A study of page replacement performance in garbage collection heap

Abstract

Large number of page-faults can severely degrade the performance of any system. While much attention has been paid on the virtual memory space of an entire process, the paging behavior of one particular memory segment has not been reported. Unlike the static behavior in most of the memory segments, the heap segment has unique characteristics closely related to its memory management scheme. First, this paper presents a thorough study on the effect of heap page-faults on the performance of Kaffe JVM version 1.0.5 and the Kaffe Java virtual machine (JVM) with the modified buddy system. Second, a modified least recently used (mLRU) is proposed to improve the performance of the LRU page-replacement policy. Four different page-replacement policies, first-in-first-out (FIFO), Random, LRU and mLRU, are used to study the performance of each JVM. Third, the Java applications used in this study are SPECjvm98 benchmark suite. These programs represent real-world workload and are highly dynamic memory intensive. Fourth, an instrumented Kaffe JVM is used to generate memory traces. Then, a simulator is used to analyze and reconstruct the heap as the benchmark programs are executed. Finally, this study has shown that the modified buddy system has less page-fault occurrences in six out of eight applications. The improvement can be up to 74%. Moreover, the proposed mLRU can improve the performance up to 68.2%.