Using Parallel Program Characteristics in Dynamic Processor Allocation Policies

In multiprocessors a parallel program's execution time is directly innuenced by the number of processors it is allocated. The problem of scheduling parallel programs in a multiprogrammed environment becomes one of determining how to best allocate processors to the diierent simultaneously executing programs in order to minimize mean response time. In this paper we address the problem of how many processors to allocate to each of the executing parallel jobs by examining the following questions: 1. Is allocating processors equally among all jobs (equipartitioning) a desirable property of a scheduling algorithm? 2. Does using information about the service demand of parallel jobs signiicantly reduce mean response time? 3. Does using information about the eeciency with which parallel jobs execute sig-niicantly reduce mean response time? 4. Does allocating each job a number of processors corresponding to the knee of the execution time { eeciency curve signiicantly reduce mean response time? 5. What are the desirable properties of a scheduler that is designed to minimize mean response time? The main contributions of this paper are: a rst-order understanding of how processing power should be dynamically allocated to jobs, a new family of algorithms for dynamic processor allocation and a rough quantiication of the beneets that may be realized by properly utilizing job characteristics when making processor allocation decisions. We believe that these new algorithms can be combined with recently demonstrated techniques for obtaining suuciently accurate runtime estimates of job eeciencies to improve scheduler implementations for multiprogrammed multiproces-sors.