UDP-based Data Transfer Research Articles

UDT 플로우 간 공평성 향상을 위한 혼잡도 기반의 가용대역폭 추정 기법

End to end 데이터 전송프로토콜에서 가용대역폭을 정확하게 추정하는 것은 매우 중요하다. UDT (UDP based Data Transfer)는 송신자에서 주기적으로 보낸 패킷 쌍을 이용하여 수신자에서 현재 링크의 최대 전송 가능한 속도 (MTR: Maximum Transfer Rate)를 추정하고 송신자에서 EWMA 알고리즘을 통해 MTR을 결정한다. 가용대역폭의 크기는 MTR과 현재 전송속도 차이로 구하기 때문에 정확한 가용대역폭 추정을 위해서는 정확한 MTR 추정이 우선시된다. 하지만 트래픽 영향으로 인한 혼잡상황에서 다수의 UDT 플로우가 경쟁하는 경우 심각한 공평성 문제를 초래한다. 본 논문에서는 혼잡도를 기반으로 한 MTR 추정 알고리즘을 제안한다. 혼잡도는 병목구간에서 트래픽 영향으로 인한 혼잡상태를 나타내는 상대적인 지수이며 패킷 쌍들의 도착간격을 이용하여 구할 수 있다. 그리고 혼잡도에 따라 EWMA 알고리즘을 세분화함으로써 실제에 근접한 가용대역폭 추정이 가능하다. Ns-2 시뮬레이션 실험 결과 제안기법은 다수의 경쟁플로우가 동일 링크를 점유하는 상황에서 데이터 전송거리에 따라 UDT 보다 확연하게 높은 공평성을 보이는 것을 확인하였다.

UDT 환경에서 혼잡상황 예측 및 패킷손실을 고려한 성능향상 기법

최근 네트워크 기술의 비약적인 발전으로 사용자가 이용할 수 있는 대역폭이 증가하고 있다. 이에 따라 대용량 고속 네트워크에서 보다 신속하고 안정적인 전송기법이 요구되고 있다. UDT(UDP based Data Transfer protocol)는 UDP 기반의 전송 프로토콜이며, 일정 SYN time마다 rate control을 진행함으로써 긴 RTT 환경에서 TCP 보다 두드러진 성능을 보인다. 하지만, NAK 발생시 고정적인 sendInterval의 증가와, 이전 시간의 RTT에 기반한 flow control로 인해 최적의 성능을 기대하기 힘들다. 본 논문에서는 실험에 의한 결과값을 바탕으로 NAK 수신시 RTT 구간에 따라 sendInterval을 조절하는 rate 제어기법을 제시한다. 또한 TCP vegas에 기반하여 네트워크 혼잡을 예측하는 향상된 flow 제어기법을 제시한다. 실제 Testbed를 구성하여 실험한 결과, 각각의 제안기법에 대해 약 20Mbps정도 향상된 throughput이 측정되었다. 또한, 두 기법을 혼합 적용한 결과에서는 최고 26Mbps의 성능 향상을 확인하였다. Recently, the bandwidth available to an end user has been dramatically increasing with the advancing of network technologies. This high-speed network naturally requires faster and/or stable data transmission techniques. The UDT(UDP based Data Transfer protocol) is a UDP based transport protocol, and shows more efficient throughput than TCP in the long RTT environment, with benefit of rate control for a SYN time. With a NAK event, however, it is difficult to expect an optimum performance due to the increase of fixed sendInterval and the flow control based on the previous RTT. This paper proposes a rate control method on following a NAK, by adjusting the sendInterval according to some degree of RTT period which calculated from a set of experimental results. In addition, it suggests an improved flow control method based on the TCP vegas, in order to predict the network congestion afterward. An experimental results show that the revised flow control method improves UDT's throughput about 20Mbps. With combining the rate control and flow control proposed, the UDT throughput can be improved up to 26Mbps in average.

Ultra-rapid UT1 measurement by e-VLBI

Abstract The latency of UT1 measurement with Very Long Baseline Interferometry (VLBI) has been greatly reduced by using e-VLBI technology. VLBI observations on the baseline formed by the Kashima 34-m and the Onsala 20-m radio telescopes achieved ultra-rapid UT1 measurements, where the UT1 result was obtained within 30 min after the end of the observing session. A high speed network and a UDP-based data transfer protocol ‘Tsunami’ assisted the high data rate and long-distance data transfer from Onsala to Kashima. The accuracy of the UT1 value obtained from the 1-h single baseline e-VLBI experiment has been confirmed to be as the same level with the rapid combined solution of Bulletin-A. The newly developed technology is going to be transferred to the regular intensive VLBI sessions, and it is expected to contribute to the improved latency and accuracy of UT1 data.

UDT: UDP-based data transfer for high-speed wide area networks

In this paper, we summarize our work on the UDT high performance data transport protocol over the past four years. UDT was designed to effectively utilize the rapidly emerging high-speed wide area optical networks. It is built on top of UDP with reliability control and congestion control, which makes it quite easy to install. The congestion control algorithm is the major internal functionality to enable UDT to effectively utilize high bandwidth. Meanwhile, we also implemented a set of APIs to support easy application implementation, including both reliable data streaming and partial reliable messaging. The original UDT library has also been extended to Composable UDT, which can support various congestion control algorithms. We will describe in detail the design and implementation of UDT, the UDT congestion control algorithm, Composable UDT, and the performance evaluation.

Teraflows over Gigabit WANs with UDT

The TCP transport protocol is currently inefficient for high speed data transfers over long distance networks with high bandwidth delay products (BDP). The challenge is to develop a protocol which is fast over networks with high bandwidth delay products, fair to other high volume data streams, and friendly to TCP-based flows. We describe here a UDP-based application level transport protocol named UDT (UDP-based Data Transfer) with these properties and which is designed to support distributed data-intensive computing applications. UDT can utilize high bandwidth efficiently over wide area networks with high bandwidth delay products. Unlike TCP, UDT is fair to flows independently of their round trip times (RTT). In addition, UDT is friendly to concurrent TCP flows, which means it can be deployed not only on experimental research networks but also on production networks. To ensure these properties, UDT employs a novel congestion control approach that combines rate-based and window-based control mechanisms. In this paper, we describe the congestion control algorithms used by UDT and provide some experimental results demonstrating that UDT is fast, fair, and friendly.