Cooperative Caching Middleware

Summary of the project Unlike parallel machines cluster based servers donít have hardware mechanisms to share memory across the individual nodes. Independent memory management on cluster based servers, reduces its performance and limits its scalability. 

Cooperative caching can be used to co-manage clusterís memory by using software communication to allow nodes to access each others memory. We have reexamined the question of whether a server built on top of a generic block-based cooperative caching algorithm can perform competitively with locality-conscious servers. Specifically, we have compared the performance of a cooperative caching-based web server against L2S, a highly optimized locality-conscious server. Our results show that by modifying the replacement algorithm of traditional cooperative caching algorithms, we can achieve much of the performance provided by locality-conscious servers.

People Francisco M. Cuenca-Acuna
Xiaoyan Li
Thu D. Nguyen
Publications "Cooperative Caching Middleware for Cluster-Based Servers".  F. M. Cuenca-Acuna and T. D. Nguyen.  In Proceedings of the 10th International Symposium on High Performance Distributed Computing (HPDC), August 2001.
[PostScript, PDF, BibTeX entry, Original TR]