This paper presents a study of web content adaptation to improve server overload performance, as well as an implementation of a web content adaptation software prototype. When the request rate on a web server increases beyond server capacity, the server becomes overloaded and unresponsive. The TCP listen queue of the server's socket overflows exhibiting a drop-tail behavior. As a result, clients experience service outages. Since clients typically issue multiple requests over the duration of a session with the server, and since requests are dropped indiscriminately, all clients connecting to the server at overload are likely to experience connection failures, even though there may be enough capacity on the server to deliver all responses properly for a subset of clients. In this paper, we propose to resolve the overload problem by adapting delivered content to load conditions to alleviate overload. The premise is that successful delivery of a less resource intensive content under overlo...

The conventional way to notify the processor of a network event is through interrupts. Interrupts are more e#ective than polling for devices that generate unpredictable and infrequentevents. Interrupts, however, incur a high overhead both during and after the interrupt handling because modern superscalar processors use long pipelines, out-of-order and speculative execution, and multi-level memory systems, all of which tend to increase the interrupt overhead in terms of clock cycles. In this paper we attempt to reduce the network interface receive-overhead byintroducing a hybrid scheme #HIP# that uses interrupts under low network load conditions, and polling when the arriving network tra#c forms a highbandwidth packet stream. Additionally, the polling period is adjusted dynamically based on the rate of the arriving packet stream. Trace-driven simulations show that the average receive-overhead per packet is signi#cantly reduced compared to the pure interrupt-based mechanism. As a result of the polling operation, however, the average receive-latency per packet is increased. The #ne selection of the HIP parameters can set the trade-o# between decreased overhead and increased latency to the appropriate operating point. HIP maybe appropriate for high-throughput network interfacing in systems with a heavy multimedia or other stream-based workload.