Sizing multi-space in heap for application isolation

Authors:
Kewei Sun;Ying Li;Matt Hogstrom;Ying Chen
Affiliations:
IBM China Research Laboratory, Beijing, P.R. China;IBM China Research Laboratory, Beijing, P.R. China;IBM Software Group, Durham, NC;IBM China Research Laboratory, Beijing, P.R. China
Venue:
Companion to the 21st ACM SIGPLAN symposium on Object-oriented programming systems, languages, and applications
Year:
2006

Citing 2
Cited 2

Application isolation in the Java Virtual Machine

OOPSLA '00 Proceedings of the 15th ACM SIGPLAN conference on Object-oriented programming, systems, languages, and applications
TPC-W: A Benchmark for E-Commerce

IEEE Internet Computing

Control theory for principled heap sizing

Proceedings of the 2013 international symposium on memory management
An equation-based Heap Sizing Rule

Performance Evaluation

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we present a sizing algorithm using resonant model based on a proposed novel heap structure - multiple spaces in heap. Experiments using the algorithm and selected GC method show that, in average, the performance overhead from managing multi-spaces in heap can be reduced from 8.38% to 4.25% when CPU utilization of server is 40% and from 42.42% to 3.52% when CPU utilization of the server is 70%.