T he Web's growth has transformed communications and business services such that speed, accuracy, and availability of network-delivered content has become absolutely critical-both on their own terms and in terms of measuring Web performance. Proxy servers partially address the need for rapid content delivery by providing multiple clients with a shared cache location. In this context, if a requested object exists in a cache (and the cached version has not expired), clients get a cached copy, which typically reduces delivery time. Web caching has three primary benefits. First, it reduces bandwidth consumption, network congestion, and network traffic because it stores the frequently requested content closer to clients. Second, it reduces external latency (the time required to transfer objects from the origin server to proxy servers) because it delivers cached objects from the proxy servers. Finally, caching improves reliability because clients can obtain a cached copy even if the remote server is unavailable. Using a shared proxy cache, however, has two significant drawbacks: If the proxy is not properly updated, a client might receive stale data, and, as the number of clients grows, origin servers typically become bottlenecks. When numerous users access a Web site simultaneously-such as when "flash crowds" 1 flooded popular news sites with requests in the wake of the September 2001 terrorist attack in the US-serious caching problems result and sites typically become unavailable. Researchers have widely considered content delivery networks to be an effective solution to reducing these disadvantages. 2,3 CDNs act as trusted overlay networks that offer high-performance delivery of common Web objects, static data, and rich multimedia content by distributing content load among servers that are close to the clients. 4,5 CDN benefits include reduced origin server load, reduced latency for end users, and increased throughput. CDNs can also improve Web scalability and disperse flash-crowd events. Here we offer an overview of the CDN architecture and popular CDN service providers. CDN Overview CDNs first emerged in 1998 6 to address the fact that the Web was not designed to handle large content transmissions over long distances. 7,8 According to Network World Fusion (www.nwfusion.com), about 2,500 companies now use CDNs. In the US alone, for example, Storigen Systems (www.storigen.com) estimates that the CDN market generated US$905 million in 2000 and will reach US$12 billion by 2007. Proxies and CDNs essentially address two different issues. ISPs use proxies to store the most frequently or most recently requested content; they're designed to work on a local basis. Web servers use CDNs to store content specified by the network administrator. CDNs can improve access to content that is typically uncacheable by caching proxies, including secured content, streaming content, and dynamic content. 8
