Predicting Running Time of Grid Tasks based on CPU Load Predictions

Authors:
Yuanyuan Zhang;Wei Sun;Yasushi Inoguchi
Affiliations:
Graduate School of Information Science, Japan Advanced Institute of Science and Technology, 1-1 Asahidai, Nomi, Ishikawa, 923-1292 Japan. yuanyuan@jaist.ac.jp;Graduate School of Information Science, Japan Advanced Institute of Science and Technology, 1-1 Asahidai, Nomi, Ishikawa, 923-1292 Japan. sun-wei@jaist.ac.jp;Center for Information Science, Japan Advanced Institute of Science and Technology, 1-1 Asahidai, Nomi, Ishikawa, 923-1292 Japan. inoguchi@jaist.ac.jp
Venue:
GRID '06 Proceedings of the 7th IEEE/ACM International Conference on Grid Computing
Year:
2006

Citing 10
Cited 8

The grid: blueprint for a new computing infrastructure

The grid: blueprint for a new computing infrastructure
Host load prediction using linear models

Cluster Computing
Online Prediction of the Running Time of Tasks

Cluster Computing
Predicting Queue Times on Space-Sharing Parallel Computers

IPPS '97 Proceedings of the 11th International Symposium on Parallel Processing
A Prediction-Based Real-Time Scheduling Advisor

IPDPS '02 Proceedings of the 16th International Parallel and Distributed Processing Symposium
A Historical Application Profiler for Use by Parallel Schedulers

IPPS '97 Proceedings of the Job Scheduling Strategies for Parallel Processing
Size-Based Scheduling Policies with Inaccurate Scheduling Information

MASCOTS '04 Proceedings of the The IEEE Computer Society's 12th Annual International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunications Systems
Predicting application run times with historical information

Journal of Parallel and Distributed Computing
Conservative Scheduling: Using Predicted Variance to Improve Scheduling Decisions in Dynamic Environments

Proceedings of the 2003 ACM/IEEE conference on Supercomputing
CPU Load Predictions on the Computational Grid *

CCGRID '06 Proceedings of the Sixth IEEE International Symposium on Cluster Computing and the Grid

Load prediction using hybrid model for computational grid

GRID '07 Proceedings of the 8th IEEE/ACM International Conference on Grid Computing
Platform-independent modeling and prediction of application resource usage characteristics

Journal of Systems and Software
Cost-Minimizing Scheduling of Workflows on a Cloud of Memory Managed Multicore Machines

CloudCom '09 Proceedings of the 1st International Conference on Cloud Computing
TRACON: interference-aware scheduling for data-intensive applications in virtualized environments

Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis
Decentralized proactive resource allocation for maximizing throughput of P2P Grid

Journal of Parallel and Distributed Computing
An effective data aggregation based adaptive long term CPU load prediction mechanism on computational grid

Future Generation Computer Systems
A dynamic and adaptive load balancing strategy for parallel file system with large-scale I/O servers

Journal of Parallel and Distributed Computing
Interference and locality-aware task scheduling for MapReduce applications in virtual clusters

Proceedings of the 22nd international symposium on High-performance parallel and distributed computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

The ability to accurately predict task running time is of great importance for interactive applications and scheduling algorithms which need to determine how to use time-shared resources in a dynamic grid environment. In this paper we present and evaluate a new method to predict the running time of tasks in a grid. The prediction of task running time is based on a novel CPU load prediction method and is calculated from predictions of CPU load. We conducted evaluations using more than 10,000 randomized testcases run on load traces sampled from 39 heterogeneous machines. Our experimental results demonstrate that both our CPU load prediction method and task running time prediction strategy outperform significantly the widely used AR(16) load prediction model and the task running-time prediction method based on this model.