draft-ietf-rmcat-sbd-07.txt   draft-ietf-rmcat-sbd-08.txt 
RTP Media Congestion Avoidance Techniques D. Hayes, Ed. RTP Media Congestion Avoidance Techniques D. Hayes, Ed.
Internet-Draft S. Ferlin Internet-Draft S. Ferlin
Intended status: Experimental Simula Research Laboratory Intended status: Experimental Simula Research Laboratory
Expires: December 10, 2017 M. Welzl Expires: January 4, 2018 M. Welzl
K. Hiorth K. Hiorth
University of Oslo University of Oslo
June 8, 2017 July 3, 2017
Shared Bottleneck Detection for Coupled Congestion Control for RTP Shared Bottleneck Detection for Coupled Congestion Control for RTP
Media. Media.
draft-ietf-rmcat-sbd-07 draft-ietf-rmcat-sbd-08
Abstract Abstract
This document describes a mechanism to detect whether end-to-end data This document describes a mechanism to detect whether end-to-end data
flows share a common bottleneck. It relies on summary statistics flows share a common bottleneck. It relies on summary statistics
that are calculated based on continuous measurements and used as that are calculated based on continuous measurements and used as
input to a grouping algorithm that runs wherever the knowledge is input to a grouping algorithm that runs wherever the knowledge is
needed. This mechanism complements the coupled congestion control needed. This mechanism complements the coupled congestion control
mechanism in draft-ietf-rmcat-coupled-cc. mechanism in draft-ietf-rmcat-coupled-cc.
skipping to change at page 1, line 39 skipping to change at page 1, line 39
Internet-Drafts are working documents of the Internet Engineering Internet-Drafts are working documents of the Internet Engineering
Task Force (IETF). Note that other groups may also distribute Task Force (IETF). Note that other groups may also distribute
working documents as Internet-Drafts. The list of current Internet- working documents as Internet-Drafts. The list of current Internet-
Drafts is at http://datatracker.ietf.org/drafts/current/. Drafts is at http://datatracker.ietf.org/drafts/current/.
Internet-Drafts are draft documents valid for a maximum of six months Internet-Drafts are draft documents valid for a maximum of six months
and may be updated, replaced, or obsoleted by other documents at any and may be updated, replaced, or obsoleted by other documents at any
time. It is inappropriate to use Internet-Drafts as reference time. It is inappropriate to use Internet-Drafts as reference
material or to cite them other than as "work in progress." material or to cite them other than as "work in progress."
This Internet-Draft will expire on December 10, 2017. This Internet-Draft will expire on January 4, 2018.
Copyright Notice Copyright Notice
Copyright (c) 2017 IETF Trust and the persons identified as the Copyright (c) 2017 IETF Trust and the persons identified as the
document authors. All rights reserved. document authors. All rights reserved.
This document is subject to BCP 78 and the IETF Trust's Legal This document is subject to BCP 78 and the IETF Trust's Legal
Provisions Relating to IETF Documents Provisions Relating to IETF Documents
(http://trustee.ietf.org/license-info) in effect on the date of (http://trustee.ietf.org/license-info) in effect on the date of
publication of this document. Please review these documents publication of this document. Please review these documents
skipping to change at page 2, line 16 skipping to change at page 2, line 16
include Simplified BSD License text as described in Section 4.e of include Simplified BSD License text as described in Section 4.e of
the Trust Legal Provisions and are provided without warranty as the Trust Legal Provisions and are provided without warranty as
described in the Simplified BSD License. described in the Simplified BSD License.
Table of Contents Table of Contents
1. Introduction . . . . . . . . . . . . . . . . . . . . . . . . 3 1. Introduction . . . . . . . . . . . . . . . . . . . . . . . . 3
1.1. The basic mechanism . . . . . . . . . . . . . . . . . . . 3 1.1. The basic mechanism . . . . . . . . . . . . . . . . . . . 3
1.2. The signals . . . . . . . . . . . . . . . . . . . . . . . 3 1.2. The signals . . . . . . . . . . . . . . . . . . . . . . . 3
1.2.1. Packet loss . . . . . . . . . . . . . . . . . . . . . 3 1.2.1. Packet loss . . . . . . . . . . . . . . . . . . . . . 3
1.2.2. Packet delay . . . . . . . . . . . . . . . . . . . . 3 1.2.2. Packet delay . . . . . . . . . . . . . . . . . . . . 4
1.2.3. Path lag . . . . . . . . . . . . . . . . . . . . . . 4 1.2.3. Path lag . . . . . . . . . . . . . . . . . . . . . . 4
2. Definitions . . . . . . . . . . . . . . . . . . . . . . . . . 4 2. Definitions . . . . . . . . . . . . . . . . . . . . . . . . . 4
2.1. Parameters and their effect . . . . . . . . . . . . . . . 7 2.1. Parameters and their effect . . . . . . . . . . . . . . . 6
2.2. Recommended parameter values . . . . . . . . . . . . . . 8 2.2. Recommended parameter values . . . . . . . . . . . . . . 7
3. Mechanism . . . . . . . . . . . . . . . . . . . . . . . . . . 8 3. Mechanism . . . . . . . . . . . . . . . . . . . . . . . . . . 7
3.1. SBD feedback requirements . . . . . . . . . . . . . . . . 9 3.1. SBD feedback requirements . . . . . . . . . . . . . . . . 8
3.1.1. Feedback when all the logic is placed at the sender . 9 3.1.1. Feedback when all the logic is placed at the sender . 9
3.1.2. Feedback when the statistics are calculated at the 3.1.2. Feedback when the statistics are calculated at the
receiver and SBD performed at the sender . . . . . . 10 receiver and SBD performed at the sender . . . . . . 9
3.1.3. Feedback when bottlenecks can be determined at both 3.1.3. Feedback when bottlenecks can be determined at both
senders and receivers . . . . . . . . . . . . . . . . 11 senders and receivers . . . . . . . . . . . . . . . . 10
3.2. Key metrics and their calculation . . . . . . . . . . . . 11 3.2. Key metrics and their calculation . . . . . . . . . . . . 10
3.2.1. Mean delay . . . . . . . . . . . . . . . . . . . . . 11 3.2.1. Mean delay . . . . . . . . . . . . . . . . . . . . . 10
3.2.2. Skewness estimate . . . . . . . . . . . . . . . . . . 11 3.2.2. Skewness estimate . . . . . . . . . . . . . . . . . . 11
3.2.3. Variability estimate . . . . . . . . . . . . . . . . 12 3.2.3. Variability estimate . . . . . . . . . . . . . . . . 12
3.2.4. Oscillation estimate . . . . . . . . . . . . . . . . 12 3.2.4. Oscillation estimate . . . . . . . . . . . . . . . . 12
3.2.5. Packet loss . . . . . . . . . . . . . . . . . . . . . 13 3.2.5. Packet loss . . . . . . . . . . . . . . . . . . . . . 13
3.3. Flow Grouping . . . . . . . . . . . . . . . . . . . . . . 13 3.3. Flow Grouping . . . . . . . . . . . . . . . . . . . . . . 13
3.3.1. Flow grouping algorithm . . . . . . . . . . . . . . . 13 3.3.1. Flow grouping algorithm . . . . . . . . . . . . . . . 13
3.3.2. Using the flow group signal . . . . . . . . . . . . . 16 3.3.2. Using the flow group signal . . . . . . . . . . . . . 16
4. Enhancements to the basic SBD algorithm . . . . . . . . . . . 17 4. Enhancements to the basic SBD algorithm . . . . . . . . . . . 16
4.1. Reducing lag and improving responsiveness . . . . . . . . 17 4.1. Reducing lag and improving responsiveness . . . . . . . . 16
4.1.1. Improving the response of the skewness estimate . . . 18 4.1.1. Improving the response of the skewness estimate . . . 17
4.1.2. Improving the response of the variability estimate . 20 4.1.2. Improving the response of the variability estimate . 19
4.2. Removing oscillation noise . . . . . . . . . . . . . . . 20 4.2. Removing oscillation noise . . . . . . . . . . . . . . . 19
5. Measuring OWD . . . . . . . . . . . . . . . . . . . . . . . . 21 5. Measuring OWD . . . . . . . . . . . . . . . . . . . . . . . . 20
5.1. Time stamp resolution . . . . . . . . . . . . . . . . . . 21 5.1. Time stamp resolution . . . . . . . . . . . . . . . . . . 20
5.2. Clock skew . . . . . . . . . . . . . . . . . . . . . . . 21 5.2. Clock skew . . . . . . . . . . . . . . . . . . . . . . . 20
6. Expected feedback from experiments . . . . . . . . . . . . . 21 6. Expected feedback from experiments . . . . . . . . . . . . . 20
7. Acknowledgments . . . . . . . . . . . . . . . . . . . . . . . 22 7. Acknowledgments . . . . . . . . . . . . . . . . . . . . . . . 21
8. IANA Considerations . . . . . . . . . . . . . . . . . . . . . 22 8. IANA Considerations . . . . . . . . . . . . . . . . . . . . . 21
9. Security Considerations . . . . . . . . . . . . . . . . . . . 22 9. Security Considerations . . . . . . . . . . . . . . . . . . . 21
10. Change history . . . . . . . . . . . . . . . . . . . . . . . 22 10. Change history . . . . . . . . . . . . . . . . . . . . . . . 21
11. References . . . . . . . . . . . . . . . . . . . . . . . . . 23 11. References . . . . . . . . . . . . . . . . . . . . . . . . . 22
11.1. Normative References . . . . . . . . . . . . . . . . . . 23 11.1. Normative References . . . . . . . . . . . . . . . . . . 22
11.2. Informative References . . . . . . . . . . . . . . . . . 23 11.2. Informative References . . . . . . . . . . . . . . . . . 23
Authors' Addresses . . . . . . . . . . . . . . . . . . . . . . . 25 Authors' Addresses . . . . . . . . . . . . . . . . . . . . . . . 24
1. Introduction 1. Introduction
In the Internet, it is not normally known if flows (e.g., TCP In the Internet, it is not normally known if flows (e.g., TCP
connections or UDP data streams) traverse the same bottlenecks. Even connections or UDP data streams) traverse the same bottlenecks. Even
flows that have the same sender and receiver may take different paths flows that have the same sender and receiver may take different paths
and may or may not share a bottleneck. Flows that share a bottleneck and may or may not share a bottleneck. Flows that share a bottleneck
link usually compete with one another for their share of the link usually compete with one another for their share of the
capacity. This competition has the potential to increase packet loss capacity. This competition has the potential to increase packet loss
and delays. This is especially relevant for interactive applications and delays. This is especially relevant for interactive applications
skipping to change at page 5, line 33 skipping to change at page 5, line 38
E_T(...) -- the expectation or mean of the measurements of the E_T(...) -- the expectation or mean of the measurements of the
variable in parentheses over T variable in parentheses over T
E_N(...) -- the expectation or mean of the last N values of the E_N(...) -- the expectation or mean of the last N values of the
variable in parentheses variable in parentheses
E_M(...) -- the expectation or mean of the last M values of the E_M(...) -- the expectation or mean of the last M values of the
variable in parentheses, where M <= N. variable in parentheses, where M <= N.
max_T(...) -- the maximum recorded measurement of the variable in
parentheses taken over the interval T
min_T(...) -- the minimum recorded measurement of the variable in
parentheses taken over the interval T
num_T(...) -- the count of measurements of the variable in num_T(...) -- the count of measurements of the variable in
parentheses taken in the interval T parentheses taken in the interval T
num_VM(...) -- the count of valid values of the variable in num_VM(...) -- the count of valid values of the variable in
parentheses given M records parentheses given M records
PB -- a boolean variable indicating the particular flow PB -- a boolean variable indicating the particular flow
was identified transiting a bottleneck in the was identified transiting a bottleneck in the
previous interval T (i.e. Previously Bottleneck) previous interval T (i.e. Previously Bottleneck)
skipping to change at page 6, line 18 skipping to change at page 6, line 18
calculating var_est. calculating var_est.
freq_est -- a measure of low frequency oscillation in the OWD freq_est -- a measure of low frequency oscillation in the OWD
measurements. measurements.
p_l, p_f, p_mad, c_s, c_h, p_s, p_d, p_v -- various thresholds p_l, p_f, p_mad, c_s, c_h, p_s, p_d, p_v -- various thresholds
used in the mechanism used in the mechanism
M and F -- number of values related to N M and F -- number of values related to N
.
2.1. Parameters and their effect 2.1. Parameters and their effect
T T should be long enough so that there are enough packets T T should be long enough so that there are enough packets
received during T for a useful estimate of short term mean received during T for a useful estimate of short term mean
OWD and variation statistics. Making T too large can limit OWD and variation statistics. Making T too large can limit
the efficacy of freq_est. It will also increase the response the efficacy of freq_est. It will also increase the response
time of the mechanism. Making T too small will make the time of the mechanism. Making T too small will make the
metrics noisier. metrics noisier.
N & M N should be large enough to provide a stable estimate of N & M N should be large enough to provide a stable estimate of
skipping to change at page 9, line 48 skipping to change at page 9, line 13
document, however, it is expected that feedback will take the form document, however, it is expected that feedback will take the form
scenario 1 and operate in conjunction with sender-based congestion scenario 1 and operate in conjunction with sender-based congestion
control mechanisms. control mechanisms.
3.1.1. Feedback when all the logic is placed at the sender 3.1.1. Feedback when all the logic is placed at the sender
Having the sender calculate the summary statistics and determine the Having the sender calculate the summary statistics and determine the
shared bottlenecks based on them has the advantage of placing most of shared bottlenecks based on them has the advantage of placing most of
the functionality in one place -- the sender. the functionality in one place -- the sender.
For every packet, the sender requires accurate OWD measurements of For every packet, the sender requires accurate relative OWD
adequate precision, along with an indication of lost packets (or the measurements of adequate precision, along with an indication of lost
proportion of packets lost over an interval). These can be provided packets (or the proportion of packets lost over an interval). These
by [I-D.dt-rmcat-feedback-message]. can be provided by [I-D.dt-rmcat-feedback-message].
The mechanism performs its calculation whenever it has received Sums, var_base_T and skew_base_T are calculated incrementally as
sufficient measurements in the feedback messages to cover the T base relative OWD measurements are determined from the feedback messages.
time interval. The exact timing of these calculations will depend on When the mechanism has received sufficient measurements to cover the
the frequency of the feedback message. T base time interval for all flows, the summary statistics (see
Section 3.2) are calculated for that T interval and flows are grouped
(see Section 3.3.1). The exact timing of these calculations will
depend on the frequency of the feedback message.
3.1.2. Feedback when the statistics are calculated at the receiver and 3.1.2. Feedback when the statistics are calculated at the receiver and
SBD performed at the sender SBD performed at the sender
This scenario minimizes feedback, but requires receivers to send This scenario minimizes feedback, but requires receivers to send
selected summary statistics at an agreed regular interval. We selected summary statistics at an agreed regular interval. We
envisage the following exchange of information to initialize the envisage the following exchange of information to initialize the
system: system:
o An initialization message from the sender to the receiver will o An initialization message from the sender to the receiver will
skipping to change at page 10, line 45 skipping to change at page 10, line 15
* The values of T, N, M, and the necessary resolution and * The values of T, N, M, and the necessary resolution and
precision of the relayed statistics. precision of the relayed statistics.
o A response message from the receiver acknowledges this message o A response message from the receiver acknowledges this message
with a list of key metrics it supports (subset of the senders with a list of key metrics it supports (subset of the senders
list) and is able to relay back to the sender. list) and is able to relay back to the sender.
This initialization exchange may be repeated to finalize the agreed This initialization exchange may be repeated to finalize the agreed
metrics should not all be supported by all receivers. metrics should not all be supported by all receivers.
After initialization the agreed summary statistics SHOULD be fed back After initialization the agreed summary statistics are fed back to
to the sender (nominally every T). the sender (nominally every T).
3.1.3. Feedback when bottlenecks can be determined at both senders and 3.1.3. Feedback when bottlenecks can be determined at both senders and
receivers receivers
This type of mechanism is currently beyond the scope of SBD in RMCAT. This type of mechanism is currently beyond the scope of SBD in RMCAT.
It is mentioned here to ensure more advanced sender/receiver It is mentioned here to ensure more advanced sender/receiver
cooperative shared bottleneck determination mechanisms remain cooperative shared bottleneck determination mechanisms remain
possible in the future. possible in the future.
It is envisaged that such a mechanism would be initialized in a It is envisaged that such a mechanism would be initialized in a
skipping to change at page 15, line 18 skipping to change at page 15, line 7
Subdivide the groups obtained in 4. by grouping flows whose Subdivide the groups obtained in 4. by grouping flows whose
difference is less than a threshold difference is less than a threshold
diff(pkt_loss) < (p_d * pkt_loss) diff(pkt_loss) < (p_d * pkt_loss)
The threshold, (p_d * pkt_loss), is with respect to the highest The threshold, (p_d * pkt_loss), is with respect to the highest
value in the difference. value in the difference.
This procedure involves sorting estimates from highest to lowest. It This procedure involves sorting estimates from highest to lowest. It
is simple to implement, and efficient for small numbers of flows (up is simple to implement, and efficient for small numbers of flows (up
to 10-20).Figure 2 illustrates this algorithm to 10-20). Figure 2 illustrates this algorithm.
********* *********
* Flows * * Flows *
***.**.** ***.**.**
/ ' / '
/ '--. / '--.
/ \ / \
.---v--. .----v---. .---v--. .----v---.
1. Flows traversing | Cong | | UnCong | 1. Flows traversing | Cong | | UnCong |
a bottleneck '-.--.-' '--------' a bottleneck '-.--.-' '--------'
/ \ / \
skipping to change at page 21, line 27 skipping to change at page 20, line 27
clock offsets should be approximately constant over the measurement clock offsets should be approximately constant over the measurement
periods, the offset is subtracted out in the calculation. periods, the offset is subtracted out in the calculation.
5.1. Time stamp resolution 5.1. Time stamp resolution
The SBD mechanism requires timing information precise enough to be The SBD mechanism requires timing information precise enough to be
able to make comparisons. As a rule of thumb, the time resolution able to make comparisons. As a rule of thumb, the time resolution
should be less than one hundredth of a typical path's range of should be less than one hundredth of a typical path's range of
delays. In general, the coarser the time resolution, the more care delays. In general, the coarser the time resolution, the more care
that needs to be taken to ensure rounding errors do not bias the that needs to be taken to ensure rounding errors do not bias the
skewness calculation. Time stamp resolution such as that described skewness calculation. Timing information described by
by [I-D.dt-rmcat-feedback-message] should be sufficient. [I-D.dt-rmcat-feedback-message] should be sufficient for the sender
to calculate relative OWD.
5.2. Clock skew 5.2. Clock skew
Generally sender and receiver clock skew will be too small to cause Generally sender and receiver clock skew will be too small to cause
significant errors in the estimators. Skew_est and freq_est are the significant errors in the estimators. Skew_est and freq_est are the
most sensitive to this type of noise due to their use of a mean OWD most sensitive to this type of noise due to their use of a mean OWD
calculated over a longer interval. In circumstances where clock skew calculated over a longer interval. In circumstances where clock skew
is high, basing skew_est only on the previous T's mean and ignoring is high, basing skew_est only on the previous T's mean and ignoring
freq_est provides a noisier but reliable signal. freq_est provides a noisier but reliable signal.
skipping to change at page 22, line 30 skipping to change at page 21, line 30
Non-authenticated RTCP packets carrying OWD measurements, shared Non-authenticated RTCP packets carrying OWD measurements, shared
bottleneck indications, and/or summary statistics could allow bottleneck indications, and/or summary statistics could allow
attackers to alter the bottleneck sharing characteristics for private attackers to alter the bottleneck sharing characteristics for private
gain or disruption of other parties communication. gain or disruption of other parties communication.
10. Change history 10. Change history
Changes made to this document: Changes made to this document:
WG-07->WG-08 : Updates addressing https://www.ietf.org/mail-
archive/web/rmcat/current/msg01671.html Mainly
clarifications.
WG-06->WG-07 : Updates addressing WG-06->WG-07 : Updates addressing
https://mailarchive.ietf.org/arch/msg/ https://mailarchive.ietf.org/arch/msg/
rmcat/80B6q4nI7carGcf_ddBwx7nKvOw. Mainly rmcat/80B6q4nI7carGcf_ddBwx7nKvOw. Mainly
clarifications. Figure 2 to supplement grouping clarifications. Figure 2 to supplement grouping
algorithm description. algorithm description.
WG-05->WG-06 : Updates addressing WG reviews WG-05->WG-06 : Updates addressing WG reviews
https://mailarchive.ietf.org/arch/msg/rmcat/- https://mailarchive.ietf.org/arch/msg/rmcat/-
1JdrTMq1Y5T6ZNlOkrQJQ27TzE and 1JdrTMq1Y5T6ZNlOkrQJQ27TzE and
https://mailarchive.ietf.org/arch/msg/rmcat/ https://mailarchive.ietf.org/arch/msg/rmcat/
 End of changes. 18 change blocks. 
50 lines changed or deleted 51 lines changed or added

This html diff was produced by rfcdiff 1.45. The latest version is available from http://tools.ietf.org/tools/rfcdiff/