An Extension to the Selective Acknowledgement (SACK) Option for TCP

Floyd, Sally; Mahdavi, J.; Mathis, Matt; Podolsky, Matthew

doi:10.17487/rfc2883

Cited by 278 publications

(177 citation statements)

References 2 publications

Supporting

Mentioning

169

Contrasting

Unclassified

Order By: Relevance

“…Duplicate segments at the TCP receiver normally trigger DSACKs [9]. The DSACK statistics provide a measure of network resources that were wasted by overly aggressive retransmits of nearly all types, except segments with no pay-load.…”

Section: Tcpmentioning

confidence: 99%

Proportional Rate Reduction for TCP

Mathis¹,

Dukkipati²,

Cheng³

2013

Self Cite

View full text Add to dashboard Cite

Packet losses increase latency for Web users. Fast recovery is a key mechanism for TCP to recover from packet losses. In this paper, we explore some of the weaknesses of the standard algorithm described in RFC 3517 and the non-standard algorithms implemented in Linux. We find that these algorithms deviate from their intended behavior in the real world due to the combined effect of short flows, application stalls, burst losses, acknowledgment (ACK) loss and reordering, and stretch ACKs. Linux suffers from excessive congestion window reductions while RFC 3517 transmits large bursts under high losses, both of which harm the rest of the flow and increase Web latency.Our primary contribution is a new design to control transmission in fast recovery called proportional rate reduction (PRR). PRR recovers from losses quickly, smoothly and accurately by pacing out retransmissions across received ACKs. In addition to PRR, we evaluate the TCP early retransmit (ER) algorithm which lowers the duplicate acknowledgment threshold for short transfers, and show that delaying early retransmissions for a short interval is effective in avoiding spurious retransmissions in the presence of a small degree of reordering. PRR and ER reduce the TCP latency of connections experiencing losses by 3-10% depending on the response size. Based on our instrumentation on Google Web and YouTube servers in U.S. and India, we also present key statistics on the nature of TCP retransmissions.

show abstract

Section: Tcpmentioning

confidence: 99%

Proportional Rate Reduction for TCP

Mathis¹,

Dukkipati²,

Cheng³

2013

Self Cite

View full text Add to dashboard Cite

show abstract

“…If an out-of-order packet arrives, a duplicated ACK is sent, and if an in-order packet arrives, the ACK sending may be delayed (but one ACK should be sent for at least every second packet arrival and no later than 500 ms after the first arrival [8]). Selective ACKs (SACK), which indicate non-contiguous blocks of consecutive bytes correctly received, have also been defined [9,10].…”

Section: Reliable Delivery In Tcpmentioning

confidence: 99%

Network schemes for TCP elastic traffic in the Internet

Fàbrega

Jové

2013

NPA

View full text Add to dashboard Cite

TCP elastic traffic is generated by the traditional "data" applications in the Internet, such as web browsing, peer-to-peer file sharing, ftp, e-mail and other. These applications are built on top of TCP, which provides reliable transfers and adjusts the sending rate to the network conditions to achieve the maximum possible throughput, a feature that makes TCP flows to be called "elastic". From the point of view of the network, TCP elastic traffic requires the maximum possible throughput above a minimum value, a network service that we call the Minimum Throughput Service (MTS). In this paper we survey the main network schemes that have been proposed in the Internet to provide this service for TCP elastic traffic, classified in two broad groups, the ones that do not use Admission Control (AC) and the ones that do use it. For each network scheme we describe the main characteristics of the service (whether the minimum throughput can be different or is the same for all flows, whether isolation among flows is provided, etc.) and their architecture (the specific traffic conditioning, queue disciplines and AC mechanisms used, the required state, the use of signaling, etc.).

show abstract

“…It then reacts, say, by recovering previous congestion responses and/or disabling future congestion responses for a time period. The Eifel algorithm (Ludwig and Katz, 2000), DSACK TCP (Floyd et al, 2000), and TCP-DOOR (Wang and Zhang, 2002), belong to this class.…”

Section: Related Workmentioning

confidence: 99%

OSIA: Out-of-order Scheduling for In-order Arriving in concurrent multi-path transfer

Wang

Liao

2012

Journal of Network and Computer Applications

View full text Add to dashboard Cite

One major problem of concurrent multi-path transfer (CMT) scheme in multi-homed mobile networks is that the utilization of different paths with diverse delays may cause packet reordering among packets of the same flow. In the case of TCP-like, the reordering exacerbates the problem by bringing more timeouts and unnecessary retransmissions, which eventually degrades the throughput of connections considerably. To address this issue, we first propose an Out-of-order Scheduling for In-order Arriving (OSIA), which exploits the sending time discrepancy to preserve the in-order packet arrival. Then, we formulate the optimal traffic scheduling as a constrained optimization problem and derive its closedform solution by our proposed progressive water-filling solution. We also present an implementation to enforce the optimal scheduling scheme using cascaded leaky buckets with multiple faucets, which provides simple guidelines on maximizing the utilization of aggregate bandwidth while decreasing the probability of triggering 3 dupACKs. Compared with previous work, the proposed scheme has lower computation complexity and can also provide the possibility for dynamic network adaptability and finer-grain load balancing. Simulation results show that our scheme significantly alleviates reordering and enhances transmission performance.

show abstract

An Extension to the Selective Acknowledgement (SACK) Option for TCP

Cited by 278 publications

References 2 publications

Proportional Rate Reduction for TCP

Proportional Rate Reduction for TCP

Network schemes for TCP elastic traffic in the Internet

OSIA: Out-of-order Scheduling for In-order Arriving in concurrent multi-path transfer

Contact Info

Product

Resources

About