Deadlock-Free TCP Over High- Speed Internet
نویسندگان
چکیده
In this paper, we consider TCP throughput deadlock problems caused by an interplay between the Nagle algorithm, delayed acknowledgment algorithm, and several implementation details. For some combinations of send and receive buffers, a TCP sender cannot send more segments due to the Nagle algorithm and, at the same time, a TCP receiver cannot acknowledge more segments received due to the delayed acknowledgment algorithm. The outcome is a deadlock, which can only be resolved by the receiver's timer. Although the deadlock can take place in any types of networks, it is generally more difficult to ensure deadlock-free connections on high-speed networks. Moreover, the impact is much more significant on high-speed networks, and the deadlock renders the connection practically unusable. Several straightforward solutions, such as turning off the Nagle algorithm and acknowledging every segment, have been proposed; however, they reintroduce the same problems that they were initially designed for. In this paper we propose an adaptive acknowledgment algorithm (A 3) to eliminate throughput deadlocks on the receiver side while preserving the original intent of employing the Nagle algorithm and delayed acknowledgment. An A 3-receiver uses the same delayed acknowledgment as before, but with an additional component to adaptively
منابع مشابه
A throughput deadlock-free TCP for high-speed Internet
Throughput deadlocks were observed when TCP was operated on high-speed networks. This deadlock problem is caused by the interaction of the sender-side and receiverside silly window syndrome avoidance algorithms, because a TCP connection’s Maximum Segment Size is no longer small on high-speed Internet when compared with the send and receive socket buffer sizes. In this paper we propose a new Con...
متن کاملDeadlock situations in TCP over ATM
The implementation of protocols, such as TCP/IP, and their integration into the operating system environment is very decisive for protocol performance. Putting TCP on high-speed networks, e.g. ATM, with large maximum transmission units causes the TCP maximum segment size to be relatively large. What Nagle’s consider “small” is not small anymore. We report on TCP/IP throughput performance measur...
متن کاملCan high-speed transport protocols be deployed on the Internet? : Evaluation through experiments on JGNII
While a variety of high-speed transport protocols have been proposed to meet the requirement of high throughput data transfer over fast long-distance networks, less attention has been paid to the problems involved when those transport protocols are deployed in heterogeneously shared network environments like the global Internet. We are investigating several high-speed transport protocols: HighS...
متن کاملEffects of Applying High Speed Congestion Control Algorithms in the Internet
In recent years, many high speed congestion control algorithms have been proposed for utilizing network pipes with large bandwidth-delay product, and some of them have also been implemented in popular operating systems. Since the Internet is and tends to be lightly-loaded and there are many bandwidth-greedy applications, high speed congestion control algorithms may be used by many flows of the ...
متن کاملHigh Speed Internet Access Using Satellite-Based DVB Networks
Digital Video Broadcasting (DVB) provides the opportunity for high-speed Internet delivery direct to user’s homes and offices. Most applications require full duplex communication, and the return path from the user to the Internet will be provided using lower speed terrestrial connections. Two challenges are presented when using DVB for high-speed Internet access: the poor performance of TCP ove...
متن کامل