ABSTRACT
Web content caching is recognized as an effective mechanism to decrease server load, network traffic, and user-perceived latency. An HTTP compliant cache associates with each cached object an expiration time calculated according to directives set by the object's origin server. The cache incurs a miss when it has no cached copy of a requested object or when the existing copy had expired (is not fresh). Upon a miss, the cache needs to fetch or validate a copy through exchanges with another cache with a fresh copy or the origin server. Thus, misses generate traffic and prolong service times.
Caches are deployed as proxies, reverse proxies, and hierarchically and as a result, caches often serve other caches. As this happens, content age at higher-level caches, in addition to availability and freshness, emerges as a performance factor. The age of a cached copy of an object is the elapsed time since fetched from the respective origin. Fresh cached copies of the same object can have different ages and older copies typically expire sooner. Therefore, a proxy cache would suffer a higher miss rate if it receives older objects (e.g., from a reverse-proxy cache). Similarly, reverse-proxy caches that serve proxy-caches receive more requests than an origin server would have received. We refer to the increase in miss rate due to age as the age penalty. We use trace-based simulations to measure the extent of the age penalty for content served by content delivery networks and large caches. Even though the age penalty had not been considered previously, we demonstrate that it can be significant, and moreover, can highly vary under different practices.
- {1} Akamai. http://www.akamai.com.Google Scholar
- {2} T. Berners-Lee, R. Fielding, and H. Frystyk. Hypertext Transfer Protocol--HTTP/1.0. RFC 1945, MIT/LCS, May 1996. Google Scholar
- {3} E. Cohen, E. Halperin, and H. Kaplan. Performance aspects of distributed caches using TTL-based consistency. Manuscript, 2000.Google Scholar
- {4} E. Cohen and H. Kaplan. Aging through cascaded caches: performance issues in the distribution of web content. Manuscript, 2000.Google Scholar
- {5} R. Fielding, J. Gettys, J. Mogul, H. Frystyk, L. Masinter, and T. Leach, P. Berners-Lee. Hypertext Transfer Protocol--HTTP/1.1. RFC 2616, ISI, June 1999. Google Scholar
- {6} A Distributed Testbed for National Information Provisioning. http://www.ircache.net.Google Scholar
- {7} J. C. Mogul. Errors in timestamp-based HTTP header values. Technical Report 99/3, Compaq Western Research Lab, December 1999.Google Scholar
- {8} M. Nottingham. Optimizing object freshness controls in Web caches. In The 4th International Web Caching Workshop , 1999.Google Scholar
- {9} M. Nottingham. On defining a role for demand-driven surrogate origin servers. In The 5th International Web Caching and Content Delivery Workshop, 2000.Google Scholar
- {10} Digital Island (Sandpiper). http://www.sandpiper.com.Google Scholar
- {11} Squid internet object cache. http://squid.nlanr.net/Squid.Google Scholar
Index Terms
- The age penalty and its effect on cache performance
Recommendations
High performance cache replacement using re-reference interval prediction (RRIP)
ISCA '10Practical cache replacement policies attempt to emulate optimal replacement by predicting the re-reference interval of a cache block. The commonly used LRU replacement policy always predicts a near-immediate re-reference interval on cache hits and ...
High performance cache replacement using re-reference interval prediction (RRIP)
ISCA '10: Proceedings of the 37th annual international symposium on Computer architecturePractical cache replacement policies attempt to emulate optimal replacement by predicting the re-reference interval of a cache block. The commonly used LRU replacement policy always predicts a near-immediate re-reference interval on cache hits and ...
Comments