draft-ietf-rmt-bb-tfmcc-06.txt   draft-ietf-rmt-bb-tfmcc-07.txt 
Internet Engineering Task Force RMT WG Internet Engineering Task Force RMT WG
INTERNET-DRAFT Joerg Widmer/DoCoMo Euro-Labs INTERNET-DRAFT Joerg Widmer/DoCoMo Euro-Labs
draft-ietf-rmt-bb-tfmcc-06.txt Mark Handley/UCL draft-ietf-rmt-bb-tfmcc-07.txt Mark Handley/UCL
3 March 2006 9 May 2006
Expires: September 2006 Expires: November 2006
TCP-Friendly Multicast Congestion Control (TFMCC): TCP-Friendly Multicast Congestion Control (TFMCC):
Protocol Specification Protocol Specification
Status of this Document Status of this Document
By submitting this Internet-Draft, each author represents that any By submitting this Internet-Draft, each author represents that any
applicable patent or other IPR claims of which he or she is aware have applicable patent or other IPR claims of which he or she is aware have
been or will be disclosed, and any of which he or she becomes aware will been or will be disclosed, and any of which he or she becomes aware will
be disclosed, in accordance with Section 6 of BCP 79. be disclosed, in accordance with Section 6 of BCP 79.
skipping to change at page 2, line 5 skipping to change at page 2, line 5
This document is a product of the IETF RMT WG. Comments should be This document is a product of the IETF RMT WG. Comments should be
addressed to the authors, or the WG's mailing list at rmt@lbl.gov. addressed to the authors, or the WG's mailing list at rmt@lbl.gov.
Abstract Abstract
This document specifies TCP-Friendly Multicast Congestion This document specifies TCP-Friendly Multicast Congestion
Control (TFMCC). TFMCC is a congestion control mechanism for Control (TFMCC). TFMCC is a congestion control mechanism for
multicast transmissions in a best-effort Internet environment. multicast transmissions in a best-effort Internet environment.
Expires: September 2006 March 2006 Expires: November 2006 May 2006
It is a single-rate congestion control scheme, where the It is a single-rate congestion control scheme, where the
sending rate is adapted to the receiver experiencing the worst sending rate is adapted to the receiver experiencing the worst
network conditions. TFMCC is reasonably fair when competing network conditions. TFMCC is reasonably fair when competing
for bandwidth with TCP flows and has a relatively low for bandwidth with TCP flows and has a relatively low
variation of throughput over time, making it suitable for variation of throughput over time, making it suitable for
applications such as streaming media where a relatively smooth applications such as streaming media where a relatively smooth
sending rate is of importance. sending rate is of importance.
Expires: September 2006 March 2006 Expires: November 2006 May 2006
Table of Contents Table of Contents
1. Introduction. . . . . . . . . . . . . . . . . . . . . . 4 1. Introduction. . . . . . . . . . . . . . . . . . . . . . 4
1.1. Terminology. . . . . . . . . . . . . . . . . . . . . 4 1.1. Terminology. . . . . . . . . . . . . . . . . . . . . 4
1.2. Related Documents. . . . . . . . . . . . . . . . . . 5 1.2. Related Documents. . . . . . . . . . . . . . . . . . 5
1.3. Environmental Requirements and Considerations. . . . 5 1.3. Environmental Requirements and Considerations. . . . 5
2. Protocol Overview . . . . . . . . . . . . . . . . . . . 6 2. Protocol Overview . . . . . . . . . . . . . . . . . . . 6
2.1. TCP Throughput Equation. . . . . . . . . . . . . . . 7 2.1. TCP Throughput Equation. . . . . . . . . . . . . . . 7
2.2. Packet Contents. . . . . . . . . . . . . . . . . . . 8 2.2. Packet Contents. . . . . . . . . . . . . . . . . . . 8
2.2.1. Sender Packets. . . . . . . . . . . . . . . . . . 8 2.2.1. Sender Packets. . . . . . . . . . . . . . . . . . 9
2.2.2. Feedback Packets. . . . . . . . . . . . . . . . . 10 2.2.2. Feedback Packets. . . . . . . . . . . . . . . . . 10
3. Data Sender Protocol. . . . . . . . . . . . . . . . . . 10 3. Data Sender Protocol. . . . . . . . . . . . . . . . . . 11
3.1. Sender Initialization. . . . . . . . . . . . . . . . 11 3.1. Sender Initialization. . . . . . . . . . . . . . . . 11
3.2. Determining the Maximum RTT. . . . . . . . . . . . . 11 3.2. Determining the Maximum RTT. . . . . . . . . . . . . 11
3.3. Adjusting the Sending Rate . . . . . . . . . . . . . 12 3.3. Adjusting the Sending Rate . . . . . . . . . . . . . 12
3.4. Controlling Receiver Feedback. . . . . . . . . . . . 13 3.4. Controlling Receiver Feedback. . . . . . . . . . . . 13
3.5. Assisting Receiver-Side RTT Measurements . . . . . . 14 3.5. Assisting Receiver-Side RTT Measurements . . . . . . 14
3.6. Slowstart. . . . . . . . . . . . . . . . . . . . . . 15 3.6. Slowstart. . . . . . . . . . . . . . . . . . . . . . 15
3.7. Scheduling of Packet Transmissions . . . . . . . . . 16 3.7. Scheduling of Packet Transmissions . . . . . . . . . 16
4. Data Receiver Protocol. . . . . . . . . . . . . . . . . 16 4. Data Receiver Protocol. . . . . . . . . . . . . . . . . 17
4.1. Receiver Initialization. . . . . . . . . . . . . . . 17 4.1. Receiver Initialization. . . . . . . . . . . . . . . 17
4.2. Receiver Leave . . . . . . . . . . . . . . . . . . . 17 4.2. Receiver Leave . . . . . . . . . . . . . . . . . . . 17
4.3. Measurement of the Network Conditions. . . . . . . . 17 4.3. Measurement of the Network Conditions. . . . . . . . 18
4.3.1. Updating the Loss Event Rate. . . . . . . . . . . 17 4.3.1. Updating the Loss Event Rate. . . . . . . . . . . 18
4.3.2. Basic Round-Trip Time Measurement . . . . . . . . 17 4.3.2. Basic Round-Trip Time Measurement . . . . . . . . 18
4.3.3. One-Way Delay Adjustments . . . . . . . . . . . . 18 4.3.3. One-Way Delay Adjustments . . . . . . . . . . . . 19
4.3.4. Receive Rate Measurements . . . . . . . . . . . . 19 4.3.4. Receive Rate Measurements . . . . . . . . . . . . 19
4.4. Setting the Desired Rate . . . . . . . . . . . . . . 19 4.4. Setting the Desired Rate . . . . . . . . . . . . . . 20
4.5. Feedback and Feedback Suppression. . . . . . . . . . 20 4.5. Feedback and Feedback Suppression. . . . . . . . . . 20
5. Calculation of the Loss Event Rate. . . . . . . . . . . 21 5. Calculation of the Loss Event Rate. . . . . . . . . . . 22
5.1. Detection of Lost or Marked Packets. . . . . . . . . 22 5.1. Detection of Lost or Marked Packets. . . . . . . . . 22
5.2. Translation from Loss History to Loss Events . . . . 22 5.2. Translation from Loss History to Loss Events . . . . 23
5.3. Inter-Loss Event Interval. . . . . . . . . . . . . . 23 5.3. Inter-Loss Event Interval. . . . . . . . . . . . . . 24
5.4. Average Loss Interval. . . . . . . . . . . . . . . . 24 5.4. Average Loss Interval. . . . . . . . . . . . . . . . 24
5.5. History Discounting. . . . . . . . . . . . . . . . . 25 5.5. History Discounting. . . . . . . . . . . . . . . . . 25
5.6. Initializing the Loss History after the First 5.6. Initializing the Loss History after the First
Loss Event. . . . . . . . . . . . . . . . . . . . . . . . 27 Loss Event. . . . . . . . . . . . . . . . . . . . . . . . 28
6. Security Considerations . . . . . . . . . . . . . . . . 28 6. Security Considerations . . . . . . . . . . . . . . . . 29
7. IANA Considerations . . . . . . . . . . . . . . . . . . 29 7. IANA Considerations . . . . . . . . . . . . . . . . . . 29
8. Authors' Addresses. . . . . . . . . . . . . . . . . . . 29 8. Authors' Addresses. . . . . . . . . . . . . . . . . . . 30
9. Acknowledgments . . . . . . . . . . . . . . . . . . . . 29 9. Acknowledgments . . . . . . . . . . . . . . . . . . . . 30
10. References . . . . . . . . . . . . . . . . . . . . . . 30 10. References . . . . . . . . . . . . . . . . . . . . . . 30
10.1. Normative References. . . . . . . . . . . . . . . . 30
10.2. Informative References. . . . . . . . . . . . . . . 30
11. Copyright Notice . . . . . . . . . . . . . . . . . . . 31 11. Copyright Notice . . . . . . . . . . . . . . . . . . . 31
Expires: September 2006 March 2006 Expires: November 2006 May 2006
1. Introduction 1. Introduction
This document specifies TCP-Friendly Multicast Congestion Control This document specifies TCP-Friendly Multicast Congestion Control
(TFMCC) [10]. TFMCC is a source-based, single-rate congestion control (TFMCC) [4]. TFMCC is a source-based, single-rate congestion control
scheme that builds upon the unicast TCP-Friendly Rate Control mechanism scheme that builds upon the unicast TCP-Friendly Rate Control mechanism
(TFRC) [2]. TFMCC is stable and responsive under a wide range of network (TFRC) [5]. TFMCC is stable and responsive under a wide range of
conditions and scales to receiver sets on the order of several thousand network conditions and scales to receiver sets on the order of several
receivers. To support scalability, as much congestion control thousand receivers. To support scalability, as much congestion control
functionality as possible is located at the receivers. Each receiver functionality as possible is located at the receivers. Each receiver
continuously determines a desired receive rate that is TCP-friendly for continuously determines a desired receive rate that is TCP-friendly for
the path from the sender to this receiver. Selected receivers then the path from the sender to this receiver. Selected receivers then
report the rate to the sender in feedback packets. report the rate to the sender in feedback packets.
TFMCC is a building block as defined in RFC 3048. Instead of specifying TFMCC is a building block as defined in RFC 3048 [1]. Instead of
a complete protocol, this document simply specifies a congestion control specifying a complete protocol, this document simply specifies a
mechanism that could be used in a transport protocol such as RTP [7], in congestion control mechanism that could be used in a transport protocol
an application incorporating end-to-end congestion control at the such as RTP [12], in an application incorporating end-to-end congestion
application level. This document does not discuss packet formats, control at the application level. This document does not discuss packet
reliability, or implementation-related issues. formats, reliability, or implementation-related issues.
TFMCC is designed to be reasonably fair when competing for bandwidth TFMCC is designed to be reasonably fair when competing for bandwidth
with TCP flows. A multicast flow is ``reasonably fair'' if its sending with TCP flows. A multicast flow is ``reasonably fair'' if its sending
rate is generally within a factor of two of the sending rate of a TCP rate is generally within a factor of two of the sending rate of a TCP
flow from the sender to the slowest receiver of the multicast group flow from the sender to the slowest receiver of the multicast group
under the same network conditions. under the same network conditions.
In general, TFMCC has a low variation of throughput, which makes it In general, TFMCC has a low variation of throughput, which makes it
suitable for applications such as streaming media where a relatively suitable for applications such as streaming media where a relatively
smooth sending rate is of importance. The penalty of having smooth smooth sending rate is of importance. The penalty of having smooth
throughput while competing fairly for bandwidth is a reduced throughput while competing fairly for bandwidth is a reduced
responsiveness to changes in available bandwidth. Thus TFMCC should be responsiveness to changes in available bandwidth. Thus TFMCC should be
used when the application has a requirement for smooth throughput, in used when the application has a requirement for smooth throughput, in
particular, avoiding halving of the sending rate in response to a single particular, avoiding halving of the sending rate in response to a single
packet drop. For applications that simply need to multicast as much packet drop. For applications that simply need to multicast as much
data as possible in as short a time as possible, PGMCC [6] may be more data as possible in as short a time as possible, PGMCC [11] may be more
suitable. suitable.
1.1. Terminology 1.1. Terminology
In this document, the key words "MUST", "MUST NOT", "REQUIRED", "SHALL", In this document, the key words "MUST", "MUST NOT", "REQUIRED", "SHALL",
"SHALL NOT", "SHOULD", "SHOULD NOT", "RECOMMENDED", "MAY", and "SHALL NOT", "SHOULD", "SHOULD NOT", "RECOMMENDED", "MAY", and
"OPTIONAL" are to be interpreted as described in RFC 2119 and indicate "OPTIONAL" are to be interpreted as described in BCP 14, RFC 2119 [2]
requirement levels for compliant TFMCC implementations. and indicate requirement levels for compliant TFMCC implementations.
Expires: September 2006 March 2006 Expires: November 2006 May 2006
1.2. Related Documents 1.2. Related Documents
As described in RFC 3048, TFMCC is a building block that is intended to As described in RFC 3048 [1], TFMCC is a building block that is intended
be used, in conjunction with other building blocks, to help specify a to be used, in conjunction with other building blocks, to help specify a
protocol instantiation. In particular, TFMCC is a suitable congestion protocol instantiation. It follows the general guidelines provided in
control building block for NACK-Oriented Reliable Multicast (NORM) [1]. RFC 3269 [3]. In particular, TFMCC is a suitable congestion control
building block for NACK-Oriented Reliable Multicast (NORM) [6].
1.3. Environmental Requirements and Considerations 1.3. Environmental Requirements and Considerations
TFMCC is intended to be a congestion control scheme that can be used in TFMCC is intended to be a congestion control scheme that can be used in
a complete protocol instantiation that delivers objects and streams a complete protocol instantiation that delivers objects and streams
(both reliable content delivery and streaming of multimedia (both reliable content delivery and streaming of multimedia
information). information).
TFMCC is most applicable for sessions that deliver a substantial amount TFMCC is most applicable for sessions that deliver a substantial amount
of data, i.e., in length from hundreds of kilobytes to many gigabytes, of data, i.e., in length from hundreds of kilobytes to many gigabytes,
and whose duration is in the order of tens of seconds or more. and whose duration is in the order of tens of seconds or more.
TFMCC is intended for multicast delivery. There are currently two TFMCC is intended for multicast delivery. There are currently two
models of multicast delivery, the Any-Source Multicast (ASM) model as models of multicast delivery, the Any-Source Multicast (ASM) model as
defined in RFC 1112 and the Source-Specific Multicast (SSM) model as defined in [7] defined in [8]. TFMCC works with both multicast models,
defined in [3]. TFMCC works with both multicast models, but in a but in a slightly different way. When using ASM, feedback from the
slightly different way. When using ASM, feedback from the receivers is receivers is multicast to the sender as well as to all other receivers.
multicast to the sender as well as to all other receivers. Feedback can Feedback can be either multicast on the same group address used for
be either multicast on the same group address used for sending data or sending data or on a separate multicast feedback group address. For
on a separate multicast feedback group address. For SSM, the receivers SSM, the receivers must unicast the feedback directly to the sender.
must unicast the feedback directly to the sender. Hence, feedback from Hence, feedback from a receiver will not be received by other receivers.
a receiver will not be received by other receivers.
TFMCC inherently works with all types of networks, including LANs, WANs, TFMCC inherently works with all types of networks that allow bi-
Intranets, the Internet, asymmetric networks, wireless networks, and directional communication, including LANs, WANs, Intranets, the
satellite networks. However, in some network environments varying the Internet, asymmetric networks, wireless networks, and satellite
sending rate to the receivers may not be advantageous (e.g., for a networks. However, in some network environments varying the sending
satellite or wireless network, there may be no mechanism for receivers rate to the receivers may not be advantageous (e.g., for a satellite or
to effectively reduce their reception rate since there may be a fixed wireless network, there may be no mechanism for receivers to effectively
transmission rate allocated to the session). reduce their reception rate since there may be a fixed transmission rate
allocated to the session).
The difference in responsiveness of TFMCC and TCP may result in The difference in responsiveness of TFMCC and TCP may result in
significant throughput differences in case of a very low bitrate. TFMCC significant throughput differences in case of a very low bitrate. TFMCC
requires an estimate of the loss event rate to calculate a fair sending requires an estimate of the loss event rate to calculate a fair sending
rate. This estimate may be inaccurate in case TFMCC receives only very rate. This estimate may be inaccurate in case TFMCC receives only very
few packets per RTT. TFMCC should not be used together with TCP if the few packets per RTT. TFMCC should not be used together with TCP if the
capacity of the bottleneck link is less than 30KBit/s (e.g., a very slow capacity of the bottleneck link is less than 30KBit/s (e.g., a very slow
modem connection). TFMCC may also achieve a rate that is very different modem connection). TFMCC may also achieve a rate that is very different
from the average TCP rate in case buffer space at the bottleneck is from the average TCP rate in case buffer space at the bottleneck is
severely underprovisioned. In particular, TFMCC is less susceptible to severely underprovisioned. In particular, TFMCC is less susceptible to
small buffer sizes since TFMCC spaces out packets in time, while TCP Expires: November 2006 May 2006
Expires: September 2006 March 2006
small buffer sizes since TFMCC spaces out packets in time, while TCP
sends them back-to-back. Thus TCP is much more likely to see a packet sends them back-to-back. Thus TCP is much more likely to see a packet
loss if buffer space is scarce. loss if buffer space is scarce.
TFMCC is designed for applications that use a fixed packet size, and TFMCC is designed for applications that use a fixed packet size, and
vary their sending rate in packets per second in response to congestion. vary their sending rate in packets per second in response to congestion.
Some audio applications require a fixed interval of time between packets Some applications, e.g. those using audio, require a fixed interval of
and vary their packet size instead of their packet rate in response to time between packets and vary their packet size instead of their packet
congestion. The congestion control mechanism in this document cannot be rate in response to congestion. The congestion control mechanism in
used by those applications. this document cannot be used by those applications.
2. Protocol Overview 2. Protocol Overview
TFMCC extends the basic mechanisms of TFRC into the multicast domain. TFMCC extends the basic mechanisms of TFRC into the multicast domain.
In order to compete fairly with TCP, TFMCC receivers individually In order to compete fairly with TCP, TFMCC receivers individually
measure the prevalent network conditions and calculate a rate that is measure the prevalent network conditions and calculate a rate that is
TCP-friendly on the path from the sender to themselves. The rate is TCP-friendly on the path from the sender to themselves. The rate is
determined using an equation for TCP throughput, which roughly describes determined using an equation for TCP throughput, which roughly describes
TCP's sending rate as a function of the loss event rate, round-trip time TCP's sending rate as a function of the loss event rate, round-trip time
(RTT), and packet size. We define a loss event as one or more lost or (RTT), and packet size. We define a loss event as one or more lost or
marked packets from the packets received during one RTT, where a marked marked packets from the packets received during one RTT, where a marked
packet refers to a congestion indication from Explicit Congestion packet refers to a congestion indication from Explicit Congestion
Notification (ECN) [5]. The sending rate of the multicast transmission Notification (ECN) [10]. The sending rate of the multicast transmission
is adapted to the receiver experiencing the worst network conditions. is adapted to the receiver experiencing the worst network conditions.
Basically, TFMCC's congestion control mechanism works as follows: Basically, TFMCC's congestion control mechanism works as follows:
o Each receiver measures the loss event rate and its RTT to the sender. o Each receiver measures the loss event rate and its RTT to the sender.
o Each receiver then uses this information, together with an equation o Each receiver then uses this information, together with an equation
for TCP throughput, to derive a TCP-friendly sending rate. for TCP throughput, to derive a TCP-friendly sending rate.
o Through a distributed feedback suppression mechanism, only a subset of o Through a distributed feedback suppression mechanism, only a subset of
skipping to change at page 6, line 52 skipping to change at page 7, line 4
o Receivers whose feedback is not suppressed report the calculated o Receivers whose feedback is not suppressed report the calculated
transmission rate back to the sender in so-called receiver reports. transmission rate back to the sender in so-called receiver reports.
The receiver reports serve two purposes: they inform the sender about The receiver reports serve two purposes: they inform the sender about
the appropriate transmit rate, and they allow the receivers to measure the appropriate transmit rate, and they allow the receivers to measure
their RTT. their RTT.
o The sender selects the receiver that reports the lowest rate as o The sender selects the receiver that reports the lowest rate as
current limiting receiver (CLR). Whenever feedback with an even lower current limiting receiver (CLR). Whenever feedback with an even lower
rate reaches the sender, the corresponding receiver becomes CLR and rate reaches the sender, the corresponding receiver becomes CLR and
the sending rate is reduced to match that receiver's calculated rate. Expires: November 2006 May 2006
Expires: September 2006 March 2006
the sending rate is reduced to match that receiver's calculated rate.
The sending rate increases when the CLR reports a calculated rate The sending rate increases when the CLR reports a calculated rate
higher than the current sending rate. higher than the current sending rate.
The dynamics of TFMCC are sensitive to how the measurements are The dynamics of TFMCC are sensitive to how the measurements are
performed and applied and what feedback suppression mechanism is chosen. performed and applied and what feedback suppression mechanism is chosen.
We recommend specific mechanisms below to perform and apply these We recommend specific mechanisms below to perform and apply these
measurements. Other mechanisms are possible, but it is important to measurements. Other mechanisms are possible, but it is important to
understand how the interactions between mechanisms affect the dynamics understand how the interactions between mechanisms affect the dynamics
of TFMCC. of TFMCC.
skipping to change at page 7, line 31 skipping to change at page 7, line 31
the TCP throughput equation used must reflect TCP's retransmit timeout the TCP throughput equation used must reflect TCP's retransmit timeout
behavior, as this dominates TCP throughput at higher loss rates. We behavior, as this dominates TCP throughput at higher loss rates. We
also note that the assumptions implicit in the throughput equation about also note that the assumptions implicit in the throughput equation about
the loss event rate parameter have to be a reasonable match to how the the loss event rate parameter have to be a reasonable match to how the
loss rate or loss event rate is actually measured. While this match is loss rate or loss event rate is actually measured. While this match is
not perfect for the throughput equation and loss rate measurement not perfect for the throughput equation and loss rate measurement
mechanisms given below, in practice the assumptions turn out to be close mechanisms given below, in practice the assumptions turn out to be close
enough. enough.
The throughput equation we currently recommend for TFMCC is a slightly The throughput equation we currently recommend for TFMCC is a slightly
simplified version of the throughput equation for Reno TCP from [4]: simplified version of the throughput equation for Reno TCP from [9]:
8 s 8 s
X = --------------------------------------------------------- (1) X = --------------------------------------------------------- (1)
R * (sqrt(2*p/3) + (12*sqrt(3*p/8) * p * (1+32*p^2))) R * (sqrt(2*p/3) + (12*sqrt(3*p/8) * p * (1+32*p^2)))
where where
X is the transmit rate in bits/second. X is the transmit rate in bits/second.
s is the packet size in bytes. s is the packet size in bytes.
R is the round-trip time in seconds. R is the round-trip time in seconds.
p is the loss event rate, between 0.0 and 1.0, of the number of p is the loss event rate, between 0.0 and 1.0, of the number of
loss events as a fraction of the number of packets transmitted. loss events as a fraction of the number of packets transmitted.
Expires: November 2006 May 2006
In future, different TCP equations may be substituted for this equation. In future, different TCP equations may be substituted for this equation.
The requirement is that the throughput equation be a reasonable The requirement is that the throughput equation be a reasonable
Expires: September 2006 March 2006
approximation of the sending rate of TCP for conformant TCP congestion approximation of the sending rate of TCP for conformant TCP congestion
control. control.
The parameters s (packet size), p (loss event rate) and R (RTT) need to The parameters s (packet size), p (loss event rate) and R (RTT) need to
be measured or calculated by a TFMCC implementation. The measurement of be measured or calculated by a TFMCC implementation. The measurement of
R is specified in Section 4.3.2, and the measurement of p is specified R is specified in Section 4.3.2, and the measurement of p is specified
in Section 5. The parameter s (packet size) is normally known to an in Section 5. The parameter s (packet size) is normally known to an
application. This may not be so in two cases: application. This may not be so in two cases:
o The packet size naturally varies depending on the data. In this case, o The packet size naturally varies depending on the data. In this case,
skipping to change at page 8, line 47 skipping to change at page 9, line 5
include timestamp information destined for more than one receiver to include timestamp information destined for more than one receiver to
allow a sufficient number of receivers to measure their RTT. allow a sufficient number of receivers to measure their RTT.
As TFMCC will be used along with a transport protocol, we do not specify As TFMCC will be used along with a transport protocol, we do not specify
packet formats, since these depend on the details of the transport packet formats, since these depend on the details of the transport
protocol used. The recommended representation of the header fields is protocol used. The recommended representation of the header fields is
given below. Alternatively, if the computational overhead of a floating given below. Alternatively, if the computational overhead of a floating
point representation is prohibitive, fixed point arithmetic can be used point representation is prohibitive, fixed point arithmetic can be used
at the expense of larger packet headers. at the expense of larger packet headers.
Expires: November 2006 May 2006
2.2.1. Sender Packets 2.2.1. Sender Packets
Each packet sent by the data sender contains the following information: Each packet sent by the data sender contains the following information:
Expires: September 2006 March 2006
o A sequence number i. This number is incremented by one for each data o A sequence number i. This number is incremented by one for each data
packet transmitted. The field must be sufficiently large that it does packet transmitted. The field must be sufficiently large that it does
not wrap causing two different packets with the same sequence number not wrap causing two different packets with the same sequence number
to be in the receiver's recent packet history at the same time. In to be in the receiver's recent packet history at the same time. In
most cases the sequence number will be supplied by the transport most cases the sequence number will be supplied by the transport
protocol used along with TFMCC. protocol used along with TFMCC.
o A suppression rate X_supp in bits/s. Only receivers with a calculated o A suppression rate X_supp in bits/s. Only receivers with a calculated
rate lower than the suppression rate are eligible to give feedback, rate lower than the suppression rate are eligible to give feedback,
unless their RTT is higher than the maximum RTT described below in unless their RTT is higher than the maximum RTT described below in
which case they are also eligible to give feedback. The suppression which case they are also eligible to give feedback. The suppression
rate should be represented as a 12 bit floating point value with 5 rate should be represented as a 12 bit floating point value with 5
bits for the unsigned exponent and 7 bits for the unsigned mantissa bits for the unsigned exponent and 7 bits for the unsigned mantissa
(to represent rates from 100 bit/s to 400 Gbit/s with an error of less (to represent rates from 100 bit/s to 400 Gbit/s with an error of less
than 1%). than 1%).
o A timestamp ts_i indicating when the packet is sent. The resolution o A timestamp ts_i indicating when the packet is sent. The resolution
of the timestamp should typically be milliseconds and the timestamp of the timestamp should typically be milliseconds and the timestamp
should be an unsigned integer value no less than 16 bits wide. should be an unsigned integer value no less than 16 bits wide.
o A receiver ID r and a copy of the timestamp ts_r of that receiver's o A receiver ID r and a copy of the timestamp tr_r' = tr_r of that
last report, which allows the receiver to measure its RTT. The receiver's last report, which allows the receiver to measure its RTT.
receiver ID is described in the next section. The resolution of the If there is a delay ts_d between receiving the report from receiver r
timestamp echo should be milliseconds and the timestamp should be an and sending the data packet, then tr_r' = tr_r + ts_d is included in
unsigned integer value no less than 16 bits wide. If separate instead the packet instead. The receiver ID is described in the next section.
of piggybacked congestion control messages are used, the packet needs The resolution of the timestamp echo should be milliseconds and the
to contain a list of receiver IDs with corresponding timestamps to timestamp should be an unsigned integer value no less than 16 bits
allow a sufficient number of receivers to simultaneously measure their wide. If separate instead of piggybacked congestion control messages
RTT. For the default values used for the feedback process this are used, the packet needs to contain a list of receiver IDs with
corresponds to a list size on the order of 10 to 20 entries. corresponding timestamps to allow a sufficient number of receivers to
simultaneously measure their RTT. For the default values used for the
feedback process this corresponds to a list size on the order of 10 to
20 entries.
o A flag is_CLR indicating whether the receiver with ID r is the CLR. o A flag is_CLR indicating whether the receiver with ID r is the CLR.
o A feedback round counter fb_nr. This counter is incremented by the o A feedback round counter fb_nr. This counter is incremented by the
sender at the beginning of a new feedback round to notify the sender at the beginning of a new feedback round to notify the
receivers than all feedback for older rounds should be suppressed. receivers than all feedback for older rounds should be suppressed.
The feedback round counter should be at least 4 bits wide. The feedback round counter should be at least 4 bits wide.
o A maximum RTT value R_max, representing the maximum of the RTTs of all o A maximum RTT value R_max, representing the maximum of the RTTs of all
receivers. The RTT should be measured in milliseconds. An 8 bit receivers. The RTT should be measured in milliseconds. An 8 bit
floating point value with 4 bits for the unsigned exponent and 4 bits floating point value with 4 bits for the unsigned exponent and 4 bits
Expires: November 2006 May 2006
for the unsigned mantissa (to represent RTTs from 1 millisecond to 64 for the unsigned mantissa (to represent RTTs from 1 millisecond to 64
seconds with an error of ca. 6%) should be used for the seconds with an error of ca. 6%) should be used for the
representation. representation.
Expires: September 2006 March 2006
2.2.2. Feedback Packets 2.2.2. Feedback Packets
Each feedback packet sent by a data receiver contains the following Each feedback packet sent by a data receiver contains the following
information: information:
o A unique receiver ID r. In most cases the receiver ID will be o A unique receiver ID r. In most cases the receiver ID will be
supplied by the transport protocol, but it may simply be the IP supplied by the transport protocol, but it may simply be the IP
address of the receiver. address of the receiver.
o A flag have_RTT indicating whether the receiver has made at least one o A flag have_RTT indicating whether the receiver has made at least one
RTT measurement since it joined the session. RTT measurement since it joined the session.
o A flag have_loss indicating whether the receiver experienced at least o A flag have_loss indicating whether the receiver experienced at least
one loss event since it joined the session. one loss event since it joined the session.
o A flag receiver_leave indicating that the receiver will leave the o A flag receiver_leave indicating that the receiver will leave the
session (and should therefore not be CLR). session (and should therefore not be CLR).
o A timestamp ts_r indicating when the feedback packet is sent. The o A timestamp tr_r indicating when the feedback packet is sent. The
representation of the timestamp should be the same as that of the representation of the timestamp should be the same as that of the
timestamp echo in the data packets. timestamp echo in the data packets.
o An echo of the timestamp of the last data packet received. If the o An echo ts_i' of the timestamp of the last data packet received. If
last packet received at the receiver has sequence number i, then ts_i the last packet received at the receiver has sequence number i, then
is included in the feedback. If there is a delay t_d between ts_i' = ts_i is included in the feedback. If there is a delay tr_d
receiving that last data packet and sending feedback, then ts_i' = between receiving that last data packet and sending feedback, then
ts_i + t_d is included in the feedback instead of ts_i. The ts_i' = ts_i + tr_d is included in the feedback instead. The
representation of the timestamp echo should be the same as that of the representation of the timestamp echo should be the same as that of the
timestamp in the data packets. timestamp in the data packets.
o A feedback round echo fb_nr, reflecting the highest feedback round o A feedback round echo fb_nr, reflecting the highest feedback round
counter value received so far. The representation of the feedback counter value received so far. The representation of the feedback
round echo should be the same as the one used for the feedback round round echo should be the same as the one used for the feedback round
counter in the data packets. counter in the data packets.
o The desired sending rate X_r. This is the rate calculated by the o The desired sending rate X_r. This is the rate calculated by the
receiver to be TCP-friendly on the path from the sender to this receiver to be TCP-friendly on the path from the sender to this
receiver. The representation of the desired sending rate should be receiver. The representation of the desired sending rate should be
the same as that of the suppression rate in the data packets. the same as that of the suppression rate in the data packets.
Expires: November 2006 May 2006
3. Data Sender Protocol 3. Data Sender Protocol
The data sender multicasts a stream of data packets to the data The data sender multicasts a stream of data packets to the data
receivers at a controlled rate. Whenever feedback is received, the receivers at a controlled rate. Whenever feedback is received, the
sender checks if it is necessary to switch CLRs and to readjust the sender checks if it is necessary to switch CLRs and to readjust the
sending rate. sending rate.
Expires: September 2006 March 2006
The main tasks that have to be provided by a TFMCC sender are: The main tasks that have to be provided by a TFMCC sender are:
o adjusting the sending rate, o adjusting the sending rate,
o controlling receiver feedback, and o controlling receiver feedback, and
o assisting receiver-side RTT measurements. o assisting receiver-side RTT measurements.
3.1. Sender Initialization 3.1. Sender Initialization
skipping to change at page 11, line 28 skipping to change at page 11, line 35
should be larger than the highest RTT to any of the receivers. It should be larger than the highest RTT to any of the receivers. It
should not be smaller than 500 milliseconds for operation in the public should not be smaller than 500 milliseconds for operation in the public
Internet. The sending rate X is initialized to 1 packet per maximum Internet. The sending rate X is initialized to 1 packet per maximum
RTT. RTT.
3.2. Determining the Maximum RTT 3.2. Determining the Maximum RTT
For each feedback packet that arrives at the sender, the sender computes For each feedback packet that arrives at the sender, the sender computes
the instantaneous RTT to the receiver as the instantaneous RTT to the receiver as
R_r = t_now - ts_i R_r = ts_now - ts_i'
where t_now is the time the feedback packet arrived. Receivers will where ts_now is the time the feedback packet arrived. Receivers will
have adjusted ts_i for the time interval between receiving the last data have adjusted ts_i' for the time interval between receiving the last
packet and sending the corresponding report so that this interval will data packet and sending the corresponding report so that this interval
not be included in R_r. If the actual RTT is smaller than the will not be included in R_r. If the actual RTT is smaller than the
resolution of the timestamps and t_now equals ts_i, then R_r is set to resolution of the timestamps and ts_now equals ts_i', then R_r is set to
the smallest positive RTT value larger than 0 (i.e., 1 millisecond in the smallest positive RTT value larger than 0 (i.e., 1 millisecond in
our case). If the instantaneous RTT is larger than the current maximum our case). If the instantaneous RTT is larger than the current maximum
RTT, the maximum RTT is increased to that value RTT, the maximum RTT is increased to that value
R_max = R_r R_max = R_r
Otherwise, if no feedback with a higher instantaneous RTT than the Otherwise, if no feedback with a higher instantaneous RTT than the
maximum RTT is received during a feedback round (see Section 3.4), the maximum RTT is received during a feedback round (see Section 3.4), the
maximum RTT is reduced to maximum RTT is reduced to
Expires: November 2006 May 2006
R_max = MAX(R_max * 0.9, R_peak) R_max = MAX(R_max * 0.9, R_peak)
where R_peak is the peak receiver RTT measured during the feedback where R_peak is the peak receiver RTT measured during the feedback
round. round.
The maximum RTT is mainly used for feedback suppression among receivers The maximum RTT is mainly used for feedback suppression among receivers
with heterogeneous RTTs. Feedback suppression is closely coupled to the with heterogeneous RTTs. Feedback suppression is closely coupled to the
sending of data packets and for this reason, the maximum RTT must not sending of data packets and for this reason, the maximum RTT must not
Expires: September 2006 March 2006
decrease below the maximum time interval between consecutive data decrease below the maximum time interval between consecutive data
packets: packets:
R_max = max(R_max, s/X + t_gran) R_max = max(R_max, 8s/X + ts_gran)
where t_gran is the granularity of the sender's system clock (see where ts_gran is the granularity of the sender's system clock (see
Section 3.7). Section 3.7).
3.3. Adjusting the Sending Rate 3.3. Adjusting the Sending Rate
When a feedback packet from receiver r arrives at the sender, the sender When a feedback packet from receiver r arrives at the sender, the sender
has to check whether it is necessary to adjust the transmission rate and has to check whether it is necessary to adjust the transmission rate and
to switch to a new CLR. to switch to a new CLR.
How the rate is adjusted depends on the desired rate X_r of the receiver How the rate is adjusted depends on the desired rate X_r of the receiver
report. We distinguish four cases: report. We distinguish four cases:
skipping to change at page 12, line 46 skipping to change at page 13, line 5
3 If receiver r is not the CLR but a CLR is present and the 3 If receiver r is not the CLR but a CLR is present and the
receiver_leave flag of the CLR's last report was set, then receiver receiver_leave flag of the CLR's last report was set, then receiver
r becomes the current limiting receiver. However, if X_r > X, the r becomes the current limiting receiver. However, if X_r > X, the
sending rate is not increased to X_r for the duration of a feedback sending rate is not increased to X_r for the duration of a feedback
round to allow other (lower rate) receivers to give feedback and be round to allow other (lower rate) receivers to give feedback and be
selected as CLR. selected as CLR.
4 If receiver r is the CLR, the sending rate is set to the minimum of 4 If receiver r is the CLR, the sending rate is set to the minimum of
X_r and X + 8s/R_max bits/s. X_r and X + 8s/R_max bits/s.
Expires: November 2006 May 2006
If the receiver has not yet measured its RTT but already experienced If the receiver has not yet measured its RTT but already experienced
packet loss (indicated by the corresponding flags in the receiver packet loss (indicated by the corresponding flags in the receiver
report), the receiver report will include a desired rate that is based report), the receiver report will include a desired rate that is based
on the maximum RTT rather than the actual RTT to that receiver. In this on the maximum RTT rather than the actual RTT to that receiver. In this
case, the sender adjusts the desired rate using its measurement of the case, the sender adjusts the desired rate using its measurement of the
instantaneous RTT R_r to that receiver: instantaneous RTT R_r to that receiver:
Expires: September 2006 March 2006
X_r' = X_r * R_max / R_r X_r' = X_r * R_max / R_r
X_r' is then used instead of X_r to detect whether to switch to a new X_r' is then used instead of X_r to detect whether to switch to a new
CLR. CLR.
If the TFMCC sender receives no reports from the CLR for 4 RTTs, the If the TFMCC sender receives no reports from the CLR for 4 RTTs, the
sending rate is cut in half unless the CLR was selected less than 10 sending rate is cut in half unless the CLR was selected less than 10
RTTs ago. In addition, if the sender receives no reports from the CLR RTTs ago. In addition, if the sender receives no reports from the CLR
for at least 10 RTTs, it assumes that the CLR crashed or left the group. for at least 10 RTTs, it assumes that the CLR crashed or left the group.
A new CLR is selected from the feedback that subsequently arrives at the A new CLR is selected from the feedback that subsequently arrives at the
skipping to change at page 13, line 48 skipping to change at page 14, line 5
Only receivers wishing to report a rate that is lower than the Only receivers wishing to report a rate that is lower than the
suppression rate X_supp, or those with a higher RTT than R_max may send suppression rate X_supp, or those with a higher RTT than R_max may send
feedback. At the beginning of each feedback round, X_supp is set to the feedback. At the beginning of each feedback round, X_supp is set to the
highest possible value that can be represented. When feedback arrives highest possible value that can be represented. When feedback arrives
at the sender over the course of a feedback round, X_supp is decreased at the sender over the course of a feedback round, X_supp is decreased
such that more and more feedback is suppressed towards the end of the such that more and more feedback is suppressed towards the end of the
round. How receiver feedback is spread out over the feedback round is round. How receiver feedback is spread out over the feedback round is
discussed in Section 4.5. discussed in Section 4.5.
Expires: November 2006 May 2006
Whenever non-CLR feedback for the current round arrives at the sender, Whenever non-CLR feedback for the current round arrives at the sender,
X_supp is reduced to X_supp is reduced to
X_supp = (1-g) * X_r X_supp = (1-g) * X_r
if X_supp > X_r. Feedback that causes the corresponding receiver to be if X_supp > X_r. Feedback that causes the corresponding receiver to be
Expires: September 2006 March 2006
selected as CLR, but was from a non-CLR receiver at the time of sending selected as CLR, but was from a non-CLR receiver at the time of sending
also contributes to the feedback suppression. Note that X_r must not be also contributes to the feedback suppression. Note that X_r must not be
adjusted by the sender to reflect the receiver's real RTT in case X_r adjusted by the sender to reflect the receiver's real RTT in case X_r
was calculated using the maximum RTT, as is done for setting the sending was calculated using the maximum RTT, as is done for setting the sending
rate (Section 3.3), otherwise a feedback implosion is possible. The rate (Section 3.3), otherwise a feedback implosion is possible. The
parameter g determines to what extent higher rate feedback can suppress parameter g determines to what extent higher rate feedback can suppress
lower rate feedback. This mechanism guarantees, that the lowest lower rate feedback. This mechanism guarantees, that the lowest
calculated rate reported lies within a factor of g of the actual lowest calculated rate reported lies within a factor of g of the actual lowest
calculated rate of the receiver set (see [9]). A value of g of 0.1 is calculated rate of the receiver set (see [14]). A value of g of 0.1 is
recommended. recommended.
To allow receivers to suppress their feedback, the sender's suppression To allow receivers to suppress their feedback, the sender's suppression
rate needs to be updated whenever feedback is received. This rate needs to be updated whenever feedback is received. This
suppression rate has to be communicated to the receivers in a timely suppression rate has to be communicated to the receivers in a timely
manner, either by including it in the data packet header or, if separate manner, either by including it in the data packet header or, if separate
congestion control messages are used, by sending a message with the congestion control messages are used, by sending a message with the
suppression rate whenever the rate changes significantly (i.e., when it suppression rate whenever the rate changes significantly (i.e., when it
is reduced to less than (1-g) times the previously advertised is reduced to less than (1-g) times the previously advertised
suppression rate). suppression rate).
skipping to change at page 14, line 46 skipping to change at page 15, line 5
report, which is echoed by the sender. If congestion control report, which is echoed by the sender. If congestion control
information is piggybacked onto data packets, usually only one receiver information is piggybacked onto data packets, usually only one receiver
ID and timestamp can be included. If multiple feedback messages from ID and timestamp can be included. If multiple feedback messages from
different receivers arrive at the sender during the time interval different receivers arrive at the sender during the time interval
between two data packets, the sender has to decide which receiver to between two data packets, the sender has to decide which receiver to
allow to measure RTT. The same applies if separate congestion control allow to measure RTT. The same applies if separate congestion control
messages allow to echo multiple receiver timestamps simultaneously but messages allow to echo multiple receiver timestamps simultaneously but
the number of receivers that gave feedback since the last congestion the number of receivers that gave feedback since the last congestion
control message exceeds the list size. control message exceeds the list size.
Expires: November 2006 May 2006
The sender's timestamp echoes are prioritized in the following order: The sender's timestamp echoes are prioritized in the following order:
1. a new CLR (after a change of CLR's) or a CLR without any previous 1. a new CLR (after a change of CLR's) or a CLR without any previous
RTT measurements RTT measurements
2. receivers without any previous RTT measurements in the order of the 2. receivers without any previous RTT measurements in the order of the
feedback round echo of the corresponding receiver report (i.e., feedback round echo of the corresponding receiver report (i.e.,
Expires: September 2006 March 2006
older feedback first) older feedback first)
3. non-CLR receivers with previous RTT measurements, again in 3. non-CLR receivers with previous RTT measurements, again in
ascending order of the feedback round echo of the report ascending order of the feedback round echo of the report
4. the CLR 4. the CLR
Ties are broken in favor of the receiver with the lowest reported rate. Ties are broken in favor of the receiver with the lowest reported rate.
It is necessary to account for the time that elapses between receiving a It is necessary to account for the time that elapses between receiving a
skipping to change at page 15, line 46 skipping to change at page 16, line 4
8s/R_max bits/s, the sender may choose to increase the rate by up to 8s/R_max bits/s, the sender may choose to increase the rate by up to
8s/R_max bits/s every R_max. The current sending rate is gradually 8s/R_max bits/s every R_max. The current sending rate is gradually
adjusted to the target rate reported in the receiver reports over the adjusted to the target rate reported in the receiver reports over the
course of a RTT. Slowstart is terminated as soon as any one of the course of a RTT. Slowstart is terminated as soon as any one of the
receivers experiences its first packet loss. Since that receiver's receivers experiences its first packet loss. Since that receiver's
calculated rate will be lower than the current sending rate, the calculated rate will be lower than the current sending rate, the
receiver will be selected as CLR. receiver will be selected as CLR.
During slowstart, the upper bound on the rate increase of 8s/R_max During slowstart, the upper bound on the rate increase of 8s/R_max
bits/s every RTT does not apply. Only after the TFMCC sender receives bits/s every RTT does not apply. Only after the TFMCC sender receives
Expires: November 2006 May 2006
the first report with the have_loss flag set is the rate increase the first report with the have_loss flag set is the rate increase
limited in this way. limited in this way.
Expires: September 2006 March 2006 Slowstart may also be used after the sender has been idle for some time,
to quickly reach the previous sending rate. When the sender stops
sending data packets, it records the current sending rate X' = X. Every
10 RTTs, the allowed sending rate will be halved due to lack of receiver
feedback as specified in Section 3.3. This halving may take place
multiple times. When the sender resumes, it may perform a slowstart
from the current allowed rate up to the recorded rate X'. Slowstart
ends after the first packet loss by any of the receivers or as soon as
X' is reached.
To this end, receivers have to clear the have_loss flag after 10 RTTs
without data packets as specified in Section 4.3.1. The have_loss flag
is only used during slowstart. Therefore, clearing the flag has no
effect if no packets arrived due to network partitioning or packet loss.
3.7. Scheduling of Packet Transmissions 3.7. Scheduling of Packet Transmissions
As TFMCC is rate-based, and as operating systems typically cannot As TFMCC is rate-based, and as operating systems typically cannot
schedule events precisely, it is necessary to be opportunistic about schedule events precisely, it is necessary to be opportunistic about
sending data packets so that the correct average rate is maintained sending data packets so that the correct average rate is maintained
despite the coarse-grain or irregular scheduling of the operating despite the coarse-grain or irregular scheduling of the operating
system. Thus a typical sending loop will calculate the correct inter- system. Thus a typical sending loop will calculate the correct inter-
packet interval, t_ipi, as follows: packet interval, ts_ipi, as follows:
t_ipi = s/X ts_ipi = 8s/X
When a sender first starts sending at time t_0, it calculates t_ipi, and When a sender first starts sending at time t_0, it calculates ts_ipi,
calculates a nominal send time t_1 = t_0 + t_ipi for packet 1. When the and calculates a nominal send time t_1 = t_0 + ts_ipi for packet 1.
application becomes idle, it checks the current time, t_now, and then When the application becomes idle, it checks the current time, ts_now,
requests re-scheduling after (t_ipi - (t_now - t_0)) seconds. When the and then requests re-scheduling after (ts_ipi - (ts_now - t_0)) seconds.
application is re-scheduled, it checks the current time, t_now, again. When the application is re-scheduled, it checks the current time,
If (t_now > t_1 - delta) then packet 1 is sent (see below for delta). ts_now, again. If (ts_now > t_1 - delta) then packet 1 is sent (see
below for delta).
Now a new t_ipi may be calculated, and used to calculate a nominal send Now a new ts_ipi may be calculated, and used to calculate a nominal send
time t_2 for packet 2: t2 = t_1 + t_ipi. The process then repeats, with time t_2 for packet 2: t_2 = t_1 + ts_ipi. The process then repeats,
each successive packet's send time being calculated from the nominal with each successive packet's send time being calculated from the
send time of the previous packet. nominal send time of the previous packet. Note that the actual send
time ts_i and not the nominal send time is included as timestamp in the
packet header.
In some cases, when the nominal send time, t_i, of the next packet is In some cases, when the nominal send time, t_i, of the next packet is
calculated, it may already be the case that t_now > t_i - delta. In calculated, it may already be the case that ts_now > t_i - delta. In
such a case the packet should be sent immediately. Thus if the such a case the packet should be sent immediately. Thus if the
Expires: November 2006 May 2006
operating system has coarse timer granularity and the transmit rate is operating system has coarse timer granularity and the transmit rate is
high, then TFMCC may send short bursts of several packets separated by high, then TFMCC may send short bursts of several packets separated by
intervals of the OS timer granularity. intervals of the OS timer granularity.
The parameter delta is to allow a degree of flexibility in the send time The parameter delta is to allow a degree of flexibility in the send time
of a packet. If the operating system has a scheduling timer granularity of a packet. If the operating system has a scheduling timer granularity
of t_gran seconds, then delta would typically be set to: of ts_gran seconds, then delta would typically be set to:
delta = min(t_ipi/2, t_gran/2) delta = min(ts_ipi/2, ts_gran/2)
t_gran is 10 milliseconds on many Unix systems. If t_gran is not known, ts_gran is 10 milliseconds on many Unix systems. If ts_gran is not
a value of 10 milliseconds can be safely assumed. known, a value of 10 milliseconds can be safely assumed.
4. Data Receiver Protocol 4. Data Receiver Protocol
Receivers measure the current network conditions, namely RTT and loss Receivers measure the current network conditions, namely RTT and loss
event rate, and use this information to calculate a rate that is fair to event rate, and use this information to calculate a rate that is fair to
competing traffic. The rate is then communicated to the sender in competing traffic. The rate is then communicated to the sender in
receiver reports. Due to the potentially large number of receivers, it receiver reports. Due to the potentially large number of receivers, it
is undesirable that all receivers send reports, especially not at the is undesirable that all receivers send reports, especially not at the
same time. same time.
Expires: September 2006 March 2006
In the description of the receiver functionality, we will first address In the description of the receiver functionality, we will first address
how the receivers measure the network parameters and then discuss the how the receivers measure the network parameters and then discuss the
feedback process. feedback process.
4.1. Receiver Initialization 4.1. Receiver Initialization
The receiver is initialized when it receives the first data packet. The The receiver is initialized when it receives the first data packet. The
RTT is set to the maximum RTT value contained in the data packet. This RTT is set to the maximum RTT value contained in the data packet. This
initial value is used as the receiver's RTT until the first real RTT initial value is used as the receiver's RTT until the first real RTT
measurement is made. The loss event rate is initialized to 0. measurement is made. The loss event rate is initialized to 0. Also,
the flags receiver_leave, have_RTT, and have_loss are cleared.
4.2. Receiver Leave 4.2. Receiver Leave
A receiver that sends feedback but wishes to leave the TFMCC session A receiver that sends feedback but wishes to leave the TFMCC session
within the next feedback round may indicate the pending leave by setting within the next feedback round may indicate the pending leave by setting
the receiver_leave flag in its report. If the leaving receiver is the the receiver_leave flag in its report. If the leaving receiver is the
CLR, the receiver_leave flag should be set for all the reports within CLR, the receiver_leave flag should be set for all the reports within
the feedback round before the leave takes effect. the feedback round before the leave takes effect.
Expires: November 2006 May 2006
4.3. Measurement of the Network Conditions 4.3. Measurement of the Network Conditions
Receivers have to update their estimate of the network parameters with Receivers have to update their estimate of the network parameters with
each new data packet they receive. each new data packet they receive.
4.3.1. Updating the Loss Event Rate 4.3.1. Updating the Loss Event Rate
When a data packet is received, the receiver adds the packet to the When a data packet is received, the receiver adds the packet to the
packet history. It then recalculates the new value of the loss event packet history. It then recalculates the new value of the loss event
rate p. The loss event rate measurement mechanism is described rate p. The loss event rate measurement mechanism is described
separately in Section 5. separately in Section 5.
When a loss event is detected, the flag have_loss is set. In case no
data packets are received for 10 consecutive RTTs, the flag is cleared
to allow the sender to slowstart. It is set again when new data packets
arrive and a loss event is detected.
4.3.2. Basic Round-Trip Time Measurement 4.3.2. Basic Round-Trip Time Measurement
When a receiver gets a data packet that carries the receiver's own ID in When a receiver gets a data packet that carries the receiver's own ID in
the r field, the receiver updates its RTT estimate. the r field, the receiver updates its RTT estimate.
1. The current RTT is calculated as: 1. The current RTT is calculated as:
R_sample = t_now - ts_r R_sample = tr_now - tr_r'
where t_now is the time the data packet arrives at the receiver and
ts_r is the receiver report timestamp echoed in the data packet. If
the actual RTT is smaller than the resolution of the timestamps and
Expires: September 2006 March 2006
t_now equals ts_r, then R_sample is set to the smallest positive where tr_now is the time the data packet arrives at the receiver
RTT value larger than 0 (i.e., 1 millisecond in our case). and tr_r' is the receiver report timestamp echoed in the data
packet. If the actual RTT is smaller than the resolution of the
timestamps and tr_now equals tr_r', then R_sample is set to the
smallest positive RTT value larger than 0 (i.e., 1 millisecond in
our case).
2. The smoothed RTT estimate R is updated: 2. The smoothed RTT estimate R is updated:
If no feedback has been received before If no feedback has been received before
R = R_sample R = R_sample
Else Else
R = q*R + (1-q)*R_sample R = q*R + (1-q)*R_sample
A filter parameter q of 0.5 is recommended for non-CLR receivers. A filter parameter q of 0.5 is recommended for non-CLR receivers.
The CLR performs RTT measurements much more frequently and hence The CLR performs RTT measurements much more frequently and hence
should use a higher filter value. We recommend using q=0.9. Note should use a higher filter value. We recommend using q=0.9. Note
that TFMCC is not sensitive to the precise value for the filter that TFMCC is not sensitive to the precise value for the filter
constant. constant.
Expires: November 2006 May 2006
Optionally, sender-based instead of receiver-based RTT measurements may Optionally, sender-based instead of receiver-based RTT measurements may
be used. The sender already determines the RTT to a receiver from the be used. The sender already determines the RTT to a receiver from the
receiver's echo of the sender's own timestamp for the calculation of the receiver's echo of the sender's own timestamp for the calculation of the
maximum RTT. For sender-based RTT measurements, this RTT measurement maximum RTT. For sender-based RTT measurements, this RTT measurement
needs to be communicated to the receiver. Instead of including an echo needs to be communicated to the receiver. Instead of including an echo
of the receiver's timestamp, the sender includes the receiver's RTT in of the receiver's timestamp, the sender includes the receiver's RTT in
the next data packet, using the prioritization rules described in the next data packet, using the prioritization rules described in
Section 3.5. Section 3.5.
To simplify sender operation, smoothing of RTT samples as described To simplify sender operation, smoothing of RTT samples as described
above should still be done at the receiver. above should still be done at the receiver.
4.3.3. One-Way Delay Adjustments 4.3.3. One-Way Delay Adjustments
When a RTT measurement is performed, the receiver also determines the When a RTT measurement is performed, the receiver also determines the
one-way delay D_r from itself to the sender: one-way delay D_r from itself to the sender:
D_r = ts_r - ts_i D_r = tr_r' - ts_i
where ts_i and ts_r are the timestamp and timestamp echo contained in where ts_i and tr_r' are the timestamp and receiver report timestamp
the data packet. With each new data packet i', the receiver can now echo contained in the data packet. With each new data packet j, the
calculate an updated RTT estimate as: receiver can now calculate an updated RTT estimate as:
R' = max(D_r + t_now - ts_i', 1 millisecond) R' = max(D_r + tr_now - ts_j, 1 millisecond)
In between RTT measurements, the updated R' is used instead of the In between RTT measurements, the updated R' is used instead of the
smoothed RTT R. Like the RTT samples, R' must be strictly positive. When smoothed RTT R. Like the RTT samples, R' must be strictly positive.
a new measurement is made, all interim one-way delay measurements are When a new measurement is made, all interim one-way delay measurements
discarded (i.e., the smoothed RTT is updated according to Section 4.3.2 are discarded (i.e., the smoothed RTT is updated according to Section
without taking one-way delay adjustments into account). 4.3.2 without taking the interim one-way delay adjustments into
account).
Expires: September 2006 March 2006
For the one-way delay measurements, the clocks of sender and receivers For the one-way delay measurements, the clocks of sender and receivers
need not be synchronized. Clock skew will cancel itself out when both need not be synchronized. Clock skew will cancel itself out when both
one-way measurements are added to form a RTT estimate, as long as clock one-way measurements are added to form a RTT estimate, as long as clock
drift between real RTT measurements is negligible. drift between real RTT measurements is negligible.
The same one-way delay adjustments should be applied to the RTT supplied The same one-way delay adjustments should be applied to the RTT supplied
by the sender when using sender-based RTT measurements. by the sender when using sender-based RTT measurements.
4.3.4. Receive Rate Measurements 4.3.4. Receive Rate Measurements
When a receiver has not experienced any loss events, it cannot calculate When a receiver has not experienced any loss events, it cannot calculate
a TCP-friendly rate to include in the receiver reports. Instead, the a TCP-friendly rate to include in the receiver reports. Instead, the
receiver measures the current receive rate and sets the desired rate X_r receiver measures the current receive rate and sets the desired rate X_r
to twice the receive rate. to twice the receive rate.
Expires: November 2006 May 2006
The receive rate in bits/s is measured as the number of bits received The receive rate in bits/s is measured as the number of bits received
over the last k RTTs, taking into account the IP and transport packet over the last k RTTs, taking into account the IP and transport packet
headers, but excluding the link-layer packet headers. A value for k headers, but excluding the link-layer packet headers. A value for k
between 2 and 4 is recommended. between 2 and 4 is recommended.
4.4. Setting the Desired Rate 4.4. Setting the Desired Rate
When a receiver measures a non-zero loss event rate, it calculates the When a receiver measures a non-zero loss event rate, it calculates the
desired rate using Equation (1). In case no RTT measurement is desired rate using Equation (1). In case no RTT measurement is
available yet, the maximum RTT is used instead of the receiver's RTT. available yet, the maximum RTT is used instead of the receiver's RTT.
skipping to change at page 19, line 44 skipping to change at page 20, line 29
A receiver may decide to not report desired rates that are below 1 A receiver may decide to not report desired rates that are below 1
packet per 8 seconds, since a sender is very slow to recover from such packet per 8 seconds, since a sender is very slow to recover from such
low sending rates. In this case, the receiver reports a desired rate of low sending rates. In this case, the receiver reports a desired rate of
1 packet per 8 seconds. However, it must leave the multicast group if 1 packet per 8 seconds. However, it must leave the multicast group if
for more than 120 seconds the calculated rate falls below the reported for more than 120 seconds the calculated rate falls below the reported
rate and the current sending rate is higher than the receiver's rate and the current sending rate is higher than the receiver's
calculated rate. calculated rate.
As mentioned above, calculation of the desired rate is not possible As mentioned above, calculation of the desired rate is not possible
before the receiver experiences the first loss event and in that case before the receiver experiences the first loss event. In that case,
twice the rate at which data is received is included in the receiver twice the rate at which data is received is included in the receiver
reports as X_r. This mechanism allows the sender to slowstart as reports as X_r to allow the sender to slowstart as described in Section
described in Section 3.6. 3.6. This is also done when the sender resumes sending data packets
after the have_loss flag was cleared due to the sender being idle.
Expires: September 2006 March 2006
4.5. Feedback and Feedback Suppression 4.5. Feedback and Feedback Suppression
Let fb_nr be the highest feedback round counter value received by a Let fb_nr be the highest feedback round counter value received by a
receiver. When a new data packet arrives with a higher feedback round receiver. When a new data packet arrives with a higher feedback round
counter than fb_nr, a new feedback round begins and fb_nr is updated. counter than fb_nr, a new feedback round begins and fb_nr is updated.
Outstanding feedback for the old round is canceled. In case a feedback Outstanding feedback for the old round is canceled. In case a feedback
number with a value that is more than half the feedback number space number with a value that is more than half the feedback number space
lower than fb_nr is received, the receiver assumes that the feedback lower than fb_nr is received, the receiver assumes that the feedback
round counter wrapped and also cancels the feedback timer and updates round counter wrapped and also cancels the feedback timer and updates
fb_nr. fb_nr.
The CLR sends its feedback independently from all the other receivers The CLR sends its feedback independently from all the other receivers
once per RTT. Its feedback does not suppress other feedback and cannot once per RTT. Its feedback does not suppress other feedback and cannot
be suppressed by other receiver's feedback. be suppressed by other receiver's feedback.
Non-CLR receivers set a feedback timer at the beginning of a feedback Non-CLR receivers set a feedback timer at the beginning of a feedback
round. Using an exponentially weighted random timer mechanism, the round. Using an exponentially weighted random timer mechanism, the
feedback timer is set to expire after feedback timer is set to expire after
Expires: November 2006 May 2006
t = max(T * (1 + log(x)/log(N)), 0) t = max(T * (1 + log(x)/log(N)), 0)
where where
x is a random variable uniformly distributed in (0,1], x is a random variable uniformly distributed in (0,1],
T is the duration of a feedback round (i.e., 6 * R_max), T is the duration of a feedback round (i.e., 6 * R_max),
N is an estimated upper bound on the number of receivers. N is an estimated upper bound on the number of receivers.
skipping to change at page 21, line 4 skipping to change at page 21, line 35
when the feedback timer is set). The copy of the timestamp ts_i of the when the feedback timer is set). The copy of the timestamp ts_i of the
last data packet received, which is included in the feedback packet, last data packet received, which is included in the feedback packet,
needs to be adjusted by the time interval between receiving the data needs to be adjusted by the time interval between receiving the data
packet and sending the report to allow the sender to correctly infer the packet and sending the report to allow the sender to correctly infer the
instantaneous RTT (i.e., that time interval has to be added to the instantaneous RTT (i.e., that time interval has to be added to the
timestamp value). timestamp value).
The timer is canceled if a data packet with a lower suppression rate The timer is canceled if a data packet with a lower suppression rate
than the receiver's calculated rate and a higher or equal maximum RTT than the receiver's calculated rate and a higher or equal maximum RTT
than the receiver's RTT is received. Likewise, a data packet indicating than the receiver's RTT is received. Likewise, a data packet indicating
Expires: September 2006 March 2006
the beginning of a new feedback round cancels all feedback for older the beginning of a new feedback round cancels all feedback for older
rounds. In case of ASM, the timer is also canceled if a feedback packet rounds. In case of ASM, the timer is also canceled if a feedback packet
from another non-CLR receiver reporting a lower rate is received. from another non-CLR receiver reporting a lower rate is received.
The feedback suppression process is complicated by the fact that the The feedback suppression process is complicated by the fact that the
calculated rates of the receivers will change during a feedback round. calculated rates of the receivers will change during a feedback round.
If the calculated rates decrease rapidly for all receivers, feedback If the calculated rates decrease rapidly for all receivers, feedback
suppression can no longer prevent a feedback implosion since earlier suppression can no longer prevent a feedback implosion since earlier
feedback will always report a higher rate than current feedback. To make feedback will always report a higher rate than current feedback. To
the feedback suppression mechanism robust in the face of changing rates, make the feedback suppression mechanism robust in the face of changing
it is necessary to introduce X_fbr, the calculated rate of a receiver at rates, it is necessary to introduce X_fbr, the calculated rate of a
the beginning of a feedback round. A receiver needs to suppress its receiver at the beginning of a feedback round. A receiver needs to
feedback not only when the suppression rate is less than the receiver's suppress its feedback not only when the suppression rate is less than
current calculated rate but also in the case that the suppression rate the receiver's current calculated rate but also in the case that the
falls below X_fbr. suppression rate falls below X_fbr.
When the maximum RTT changes significantly during one feedback round, it When the maximum RTT changes significantly during one feedback round, it
is necessary to reschedule the feedback timer in proportion to the is necessary to reschedule the feedback timer in proportion to the
change. change.
Expires: November 2006 May 2006
t = t * R_max / R_max' t = t * R_max / R_max'
where R_max is the new maximum RTT and R_max' is the previous maximum where R_max is the new maximum RTT and R_max' is the previous maximum
RTT. The same considerations hold, when the last data packets were RTT. The same considerations hold, when the last data packets were
received more than a time interval of R_max ago. In this case, it is received more than a time interval of R_max ago. In this case, it is
necessary to add the difference of the inter-packet gap and the maximum necessary to add the difference of the inter-packet gap and the maximum
RTT to the feedback time to prevent a feedback implosion (e.g., in case RTT to the feedback time to prevent a feedback implosion (e.g., in case
the sender crashed). the sender crashed).
t = t + max(t_now - tr_i - R_max, 0) t = t + max(tr_now - tr_i - R_max, 0)
where tr_i is the time when the last data packet arrived at the where tr_i is the time when the last data packet arrived at the
receiver. receiver.
More details on the characteristics of the feedback suppression More details on the characteristics of the feedback suppression
mechanism can be found in [9] and [10]. mechanism can be found in [14] and [4].
5. Calculation of the Loss Event Rate 5. Calculation of the Loss Event Rate
Obtaining an accurate and stable measurement of the loss event rate is Obtaining an accurate and stable measurement of the loss event rate is
of primary importance for TFMCC. Loss rate measurement is performed at of primary importance for TFMCC. Loss rate measurement is performed at
the receiver, based on the detection of lost or marked packets from the the receiver, based on the detection of lost or marked packets from the
sequence numbers of arriving packets. sequence numbers of arriving packets.
Expires: September 2006 March 2006
5.1. Detection of Lost or Marked Packets 5.1. Detection of Lost or Marked Packets
TFMCC assumes that all packets contain a sequence number that is TFMCC assumes that all packets contain a sequence number that is
incremented by one for each packet that is sent. For the purposes of incremented by one for each packet that is sent. For the purposes of
this specification, we require that if a lost packet is retransmitted, this specification, we require that if a lost packet is retransmitted,
the retransmission is given a new sequence number that is the latest in the retransmission is given a new sequence number that is the latest in
the transmission sequence, and not the same sequence number as the the transmission sequence, and not the same sequence number as the
packet that was lost. If a transport protocol has the requirement that packet that was lost. If a transport protocol has the requirement that
it must retransmit with the original sequence number, then the transport it must retransmit with the original sequence number, then the transport
protocol designer must figure out how to distinguish delayed from protocol designer must figure out how to distinguish delayed from
skipping to change at page 22, line 29 skipping to change at page 23, line 4
The receivers each maintain a data structure that keeps track of which The receivers each maintain a data structure that keeps track of which
packets have arrived and which are missing. For the purposes of packets have arrived and which are missing. For the purposes of
specification, we assume that the data structure consists of a list of specification, we assume that the data structure consists of a list of
packets that have arrived along with the timestamp when each packet was packets that have arrived along with the timestamp when each packet was
received. In practice this data structure will normally be stored in a received. In practice this data structure will normally be stored in a
more compact representation, but this is implementation-specific. more compact representation, but this is implementation-specific.
The loss of a packet is detected by the arrival of at least three The loss of a packet is detected by the arrival of at least three
packets with a higher sequence number than the lost packet. The packets with a higher sequence number than the lost packet. The
requirement for three subsequent packets is the same as with TCP, and is requirement for three subsequent packets is the same as with TCP, and is
Expires: November 2006 May 2006
to make TFMCC more robust in the presence of reordering. In contrast to to make TFMCC more robust in the presence of reordering. In contrast to
TCP, if a packet arrives late (after 3 subsequent packets arrived) at a TCP, if a packet arrives late (after 3 subsequent packets arrived) at a
receiver, the late packet can fill the hole in the reception record, and receiver, the late packet can fill the hole in the reception record, and
the receiver can recalculate the loss event rate. Future versions of the receiver can recalculate the loss event rate. Future versions of
TFMCC might make the requirement for three subsequent packets adaptive TFMCC might make the requirement for three subsequent packets adaptive
based on experienced packet reordering, but we do not specify such a based on experienced packet reordering, but we do not specify such a
mechanism here. mechanism here.
For an ECN-capable connection, a marked packet is detected as a For an ECN-capable connection, a marked packet is detected as a
congestion event as soon as it arrives, without having to wait for the congestion event as soon as it arrives, without having to wait for the
skipping to change at page 23, line 4 skipping to change at page 23, line 31
packets lost where those packets are part of the same loss event. This packets lost where those packets are part of the same loss event. This
is similar to TCP, which (typically) only performs one halving of the is similar to TCP, which (typically) only performs one halving of the
congestion window during any single RTT. Thus the receivers needs to congestion window during any single RTT. Thus the receivers needs to
map the packet loss history into a loss event record, where a loss event map the packet loss history into a loss event record, where a loss event
is one or more packets lost in a RTT. is one or more packets lost in a RTT.
To determine whether a lost or marked packet should start a new loss To determine whether a lost or marked packet should start a new loss
event, or be counted as part of an existing loss event, we need to event, or be counted as part of an existing loss event, we need to
compare the sequence numbers and timestamps of the packets that arrived compare the sequence numbers and timestamps of the packets that arrived
at the receiver. For a marked packet S_new, its reception time T_new at the receiver. For a marked packet S_new, its reception time T_new
Expires: September 2006 March 2006
can be noted directly. For a lost packet, we can interpolate to infer can be noted directly. For a lost packet, we can interpolate to infer
the nominal "arrival time". Assume: the nominal "arrival time". Assume:
S_loss is the sequence number of a lost packet. S_loss is the sequence number of a lost packet.
S_before is the sequence number of the last packet to arrive with S_before is the sequence number of the last packet to arrive with
sequence number before S_loss. sequence number before S_loss.
S_after is the sequence number of the first packet to arrive with S_after is the sequence number of the first packet to arrive with
sequence number after S_loss. sequence number after S_loss.
T_before is the reception time of S_before. T_before is the reception time of S_before.
T_after is the reception time of S_after. T_after is the reception time of S_after.
Note that T_before can either be before or after T_after due to Note that T_before can either be before or after T_after due to
reordering. reordering.
For a lost packet S_loss, we can interpolate its nominal "arrival time" For a lost packet S_loss, we can interpolate its nominal "arrival time"
at the receiver from the arrival times of S_before and S_after. Thus at the receiver from the arrival times of S_before and S_after. Thus
Expires: November 2006 May 2006
T_loss = T_before + ( (T_after - T_before) T_loss = T_before + ( (T_after - T_before)
* (S_loss - S_before)/(S_after - S_before) ); * (S_loss - S_before)/(S_after - S_before) );
Note that if the sequence space wrapped between S_before and S_after, Note that if the sequence space wrapped between S_before and S_after,
then the sequence numbers must be modified to take this into account then the sequence numbers must be modified to take this into account
before performing the calculation. If the largest possible sequence before performing the calculation. If the largest possible sequence
number is S_max, and S_before > S_after, then modifying each sequence number is S_max, and S_before > S_after, then modifying each sequence
number S by S' = (S + (S_max + 1)/2) mod (S_max + 1) would normally be number S by S' = (S + (S_max + 1)/2) mod (S_max + 1) would normally be
sufficient. sufficient.
skipping to change at page 24, line 5 skipping to change at page 24, line 31
If T_old + R >= T_new, then S_new is part of the existing loss event. If T_old + R >= T_new, then S_new is part of the existing loss event.
Otherwise S_new is the first packet of a new loss event. Otherwise S_new is the first packet of a new loss event.
5.3. Inter-Loss Event Interval 5.3. Inter-Loss Event Interval
If a loss interval, A, is determined to have started with packet If a loss interval, A, is determined to have started with packet
sequence number S_A and the next loss interval, B, started with packet sequence number S_A and the next loss interval, B, started with packet
sequence number S_B, then the number of packets in loss interval A is sequence number S_B, then the number of packets in loss interval A is
given by (S_B - S_A). given by (S_B - S_A).
Expires: September 2006 March 2006
5.4. Average Loss Interval 5.4. Average Loss Interval
To calculate the loss event rate p, we first calculate the average loss To calculate the loss event rate p, we first calculate the average loss
interval. This is done using a filter that weights the n most recent interval. This is done using a filter that weights the n most recent
loss event intervals in such a way that the measured loss event rate loss event intervals in such a way that the measured loss event rate
changes smoothly. changes smoothly.
Weights w_0 to w_(n-1) are calculated as: Weights w_0 to w_(n-1) are calculated as:
If (i < n/2) If (i < n/2)
w_i = 1; w_i = 1;
Else Else
w_i = 1 - (i - (n/2 - 1))/(n/2 + 1); w_i = 1 - (i - (n/2 - 1))/(n/2 + 1);
Thus if n=8, the values of w_0 to w_7 are: Thus if n=8, the values of w_0 to w_7 are:
1.0, 1.0, 1.0, 1.0, 0.8, 0.6, 0.4, 0.2 1.0, 1.0, 1.0, 1.0, 0.8, 0.6, 0.4, 0.2
Expires: November 2006 May 2006
The value n for the number of loss intervals used in calculating the The value n for the number of loss intervals used in calculating the
loss event rate determines TFMCC's speed in responding to changes in the loss event rate determines TFMCC's speed in responding to changes in the
level of congestion. As currently specified, TFMCC should not be used level of congestion. As currently specified, TFMCC should not be used
for values of n significantly greater than 8, for traffic that might for values of n significantly greater than 8, for traffic that might
compete in the global Internet with TCP. At the very least, safe compete in the global Internet with TCP. At the very least, safe
operation with values of n greater than 8 would require a slight change operation with values of n greater than 8 would require a slight change
to TFMCC's mechanisms to include a more severe response to two or more to TFMCC's mechanisms to include a more severe response to two or more
round-trip times with heavy packet loss. round-trip times with heavy packet loss.
When calculating the average loss interval we need to decide whether to When calculating the average loss interval we need to decide whether to
include the interval since the most recent packet loss event. We only include the interval since the most recent packet loss event. We only
do this if it is sufficiently large to increase the average loss do this if it is sufficiently large to increase the average loss
interval. interval.
Thus if the most recent loss intervals are I_0 to I_n, with I_0 being Thus if the most recent loss intervals are I_0 to I_n, with I_0 being
the interval since the most recent loss event, then we calculate the the interval since the most recent loss event, then we calculate the
average loss interval I_mean as: average loss interval I_mean as:
Expires: September 2006 March 2006
I_tot0 = 0; I_tot0 = 0;
I_tot1 = 0; I_tot1 = 0;
W_tot = 0; W_tot = 0;
for (i = 0 to n-1) { for (i = 0 to n-1) {
I_tot0 = I_tot0 + (I_i * w_i); I_tot0 = I_tot0 + (I_i * w_i);
W_tot = W_tot + w_i; W_tot = W_tot + w_i;
} }
for (i = 1 to n) { for (i = 1 to n) {
I_tot1 = I_tot1 + (I_i * w_(i-1)); I_tot1 = I_tot1 + (I_i * w_(i-1));
} }
skipping to change at page 25, line 35 skipping to change at page 26, line 5
As described in Section 5.4, the most recent loss interval is only As described in Section 5.4, the most recent loss interval is only
assigned 4/(3*n) of the total weight in calculating the average loss assigned 4/(3*n) of the total weight in calculating the average loss
interval, regardless of the size of the most recent loss interval. This interval, regardless of the size of the most recent loss interval. This
section describes an optional history discounting mechanism that allows section describes an optional history discounting mechanism that allows
the TFMCC receivers to adjust the weights, concentrating more of the the TFMCC receivers to adjust the weights, concentrating more of the
relative weight on the most recent loss interval, when the most recent relative weight on the most recent loss interval, when the most recent
loss interval is more than twice as large as the computed average loss loss interval is more than twice as large as the computed average loss
interval. interval.
Expires: November 2006 May 2006
To carry out history discounting, we associate a discount factor DF_i To carry out history discounting, we associate a discount factor DF_i
with each loss interval L_i, where each discount factor is a floating with each loss interval L_i, where each discount factor is a floating
point number. The discount array maintains the cumulative history of point number. The discount array maintains the cumulative history of
discounting for each loss interval. At the beginning, the values of discounting for each loss interval. At the beginning, the values of
DF_i in the discount array are initialized to 1: DF_i in the discount array are initialized to 1:
for (i = 0 to n) { for (i = 0 to n) {
DF_i = 1; DF_i = 1;
} }
History discounting also uses a general discount factor DF, also a History discounting also uses a general discount factor DF, also a
floating point number, that is also initialized to 1. First we show how floating point number, that is also initialized to 1. First we show how
the discount factors are used in calculating the average loss interval, the discount factors are used in calculating the average loss interval,
and then we describe later in this section how the discount factors are and then we describe later in this section how the discount factors are
modified over time. modified over time.
As described in Section 5.4 the average loss interval is calculated As described in Section 5.4 the average loss interval is calculated
using the n previous loss intervals I_1, ..., I_n, and the interval I_0 using the n previous loss intervals I_1, ..., I_n, and the interval I_0
Expires: September 2006 March 2006
that represents the number of packets received since the last loss that represents the number of packets received since the last loss
event. The computation of the average loss interval using the discount event. The computation of the average loss interval using the discount
factors is a simple modification of the procedure in Section 5.4, as factors is a simple modification of the procedure in Section 5.4, as
follows: follows:
I_tot0 = I_0 * w_0 I_tot0 = I_0 * w_0
I_tot1 = 0; I_tot1 = 0;
W_tot0 = w_0 W_tot0 = w_0
W_tot1 = 0; W_tot1 = 0;
for (i = 1 to n-1) { for (i = 1 to n-1) {
skipping to change at page 26, line 29 skipping to change at page 27, line 5
for (i = 1 to n) { for (i = 1 to n) {
I_tot1 = I_tot1 + (I_i * w_(i-1) * DF_i); I_tot1 = I_tot1 + (I_i * w_(i-1) * DF_i);
W_tot1 = W_tot1 + w_(i-1) * DF_i; W_tot1 = W_tot1 + w_(i-1) * DF_i;
} }
p = min(W_tot0/I_tot0, W_tot1/I_tot1); p = min(W_tot0/I_tot0, W_tot1/I_tot1);
The general discounting factor, DF is updated on every packet arrival as The general discounting factor, DF is updated on every packet arrival as
follows. First, a receiver computes the weighted average I_mean of the follows. First, a receiver computes the weighted average I_mean of the
loss intervals I_1, ..., I_n: loss intervals I_1, ..., I_n:
Expires: November 2006 May 2006
I_tot = 0; I_tot = 0;
W_tot = 0; W_tot = 0;
for (i = 1 to n) { for (i = 1 to n) {
W_tot = w_(i-1) * DF_i; W_tot = w_(i-1) * DF_i;
I_tot = I_tot + (I_i * w_(i-1) * DF_i); I_tot = I_tot + (I_i * w_(i-1) * DF_i);
} }
I_mean = I_tot / W_tot; I_mean = I_tot / W_tot;
This weighted average I_mean is compared to I_0, the number of packets This weighted average I_mean is compared to I_0, the number of packets
received since the last loss event. If I_0 is greater than twice received since the last loss event. If I_0 is greater than twice
skipping to change at page 27, line 5 skipping to change at page 27, line 33
if (DF < THRESHOLD) if (DF < THRESHOLD)
DF = THRESHOLD; DF = THRESHOLD;
} else } else
DF = 1; DF = 1;
A nonzero value for THRESHOLD ensures that older loss intervals from an A nonzero value for THRESHOLD ensures that older loss intervals from an
earlier time of high congestion are not discounted entirely. We earlier time of high congestion are not discounted entirely. We
recommend a THRESHOLD of 0.5. Note that with each new packet arrival, recommend a THRESHOLD of 0.5. Note that with each new packet arrival,
I_0 will increase further, and the discount factor DF will be updated. I_0 will increase further, and the discount factor DF will be updated.
Expires: September 2006 March 2006
When a new loss event occurs, the current interval shifts from I_0 to When a new loss event occurs, the current interval shifts from I_0 to
I_1, loss interval I_i shifts to interval I_(i+1), and the loss interval I_1, loss interval I_i shifts to interval I_(i+1), and the loss interval
I_n is forgotten. The previous discount factor DF has to be I_n is forgotten. The previous discount factor DF has to be
incorporated into the discount array. Because DF_i carries the discount incorporated into the discount array. Because DF_i carries the discount
factor associated with loss interval I_i, the DF_i array has to be factor associated with loss interval I_i, the DF_i array has to be
shifted as well. This is done as follows: shifted as well. This is done as follows:
for (i = 1 to n) { for (i = 1 to n) {
DF_i = DF * DF_i; DF_i = DF * DF_i;
} }
skipping to change at page 27, line 28 skipping to change at page 28, line 4
DF_(i+1) = DF_i; DF_(i+1) = DF_i;
} }
I_0 = 1; I_0 = 1;
DF_0 = 1; DF_0 = 1;
DF = 1; DF = 1;
This completes the description of the optional history discounting This completes the description of the optional history discounting
mechanism. We emphasize that this is an optional mechanism whose sole mechanism. We emphasize that this is an optional mechanism whose sole
purpose is to allow TFMCC to response somewhat more quickly to the purpose is to allow TFMCC to response somewhat more quickly to the
sudden absence of congestion, as represented by a long current loss sudden absence of congestion, as represented by a long current loss
Expires: November 2006 May 2006
interval. interval.
5.6. Initializing the Loss History after the First Loss Event 5.6. Initializing the Loss History after the First Loss Event
The number of packets received before the first loss event usually does The number of packets received before the first loss event usually does
not reflect the current loss event rate. When the first loss event not reflect the current loss event rate. When the first loss event
occurs, a TFMCC receiver assumes that the correct data rate is the rate occurs, a TFMCC receiver assumes that the correct data rate is the rate
at which data was received during the last RTT when the loss occurred. at which data was received during the last RTT when the loss occurred.
Instead of initializing the first loss interval to the number of packets Instead of initializing the first loss interval to the number of packets
sent until the first loss event, the TFMCC receiver calculates the loss sent until the first loss event, the TFMCC receiver calculates the loss
interval that would be required to produce the receive rate X_recv, and interval that would be required to produce the receive rate X_recv, and
uses this synthetic loss interval l_0 to seed the loss history uses this synthetic loss interval l_0 to seed the loss history
mechanism. mechanism.
The initial loss interval is calculated by inverting a simplified The initial loss interval is calculated by inverting a simplified
version of the TCP Equation (1). version of the TCP Equation (1).
Expires: September 2006 March 2006 8s
s
X_recv = sqrt(3/2) * ----------------- X_recv = sqrt(3/2) * -----------------
R * sqrt(1/l_0) R * sqrt(1/l_0)
X_recv * R X_recv * R
==> l_0 = (---------------)^2 ==> l_0 = (----------------)^2
sqrt(3/2) * s sqrt(3/2) * 8s
The resulting initial loss interval is too small at higher loss rates The resulting initial loss interval is too small at higher loss rates
compared to using the more accurate Equation (1), which leads to a more compared to using the more accurate Equation (1), which leads to a more
conservative initial loss event rate. conservative initial loss event rate.
If a receiver still uses the initial RTT R_max instead of its real RTT, If a receiver still uses the initial RTT R_max instead of its real RTT,
the initial loss interval is too large in case the initial RTT is higher the initial loss interval is too large in case the initial RTT is higher
than the actual RTT. As a consequence, the receiver will calculate a than the actual RTT. As a consequence, the receiver will calculate a
too high desired rate when the first RTT measurement R is made and the too high desired rate when the first RTT measurement R is made and the
initial loss interval is still in the loss history. The receiver has to initial loss interval is still in the loss history. The receiver has to
adjust l_0 as follows: adjust l_0 as follows:
l_0 = l_0 * (R/R_max)^2 l_0 = l_0 * (R/R_max)^2
No action needs to be taken when the first RTT measurement is made after No action needs to be taken when the first RTT measurement is made after
the initial loss interval left the loss history. the initial loss interval left the loss history.
Expires: November 2006 May 2006
6. Security Considerations 6. Security Considerations
TFMCC is not a transport protocol in its own right, but a congestion TFMCC is not a transport protocol in its own right, but a congestion
control mechanism that is intended to be used in conjunction with a control mechanism that is intended to be used in conjunction with a
transport protocol. Therefore security primarily needs to be considered transport protocol. Therefore security primarily needs to be considered
in the context of a specific transport protocol and its authentication in the context of a specific transport protocol and its authentication
mechanisms. mechanisms.
Congestion control mechanisms can potentially be exploited to create Congestion control mechanisms can potentially be exploited to create
denial of service. This may occur through spoofed feedback. Thus any denial of service. This may occur through spoofed feedback. Thus any
transport protocol that uses TFMCC should take care to ensure that transport protocol that uses TFMCC should take care to ensure that
feedback is only accepted from valid receivers of the data. The precise feedback is only accepted from valid receivers of the data. The precise
mechanism to achieve this will however depend on the transport protocol mechanism to achieve this will however depend on the transport protocol
itself. itself.
Congestion control mechanisms may potentially be manipulated by a greedy Congestion control mechanisms may potentially be manipulated by a greedy
receiver that wishes to receive more than its fair share of network receiver that wishes to receive more than its fair share of network
bandwidth. However, in TFMCC a receiver can only influence the sending bandwidth. However, in TFMCC a receiver can only influence the sending
Expires: September 2006 March 2006
rate if it is the CLR and thus has the lowest calculated rate of all rate if it is the CLR and thus has the lowest calculated rate of all
receivers. If the calculated rate is then manipulated such that it receivers. If the calculated rate is then manipulated such that it
exceeds the calculated rate of the second to lowest receiver, it will exceeds the calculated rate of the second to lowest receiver, it will
cease to be CLR. A greedy receiver can only significantly increase then cease to be CLR. A greedy receiver can only significantly increase then
transmission rate if it is the only participant in the session. If such transmission rate if it is the only participant in the session. If such
scenarios are of concern, possible defenses against such a receiver scenarios are of concern, possible defenses against such a receiver
would normally include some form of nonce that the receiver must feed would normally include some form of nonce that the receiver must feed
back to the sender to prove receipt. However, the details of such a back to the sender to prove receipt. However, the details of such a
nonce would depend on the transport protocol, and in particular on nonce would depend on the transport protocol, and in particular on
whether the transport protocol is reliable or unreliable. whether the transport protocol is reliable or unreliable.
It is possible that a receiver sends feedback claiming it has a very low It is possible that a receiver sends feedback claiming it has a very low
calculated rate. This will reduce the rate of the multicast session and calculated rate. This will reduce the rate of the multicast session and
might render it useless but obviously cannot hurt the network itself. might render it useless but obviously cannot hurt the network itself.
We expect that protocols incorporating ECN with TFMCC will also want to We expect that protocols incorporating ECN with TFMCC will also want to
incorporate feedback from the receiver to the sender using the ECN nonce incorporate feedback from the receiver to the sender using the ECN nonce
[8]. The ECN nonce is a modification to ECN that protects the sender [13]. The ECN nonce is a modification to ECN that protects the sender
from the accidental or malicious concealment of marked packets. Again, from the accidental or malicious concealment of marked packets. Again,
the details of such a nonce would depend on the transport protocol, and the details of such a nonce would depend on the transport protocol, and
are not addressed in this document. are not addressed in this document.
7. IANA Considerations 7. IANA Considerations
There are no IANA actions required for this document. There are no IANA actions required for this document.
Expires: November 2006 May 2006
8. Authors' Addresses 8. Authors' Addresses
Joerg Widmer Joerg Widmer
DoCoMo Euro-Labs DoCoMo Euro-Labs
Landsberger Str. 312, Munich, Germany Landsberger Str. 312, Munich, Germany
widmer@acm.org widmer@acm.org
Mark Handley Mark Handley
UCL (University College London) UCL (University College London)
Gower Street, London WC1E 6BT, UK Gower Street, London WC1E 6BT, UK
m.handley@cs.ucl.ac.uk m.handley@cs.ucl.ac.uk
9. Acknowledgments 9. Acknowledgments
We would like to acknowledge feedback and discussions on equation-based We would like to acknowledge feedback and discussions on equation-based
congestion control with a wide range of people, including members of the congestion control with a wide range of people, including members of the
Reliable Multicast Research Group, the Reliable Multicast Transport Reliable Multicast Research Group, the Reliable Multicast Transport
Expires: September 2006 March 2006
Working Group, and the End-to-End Research Group. We would particularly Working Group, and the End-to-End Research Group. We would particularly
like to thank Brian Adamson, Mark Pullen, and Fei Zhao for feedback on like to thank Brian Adamson, Mark Pullen, Fei Zhao, and Magnus
earlier versions of this document. Westerlund for feedback on earlier versions of this document.
10. References 10. References
[1] B. Adamson, C. Bormann, M. Handley, and J. Macker, "NACK-Oriented 10.1. Normative References
Reliable Multicast (NORM) Protocol Building Blocks", Internet Draft
draft-ietf-rmt-norm-bb-09.txt, July 2004, work in progress.
Citation for informational purposes only.
[2] S. Floyd, M. Handley, J. Padhye, and J. Widmer, "Equation-Based [1] B. Whetten, L. Vicisano, R. Kermode, M. Handley, S. Floyd, and M.
Luby, "Reliable Multicast Transport Building Blocks for One-to-Many
Bulk-Data Transfer", RFC 3048, January 2001.
[2] S. Bradner, "Key words for use in RFCs to Indicate Requirement
Levels", BCP 14, RFC 2119, March 1997.
[3] R. Kermode and L. Vicisano, "Author Guidelines for Reliable
Multicast Transport (RMT) Building Blocks and Protocol
Instantiation documents", RFC 3269, April 2002.
10.2. Informative References
[4] J. Widmer and M. Handley, "Extending Equation-Based Congestion
Control to Multicast Applications", Proc ACM Sigcomm 2001, San
Expires: November 2006 May 2006
Diego, August 2001.
[5] S. Floyd, M. Handley, J. Padhye, and J. Widmer, "Equation-Based
Congestion Control for Unicast Applications", Proc ACM SIGCOMM Congestion Control for Unicast Applications", Proc ACM SIGCOMM
2000, Stockholm, August 2000 2000, Stockholm, August 2000.
[3] H. W. Holbrook, "A Channel Model for Multicast," Ph.D. [6] B. Adamson, C. Bormann, M. Handley, and J. Macker, "Negative-
Acknowledgment (NACK)-Oriented Reliable Multicast (NORM) Building
Blocks", RFC 3941, November 2004.
[7] S. Deering, "Host Extensions for IP Multicasting", STD 5, RFC 1112,
August 1989.
[8] H. W. Holbrook, "A Channel Model for Multicast," Ph.D.
Dissertation, Stanford University, Department of Computer Science, Dissertation, Stanford University, Department of Computer Science,
Stanford, California, August 2001. Stanford, California, August 2001.
[4] J. Padhye, V. Firoiu, D. Towsley, and J. Kurose, "Modeling TCP [9] J. Padhye, V. Firoiu, D. Towsley, and J. Kurose, "Modeling TCP
Throughput: A Simple Model and its Empirical Validation", Proc ACM Throughput: A Simple Model and its Empirical Validation", Proc ACM
SIGCOMM 1998. SIGCOMM 1998.
[5] K. Ramakrishnan and S. Floyd, "A Proposal to add Explicit Congestion [10] K. Ramakrishnan and S. Floyd, "A Proposal to add Explicit
Notification (ECN) to IP", RFC 2481, January 1999. Congestion Notification (ECN) to IP", RFC 2481, January 1999.
[6] L. Rizzo, "pgmcc: a TCP-friendly single-rate multicast congestion [11] L. Rizzo, "pgmcc: a TCP-friendly single-rate multicast congestion
control scheme", Proc ACM SIGCOMM 2000, Stockholm, August 2000 control scheme", Proc ACM Sigcomm 2000, Stockholm, August 2000.
[7] H. Schulzrinne, S. Casner, R. Frederick, and V. Jacobson, "RTP: A [12] H. Schulzrinne, S. Casner, R. Frederick, and V. Jacobson, "RTP: A
Transport Protocol for Real-Time Applications", RFC 1889, January Transport Protocol for Real-Time Applications", RFC 1889, January
1996. 1996.
[8] N. Spring, D. Wetherall, and D. Ely, "Robust Explicit Congestion [13] N. Spring, D. Wetherall, and D. Ely, "Robust Explicit Congestion
Notification (ECN) Signaling with Nonces", RFC 3540, June 2003. Notification (ECN) Signaling with Nonces", RFC 3540, June 2003.
[9] J. Widmer and T. Fuhrmann, "Extremum Feedback for Very Large [14] J. Widmer and T. Fuhrmann, "Extremum Feedback for Very Large
Multicast Groups", Proc NGC 2001, London, November 2001. Multicast Groups", Proc NGC 2001, London, November 2001.
[10] J. Widmer and M. Handley, "Extending Equation-Based Congestion
Control to Multicast Applications", Proc ACM SIGCOMM 2001, San
Diego, August 2001
Expires: September 2006 March 2006
11. Copyright Notice 11. Copyright Notice
Copyright (C) The Internet Society (2005). This document is subject to Copyright (C) The Internet Society (2006). This document is subject to
the rights, licenses and restrictions contained in BCP 78, and except as the rights, licenses and restrictions contained in BCP 78, and except as
set forth therein, the authors retain all their rights. set forth therein, the authors retain all their rights.
This document and the information contained herein are provided on an This document and the information contained herein are provided on an
"AS IS" basis and THE CONTRIBUTOR, THE ORGANIZATION HE/SHE REPRESENTS OR "AS IS" basis and THE CONTRIBUTOR, THE ORGANIZATION HE/SHE REPRESENTS OR
IS SPONSORED BY (IF ANY), THE INTERNET SOCIETY AND THE INTERNET IS SPONSORED BY (IF ANY), THE INTERNET SOCIETY AND THE INTERNET
ENGINEERING TASK FORCE DISCLAIM ALL WARRANTIES, EXPRESS OR IMPLIED, ENGINEERING TASK FORCE DISCLAIM ALL WARRANTIES, EXPRESS OR IMPLIED,
Expires: November 2006 May 2006
INCLUDING BUT NOT LIMITED TO ANY WARRANTY THAT THE USE OF THE INCLUDING BUT NOT LIMITED TO ANY WARRANTY THAT THE USE OF THE
INFORMATION HEREIN WILL NOT INFRINGE ANY RIGHTS OR ANY IMPLIED INFORMATION HEREIN WILL NOT INFRINGE ANY RIGHTS OR ANY IMPLIED
WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE. WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE.
 End of changes. 119 change blocks. 
207 lines changed or deleted 255 lines changed or added

This html diff was produced by rfcdiff 1.30. The latest version is available from http://www.levkowetz.com/ietf/tools/rfcdiff/