TCP Optimization through FEC, ARQ and Transmission Power Tradeoffs

TCP performance degrades when end-to-end connections extend over wireless connections-links which are characterized by high bit error rate and intermittent connectivity. Such link characteristics can significantly degrade TCP performance as the TCP sender assumes wireless losses to be congestion losses resulting in unnecessary congestion control actions. Link errors can be reduced by increasing transmission power, code redundancy (FEC) or number of retransmissions (ARQ). But increasing power costs resources, increasing code redundancy reduces available channel bandwidth and increasing persistency increases end-to-end delay. The paper proposes a TCP optimization through proper tuning of power management, FEC and ARQ in wireless environments (WLAN and WWAN). In particular, we conduct analytical and numerical analysis taking into "wireless-aware" TCP) performance under different settings. Our results show that increasing power, redundancy and/or retransmission levels always improves TCP performance by reducing link-layer losses. However, such improvements are often associated with cost and arbitrary improvement cannot be realized without paying a lot in return. It is therefore important to consider some kind of net utility function that should be optimized, thus maximizing throughput at the least possible cost.

The War Between Mice and Elephants

Recent measurement based studies reveal that most of the Internet connections are short in terms of the amount of traffic they carry (mice), while a small fraction of the connections are carrying a large portion of the traffic (elephants). A careful study of the TCP protocol shows that without help from an Active Queue Management (AQM) policy, short connections tend to lose to long connections in their competition for bandwidth. This is because short connections do not gain detailed knowledge of the network state, and therefore they are doomed to be less competitive due to the conservative nature of the TCP congestion control algorithm. Inspired by the Differentiated Services (Diffserv) architecture, we propose to give preferential treatment to short connections inside the bottleneck queue, so that short connections experience less packet drop rate than long connections. This is done by employing the RIO (RED with In and Out) queue management policy which uses different drop functions for different classes of traffic. Our simulation results show that: (1) in a highly loaded network, preferential treatment is necessary to provide short TCP connections with better response time and fairness without hurting the performance of long TCP connections; (2) the proposed scheme still delivers packets in FIFO manner at each link, thus it maintains statistical multiplexing gain and does not misorder packets; (3) choosing a smaller default initial timeout value for TCP can help enhance the performance of short TCP flows, however not as effectively as our scheme and at the risk of congestion collapse; (4) in the worst case, our proposal works as well as a regular RED scheme, in terms of response time and goodput.

Connection Scheduling in Web Servers

Under high loads, a Web server may be servicing many hundreds of connections concurrently. In traditional Web servers, the question of the order in which concurrent connections are serviced has been left to the operating system. In this paper we ask whether servers might provide better service by using non-traditional service ordering. In particular, for the case when a Web server is serving static files, we examine the costs and benefits of a policy that gives preferential service to short connections. We start by assessing the scheduling behavior of a commonly used server (Apache running on Linux) with respect to connection size and show that it does not appear to provide preferential service to short connections. We then examine the potential performance improvements of a policy that does favor short connections (shortest-connection-first). We show that mean response time can be improved by factors of four or five under shortest-connection-first, as compared to an (Apache-like) size-independent policy. Finally we assess the costs of shortest-connection-first scheduling in terms of unfairness (i.e., the degree to which long connections suffer). We show that under shortest-connection-first scheduling, long connections pay very little penalty. This surprising result can be understood as a consequence of heavy-tailed Web server workloads, in which most connections are small, but most server load is due to the few large connections. We support this explanation using analysis.