An Evaluation of Tail Loss Recovery Mechanisms for TCP

Rajiullah, Mohammad; Hurtig, Per; Brunström, Anna; Petlund, Andreas; Welzl, Michael

doi:10.1145/2717646.2717648

Cited by 22 publications

(8 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An RTO algorithm represents a trade-off between latency and correctness, and thus no RTO algorithm will offer the best performance in all metrics and in all possible scenarios [20]. However, several works have identified TCP RTO calculation issues [21][22][23][24][25]. The impact of parameter settings, such as the initial RTO or the minimum RTO, on spurious timeouts has been investigated [22][23][24].…”

Section: B Alternative Rto Algorithms For Tcpmentioning

confidence: 99%

Multimodal Retransmission Timer for LPWAN

Gómez

Crowcroft

2020

IEEE Internet Things J.

View full text Add to dashboard Cite

Low Power Wide Area Networks (LPWANs) are experiencing high momentum as an inexpensive solution for enabling Internet of Things (IoT) applications. Recent Internet connectivity support developments are expected to further fuel the adoption of LPWAN. However, the latter present challenges to Internet protocols. Remarkably, many LPWAN scenarios exhibit a multimodal Round Trip Time (RTT) distribution, which deviates from common Internet RTT characteristics. This leads to a significant mismatch between Retransmission TimeOut (RTO), computed by the standard TCP or alternative experimental RTO algorithms, and RTT. In this paper, we present the Multimodal RTO algorithm, which is able to selfadapt to the current RTT mode and produce suitable RTO values. Evaluation results show that the Multimodal RTO reduces the RTO versus RTT misalignment of the TCP RTO algorithm by an average factor of up to 5, and reduces latency in the presence of losses by up to 2 orders of magnitude, while operating safely. The Multimodal RTO is currently being considered by the IETF as a candidate mechanism for standardization.

show abstract

Section: B Alternative Rto Algorithms For Tcpmentioning

confidence: 99%

Multimodal Retransmission Timer for LPWAN

Gómez

Crowcroft

2020

IEEE Internet Things J.

View full text Add to dashboard Cite

show abstract

“…TLP is a more advanced mechanism than RTOR, requiring e.g., SACK to work, and is often able to further reduce loss recovery times. However, it also noticeably increases the amount of spurious retransmissions, as compared to RTOR [RHB15].…”

Section: Related Workmentioning

confidence: 99%

TCP and Stream Control Transmission Protocol (SCTP) RTO Restart

Welzl¹,

Brunström²,

Hurtig³

et al. 2016

View full text Add to dashboard Cite

This document describes a modified sender-side algorithm for managing the TCP and Stream Control Transmission Protocol (SCTP) retransmission timers that provides faster loss recovery when there is a small amount of outstanding data for a connection. The modification, RTO Restart (RTOR), allows the transport to restart its retransmission timer using a smaller timeout duration, so that the effective retransmission timeout (RTO) becomes more aggressive in situations where fast retransmit cannot be used. This enables faster loss detection and recovery for connections that are short lived or application limited.

show abstract

“…For instance, by striping data across a set of simultaneous connections, parallel TCP increases the end-to-end throughput [37] and is likely beneficial for dataintensive cloud gaming applications in terms of throughput and delay. Recent advances in TCP tail loss recovery mechanisms have demonstrated further latency reduction for TCP against traffic bursts [38], and several Linux distributions have readily provided advanced TCP streaming extensions, such as thin dupACK and thin retransmit.…”

Section: Future Work and Conclusionmentioning

confidence: 99%

Cloud Gaming: Understanding the Support From Advanced Virtualization and Hardware

Shea

Liu

2015

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

Existing cloud gaming platforms have mainly focused on private, non-virtualized environments with proprietary hardware. Modern public cloud platforms heavily rely on virtualization for efficient resource sharing, the potentials of which have yet to be explored. Migrating gaming to a public cloud is non-trivial however, particularly considering the overhead for virtualization and that the GPUs for game rendering has long been an obstacle in virtualization.This paper takes a first step towards bridging the online gaming system and the public cloud platforms. We present the design and implementation of a fully virtualized cloud gaming platform with the latest hardware support for both remote servers and local clients. We explore many critical design issues inherent in cloud gaming, including the choice of hardware or software video encoding, the configuration and the detailed power consumption of thin client. We demonstrate that, with the latest hardware and virtualization support, gaming over virtualized cloud can be made possible with careful optimization and integration of the different modules. We also highlight critical challenges towards full-fledge deployment of gaming services over the public virtualized cloud.

show abstract

An Evaluation of Tail Loss Recovery Mechanisms for TCP

Cited by 22 publications

References 20 publications

Multimodal Retransmission Timer for LPWAN

Multimodal Retransmission Timer for LPWAN

TCP and Stream Control Transmission Protocol (SCTP) RTO Restart

Cloud Gaming: Understanding the Support From Advanced Virtualization and Hardware

Contact Info

Product

Resources

About