Static caching in Web servers Export

@proceedings{citeulike:1165050, abstract = {This paper studies caching in primary Web servers. We use log files from four Web servers to analyze the performance of various proposed cache policies for Web servers: LRU-threshold, LFU, LRU-SIZE, LRU-MIN, LRU-k-threshold and the Pitkow/Recker (1994) policy. Web document access patterns change very slowly. Based on this fact, we propose and evaluate static caching, a novel cache policy for Web servers. In static caching, the set of documents kept in the cache is determined periodically by analyzing the request log file for the previous period. The cache is filled with documents to maximize cache performance provided document access patterns do not change. The set of cached documents remains constant during the period. Surprisingly, this simple policy results in high cache performance, especially for small cache sizes. Unlike other policies, static caching incur no CPU overhead and does not suffer from memory fragmentation}, author = {Tatarinov, I. and Rousskov, A. and Soloviev, V.}, citeulike-article-id = {1165050}, citeulike-linkout-0 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=623344}, journal = {Computer Communications and Networks, 1997. Proceedings., Sixth International Conference on}, keywords = {caching}, pages = {410--417}, posted-at = {2008-04-15 05:04:17}, priority = {2}, title = {Static caching in Web servers}, url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=623344}, year = {1997} }

TY - CONF ID - citeulike:1165050 L3 - citeulike-article-id:1165050 N2 - This paper studies caching in primary Web servers. We use log files from four Web servers to analyze the performance of various proposed cache policies for Web servers: LRU-threshold, LFU, LRU-SIZE, LRU-MIN, LRU-k-threshold and the Pitkow/Recker (1994) policy. Web document access patterns change very slowly. Based on this fact, we propose and evaluate static caching, a novel cache policy for Web servers. In static caching, the set of documents kept in the cache is determined periodically by analyzing the request log file for the previous period. The cache is filled with documents to maximize cache performance provided document access patterns do not change. The set of cached documents remains constant during the period. Surprisingly, this simple policy results in high cache performance, especially for small cache sizes. Unlike other policies, static caching incur no CPU overhead and does not suffer from memory fragmentation JF - Computer Communications and Networks, 1997. Proceedings., Sixth International Conference on EP - 417 TI - Static caching in Web servers SP - 410 KW - caching AU - Tatarinov, I AU - Rousskov, A AU - Soloviev, V PY - 1997/// UR - http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=623344 ER -