Increase of the Congestion Window when the Sender Is Rate-Limited
draft-ietf-ccwg-ratelimited-increase-08
The information below is for an old version of the document.
| Document | Type |
This is an older version of an Internet-Draft whose latest revision state is "Active".
|
|
|---|---|---|---|
| Authors | Michael Welzl , Tom Henderson , Gorry Fairhurst , Mohit P. Tahiliani | ||
| Last updated | 2026-08-06 (Latest revision 2026-08-05) | ||
| Replaces | draft-welzl-ccwg-ratelimited-increase | ||
| RFC stream | Internet Engineering Task Force (IETF) | ||
| Formats | |||
| Reviews | |||
| Additional resources | Mailing list discussion | ||
| Stream | WG state | Submitted to IESG for Publication | |
| Associated WG milestone |
|
||
| Document shepherd | Reese Enghardt | ||
| Shepherd write-up | Show Last changed 2026-04-24 | ||
| IESG | IESG state | IESG Evaluation::AD Followup | |
| Consensus boilerplate | Yes | ||
| Telechat date |
(None)
Has enough positions to pass. |
||
| Responsible AD | Mike Bishop | ||
| Send notices to | ietf@tenghardt.net | ||
| IANA | IANA review state | IANA OK - No Actions Needed |
draft-ietf-ccwg-ratelimited-increase-08
Congestion Control Working Group M. Welzl
Internet-Draft University of Oslo
Updates: 4341, 5681, 9002, 9260, 9438 (if T. Henderson
approved) University of Washington
Intended status: Standards Track G. Fairhurst
Expires: 6 February 2027 University of Aberdeen
M. P. Tahiliani
National Institute of Technology Karnataka
5 August 2026
Increase of the Congestion Window when the Sender Is Rate-Limited
draft-ietf-ccwg-ratelimited-increase-08
Abstract
This document specifies how transport protocols increase their
congestion window when the sender is rate-limited, and updates RFCs
4341, 5681, 9002, 9260, and 9438. Such a limitation can be caused by
the sending application not supplying data or by receiver flow
control.
About This Document
This note is to be removed before publishing as an RFC.
The latest revision of this draft can be found at https://ietf-wg-
ccwg.github.io/draft-ietf-ccwg-ratelimited-increase/draft-ietf-ccwg-
ratelimited-increase.html. Status information for this document may
be found at https://datatracker.ietf.org/doc/draft-ietf-ccwg-
ratelimited-increase/.
Discussion of this document takes place on the Congestion Control
Working Group mailing list (mailto:ccwg@ietf.org), which is archived
at https://mailarchive.ietf.org/arch/browse/ccwg/. Subscribe at
https://www.ietf.org/mailman/listinfo/ccwg/.
Source for this draft and an issue tracker can be found at
https://github.com/ietf-wg-ccwg/draft-ietf-ccwg-ratelimited-increase.
Status of This Memo
This Internet-Draft is submitted in full conformance with the
provisions of BCP 78 and BCP 79.
Welzl, et al. Expires 6 February 2027 [Page 1]
Internet-Draft Rate-Limited cwnd Increase August 2026
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 https://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 6 February 2027.
Copyright Notice
Copyright (c) 2026 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 (https://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 Revised BSD License text as
described in Section 4.e of the Trust Legal Provisions and are
provided without warranty as described in the Revised BSD License.
Table of Contents
1. Introduction . . . . . . . . . . . . . . . . . . . . . . . . 3
2. Conventions and Definitions . . . . . . . . . . . . . . . . . 3
2.1. Terminology . . . . . . . . . . . . . . . . . . . . . . . 3
3. Rate-Limited Increase . . . . . . . . . . . . . . . . . . . . 4
3.1. Example . . . . . . . . . . . . . . . . . . . . . . . . . 5
3.1.1. Unconstrained sender . . . . . . . . . . . . . . . . 5
3.1.2. Sender constrained by Rate-Limited Increase . . . . . 6
3.2. Discussion . . . . . . . . . . . . . . . . . . . . . . . 6
3.2.1. Rate-based congestion control . . . . . . . . . . . . 6
3.2.2. Pacing . . . . . . . . . . . . . . . . . . . . . . . 7
4. Updates to RFCs 4341, 5681, 9002, 9260, and 9438 . . . . . . 7
4.1. RFC 4341: Profile for Datagram Congestion Control Protocol
(DCCP) Congestion Control ID 2: TCP-like Congestion
Control . . . . . . . . . . . . . . . . . . . . . . . . . 7
4.2. RFC 5681: TCP Congestion Control . . . . . . . . . . . . 7
4.3. RFC 9002: QUIC Loss Detection and Congestion Control . . 7
4.4. RFC 9260: Stream Control Transmission Protocol . . . . . 8
4.5. RFC 9438: CUBIC for Fast and Long-Distance Networks . . . 8
5. Security Considerations . . . . . . . . . . . . . . . . . . . 9
6. IANA Considerations . . . . . . . . . . . . . . . . . . . . . 9
Welzl, et al. Expires 6 February 2027 [Page 2]
Internet-Draft Rate-Limited cwnd Increase August 2026
7. References . . . . . . . . . . . . . . . . . . . . . . . . . 9
7.1. Normative References . . . . . . . . . . . . . . . . . . 9
7.2. Informative References . . . . . . . . . . . . . . . . . 10
Appendix A. An Example Using cwnd Represented in Bytes . . . . . 10
Appendix B. Change Log . . . . . . . . . . . . . . . . . . . . . 13
Acknowledgments . . . . . . . . . . . . . . . . . . . . . . . . . 15
Authors' Addresses . . . . . . . . . . . . . . . . . . . . . . . 15
1. Introduction
A sender of a congestion controlled transport protocol becomes "rate-
limited" when it does not send any data even though the congestion
control rules would allow it to transmit data. This could occur
because the application has not provided sufficient data to fully
utilize the congestion window (cwnd). It could also occur because
the receiver has limited the sender using flow control (e.g., by the
advertised TCP receiver window (rwnd) or by the connection or stream
flow credit in QUIC). Current RFCs specifying congestion control
algorithms diverge regarding the rules for increasing the cwnd when
the sender is rate-limited. This document provides a uniform
behavior in (Section 3), and specifies updates to RFCs 4341, 5681,
9002, 9260, and 9438 in (Section 4).
Congestion Window Validation (CWV) [RFC7661] provides an experimental
specification defining how to manage a cwnd that has become larger
than the current flight size, and how to respond to detected
congestion when this is the case. In contrast, this present document
concerns the increase in cwnd when a sender is rate-limited. These
two topics are distinct, but are related, because both describe the
management of the cwnd when a sender does not fully utilize the
current cwnd.
An appendix provides an example of how rate-limited increase can play
out.
2. Conventions and Definitions
The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT",
"SHOULD", "SHOULD NOT", "RECOMMENDED", "NOT RECOMMENDED", "MAY", and
"OPTIONAL" in this document are to be interpreted as described in
BCP 14 [RFC2119] [RFC8174] when, and only when, they appear in all
capitals, as shown here.
2.1. Terminology
This document uses the terms defined in Section 2 of [RFC5681].
Additionally, the following are defined:
Welzl, et al. Expires 6 February 2027 [Page 3]
Internet-Draft Rate-Limited cwnd Increase August 2026
* cwnd-limited: A flow that has sent the maximum number of segments
permitted by the cwnd, where the application utilises the allowed
sending rate (based on the definition for TCP in Section 4.5.3 of
[RFC7661]).
* rate-limited: A flow that does not consume more than one half of
cwnd and hence operates in the non-validated phase. This includes
periods when an application is either idle or chooses to send at a
rate less than the maximum permitted by the cwnd (based on the
definition for TCP in Section 3 of [RFC7661]).
* initcwnd: The initial value of the congestion window, also known
as the "initial window" ("IW" in [RFC5681]).
* maxFS: the largest value of FlightSize since the last time that
cwnd was decreased. If cwnd has never been decreased, maxFS is
the maximum value of FlightSize since the start of the data
transfer, and at least as large as initcwnd.
3. Rate-Limited Increase
When FlightSize < cwnd, regardless of the current state of a
congestion control algorithm, the following "Rate-Limited Increase"
rules apply for senders using a congestion controlled transport
protocol:
* The sender MUST initialise the maxFS parameter to initcwnd when
the congestion control algorithm is started. Thereafter, when the
FlightSize is updated, the sender also updates the maxFS:
maxFS = max(FlightSize, maxFS)
* Upon a reduction of cwnd (for any reason), maxFS MUST be reset to
zero. This ensures that maxFS is reinitialized using the first
FlightSize measurement taken after the cwnd reduction.
* The sender MUST cap cwnd to be no larger than limit(maxFS).
The function limit() returns the maximum cwnd value the congestion
control algorithm would yield by increasing for all ACKs that would
be produced by successfully transmitting one window of size maxFS.
For example, for Slow Start, as specified in [RFC5681],
limit(maxFS)=2*maxFS, such that equation 2 in [RFC5681] becomes:
cwnd_new = cwnd + min (N, SMSS)
cwnd = min(cwnd_new, 2*maxFS)
Welzl, et al. Expires 6 February 2027 [Page 4]
Internet-Draft Rate-Limited cwnd Increase August 2026
where cwnd and SMSS follow their definitions in [RFC5681] and N is
the number of previously unacknowledged bytes acknowledged in the
incoming ACK.
Similarly, with Rate-Limited Increase applied in Congestion
Avoidance, limit(maxFS)=SMSS+maxFS, such that equation 3 in [RFC5681]
becomes:
cwnd_new = cwnd + SMSS*SMSS/cwnd
cwnd = min(cwnd_new, SMSS+maxFS)
where cwnd and SMSS follow their definitions in [RFC5681].
NOTE: This specification defines the current method used to increase
the cwnd for a rate-limited sender. Without a way to reduce cwnd
when the transport sender becomes rate-limited, maxFS can stay valid
for a long time, possibly not reflecting the reality of the end-to-
end Internet path in use. This can be remedied by "Congestion Window
Validation" in [RFC7661], which also defines a "pipeACK" variable
that measures the recently acknowledged size of the network pipe when
the sender was rate-limited.
3.1. Example
The working of Rate-Limited Increase can be illustrated by showing
the increase of cwnd in two scenarios: when the growth of cwnd is
unconstrained, and when the rate-limited sender is constrained by
Rate-Limited Increase. For simplicity, this example accounts for the
cwnd in TCP segments (or QUIC packets), rather than bytes. In both
cases, this assumes the initial cwnd (initcwnd) = 10 segments, as
defined for TCP in [RFC6928] and QUIC in [RFC9002], a single
connection begins with Slow Start, the sender transmits a total of 14
segments but pauses after transmitting 10 segments and resumes the
transmission for the remaining 4 segments afterward, no packets are
lost, and an ACK is sent for every packet.
3.1.1. Unconstrained sender
Initially, cwnd = initcwnd. Therefore, using initcwnd = 10 segments,
the sender transmits 10 segments and pauses. Since the sender is in
the Slow Start phase, the arrival of each ACK for the 10 sent
segments increases the cwnd by 1 segment, resulting in the cwnd
increasing to 20 segments. Subsequently, after the pause, the sender
transmits 4 segments and pauses again. As a consequence, the arrival
of 4 ACKs results in cwnd further increasing to 24 segments, even
though the sender is rate-limited (i.e., has never sent more than 10
segments per round-trip time (RTT)).
Welzl, et al. Expires 6 February 2027 [Page 5]
Internet-Draft Rate-Limited cwnd Increase August 2026
3.1.2. Sender constrained by Rate-Limited Increase
Initially, cwnd = initcwnd. Therefore, using initcwnd = 10 segments,
the sender transmits 10 segments and pauses; note that FlightSize and
maxFS are both 10 segments at this point. Since the sender is in the
Slow Start phase, the arrival of each ACK for the 10 sent segments
increases the cwnd by 1 segment, resulting in the cwnd increasing to
20 segments. Subsequently, when the sender resumes and transmits 4
new segments, Rate-Limited Increase constrains the growth of the cwnd
because FlightSize < cwnd and therefore this caps the cwnd to be no
larger than limit(maxFS) = 2 X maxFS = 2 X 10 segments = 20 segments.
3.2. Discussion
If the sending rate is less than the rate permitted by the cwnd for
multiple RTTs, limited either by the sending application or by the
receiver-advertised window, a continuous increase in the cwnd would
cause a mismatch between the cwnd and the capacity that the path
supports (i.e., over-estimating the capacity). Such unlimited growth
in the cwnd is therefore disallowed.
However, in most common congestion control algorithms, in the absence
of an indication of congestion, a cwnd that has been fully utilized
during an RTT (where a sender was cwnd-limited) permits the cwnd to
be increased during the immediately following RTT. This increase is
allowed by Rate-Limited Increase.
3.2.1. Rate-based congestion control
The present document updates congestion control specifications that
use a cwnd to limit the number of unacknowledged bytes (or packets)
that a sender is allowed to emit. Use of a cwnd variable to control
sending rate is not the only mechanism available and not the only
mechanism that is used in practice.
Congestion control algorithms can also constrain data transmission by
explicitly calculating the sending rate over some time interval, by
"pacing" packets (injecting pauses in between their transmission) or
via combinations of the above (e.g., BBR combines these three methods
[I-D.ietf-ccwg-bbr]). The guiding principle behind Rate-Limited
Increase applies to all congestion control algorithms: in the absence
of a congestion indication, a sender is allowed to increase its rate
from the amount of data that it has transmitted during the previous
RTT (this holds irrespective of whether the sender is rate-limited or
not).
Welzl, et al. Expires 6 February 2027 [Page 6]
Internet-Draft Rate-Limited cwnd Increase August 2026
Rate-based congestion control algorithms MUST ensure their maximum
sustained rate is limited to a value that is not greater than would
have been permitted by the Rate-Limited Increase method defined in
Section 3.
3.2.2. Pacing
Pacing mechanisms seek to avoid the negative impacts associated with
"bursts" (flights of packets transmitted back-to-back). Rate-Limited
Increase introduces a limit using "maxFS", which is based on the
number of bytes in flight during a previous RTT; thus, as long as the
number of bytes in flight per RTT is unaffected by pacing, Rate-
Limited Increase does not constrain the use of pacing mechanisms.
4. Updates to RFCs 4341, 5681, 9002, 9260, and 9438
4.1. RFC 4341: Profile for Datagram Congestion Control Protocol (DCCP)
Congestion Control ID 2: TCP-like Congestion Control
According to [RFC4341], a DCCP CCID specifying TCP-like behavior is
allowed to grow the cwnd without limit during an uncongested period
when it sends at a rate unconstrained by the current cwnd. This
document updates Section 5.1 of [RFC4341] by adding the text in
Section 3 to specify how the cwnd is managed when the sender is rate-
limited.
4.2. RFC 5681: TCP Congestion Control
[RFC5681] specifies no limit on cwnd growth in the standard TCP
behavior when a TCP sender is unable to send at the maximum rate
allowed by the cwnd.
This document updates [RFC5681] by adding the text in Section 3 to
specify how the cwnd is managed when the sender is rate-limited.
4.3. RFC 9002: QUIC Loss Detection and Congestion Control
Section 7.8 of [RFC9002] states:
"When bytes in flight is smaller than the congestion window and
sending is not pacing limited, the congestion window is
underutilized. This can happen due to insufficient application
data or flow control limits. When this occurs, the congestion
window SHOULD NOT be increased in either slow start or congestion
avoidance."
This limits the cwnd growth in accordance with Rate-Limited Increase,
but it is more conservative.
Welzl, et al. Expires 6 February 2027 [Page 7]
Internet-Draft Rate-Limited cwnd Increase August 2026
This document updates [RFC9002] by replacing the final sentence of
the cited text with the text in Section 3 to specify how the cwnd is
managed when the sender is rate-limited.
4.4. RFC 9260: Stream Control Transmission Protocol
Section 7.2.1 of [RFC9260] states:
"When cwnd is less than or equal to ssthresh, an SCTP endpoint
MUST use the slow-start algorithm to increase cwnd only if the
current congestion window is being fully utilized and the data
sender is not in Fast Recovery. Only when these two conditions
are met can the cwnd be increased; otherwise, the cwnd MUST NOT be
increased."
The quoted statement from [RFC9260] limits cwnd growth in accordance
with Rate-Limited Increase, but it is more conservative.
Section 7.2.1 of [RFC9260] only discusses Slow Start. Congestion
Avoidance is discussed in Section 7.2.2 of [RFC9260]; however, this
section does not contain a similar rule. It is therefore clear that
the quoted statement from [RFC9260] only applies to Slow Start.
This document updates [RFC9260] by replacing the final sentence of
the quoted text with the text in Section 3 to specify how the cwnd is
managed when the sender is rate-limited.
Section 7.2.2 of [RFC9260] is also updated to add text in Section 3.
This ensures that the update applies to both Slow Start and
Congestion Avoidance.
4.5. RFC 9438: CUBIC for Fast and Long-Distance Networks
Section 5.8 of [RFC9438] states:
"Cubic doesn't increase cwnd when it's limited by the sending
application or rwnd".
This limits the cwnd growth in accordance with Rate-Limited Increase,
but it is more conservative.
This document updates [RFC9438] by replacing the quoted text with the
text in Section 3 to specify how the cwnd is managed when the sender
is rate-limited.
Welzl, et al. Expires 6 February 2027 [Page 8]
Internet-Draft Rate-Limited cwnd Increase August 2026
5. Security Considerations
While congestion control designs could result in unwanted competing
traffic, they do not directly result in new security considerations.
The security considerations are the same as for other congestion
control methods. Such methods rely on the receiver appropriately
acknowledging receipt of data. The ability of an on-path or off-path
attacker to influence congestion control depends upon the security
properties of the transport protocol being used. Transport protocols
that provide authentication (including those using encryption), or
are carried over protocols that provide authentication, can protect
their congestion control algorithm from network attack. This is
orthogonal to the specification of congestion control rules.
6. IANA Considerations
This document requests no IANA action.
7. References
7.1. Normative References
[RFC2119] Bradner, S., "Key words for use in RFCs to Indicate
Requirement Levels", BCP 14, RFC 2119,
DOI 10.17487/RFC2119, March 1997,
<https://www.rfc-editor.org/rfc/rfc2119>.
[RFC4341] Floyd, S. and E. Kohler, "Profile for Datagram Congestion
Control Protocol (DCCP) Congestion Control ID 2: TCP-like
Congestion Control", RFC 4341, DOI 10.17487/RFC4341, March
2006, <https://www.rfc-editor.org/rfc/rfc4341>.
[RFC5681] Allman, M., Paxson, V., and E. Blanton, "TCP Congestion
Control", RFC 5681, DOI 10.17487/RFC5681, September 2009,
<https://www.rfc-editor.org/rfc/rfc5681>.
[RFC8174] Leiba, B., "Ambiguity of Uppercase vs Lowercase in RFC
2119 Key Words", BCP 14, RFC 8174, DOI 10.17487/RFC8174,
May 2017, <https://www.rfc-editor.org/rfc/rfc8174>.
[RFC9002] Iyengar, J., Ed. and I. Swett, Ed., "QUIC Loss Detection
and Congestion Control", RFC 9002, DOI 10.17487/RFC9002,
May 2021, <https://www.rfc-editor.org/rfc/rfc9002>.
[RFC9260] Stewart, R., Tüxen, M., and K. Nielsen, "Stream Control
Transmission Protocol", RFC 9260, DOI 10.17487/RFC9260,
June 2022, <https://www.rfc-editor.org/rfc/rfc9260>.
Welzl, et al. Expires 6 February 2027 [Page 9]
Internet-Draft Rate-Limited cwnd Increase August 2026
[RFC9438] Xu, L., Ha, S., Rhee, I., Goel, V., and L. Eggert, Ed.,
"CUBIC for Fast and Long-Distance Networks", RFC 9438,
DOI 10.17487/RFC9438, August 2023,
<https://www.rfc-editor.org/rfc/rfc9438>.
7.2. Informative References
[I-D.ietf-ccwg-bbr]
Cardwell, N., Swett, I., and J. Beshay, "BBR Congestion
Control", Work in Progress, Internet-Draft, draft-ietf-
ccwg-bbr-06, 6 July 2026,
<https://datatracker.ietf.org/doc/html/draft-ietf-ccwg-
bbr-06>.
[RFC6928] Chu, J., Dukkipati, N., Cheng, Y., and M. Mathis,
"Increasing TCP's Initial Window", RFC 6928,
DOI 10.17487/RFC6928, April 2013,
<https://www.rfc-editor.org/rfc/rfc6928>.
[RFC7661] Fairhurst, G., Sathiaseelan, A., and R. Secchi, "Updating
TCP to Support Rate-Limited Traffic", RFC 7661,
DOI 10.17487/RFC7661, October 2015,
<https://www.rfc-editor.org/rfc/rfc7661>.
Appendix A. An Example Using cwnd Represented in Bytes
The following informative example is provided for a sender that
maintains the cwnd in bytes. 36 packets (or segments in the case of
TCP) are sent in this example over four rounds of transmission. This
shows the initial growth of the cwnd by a rate-limited sender,
followed by a transmission that uses the full available cwnd. The
SMSS (QUIC MPS)=1000. N is the number of previously unacknowledged
bytes in a received acknowledgement. For simplicity, in this example
the receiver sends an ACK for each received packet.
The initial sender state is:
Sender sequence number (seqno) = 0
SMSS = 1000 bytes
cwnd = 10000 bytes (initcwnd)
maxFS = 10000 bytes (initcwnd)
FlightSize (FS) = 0 bytes
ssthresh is infinity, i.e. the congestion control algorithm is in slow start.
The network path’s bandwidth-delay product is such that, throughout
this example, all packets in each round are sent before an ACK is
received for the first packet in a round. One ACK is generated for
each received packet.
Welzl, et al. Expires 6 February 2027 [Page 10]
Internet-Draft Rate-Limited cwnd Increase August 2026
Round 1, the sender has 4000B to send in 4 packets (1000B);
cwnd=10000
Send seqno=0; FS=1000; maxFS=10000
Send seqno=1000; FS=2000; maxFS=10000
Send seqno=2000; FS=3000; maxFS=10000
Send seqno=3000; FS=4000; maxFS=10000
Received 4 ACKs (each N=1000); maxFS=10000 cwnd_new += N; cwnd =
min(cwnd_new, 2*maxFS)
ACK for 1000 ACK’ed=1000; FS-=1000: cwnd+= 1000; cwnd=11000
ACK for 2000 ACK’ed=1000; FS-=1000: cwnd+= 1000; cwnd=12000
ACK for 3000 ACK’ed=1000; FS-=1000: cwnd+= 1000; cwnd=13000
ACK for 4000 ACK’ed=1000; FS-=1000: cwnd+= 1000; cwnd=14000
Note: This round maxFS was not increased and cwnd was increased.
Round 2, the sender has 8000B to send in 8 packets (1000B),
cwnd=14000
Send seqno=4000; FS=1000; maxFS=10000
Send seqno=5000; FS=2000; maxFS=10000
Send seqno=6000; FS=3000; maxFS=10000
Send seqno=7000; FS=4000; maxFS=10000
Send seqno=8000; FS=5000; maxFS=10000
Send seqno=9000; FS=6000; maxFS=10000
Send seqno=10000; FS=7000; maxFS=10000
Send seqno=11000; FS=8000; maxFS=10000
Received 8 ACKs (N=2000); maxFS=10000 cwnd_new += N; cwnd =
min(cwnd_new, 2*maxFS)
ACK for 5000 ACK’ed=1000; FS-=1000: cwnd+=1000; cwnd=15000
ACK for 6000 ACK’ed=1000; FS-=1000: cwnd+=1000; cwnd=16000
ACK for 7000 ACK’ed=1000; FS-=1000: cwnd+=1000; cwnd=17000
ACK for 8000 ACK’ed=1000; FS-=1000: cwnd+=1000; cwnd=18000
ACK for 9000 ACK’ed=1000; FS-=1000: cwnd+=1000; cwnd=19000
ACK for 10000 ACK’ed=1000; FS-=1000: cwnd+=1000; cwnd=20000
ACK for 11000 ACK’ed=1000; FS-=1000: cwnd+=0; cwnd=20000
ACK for 12000 ACK’ed=1000; FS-=1000: cwnd+=0; cwnd=20000
Note: This round maxFS was not increased and cwnd was limited to
2*maxFS.
Round 3, the sender has 4000B to send in 4 packets (1000B),
cwnd=20000
Welzl, et al. Expires 6 February 2027 [Page 11]
Internet-Draft Rate-Limited cwnd Increase August 2026
Send seqno=12000; FS=1000; maxFS=10000
Send seqno=13000; FS=2000; maxFS=10000
Send seqno=14000; FS=3000; maxFS=10000
Send seqno=15000; FS=4000; maxFS=10000
Received 2 ACKs (N=2000); maxFS=10000 cwnd_new += N; cwnd =
min(cwnd_new, 2*maxFS)
ACK for 13000 ACK’ed=1000; FS-=1000: cwnd+=0; cwnd=20000
ACK for 14000 ACK’ed=1000; FS-=1000: cwnd+=0; cwnd=20000
ACK for 15000 ACK’ed=1000; FS-=1000: cwnd+=0; cwnd=20000
ACK for 16000 ACK’ed=1000; FS-=1000: cwnd+=0; cwnd=20000
Note: This round maxFS was not increased and cwnd was not increased.
Round 4, the sender has 20000B to send in 20 packets (1000B),
cwnd=20000
Send seqno=16000; FS= 1000; maxFS=10000
Send seqno=17000; FS= 2000; maxFS=10000
Send seqno=18000; FS= 3000; maxFS=10000
Send seqno=19000; FS= 4000; maxFS=10000
Send seqno=20000; FS= 5000; maxFS=10000
Send seqno=21000; FS= 6000; maxFS=10000
Send seqno=22000; FS= 7000; maxFS=10000
Send seqno=23000; FS= 8000; maxFS=10000
Send seqno=24000; FS= 9000; maxFS=10000
Send seqno=25000; FS=10000; maxFS=10000
Send seqno=26000; FS=11000; maxFS=11000
Send seqno=27000; FS=12000; maxFS=12000
Send seqno=28000; FS=13000; maxFS=13000
Send seqno=29000; FS=14000; maxFS=14000
Send seqno=30000; FS=15000; maxFS=15000
Send seqno=31000; FS=16000; maxFS=16000
Send seqno=32000; FS=17000; maxFS=17000
Send seqno=33000; FS=18000; maxFS=18000
Send seqno=34000; FS=19000; maxFS=19000
Send seqno=35000; FS=20000; maxFS=20000
Received 10 ACKs (N=2000); maxFS=20000 cwnd_new += N; cwnd =
min(cwnd_new, 2*maxFS)
Welzl, et al. Expires 6 February 2027 [Page 12]
Internet-Draft Rate-Limited cwnd Increase August 2026
ACK for 18000 ACK’ed=1000; FS-=1000: cwnd+=1000; cwnd=21000
ACK for 19000 ACK’ed=1000; FS-=1000: cwnd+=1000; cwnd=22000
ACK for 19000 ACK’ed=1000; FS-=1000: cwnd+=1000; cwnd=23000
ACK for 20000 ACK’ed=1000; FS-=1000: cwnd+=1000; cwnd=24000
ACK for 21000 ACK’ed=1000; FS-=1000: cwnd+=1000; cwnd=25000
ACK for 22000 ACK’ed=1000; FS-=1000: cwnd+=1000; cwnd=26000
ACK for 23000 ACK’ed=1000; FS-=1000: cwnd+=1000; cwnd=27000
ACK for 24000 ACK’ed=1000; FS-=1000: cwnd+=1000; cwnd=28000
ACK for 25000 ACK’ed=1000; FS-=1000: cwnd+=1000; cwnd=29000
ACK for 26000 ACK’ed=1000; FS-=1000: cwnd+=1000; cwnd=30000
ACK for 27000 ACK’ed=1000; FS-=1000: cwnd+=1000; cwnd=31000
ACK for 28000 ACK’ed=1000; FS-=1000: cwnd+=1000; cwnd=32000
ACK for 29000 ACK’ed=1000; FS-=1000: cwnd+=1000; cwnd=33000
ACK for 30000 ACK’ed=1000; FS-=1000: cwnd+=1000; cwnd=34000
ACK for 31000 ACK’ed=1000; FS-=1000: cwnd+=1000; cwnd=35000
ACK for 32000 ACK’ed=1000; FS-=1000: cwnd+=1000; cwnd=36000
ACK for 33000 ACK’ed=1000; FS-=1000: cwnd+=1000; cwnd=37000
ACK for 34000 ACK’ed=1000; FS-=1000: cwnd+=1000; cwnd=38000
ACK for 35000 ACK’ed=1000; FS-=1000: cwnd+=1000; cwnd=39000
ACK for 36000 ACK’ed=1000; FS-=1000: cwnd+=1000; cwnd=40000
Note: In this round, maxFS increased and therefore cwnd increased to
2*maxFS.
Appendix B. Change Log
* -00 was the first individual submission for feedback by CCWG.
* -01 includes editorial improvements
- Removes application interaction with QUIC pacing, since pacing
might be within the QUIC stack.
- Adds explicit mention of DCCP/CCID2.
- Adds this change log.
* -02 addresses comments from IETF-119
- Discusses rate-based controls and pacing.
- Trims the list of possible RFCs to update.
- Some editorial fixes: "congestion control algorithm" instead of
"mechanism" for consistency with RFC5033.bis; earlier
definition of maxFS; explicit mention of RFCs to update in
abstract.
Welzl, et al. Expires 6 February 2027 [Page 13]
Internet-Draft Rate-Limited cwnd Increase August 2026
* -03 addresses comments from IETF-120
- Introduces a third rule, with MAY, that avoids having an
unvalidated long-lived maxFS (using pipeACK from RFC 7661).
- Changes "inc" to "limit" and adapts the wording of rule 2 to
make it clearer (thanks to Neal Cardwell).
- Appendix: updates ns-3 in line with the recent implementation.
- Appendix: makes the RFC 9002 text clearer and shorter.
* draft-ietf-ccwg-ratelimited-increase-00
- adds Mohit Tahiliani as a co-author
- refines the "rule" text (shorter, clearer)
- adds an example
* draft-ietf-ccwg-ratelimited-increase-01
- Clarified what we mean with an RTT
- rephrased example regarding initcwnd, citing RFCs 6928 and 9002
- removed the too vague rule 1 and made rule 2 (now rule 1) a
MUST
* draft-ietf-ccwg-ratelimited-increase-02
- Improved the last sentence of section 3.1.2.
- Removed a confusing and unnecessary sentence about pacing (as
suggested at IETF-123).
* draft-ietf-ccwg-ratelimited-increase-03
- The editors checked rule 2, and found that rule 1 was
sufficient, and did not depend on the ordering of rules in
newCWV (RFC7661), hence rule 2 was finally removed.
- Cleaned language and improved text explaining how this
complements RFC7661.
- Checked/updated definitions.
- Added an example with cwnd in bytes.
Welzl, et al. Expires 6 February 2027 [Page 14]
Internet-Draft Rate-Limited cwnd Increase August 2026
* draft-ietf-ccwg-ratelimited-increase-04
- Repeated definitions from RFC 7661 instead of just pointing at
the RFC
- Made RFC 7661 informational
* draft-ietf-ccwg-ratelimited-increase-05
- Rephrased references to RFC 7661
- Nits
* draft-ietf-ccwg-ratelimited-increase-06
- Changed some TCP-specific language so it applies to QUIC too
- RFC 4341 added to list of updated RFCs in the abstract
- Nits
* draft-ietf-ccwg-ratelimited-increase-07
- Updated this list
- Made RFC 4341 reference normative
- Fixed Updates list to match boilerplate
- Moved some of appendix B to the main text as a new section that
(only) defines the RFC updates.
- Updated description lines in appendix A
* draft-ietf-ccwg-ratelimited-increase-08
- Addressed a comment from Eric Vyncke about the paragraph on
rate-based cc. algs.
Acknowledgments
The authors would like to thank Neal Cardwell and Martin Duke for
suggesting improvements to this document.
Authors' Addresses
Welzl, et al. Expires 6 February 2027 [Page 15]
Internet-Draft Rate-Limited cwnd Increase August 2026
Michael Welzl
University of Oslo
PO Box 1080 Blindern
0316 Oslo
Norway
Email: michawe@ifi.uio.no
URI: http://welzl.at/
Tom Henderson
University of Washington
185 Stevens Way
Seattle, WA 98195,
United States
Email: tomh@tomh.org
Godred Fairhurst
University of Aberdeen
Fraser Noble Building
Aberdeen, AB24 3UE
United Kingdom
Email: gorry@erg.abdn.ac.uk
URI: https://www.erg.abdn.ac.uk/
Mohit P. Tahiliani
National Institute of Technology Karnataka
P. O. Srinivasnagar, Surathkal
Mangalore, Karnataka - 575025
India
Email: tahiliani@nitk.edu.in
URI: https://tahiliani.in/
Welzl, et al. Expires 6 February 2027 [Page 16]