Achieving Fairness-Aware Two-level Scheduling for Heterogeneous Distributed Systems

0
443

Achieving Fairness-Aware Two-level Scheduling for Heterogeneous Distributed Systems

Abstract

In a heterogeneous distributed system consisting of different types of computing platforms such as supercomputers, grids, and clouds, a two-level scheduling approach can be used to effectively distribute platform resources to first-level users, and map user tasks in nodes for each second-level platform to execute multi-task applications. Achieving Fairness-aware Two-level Scheduling for Heterogeneous Distributed Systems The system service providers should consider fairness among multiple users as well as system efficiency when scheduling heterogeneous resources.

Introduction

Achieving Fairness-Aware Two-level Scheduling for Heterogeneous Distributed Systems We present three first-level resource allocation policies of a first policy on provider affinity, a first policy on application affinity, and a round-robin policy based on platform affinity, and two second-level policy mapping tasks of the most affected first policy and a round-robin policy based on co-runner affinity.

System Configuration

H/W System Configuration
Speed                   : 1.1 GHz
RAM                      : 256 MB(min)
Hard Disk              : 20 GB
Floppy Drive          : 1.44 MB
Key Board             : Standard Windows Keyboard
Mouse                  : Two or Three Button Mouse
Monitor                : SVGA
S/W System Configuration

Platform                     :  cloud computing

Operating system       : Windows Xp,7,
Server                       : WAMP/Apache
Working on                : Browser Like Firefox, IE

Conclusion

In this paper, we studied fairness in two-level scheduling for heterogeneous distributed computing systems to support multiple multi-task applications with different resource requirements. We discussed three first-level resource allocation policies and two second-level task mapping policies. We have shown that the system’s fairness is mostly affected by which resource allocation policy is used at the first level, because the decision at the first level limits possible co-runner combinations in task mapping.