Improving Object Cache Performance through Selective Placement

S. Hosseini-Khayat (UAE)

Keywords

Selective cache, cache replacement, web caching.

Abstract

Distributed systems greatly benefit from caching. Caching data objects of variable size and cost poses interesting ques tions that have been researched for the past ten years. As a result, a few good algorithms have come to the fore. These algorithms make effective decisions in selecting cache ob jects for removal. However, they make no decision about the suitability of a new object for placement into the cache. We show that “selective placement” can add further im provement to these algorithms when a request pattern con sists of frequent references to a working set of objects in terspersed with isolated references to less popular objects. The key idea is to avoid indiscriminate caching, and to weigh the benefits of caching an object against the cost of removing other objects. This paper describes a sim ple enhancement to a well-known web caching algorithm (GreedyDual-Size) to make it a selective algorithm. It is shown by simulation that the performance gain can be sub stantial. The suggested methodology can be applied to sim ilar algorithms.

Important Links:



Go Back