| TCPM Working Group | G. Fairhurst |
| Internet-Draft | A. Sathiaseelan |
| Obsoletes: 2861 (if approved) | University of Aberdeen |
| Updates: 5681 (if approved) | February 14, 2013 |
| Intended status: Standards Track | |
| Expires: August 18, 2013 |
Updating TCP to support Rate-Limited Traffic
draft-ietf-tcpm-newcwv-00
This document proposes an update to RFC 5681 to address issues that arise when TCP is used to support traffic that exhibits periods where the sending rate is limited by the application rather than the congestion window. It updates TCP to allow a TCP sender to restart quickly following either an idle or rate-limited interval. This method is expected to benefit applications that send rate-limited traffic using TCP, while also providing an appropriate response if congestion is experienced.
It also evaluates TCP Congestion Window Validation, CWV, an IETF experimental specification defined in RFC 2861, and concludes that CWV sought to address important issues, but failed to deliver a widely used solution. This document therefore proposes an update to the status of RFC 2861 by recommending it is moved from Experimental to Historic status, and that it is replaced by the current specification.
NOTE: The standards status of this WG document is under review for consideration as either Experimental (EXP) or Proposed Standard (PS). This decision will be made later as the document is finalised.
This Internet-Draft is submitted in full conformance with the provisions of BCP 78 and BCP 79.
Internet-Drafts are working documents of the Internet Engineering Task Force (IETF). Note that other groups may also distribute working documents as Internet-Drafts. The list of current Internet-Drafts is at http://datatracker.ietf.org/drafts/current/.
Internet-Drafts are draft documents valid for a maximum of six months and may be updated, replaced, or obsoleted by other documents at any time. It is inappropriate to use Internet-Drafts as reference material or to cite them other than as "work in progress."
This Internet-Draft will expire on August 18, 2013.
Copyright (c) 2013 IETF Trust and the persons identified as the document authors. All rights reserved.
This document is subject to BCP 78 and the IETF Trust's Legal Provisions Relating to IETF Documents (http://trustee.ietf.org/license-info) in effect on the date of publication of this document. Please review these documents carefully, as they describe your rights and restrictions with respect to this document. Code Components extracted from this document must include Simplified BSD License text as described in Section 4.e of the Trust Legal Provisions and are provided without warranty as described in the Simplified BSD License.
TCP is used to support a range of application behaviours. The TCP congestion window (cwnd) controls the number of unacknoeledged packets/bytes that a TCP flow may have in the network at any time, a value known as the FlightSize [RFC5681]. A bulk application will always have data available to transmit. The rate at which it sends is therefore limited by the maximum permitted by the receiver and congestion windows. In contrast, a rate-limited application will experience periods when the sender is either idle or is unable to send at the maximum rate permitted by the cwnd. This latter case is called rate-limited. The focus of this document is on the operation of TCP in such an idle or rate-limited case.
Standard TCP [RFC5681] requires the cwnd to be reset to the restart window (RW) when an application becomes idle. [RFC2861] noted that this TCP behaviour was not always observed in current implementations. Recent experiments [Bis08] confirm this to still be the case.
Standard TCP does not impose additional restrictions on the growth of the cwnd when a TCP sender is rate-limited. A rate-limited sender may therefore grow a cwnd far beyond that corresponding to the current transmit rate, resulting in a value that does not reflect current information about the state of the network path the flow is using. Use of such an invalid cwnd may result in reduced application performance and/or could significantly contribute to network congestion.
[RFC2861] proposed a solution to these issues in an experimental method known as Congestion Window Validation (CWV). CWV was intended to help reduce cases where TCP accumulated an invalid cwnd. The use and drawbacks of using CWV with an application are discussed in Section 2.
Section 3 defines relevant terminology.
Section 4 specifies an alternative to CWV that seeks to address the same issues, but does this in a way that is expected to mitigate the impact on an application that varies its sending rate. The method described applies to both a rate-limited and an idle condition.
RFC 2861 described a simple modification to the TCP congestion control algorithm that decayed the cwnd after the transition to a “sufficiently-long” idle period. This used the slow-start threshold (ssthresh) to save information about the previous value of the congestion window. The approach relaxed the standard TCP behaviour [RFC5681] for an idle session, intended to improve application performance. CWV also modified the behaviour for a rate-limited session where a sender transmitted at a rate less than allowed by cwnd.
RFC 2861 has been implemented in some mainstream operating systems as the default behaviour [Bis08]. Analysis (e.g. [Bis10] [Fai12]) has shown that a TCP sender using CWV is able to use available capacity on a shared path after an idle period. This can benefit some applications, especially over long delay paths, when compared to the slow-start restart specified by standard TCP. However, CWV would only benefit an application if the idle period were less than several Retransmission Time Out (RTO) intervals [RFC6298], since the behaviour would otherwise be the same as for standard TCP, which resets the cwnd to the RTCP Restart Window (RW) after this period.
Experience with CWV suggests that although CWV benefits the network in a rate-limited scenario (reducing the probability of network congestion), the behaviour can be too conservative for many common rate-limited applications. This mechanism does not therefore offer the desirable increase in application performance for rate-limited applications and it is unclear whether applications actually use this mechanism in the general Internet.
It is therefore concluded that CWV is often a poor solution for many rate-limited applications. It has the correct motivation, but has the wrong approach to solving this problem.
The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT", "SHOULD", "SHOULD NOT", "RECOMMENDED", "MAY", and "OPTIONAL" in this document are to be interpreted as described in [RFC2119].
The document assumes familiarity with the terminology of TCP congestion control [RFC5681].
The following new terminology is introduced:
Validated phase: The phase where the cwnd reflects a current estimate of the available path capacity.
Non-validated phase: The phase where the cwnd reflects a previous measurement of the available path capacity.
Non-validated period, NVP: The maximum period for which cwnd is preserved in the non-validated phase.
Rate-limited: A TCP flow that does not consume more than one half of cwnd, and hence operates in the non-validated phase.
pipe ACK: The measured volume of data that was acknowledged by the network per RTT.
This section proposes an update to the TCP congestion control behaviour during an idle or rate-limited period. The new method permits a TCP sender to preserve the cwnd when an application becomes idle for a period of time (to be known as the non-validated period, NVP, see section 5). The period where actual usage is less than allowed by cwnd, is named as the non-validated phase. This method allows an application to resume transmission at a previous rate without incurring the delay of slow-start. However, if the TCP sender experiences congestion using the preserved cwnd, it is required to immediately reset the cwnd to an appropriate value specified by the method. If a sender does not take advantage of the preserved cwnd within the NVP, the value of cwnd is reduced, ensuring the value better reflects the capacity that was recently actually used.
The method requires that the TCP SACK option [RFC3517]is enabled. This allows the sender to select an appropriate value for the cwnd following a congestion event that is based on the measured path capacity, and better reflects the fair-share. A similar approach was proposed by TCP Jump Start [Liu07], as a congestion response after more rapid opening of a TCP connection.
It is expected that this update will satisfy the requirements of many rate-limited applications and at the same time provide an appropriate method for use in the Internet. It also reduces the incentive for an application to send data simply to keep transport congestion state. (This is sometimes known as "padding").
The new method does not differentiate between times when the sender has become idle or rate-limited. This is partly a response to recognition that some applications wish to transmit at a rate less than allowed by the sender cwnd, and that it can be hard to make a distinction between rate-limited and idle behaviour. This is expected to encourage applications and TCP stacks to use standards-based congestion control methods. It may also encourage the use of long-lived connections where this offers benefit (such as persistent http).
The method is specified in following subsections.
The method described in this document updates [RFC5681]. Use of the method REQUIRES a TCP sender and the corresponding receiver to enable the TCP SACK option [RFC3517].
[RFC5681] defines a variable, FlightSize, that indicates the amount of outstanding data in the network. This is assumed to be equal to the value of Pipe calculated based on the pipe algorithm [RFC3517]. In RFC5681 this value is used during loss recovery, whereas in this method a new variable "pipeACK" is introduced and used to determine if the sender has validated the cwnd.
The value of pipeACK is initialised to the maxium value. This value is used to inhibt entering the nonvalidated phase until the first measurement of pipeACK completes.
A sender is not required to continuously track the pipeACK value, but MUST set this variable to the volume of data that was acknowledged by the network per measured Round Trip Time (RTT), with a sampling period of not less than one measurement for Min(RTT, 1 second). Using the variables defined in [RFC3517]. This could be implemented by caching the value of HighACK and after one RTT assigning pipeACK to the difference between the cached HighACK value and the current HighACK value. Other equivalent methods may be used.
The updated method creates a new TCP sender phase that captures whether the cwnd reflects a validated or non-validated value. The phases are defined as:
A sender starts a TCP connection in the Validated phase.
The value 1/2 was selected to reduce the effects of variations in the measured pipeACK, and to allow the sender some flexibility in when it sends data.
A TCP sender MUST enter the non-validated phase when the measured pipeACK is less than (1/2)*cwnd.
A TCP sender that enters the non-validated phase will preserve the cwnd (i.e., this neither grows nor reduces while the sender remains in this phase). The phase is concluded after a fixed period of time (the NVP, as explained in section 4.3.2) or when the sender transmits sufficient data so that pipeACK > (1/2)*cwnd (i.e. it is no longer rate-limited).
The behaviour in the non-validated phase is specified as:
Reception of congestion feedback while in the non-validated phase is interpreted as an indication that it was inappropriate for the sender to use the preserved cwnd. The sender is therefore required to quickly reduce the rate to avoid further congestion. Since the cwnd does not have a validated value, a new cwnd value must be selected based on the utilised rate.
A sender that detects a packet-drop or receives an ECN marked packet MUST calculate a safe cwnd, by setting it to the value specified in Section 3.2 of [RFC5681].
At the end of the recovery phase, the TCP sender MUST reset the cwnd using the method below:
cwnd = ((FlightSize - R)/2).
Where, R is the volume of data that was reported as unacknowledged by the SACK information. This follows the method proposed for Jump Start [Liu07].
The inclusion of the term R makes this adjustment more conservative than standard TCP. (This is required, since the sender may have sent more segments than a Standard TCP sender would have done. The additional reduction is beneficial when the FlightSize significantly overshoots the available path capacity incurring significant loss, for instance an intense traffic burst following a non-validated period.)
If the sender implements a method that allows it to identify the number of ECN-marked segments within a window that were observed by the receiver, the sender SHOULD use the method above, further reducing R by the number of marked segments.
The sender MUST also re-initialise the pipeACK variable to the maxium value. This ensures that standard TCP methods are used immediately after completing loss recovery.
During the non-validated phase, a sender can produce bursts of data of up to the cwnd in size. While this is no different to standard TCP, it is desirable to control the maximum burst size, e.g. by setting a burst size limit, using a pacing algorithm, or some other method [Hug01].
An application that remains in the non-validated phase for a period greater than the NVP is required to adjust its congestion control state. If the sender exits the non-validated phase after this period, it MUST update the ssthresh:
ssthresh = max(ssthresh, 3*cwnd/4).
(This adjustment of ssthresh ensures that the sender records that it has safely sustained the present rate. The change is beneficial to rate-limited flows that encounter occasional congestion, and could otherwise suffer an unwanted additional delay in recovering the sending rate.)
The sender MUST then update cwnd to be not greater than:
cwnd = max(1/2*cwnd, IW).
Where IW is the TCP inital window [RFC5681].
(This adjustment ensures that sender responds conservatively at the end of the non-validated phase by reducing the cwnd to better reflect the current sending rate of the sender. The cwnd update does not take into account FlightSize or pipeACK because these values only reflect data during the last RTT and do not reflect the average or peak sending rate.)
After completing this adjustment, the sender MAY re-enter the non-validated phase, if required (see section 4.2).
This section documents the rationale for selecting the maximum period that cwnd may be preserved, known as the non-validated period, NVP.
Limiting the period that cwnd may be preserved avoids undesirable side effects that would result if the cwnd were to be kept unecessarily high for an arbitrary long period, which was a part of the problem that CWV originally attempted to address. The period a sender may safely preserve the cwnd, is a function of the period that a network path is expected to sustain the capacity reflected by cwnd. There is no ideal choice for this time.
A period of five minutes was chosen for this NVP. This is a compromise that was larger than the idle intervals of common applications, but not sufficiently larger than the period for which the capacity of an Internet path may commonly be regarded as stable. The capacity of wired networks is usually relatively stable for periods of several minutes and that load stability increases with the capacity. This suggests that cwnd may be preserved for at least a few minutes.
There are cases where the TCP throughput exhibits significant variability over a time less than five minutes. Examples could include wireless topologies, where TCP rate variations may fluctuate on the order of a few seconds as a consequence of medium access protocol instabilities. Mobility changes may also impact TCP performance over short time scales. Senders that observe such rapid changes in the path characteristic may also experience increased congestion with the new method, however such variation would likely also impact TCP’s behaviour when supporting interactive and bulk applications.
Routing algorithms may modify the network path, disrupting the RTT measurement and changing the capacity available to a TCP connection, however such changes do not often occur within a time frame of a few minutes.
The value of five minutes is therefore expected to be sufficient for most current applications. Simulation studies (e.g. [Bis11]) also suggest that for many practical applications, the performance using this value will not be significantly different to that observed using a non-standard method that does not reset the cwnd after idle.
Finally, other TCP sender mechanisms have used a 5 minute timer, and there could be simplifications in some implementations by reusing the same interval. TCP defines a default user timeout of 5 minutes [RFC0793] i.e. how long transmitted data may remain unacknowledged before a connection is forcefully closed.
General security considerations concerning TCP congestion control are discussed in [RFC5681]. This document describes an algorithm that updates one aspect of the congestion control procedures, and so the considerations described in RFC 5681 also apply to this algorithm.
There are no IANA considerations.
The authors acknowledge the contributions of Dr I Biswas and Dr R Secchi in supporting the evaluation of CWV and for their help in developing the mechanisms proposed in this draft. We also acknowledge comments received from the Internet Congestion Control Research Group, in particular Yuchung Cheng, Mirja Kuehlewind, and Joe Touch.
There are several issues to be discussed more widely:
• There is potential performance loss in loss of a short burst (off list with M Allman)
RFC-Editor note: please remove this section prior to publication.
Draft 03 was submitted to ICCRG to receive comments and feedback.
Draft 04 contained the first set of clarifications after feedback:
Draft 05 contained various updates:
Draft 06 contained various updates:
WG draft 01 contained various updates:
| [RFC0793] | Postel, J., "Transmission Control Protocol", STD 7, RFC 793, September 1981. |
| [RFC2119] | Bradner, S., "Key words for use in RFCs to Indicate Requirement Levels", BCP 14, RFC 2119, March 1997. |
| [RFC2861] | Handley, M., Padhye, J. and S. Floyd, "TCP Congestion Window Validation", RFC 2861, June 2000. |
| [RFC6298] | Paxson, V., Allman, M., Chu, J. and M. Sargent, "Computing TCP's Retransmission Timer", RFC 6298, June 2011. |
| [RFC3168] | Ramakrishnan, K., Floyd, S. and D. Black, "The Addition of Explicit Congestion Notification (ECN) to IP", RFC 3168, September 2001. |
| [RFC3517] | Blanton, E., Allman, M., Fall, K. and L. Wang, "A Conservative Selective Acknowledgment (SACK)-based Loss Recovery Algorithm for TCP", RFC 3517, April 2003. |
| [RFC5681] | Allman, M., Paxson, V. and E. Blanton, "TCP Congestion Control", RFC 5681, September 2009. |