo simulations using real job traces, this transformation allows to substantially reduce the mean value and variance of makespan. For certain classes of applications task granularity may be adjusted such that a speedup of an order of magnitude or more may be achieved. We use this result to propose a general strategy for managing access to resources and optimization of workload based on Ganga and DIANE user-level overlay tools. Key features of this approach include: a late-binding scheduler, an ability to interface to a wide range of distributed systems, an ability to extend and customize the system to cover application-specific scheduling and processing patterns and finally, ease of use and lightweight deployment in the user space. We discuss the impact of this approach for some practical applications where efficient processing of many tasks is required to solve scientific problems. 2013-06-10T07:09:23Z 2019-12-06T19:24:45Z 2013-06-10T07:09:23Z 2019-12-06T19:24:45Z 2011 2011 Journal Article Mościcki, J. T., Lamanna, M., Bubak, M., & Sloot, Peter M. A. (2011). Processing moldable tasks on the grid : late job binding with lightweight user-level overlay. Future generation computer systems, 27(6), 725-736. https://hdl.handle.net/10356/96035 http://hdl.handle.net/10220/10124 10.1016/j.future.2011.02.002 en Future generation computer systems © 2011 Elsevier B.V.
spellingShingle Mościcki, J. T.
Lamanna, M.
Sloot, Peter M. A.
Bubak, Marian
Processing moldable tasks on the grid : late job binding with lightweight user-level overlay
title Processing moldable tasks on the grid : late job binding with lightweight user-level overlay
title_full Processing moldable tasks on the grid : late job binding with lightweight user-level overlay
title_fullStr Processing moldable tasks on the grid : late job binding with lightweight user-level overlay
title_full_unstemmed Processing moldable tasks on the grid : late job binding with lightweight user-level overlay
title_short Processing moldable tasks on the grid : late job binding with lightweight user-level overlay
title_sort processing moldable tasks on the grid late job binding with lightweight user level overlay
url https://hdl.handle.net/10356/96035
http://hdl.handle.net/10220/10124
work_keys_str_mv AT moscickijt processingmoldabletasksonthegridlatejobbindingwithlightweightuserleveloverlay
AT lamannam processingmoldabletasksonthegridlatejobbindingwithlightweightuserleveloverlay
AT slootpeterma processingmoldabletasksonthegridlatejobbindingwithlightweightuserleveloverlay
AT bubakmarian processingmoldabletasksonthegridlatejobbindingwithlightweightuserleveloverlay