University of Houston
Department of Computer Science
In partial fulfillment of the Requirements for the Degree of
Master of Science
Roman Reznik
will defend his thesis
Performance Data Based Scheduling Of Jobs In Distributed Computing
Abstract
There is a move away from a mainframe computing model to distributing computing. In this case, a job is split in fragments that are distributed among available network resources. With this, there is an issue that needs to be addressed. The issue is how to utilize available resources efficiently. This is the focus area of my thesis.
I will present a distributed application that I have designed and implemented that allows distributing jobs to available network machines. It collects performance data on workstations and utilizes this information to make its scheduling decisions. I also compare my algorithm with some other approaches. The application I implemented can work on two operating systems, Linux and Windows, and its architecture supports more operating systems.
Date: Wednesday, August 7, 2002
Time: 3:00 PM
Place: 550-PGH
Faculty, students, and the general public are invited.
Thesis Advisor: Dr. Stephen Huang