Applications that require good network performance often use parallel TCP streams and TCP modifications to improve the effectiveness of TCP. If the network bottleneck is fully utilized, this approach boosts throughput by unfairly stealing bandwidth from competing TCP streams. Improving the effectiveness of TCP is easy, but improving effectiveness while maintaining fairness is difficult. In this paper, we describe an approach we implemented that uses a long virtual round trip time in combination with parallel TCP streams to improve effectiveness on underutilized networks. Our approach prioritizes fairness at the expense of effectiveness when the network is fully utilized. We compared our approach with standard parallel TCP over a wide-area network, and found that our approach preserves effectiveness and is fairer to competing traffic than standard parallel TCP.

In this paper, we show that end-host based congestion prediction is more accurate than previously characterized. However, it may not be possible to entirely eliminate the uncertainties in congestion prediction. To address these uncertainties, we propose Probabilistic Early Response TCP (PERT). PERT emulates the behavior of AQM/ECN, in the congestion response function of end-hosts. We present fluid-flow analysis of PERT/RED and PERT/PI, versions of PERT that emulate router-based RED and PI controllers. Our analysis shows that PERT/RED has better stability behavior than router-based RED. We also present results from ns-2 simulations to show the practical feasibility of PERT. The scheme presented here is general and can be used for emulating other AQM algorithms.

One of TCP's critical tasks is to determine which packets are lost in the network, as a basis for control actions (ow control and packet retransmission). Modern TCP implementations use two mechanisms: timeout, and fast retransmit. Detection via timeout is necessarily a timeconsuming operation; fast retransmit, while much quicker, is only effective for a small fraction of packet losses. In this paper we consider the problem of packet loss detection in TCP more generally. We concentrate on the fact that TCP's control actions are necessarily triggered by inference of packet loss, rather than conclusive knowledge. This suggests that one might analyze TCP's packet loss detection in a standard inferencing framework based on probability of detection and probability of false alarm. This paper makes two contributions to that end: First, we study an example of more general packet loss inference, namely optimal Bayesian packet loss detection based on round trip time. We show that for long-lived ows, it is frequently possible to achieve high detection probability and low false alarm probability based on measured round trip time. Second, we construct an analytic performance model that incorporates general packet loss inference into TCP. We show that for realistic detection and false alarm probabilities (as are achievable via our Bayesian detector) and for moderate packet loss rates, the use of more general packet loss inference in TCP can improve throughput by as much as 25%.

Abstract. Modern cellular channels in 3G networks incorporate sophisticated power control and dynamic rate adaptation which can have a significant impact on adaptive transport layer protocols, such as TCP. Though there exists studies that have evaluated the performance of TCP over such networks, they are based solely on observations at the transport layer and hence have no visibility into the impact of lower layer dynamics, which are a key characteristic of these networks. In this work, we present a detailed characterization of TCP behavior based on cross-layer measurement of transport, as well as RF and MAC layer parameters. In particular, through a series of active TCP/UDP experiments and measurement of the relevant variables at all three layers, we characterize both, the wireless scheduler in a commercial CDMA2000 network and its impact on TCP dynamics. Somewhat surprisingly, our findings indicate that the wireless scheduler is mostly insensitive to channel quality and sector load over short timescales and is mainly affected by the transport layer data rate. Furthermore, we empirically demonstrate the impact of the wireless scheduler on various TCP parameters such as the round trip time, throughput and packet loss rate. 1

We describe a novel, practical and simple technique to make DNS queries more resistant to poisoning attacks: mix the upper and lower case spelling of the domain name in the query. Fortuitously, almost all DNS authority servers preserve the mixed case encoding of the query in answer messages. Attackers hoping to poison a DNS cache must therefore guess the mixed-case encoding of the query, in addition to all other fields required in a DNS poisoning attack. This increases the difficulty of the attack. We describe and measure the additional protections realized by this technique. Our analysis includes a basic model of DNS poisoning, measurement of the benefits that come from case-sensitive query encoding, implementation of the system for recursive DNS servers, and large-scale real-world experimental evaluation. Since the benefits of our technique can be significant, we have simultaneously made this DNS encoding system a proposed IETF standard. Our approach is practical enough that, just weeks after its disclosure, it is being implemented by numerous DNS vendors. General Terms DNS, DNS poisoning, DNS transaction security, DNS forgery resistance, protocol security, network security, DNS security 1.

A number of designs have been proposed for complementing TCP’s treatment of packet loss as an implicit signal of congestion, with a signal derived from measurements of round-trip times (RTT). The premise of such delay-based congestion estimators (DBCEs) is that congestion is reflected in queueing delays that can be detected by measuring changes in RTT. We conduct a large-scale empirical analysis of real-world TCP connections to evaluate the effectiveness and limitations of five prominent DBCEs. Our findings are that none of the five perform well (correctly indicate congestion before a loss is experienced) for a large percentage of real-world TCP connections. They also often perform poorly by having high rates of false-positive and false-negative estimates of congestion. Further, we find that the connection characteristics that most influence the performance of these DBCEs are so diverse that designing an effective DBCE for all types of connections is still an open research problem. 1 1

Distributed checkpointing is an important concept in providing fault tolerance in distributed systems. In today’s applications, e.g., grid and massively parallel applications, the imposed overhead of taking a distributed checkpoint using the known approaches can often outweigh its benefits due to coordination and other overhead from the processes. This paper presents an innovative approach for distributed checkpointing. In this approach, the checkpoints are obtained using offline analysis based on the application level. During execution, no coordination is required. After presenting our approach, we prove its safety and present a performance analysis of it using stochastic models.

This paper describes an ns-based simulation analysis of TCP Tahoe, Reno, NewReno and SACK congestion control over hybrid wireless and wired networks. We compare the throughput performance between the four TCP versions. Since RTT variation statistics are used by some researchers to distinguish the congestion losses from wireless channel losses, we compute RTT variation statistics under different kinds of simulation topologies such as high-speed wireless last hop, slow wireless backbone with both long router queue length and small queue length. The simulation results show that: (1)the average throughput of SACK and NewReno are slightly higher than those of Tahoe and Reno; (2)simple RTT variation schemes can not always predict congestion from wireless link error well. Moreover they do not work well under all kinds of simulation topologies and background load environments.

Delay-insensitive applications, such as P2P file sharing, generate substantial amounts of traffic and compete with other applications on an equal footing when using TCP. Further, to optimize throughput, such applications open multiple connections. This results in an unfair and potentially poor service for other applications having stringent performance objectives. In this paper, we propose NF-TCP, a TCP variant for P2P and similar background delay-insensitive applications. NF-TCP aims to be submissive to delay-sensitive applications under congestion. It is designed to be network friendly based on a fluid flow model for intermediate queues and uses explicit congestion notification (ECN) for early detection of congestion. Moreover, it exploits the measure of the available bandwidth to be able to aggressively utilize spare capacity. We implemented NF-TCP on Linux and ns-2. Our evaluations of the NF-TCP Linux implementation on ns-2 show that NF-TCP outperforms other network friendly approaches (e.g., LEDBAT, TCP-LP and RAPID). NF-TCP achieves high utilization, fair bandwidth allocation among NF-TCP flows and maintains a small average queue. Our evaluations further demonstrate that with NF-TCP, the available bandwidth can be efficiently utilized for supporting both delay-sensitive and insensitive traffic in a wide

Abstract—Can an end-host running multiple TCP sessions detect not just the occurrence, but also the location of congestion? This paper answers this question through new analytic results on the two underlying technical difficulties: synchronization effects of loss and delay in TCP and distributed hypothesis testing using only local loss and delay data, as well as practical algorithm development and extensive simulations. It presents a Congestion Location Detection algorithm that effectively allows an end host to distributedly detect whether congestion happens in the local access link or in more remote links. This further enables the practical usage of low-priority congestion control protocols. I.