Towards critical region reliability support for Grid workflows

Authors:
Guo-Zhong Tian;Jiong Yu;Jing-Sha He
Affiliations:
College of Computer Science and Technology, Beijing University of Technology, Beijing 100124, China and School of Information Science and Engineering, XinJiang University, Urumqi 830046, China;School of Computer Science and Technology, Beijing Institute of Technology, Beijing 100081, China and School of Information Science and Engineering, XinJiang University, Urumqi 830046, China;College of Computer Science and Technology, Beijing University of Technology, Beijing 100124, China
Venue:
Journal of Parallel and Distributed Computing
Year:
2009

Citing 5
Cited 1

Improving the performance of time-constrained workflow processing

Journal of Systems and Software
Performance Modeling and Prediction of Nondedicated Network Computing

IEEE Transactions on Computers
A high performance, low complexity algorithm for compile-time task scheduling in heterogeneous systems

Parallel Computing - Heterogeneous computing
MJSA: Markov job scheduler based on availability in desktop grid computing environment

Future Generation Computer Systems
NP-complete scheduling problems

Journal of Computer and System Sciences

LDAG: a new model for grid workflow applications

WSEAS Transactions on Computers

Quantified Score

Hi-index	0.00

Visualization

Abstract

Many Directed Acyclic Graph (DAG)-based workflow applications often have timing constraints such that each processing of a workflow needs to be finished within its deadline. There have been some studies to improve the performance of time-constrained workflow processing. Few of them, however, have taken into account the fact that successful execution of a workflow within its deadline is also affected by the 'normal state' and 'abnormal state' of Grid resources occurring in successive turns and by the relative difference in execution time between tasks on the critical path and tasks on the non-critical path. To solve the problem, we first put forward new some conceptions, such as the critical region and the reliability of the critical region, and then present a scheduling algorithm. In terms of the finite-state continuous-time Markov process, the algorithm selects a resource combination scheme which has the lowest expenditure under a certain credit level of the resource reliability on the critical path in the DAG-based workflow. The simulation shows the validity of theory analysis.