Multiresource malleable task scheduling to minimize response time

Abstract

We present a technique for generalizing previously known results for single resource task systems to multiresource malleable task systems: assuming a system with r resources, we apply a transformation which maps the system into a single resource task system. Our objective is to minimize the average response time. For a large class of heuristics it is shown that, given a heuristic H which is cH-optimal in a single resource system, the proposed transformation yields a cH·r-optimal algorithm for the multiresource system.