draft-ietf-aqm-docsis-pie-02.txt   rfc8034.txt 
Active Queue Management and Packet Scheduling (aqm) G. White Internet Engineering Task Force (IETF) G. White
Internet-Draft CableLabs Request for Comments: 8034 CableLabs
Intended status: Informational R. Pan Category: Informational R. Pan
Expires: August 15, 2016 Cisco Systems ISSN: 2070-1721 Cisco Systems
February 12, 2016 February 2017
A PIE-Based AQM for DOCSIS Cable Modems Active Queue Management (AQM) Based on
draft-ietf-aqm-docsis-pie-02 Proportional Integral Controller Enhanced (PIE) for
Data-Over-Cable Service Interface Specifications (DOCSIS) Cable Modems
Abstract Abstract
Cable modems based on the DOCSIS(R) specification provide broadband Cable modems based on Data-Over-Cable Service Interface
Internet access to over one hundred million users worldwide. In some Specifications (DOCSIS) provide broadband Internet access to over one
cases, the cable modem connection is the bottleneck (lowest speed) hundred million users worldwide. In some cases, the cable modem
link between the customer and the Internet. As a result, the impact connection is the bottleneck (lowest speed) link between the customer
of buffering and bufferbloat in the cable modem can have a and the Internet. As a result, the impact of buffering and
significant effect on user experience. The CableLabs DOCSIS 3.1 bufferbloat in the cable modem can have a significant effect on user
specification introduces requirements for cable modems to support an experience. The CableLabs DOCSIS 3.1 specification introduces
Active Queue Management (AQM) algorithm that is intended to alleviate requirements for cable modems to support an Active Queue Management
the impact that buffering has on latency sensitive traffic, while (AQM) algorithm that is intended to alleviate the impact that
preserving bulk throughput performance. In addition, the CableLabs buffering has on latency-sensitive traffic, while preserving bulk
DOCSIS 3.0 specifications have also been amended to contain similar throughput performance. In addition, the CableLabs DOCSIS 3.0
requirements. This document describes the requirements on Active specifications have also been amended to contain similar
Queue Management that apply to DOCSIS equipment, including a requirements. This document describes the requirements on AQM that
description of the "DOCSIS-PIE" algorithm that is required on DOCSIS apply to DOCSIS equipment, including a description of the
3.1 cable modems. "DOCSIS-PIE" algorithm that is required on DOCSIS 3.1 cable modems.
Status of This Memo Status of This Memo
This Internet-Draft is submitted in full conformance with the This document is not an Internet Standards Track specification; it is
provisions of BCP 78 and BCP 79. published for informational purposes.
Internet-Drafts are working documents of the Internet Engineering
Task Force (IETF). Note that other groups may also distribute
working documents as Internet-Drafts. The list of current Internet-
Drafts is at http://datatracker.ietf.org/drafts/current/.
Internet-Drafts are draft documents valid for a maximum of six months This document is a product of the Internet Engineering Task Force
and may be updated, replaced, or obsoleted by other documents at any (IETF). It represents the consensus of the IETF community. It has
time. It is inappropriate to use Internet-Drafts as reference received public review and has been approved for publication by the
material or to cite them other than as "work in progress." Internet Engineering Steering Group (IESG). Not all documents
approved by the IESG are a candidate for any level of Internet
Standard; see Section 2 of RFC 7841.
This Internet-Draft will expire on August 15, 2016. Information about the current status of this document, any errata,
and how to provide feedback on it may be obtained at
http://www.rfc-editor.org/info/rfc8034.
Copyright Notice Copyright Notice
Copyright (c) 2016 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
carefully, as they describe your rights and restrictions with respect carefully, as they describe your rights and restrictions with respect
to this document. Code Components extracted from this document must to this document. Code Components extracted from this document must
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 . . . . . . . . . . . . . . . . . . . . . . . . 2 1. Introduction . . . . . . . . . . . . . . . . . . . . . . . . 3
2. Overview of DOCSIS AQM Requirements . . . . . . . . . . . . . 3 2. Overview of DOCSIS AQM Requirements . . . . . . . . . . . . . 3
3. The DOCSIS MAC Layer and Service Flows . . . . . . . . . . . 3 3. The DOCSIS MAC Layer and Service Flows . . . . . . . . . . . 4
4. DOCSIS-PIE vs. PIE . . . . . . . . . . . . . . . . . . . . . 5 4. DOCSIS-PIE vs. PIE . . . . . . . . . . . . . . . . . . . . . 5
4.1. Latency Target . . . . . . . . . . . . . . . . . . . . . 5 4.1. Latency Target . . . . . . . . . . . . . . . . . . . . . 5
4.2. Departure rate estimation . . . . . . . . . . . . . . . . 5 4.2. Departure Rate Estimation . . . . . . . . . . . . . . . . 6
4.3. Enhanced burst protection . . . . . . . . . . . . . . . . 6 4.3. Enhanced Burst Protection . . . . . . . . . . . . . . . . 7
4.4. Expanded auto-tuning range . . . . . . . . . . . . . . . 7 4.4. Expanded Auto-Tuning Range . . . . . . . . . . . . . . . 7
4.5. Trigger for exponential decay . . . . . . . . . . . . . . 7 4.5. Trigger for Exponential Decay . . . . . . . . . . . . . . 8
4.6. Drop probability scaling . . . . . . . . . . . . . . . . 7 4.6. Drop Probability Scaling . . . . . . . . . . . . . . . . 8
4.7. Support for explicit congestion notification . . . . . . 8 4.7. Support for Explicit Congestion Notification . . . . . . 8
5. Implementation Guidance . . . . . . . . . . . . . . . . . . . 8 5. Implementation Guidance . . . . . . . . . . . . . . . . . . . 9
6. IANA Considerations . . . . . . . . . . . . . . . . . . . . . 8 6. Security Considerations . . . . . . . . . . . . . . . . . . . 9
7. Security Considerations . . . . . . . . . . . . . . . . . . . 9 7. References . . . . . . . . . . . . . . . . . . . . . . . . . 10
8. Informative References . . . . . . . . . . . . . . . . . . . 9 7.1. Normative References . . . . . . . . . . . . . . . . . . 10
Appendix A. DOCSIS-PIE Algorithm definition . . . . . . . . . . 9 7.2. Informative References . . . . . . . . . . . . . . . . . 10
A.1. DOCSIS-PIE AQM Constants and Variables . . . . . . . . . 10 Appendix A. DOCSIS-PIE Algorithm Definition . . . . . . . . . . 11
A.1.1. Configuration parameters . . . . . . . . . . . . . . 10 A.1. DOCSIS-PIE AQM Constants and Variables . . . . . . . . . 11
A.1.2. Constant values . . . . . . . . . . . . . . . . . . . 10 A.1.1. Configuration Parameters . . . . . . . . . . . . . . 11
A.1.3. Variables . . . . . . . . . . . . . . . . . . . . . . 10 A.1.2. Constant Values . . . . . . . . . . . . . . . . . . . 11
A.1.4. Public/system functions: . . . . . . . . . . . . . . 11 A.1.3. Variables . . . . . . . . . . . . . . . . . . . . . . 12
A.2. DOCSIS-PIE AQM Control Path . . . . . . . . . . . . . . . 11 A.1.4. Public/System Functions . . . . . . . . . . . . . . . 12
A.3. DOCSIS-PIE AQM Data Path . . . . . . . . . . . . . . . . 13 A.2. DOCSIS-PIE AQM Control Path . . . . . . . . . . . . . . . 13
Authors' Addresses . . . . . . . . . . . . . . . . . . . . . . . 15 A.3. DOCSIS-PIE AQM Data Path . . . . . . . . . . . . . . . . 15
Authors' Addresses . . . . . . . . . . . . . . . . . . . . . . . 17
1. Introduction 1. Introduction
A recent resurgence of interest in Active Queue Management, arising A recent resurgence of interest in active queue management, arising
from a recognition of the inadequacies of drop tail queuing in the from a recognition of the inadequacies of drop-tail queuing in the
presence of loss-based congestion control algorithms, has resulted in presence of loss-based congestion control algorithms, has resulted in
the development of new algorithms that appear to provide very good the development of new algorithms that appear to provide very good
congestion feedback to current TCP algorithms, while also having congestion feedback to current TCP algorithms, while also having
operational simplicity and low complexity. One of these algorithms operational simplicity and low complexity. One of these algorithms
has been selected as a requirement for cable modems built according has been selected as a requirement for cable modems built according
to the DOCSIS 3.1 specification [DOCSIS_3.1]. The Data Over Cable to the DOCSIS 3.1 specification [DOCSIS_3.1]. The Data-Over-Cable
Service Interface Specifications (DOCSIS) define the broadband Service Interface Specifications (DOCSIS) define the broadband
technology deployed worldwide for Ethernet and IP service over hybrid technology deployed worldwide for Ethernet and IP service over hybrid
fiber-coaxial cable systems. The most recent revision of the DOCSIS fiber-coaxial cable systems. The most recent revision of the DOCSIS
technology, version 3.1, was published in October 2013 and provides technology, version 3.1, was originally published in October 2013 and
support for up to 10 Gbps downstream (toward the customer) and 1 Gbps provides support for up to 10 Gbps downstream (toward the customer)
upstream (from the customer) capacity over existing cable networks. and 1 Gbps upstream (from the customer) capacity over existing cable
Previous versions of the DOCSIS technology did not contain networks. Previous versions of the DOCSIS technology did not contain
requirements for AQM. This document outlines the high-level AQM requirements for AQM. This document outlines the high-level AQM
requirements for DOCSIS systems, discusses some of the salient requirements for DOCSIS systems, discusses some of the salient
features of the DOCSIS MAC layer, and describes the DOCSIS-PIE features of the DOCSIS Media Access Control (MAC) layer, and
algorithm - largely by comparing it to its progenitor, the describes the DOCSIS-PIE algorithm -- largely by comparing it to its
[I-D.ietf-aqm-pie] algorithm. progenitor, the PIE algorithm [RFC8033].
2. Overview of DOCSIS AQM Requirements 2. Overview of DOCSIS AQM Requirements
CableLabs' DOCSIS 3.1 specification [DOCSIS_3.1] mandates that cable CableLabs' DOCSIS 3.1 specification [DOCSIS_3.1] mandates that cable
modems implement a specific variant of the Proportional Integral modems implement a specific variant of the Proportional Integral
controller Enhanced (PIE) [I-D.ietf-aqm-pie] active queue management controller Enhanced (PIE) AQM algorithm [RFC8033]. This specific
algorithm. This specific variant is provided for reference in variant is provided for reference in Appendix A, and simulation
Appendix A, and simulation results comparing it to drop tail queuing results comparing it to drop-tail queuing and other AQM options are
and other AQM options are given in [CommMag] and [DOCSIS-AQM]. In given in [CommMag] and [DOCSIS-AQM]. In addition, CableLabs' DOCSIS
addition, CableLabs' DOCSIS 3.0 specification [DOCSIS_3.0] has been 3.0 specification [DOCSIS_3.0] has been amended to recommend that
amended to recommend that cable modems implement the same algorithm. cable modems implement the same algorithm. Both specifications allow
Both specifications allow that cable modems can optionally implement that cable modems can optionally implement additional algorithms that
additional algorithms, that can then be selected for use by the can then be selected for use by the operator via the modem's
operator via the modem's configuration file. configuration file.
These requirements on the cable modem apply to upstream transmissions These requirements on the cable modem apply to upstream transmissions
(i.e. from the customer to the Internet). (i.e., from the customer to the Internet).
Both specifications also include requirements (mandatory in DOCSIS Both specifications also include requirements (mandatory in DOCSIS
3.1 and recommended in DOCSIS 3.0) that the Cable Modem Termination 3.1 and recommended in DOCSIS 3.0) that the Cable Modem Termination
System (CMTS) implement active queue management for downstream System (CMTS) implement AQM for downstream traffic; however, no
traffic, however no specific algorithm is defined for downstream use. specific algorithm is defined for downstream use.
3. The DOCSIS MAC Layer and Service Flows 3. The DOCSIS MAC Layer and Service Flows
The DOCSIS Media Access Control (sub-)layer provides tools for The DOCSIS Media Access Control (sub-)layer provides tools for
configuring differentiated Quality of Service for different configuring differentiated Quality of Service (QoS) for different
applications by the use of Packet Classifiers and Service Flows. applications by the use of Packet Classifiers and Service Flows.
Each Service Flow has an associated Quality of Service (QoS) Each Service Flow has an associated QoS parameter set that defines
parameter set that defines the treatment of the packets that traverse the treatment of the packets that traverse the Service Flow. These
the Service Flow. These parameters include (for example) Minimum parameters include, for example, Minimum Reserved Traffic Rate,
Reserved Traffic Rate, Maximum Sustained Traffic Rate, Peak Traffic Maximum Sustained Traffic Rate, Peak Traffic Rate, Maximum Traffic
Rate, Maximum Traffic Burst, and Traffic Priority. Each upstream Burst, and Traffic Priority. Each upstream Service Flow corresponds
Service Flow corresponds to a queue in the cable modem, and each to a queue in the cable modem, and each downstream Service Flow
downstream Service Flow corresponds to a queue in the CMTS. The corresponds to a queue in the CMTS. The DOCSIS AQM requirements
DOCSIS AQM requirements mandate that the CM and CMTS implement the mandate that the CM and CMTS implement the AQM algorithm (and allow
AQM algorithm (and allow it to be disabled if need be) on each it to be disabled, if needed) on each Service Flow queue
Service Flow queue independently. independently.
Packet Classifiers can match packets based upon several fields in the Packet Classifiers can match packets based upon several fields in the
packet/frame headers including the Ethernet header, IP header, and packet/frame headers including the Ethernet header, IP header, and
TCP/UDP header. Matched packets are then queued in the associated TCP/UDP header. Matched packets are then queued in the associated
Service Flow queue. Service Flow queue.
Each cable modem can be configured with multiple Packet Classifiers Each cable modem can be configured with multiple Packet Classifiers
and Service Flows. The maximum number of such entities that a cable and Service Flows. The maximum number of such entities that a cable
modem supports is an implementation decision for the manufacturer, modem supports is an implementation decision for the manufacturer,
but modems typically support 16 or 32 upstream Service Flows and at but modems typically support 16 or 32 upstream Service Flows and at
least that many Packet Classifiers. Similarly the CMTS supports least that many Packet Classifiers. Similarly, the CMTS supports
multiple downstream Service Flows and multiple Packet Classifiers per multiple downstream Service Flows and multiple Packet Classifiers per
cable modem. cable modem.
It is typical that upstream and downstream Service Flows used for It is typical that upstream and downstream Service Flows used for
broadband Internet access are configured with a Maximum Sustained broadband Internet access are configured with a Maximum Sustained
Traffic Rate. This QoS parameter rate-shapes the traffic onto the Traffic Rate. This QoS parameter rate-shapes the traffic onto the
DOCSIS link, and is the main parameter that defines the service DOCSIS link and is the main parameter that defines the service
offering. Additionally, it is common that upstream and downstream offering. Additionally, it is common that upstream and downstream
Service Flows are configured with a Maximum Traffic Burst and a Peak Service Flows are configured with a Maximum Traffic Burst and a Peak
Traffic Rate. These parameters allow the service to burst at a Traffic Rate. These parameters allow the service to burst at a
higher (sometimes significantly higher) rate than is defined in the higher (sometimes significantly higher) rate than is defined in the
Maximum Sustained Traffic Rate for the amount of bytes configured in Maximum Sustained Traffic Rate for the amount of bytes configured in
Maximum Traffic Burst, as long as the long-term average data rate Maximum Traffic Burst, as long as the long-term average data rate
remains at or below the Maximum Sustained Traffic Rate. remains at or below the Maximum Sustained Traffic Rate.
Mathematically, what is enforced is that the traffic placed on the Mathematically, what is enforced is that the traffic placed on the
DOCSIS link in the time interval (t1,t2) complies with the following DOCSIS link in the time interval (t1,t2) complies with the following
rate shaping equations: rate-shaping equations:
TxBytes(t1,t2) <= (t2-t1)*R/8 + B TxBytes(t1,t2) <= (t2-t1)*R/8 + B
TxBytes(t1,t2) <= (t2-t1)*P/8 + 1522 TxBytes(t1,t2) <= (t2-t1)*P/8 + 1522
for all values t2>t1, where: for all values t2>t1, where:
R = Maximum Sustained Traffic Rate (bps) R = Maximum Sustained Traffic Rate (bps)
P = Peak Traffic Rate (bps) P = Peak Traffic Rate (bps)
skipping to change at page 5, line 18 skipping to change at page 5, line 34
Sustained Traffic Rate, the Service Flow "earns" credit that it can Sustained Traffic Rate, the Service Flow "earns" credit that it can
then use (should the load increase) to burst at the Peak Traffic then use (should the load increase) to burst at the Peak Traffic
Rate. This dynamic is important since these rate changes Rate. This dynamic is important since these rate changes
(particularly the decrease in data rate once the traffic burst credit (particularly the decrease in data rate once the traffic burst credit
is exhausted) can induce a step increase in buffering latency. is exhausted) can induce a step increase in buffering latency.
4. DOCSIS-PIE vs. PIE 4. DOCSIS-PIE vs. PIE
There are a number of differences between the version of the PIE There are a number of differences between the version of the PIE
algorithm that is mandated for cable modems in the DOCSIS algorithm that is mandated for cable modems in the DOCSIS
specifications and the version described in [I-D.ietf-aqm-pie]. specifications and the version described in [RFC8033]. These
These differences are described in the following subsections. differences are described in the following subsections.
4.1. Latency Target 4.1. Latency Target
The latency target (aka delay reference) is a key parameter that The latency target (a.k.a. delay reference) is a key parameter that
affects, among other things, the tradeoff in performance between affects, among other things, the trade-off in performance between
latency-sensitive applications and bulk TCP applications. Via latency-sensitive applications and bulk TCP applications. Via
simulation studies, a value of 10ms was identified as providing a simulation studies, a value of 10 ms was identified as providing a
good balance of performance. However, it is recognized that there good balance of performance. However, it is recognized that there
may be service offerings for which this value doesn't provide the may be service offerings for which this value doesn't provide the
best performance balance. As a result, this is provided as a best performance balance. As a result, this is provided as a
configuration parameter that the operator can set independently on configuration parameter that the operator can set independently on
each upstream service flow. If not explicitly set by the operator, each upstream Service Flow. If not explicitly set by the operator,
the modem will use 10 ms as the default value. the modem will use 10 ms as the default value.
4.2. Departure rate estimation 4.2. Departure Rate Estimation
The PIE algorithm utilizes a departure rate estimator to track The PIE algorithm utilizes a departure rate estimator to track
fluctuations in the egress rate for the queue and to generate a fluctuations in the egress rate for the queue and to generate a
smoothed estimate of this rate for use in the drop probability smoothed estimate of this rate for use in the drop probability
calculation. This estimator may be well suited to many link calculation. This estimator may be well suited to many link
technologies, but is not ideal for DOCSIS upstream links for a number technologies but is not ideal for DOCSIS upstream links for a number
of reasons. of reasons.
First, the bursty nature of the upstream transmissions, in which the First, the bursty nature of the upstream transmissions, in which the
queue drains at line rate (up to ~100 Mbps for DOCSIS 3.0 and ~1 Gbps queue drains at line rate (up to ~100 Mbps for DOCSIS 3.0 and ~1 Gbps
for DOCSIS 3.1) and then is blocked until the next transmit for DOCSIS 3.1) and then is blocked until the next transmit
opportunity, results in the potential for inaccuracy in measurement, opportunity, results in the potential for inaccuracy in measurement,
given that the PIE departure rate estimator starts each measurement given that the PIE departure rate estimator starts each measurement
during a transmission burst and ends each measurement during a during a transmission burst and ends each measurement during a
(possibly different) transmission burst. For example, in the case (possibly different) transmission burst. For example, in the case
where the start and end of measurement occur within a single burst, where the start and end of measurement occur within a single burst,
skipping to change at page 6, line 16 skipping to change at page 6, line 36
can result in some further inaccuracy. In typical conditions, the can result in some further inaccuracy. In typical conditions, the
request-grant mechanism can add between ~4 ms and ~8 ms of latency to request-grant mechanism can add between ~4 ms and ~8 ms of latency to
the forwarding of upstream traffic. Within that range, the amount of the forwarding of upstream traffic. Within that range, the amount of
additional latency that affects any individual data burst is additional latency that affects any individual data burst is
effectively random, being influenced by the arrival time of the burst effectively random, being influenced by the arrival time of the burst
relative to the next request transmit opportunity, among other relative to the next request transmit opportunity, among other
factors. factors.
Third, in the significant majority of cases, the departure rate, Third, in the significant majority of cases, the departure rate,
while variable, is controlled by the modem itself via the pair of while variable, is controlled by the modem itself via the pair of
token bucket rate shaping equations described in Section 3. token bucket rate-shaping equations described in Section 3.
Together, these two equations enforce a maximum sustained traffic Together, these two equations enforce a Maximum Sustained Traffic
rate, a peak traffic rate, and a maximum traffic burst size for the Rate, a Peak Traffic Rate, and a Maximum Traffic Burst size for the
modem's requested bandwidth. The implication of this is that the modem's requested bandwidth. The implication of this is that the
modem, in the significant majority of cases, will know precisely what modem, in the significant majority of cases, will know precisely what
the departure rate will be, and can predict exactly when transitions the departure rate will be and can predict exactly when transitions
between peak rate and maximum sustained traffic rate will occur. between the Peak Traffic Rate and Maximum Sustained Traffic Rate will
Compare this to the PIE estimator, which would be simply reacting to occur. Compare this to the PIE estimator, which would be simply
(and smoothing its estimate of) those rate transitions after the reacting to (and smoothing its estimate of) those rate transitions
fact. after the fact.
Finally, since the modem is already implementing the dual token Finally, since the modem is already implementing the dual-token
bucket traffic shaper, it contains enough internal state to calculate bucket traffic shaper, it contains enough internal state to calculate
predicted queuing delay with a minimum of computations. Furthermore, predicted queuing delay with a minimum of computations. Furthermore,
these computations only need to be run every drop probability update these computations only need to be run at every drop probability
interval, as opposed to the PIE estimator, which runs a similar update interval, as opposed to the PIE estimator, which runs a
number of computations on each packet dequeue event. similar number of computations on each packet dequeue event.
For these reasons, the DOCSIS-PIE algorithm utilizes the For these reasons, the DOCSIS-PIE algorithm utilizes the
configuration and state of the dual token bucket traffic shaper to configuration and state of the dual-token bucket traffic shaper to
translate queue depth into predicted queuing delay, rather than translate queue depth into predicted queuing delay, rather than
implementing the departure rate estimator defined in PIE. implementing the departure rate estimator defined in PIE.
4.3. Enhanced burst protection 4.3. Enhanced Burst Protection
The PIE [I-D.ietf-aqm-pie] algorithm has two states, INACTIVE and The PIE algorithm [RFC8033] has two states: INACTIVE and ACTIVE.
ACTIVE. During the INACTIVE state, AQM packet drops are suppressed. During the INACTIVE state, AQM packet drops are suppressed. The
The algorithm transitions to the ACTIVE state when the queue exceeds algorithm transitions to the ACTIVE state when the queue exceeds 1/3
1/3 of the buffer size. Upon transition to the ACTIVE state, PIE of the buffer size. Upon transition to the ACTIVE state, PIE
includes a burst protection feature in which the AQM packet drops are includes a burst protection feature in which the AQM packet drops are
suppressed for the first 150ms. Since DOCSIS-PIE is predominantly suppressed for the first 150 ms. Since DOCSIS-PIE is predominantly
deployed on consumer broadband connections, a more sophisticated deployed on consumer broadband connections, a more sophisticated
burst protection was developed in order to provide better performance burst protection was developed to provide better performance in the
in the presence of a single TCP session. presence of a single TCP session.
Where the PIE algorithm has two states, DOCSIS-PIE has three. The Where the PIE algorithm has two states, DOCSIS-PIE has three. The
INACTIVE and ACTIVE states in DOCSIS-PIE are identical to those INACTIVE and ACTIVE states in DOCSIS-PIE are identical to those
states in PIE. The QUIESCENT state is a transitional state between states in PIE. The QUIESCENT state is a transitional state between
INACTIVE and ACTIVE. The DOCSIS-PIE algorithm transitions from INACTIVE and ACTIVE. The DOCSIS-PIE algorithm transitions from
INACTIVE to QUIESCENT when the queue exceeds 1/3 of the buffer size. INACTIVE to QUIESCENT when the queue exceeds 1/3 of the buffer size.
In the QUIESCENT state, packet drops are immediately enabled, and In the QUIESCENT state, packet drops are immediately enabled, and
upon the first packet drop, the algorithm transitions to the ACTIVE upon the first packet drop, the algorithm transitions to the ACTIVE
state (where drop probability is reset to zero for the 150ms duration state (where drop probability is reset to zero for the 150 ms
of the burst protection as in PIE). From the ACTIVE state, the duration of the burst protection as in PIE). From the ACTIVE state,
algorithm transitions to QUIESCENT if the drop_probability has the algorithm transitions to QUIESCENT if the drop probability has
decayed to zero and the queuing latency has been less than half of decayed to zero and the queuing latency has been less than half of
the LATENCY_TARGET for two update intervals. The algorithm then the LATENCY_TARGET for two update intervals. The algorithm then
fully resets to the INACTIVE state if this "quiet" condition exists fully resets to the INACTIVE state if this "quiet" condition exists
for the duration of the BURST_RESET_TIMEOUT (1 second). One end for the duration of the BURST_RESET_TIMEOUT (1 second). One end
result of the addition of the QUIESCENT state is that a single packet result of the addition of the QUIESCENT state is that a single packet
drop can occur relatively early on during an initial burst, whereas drop can occur relatively early on during an initial burst, whereas
all drops would be suppressed for at least 150ms of the burst all drops would be suppressed for at least 150 ms of the burst
duration in PIE. The other end result is that if traffic stops and duration in PIE. The other end result is that if traffic stops and
then resumes within 1 second, DOCSIS_PIE can directly drop a single then resumes within 1 second, DOCSIS-PIE can directly drop a single
packet and then re-enter burst protection, whereas PIE would require packet and then re-enter burst protection, whereas PIE would require
that the buffer exceed 1/3 full. that the buffer exceed 1/3 full.
4.4. Expanded auto-tuning range 4.4. Expanded Auto-Tuning Range
The PIE algorithm scales the PI coefficients based on the current The PIE algorithm scales the Proportional and Integral coefficients
drop probability. The DOCSIS-PIE algorithm extends this scaling to based on the current drop probability. The DOCSIS-PIE algorithm
drop probabilities below 1e-4. extends this scaling to cover values of drop probability greater than
1, which can occur as a result of the drop probability scaling
function described in Section 4.6. As an example, if a flood of non-
responsive 64-byte packets were to arrive at a rate that is twice the
departure rate, the DOCSIS-PIE steady-state condition would be to
drop 50% of these packets, which implies that drop probability would
have the value of 8.00.
4.5. Trigger for exponential decay 4.5. Trigger for Exponential Decay
The PIE algorithm includes a mechanism by which the drop probability The PIE algorithm includes a mechanism by which the drop probability
is allowed to decay exponentially (rather than linearly) when it is is allowed to decay exponentially (rather than linearly) when it is
detected that the buffer is empty. In the DOCSIS case, recently detected that the buffer is empty. In the DOCSIS case, recently
arrived packets may reside in buffer due to the request-grant latency arrived packets may reside in the buffer due to the request-grant
even if the link is effectively idle. As a result, the buffer may latency even if the link is effectively idle. As a result, the
not be identically empty in the situations for which the exponential buffer may not be identically empty in the situations for which the
decay is intended. To compensate for this, we trigger exponential exponential decay is intended. To compensate for this, we trigger
decay when the buffer occupancy is less than 5ms * Peak Traffic Rate. exponential decay when the buffer occupancy is less than 5 ms * Peak
Traffic Rate.
4.6. Drop probability scaling 4.6. Drop Probability Scaling
The DOCSIS-PIE algorithm scales the calculated drop probability based The DOCSIS-PIE algorithm scales the calculated drop probability based
on the ratio of the packet size to a constant value of 1024 bytes on the ratio of the packet size to a constant value of 1024 bytes
(representing approximate average packet size). While [RFC7567] in (representing approximate average packet size). While [RFC7567] in
general recommends against this type of scaling, we note that DOCSIS- general recommends against this type of scaling, we note that DOCSIS-
PIE is expected to predominantly be used to manage upstream queues in PIE is expected to be used predominantly to manage upstream queues in
residential broadband deployments, where we believe the benefits residential broadband deployments, where we believe the benefits
outweigh the disadvantages. As a safeguard to prevent a flood of outweigh the disadvantages. As a safeguard to prevent a flood of
small packets from starving flows that use larger packets, DOCSIS-PIE small packets from starving flows that use larger packets, DOCSIS-PIE
limits the scaled probability to a defined maximum value of 0.85. limits the scaled probability to a defined maximum value of 0.85.
4.7. Support for explicit congestion notification 4.7. Support for Explicit Congestion Notification
DOCSIS-PIE does not include support for explicit congestion DOCSIS-PIE does not include support for Explicit Congestion
notification. Cable modems are essentially IEEE 802.1d Ethernet Notification (ECN). Cable modems are essentially IEEE 802.1d
bridges and so are not designed to modify IP header fields. Ethernet bridges and so are not designed to modify IP header fields.
Additionally, the packet processing pipeline in a cable modem is Additionally, the packet-processing pipeline in a cable modem is
commonly implemented in hardware. As a result, introducing support commonly implemented in hardware. As a result, introducing support
for ECN would have engendered a more significant redesign of cable for ECN would engender a significant redesign of cable modem data
modem data paths, and implementations would have been difficult or path hardware, and would be difficult or impossible to modify in the
impossible to modify in the future. At the time of the development future. At the time of the development of DOCSIS-PIE, which
of DOCSIS-PIE, which coincided with the development of modem chip coincided with the development of modem chip designs, the benefits of
designs, the benefits of ECN marking relative to packet drop were ECN marking relative to packet drop were considered to be relatively
considered to be relatively minor, there was considerable discussion minor; there was considerable discussion about differential treatment
about differential treatment of ECN capable packets in the AQM drop/ of ECN-capable packets in the AQM drop/mark decision, and there were
mark decision, and there were some initial suggestions that a new ECN some initial suggestions that a new ECN approach was needed. Due to
approach was needed. Due to this uncertainty, we chose not to this uncertainty, we chose not to include support for ECN.
include support for ECN.
5. Implementation Guidance 5. Implementation Guidance
The AQM space is an evolving one, and it is expected that continued The AQM space is an evolving one, and it is expected that continued
research in this field may in the future result in improved research in this field may result in improved algorithms in the
algorithms. future.
As part of defining the DOCSIS-PIE algorithm, we split the pseudocode As part of defining the DOCSIS-PIE algorithm, we split the pseudocode
definition into two components, a "data path" component and a definition into two components: a "data path" component and a
"control path" component. The control path component contains the "control path" component. The control path component contains the
packet drop probability update functionality, whereas the data path packet drop probability update functionality, whereas the data path
component contains the per-packet operations, including the drop component contains the per-packet operations, including the drop
decision logic. decision logic.
It is understood that some aspects of the cable modem implementation It is understood that some aspects of the cable modem implementation
may be done in hardware, particularly functions that handle packet- may be done in hardware, particularly functions that handle packet
processing. processing.
While the DOCSIS specifications don't mandate the internal While the DOCSIS specifications don't mandate the internal
implementation details of the cable modem, modem implementers are implementation details of the cable modem, modem implementers are
strongly advised against implementing the control path functionality strongly advised against implementing the control path functionality
in hardware. The intent of this advice is to retain the possibility in hardware. The intent of this advice is to retain the possibility
that future improvements in AQM algorithms can be accommodated via that future improvements in AQM algorithms can be accommodated via
software updates to deployed devices. software updates to deployed devices.
6. IANA Considerations 6. Security Considerations
This document has no actions for IANA. This document describes an active queue management algorithm based on
[RFC8033] for implementation in DOCSIS cable modem devices. This
algorithm introduces no specific security exposures.
7. Security Considerations 7. References
This document describes an active queue management algorithm based on 7.1. Normative References
[I-D.ietf-aqm-pie] for implementation in DOCSIS cable modem devices.
This algorithm introduces no specific security exposures.
8. Informative References [RFC8033] Pan, R., Natarajan, P., Baker, F., and G. White,
"Proportional Integral Controller Enhanced (PIE): A
Lightweight Control Scheme to Address the Bufferbloat
Problem", RFC 8033, DOI 10.17487/RFC8033, February 2017,
<http://www.rfc-editor.org/info/rfc8033>.
7.2. Informative References
[CommMag] White, G., "Active queue management in DOCSIS 3.1 [CommMag] White, G., "Active queue management in DOCSIS 3.1
networks", IEEE Communications Magazine vol.53, no.3, networks", IEEE Communications Magazine vol. 53, no. 3,
pp.126-132, March 2015. pp. 126-132, DOI 10.1109/MCOM.2015.7060493, March 2015.
[DOCSIS-AQM] [DOCSIS-AQM]
White, G., "Active Queue Management in DOCSIS 3.x Cable White, G., "Active Queue Management in DOCSIS 3.x Cable
Modems", May 2014, <http://www.cablelabs.com/wp- Modems", May 2014, <http://www.cablelabs.com/
content/uploads/2014/06/DOCSIS-AQM_May2014.pdf>. wp-content/uploads/2014/06/DOCSIS-AQM_May2014.pdf>.
[DOCSIS_3.0] [DOCSIS_3.0]
CableLabs, "DOCSIS 3.0 MAC and Upper Layer Protocols CableLabs, "MAC and Upper Layer Protocols Interface
Specification", December 2015, <http://www.cablelabs.com/ Specification", DOCSIS 3.0, January 2017,
wp-content/uploads/specdocs/ <https://apps.cablelabs.com/specification/
CM-SP-MULPIv3.0-I29-151210.pdf>. CM-SP-MULPIv3.0>.
[DOCSIS_3.1] [DOCSIS_3.1]
CableLabs, "DOCSIS 3.1 MAC and Upper Layer Protocols CableLabs, "MAC and Upper Layer Protocols Interface
Specification", December 2015, <http://www.cablelabs.com/ Specification", DOCSIS 3.1, January 2017,
wp-content/uploads/specdocs/ <https://apps.cablelabs.com/specification/
CM-SP-MULPIv3.1-I08-151210.pdf>. CM-SP-MULPIv3.1>.
[I-D.ietf-aqm-pie]
Pan, R., Natarajan, P., and F. Baker, "PIE: A Lightweight
Control Scheme To Address the Bufferbloat Problem", draft-
ietf-aqm-pie-03 (work in progress), November 2015.
[RFC7567] Baker, F., Ed. and G. Fairhurst, Ed., "IETF [RFC7567] Baker, F., Ed. and G. Fairhurst, Ed., "IETF
Recommendations Regarding Active Queue Management", Recommendations Regarding Active Queue Management",
BCP 197, RFC 7567, DOI 10.17487/RFC7567, July 2015, BCP 197, RFC 7567, DOI 10.17487/RFC7567, July 2015,
<http://www.rfc-editor.org/info/rfc7567>. <http://www.rfc-editor.org/info/rfc7567>.
Appendix A. DOCSIS-PIE Algorithm definition Appendix A. DOCSIS-PIE Algorithm Definition
PIE defines two functions organized here into two design blocks: PIE defines two functions organized here into two design blocks:
1. Control path block, a periodically running algorithm that 1. Control path block -- a periodically running algorithm that
calculates a drop probability based on the estimated queuing calculates a drop probability based on the estimated queuing
latency and queuing latency trend. latency and queuing latency trend.
2. Data path block, a function that occurs on each packet enqueue: 2. Data path block, a function that occurs on each packet enqueue
per-packet drop decision based on the drop probability. that implements a per-packet drop decision based on the drop
probability.
It is desired to have the ability to update the Control path block It is desirable to have the ability to update the control path block
based on operational experience with PIE deployments. based on operational experience with PIE deployments.
A.1. DOCSIS-PIE AQM Constants and Variables A.1. DOCSIS-PIE AQM Constants and Variables
A.1.1. Configuration parameters A.1.1. Configuration Parameters
o LATENCY_TARGET. AQM Latency Target for this Service Flow o LATENCY_TARGET. AQM Latency Target for this Service Flow
o PEAK_RATE. Service Flow configured Peak Traffic Rate, expressed o PEAK_RATE. Service Flow configured Peak Traffic Rate, expressed
in Bytes/sec. in bytes/second
o MSR. Service Flow configured Max. Sustained Traffic Rate, o MSR. Service Flow configured Maximum Sustained Traffic Rate,
expressed in Bytes/sec. expressed in bytes/second
o BUFFER_SIZE. The size (in bytes) of the buffer for this Service o BUFFER_SIZE. The size (in bytes) of the buffer for this Service
Flow. Flow
A.1.2. Constant values A.1.2. Constant Values
o A = 0.25, B = 2.5. Weights in the drop probability calculation o A = 0.25, B = 2.5. Weights in the drop probability calculation
o INTERVAL = 16 ms. Update interval for drop probability. o INTERVAL = 16 ms. Update interval for drop probability
o BURST_RESET_TIMEOUT = 1 s. o BURST_RESET_TIMEOUT = 1 second
o MAX_BURST = 142 ms (150 ms - 8 ms (update error)) o MAX_BURST = 142 ms (150 ms - 8 ms (update error))
o MEAN_PKTSIZE = 1024 bytes o MEAN_PKTSIZE = 1024 bytes
o MIN_PKTSIZE = 64 bytes o MIN_PKTSIZE = 64 bytes
o PROB_LOW = 0.85 o PROB_LOW = 0.85
o PROB_HIGH = 8.5 o PROB_HIGH = 8.5
skipping to change at page 10, line 43 skipping to change at page 12, line 4
o MAX_BURST = 142 ms (150 ms - 8 ms (update error)) o MAX_BURST = 142 ms (150 ms - 8 ms (update error))
o MEAN_PKTSIZE = 1024 bytes o MEAN_PKTSIZE = 1024 bytes
o MIN_PKTSIZE = 64 bytes o MIN_PKTSIZE = 64 bytes
o PROB_LOW = 0.85 o PROB_LOW = 0.85
o PROB_HIGH = 8.5 o PROB_HIGH = 8.5
o LATENCY_LOW = 5 ms o LATENCY_LOW = 5 ms
o LATENCY_HIGH = 200 ms. o LATENCY_HIGH = 200 ms
A.1.3. Variables A.1.3. Variables
o drop_prob_. The current packet drop probability. o drop_prob_. The current packet drop probability
o accu_prob_. accumulated drop prob. since last drop o accu_prob_. Accumulated drop probability since last drop
o qdelay_old_. The previous queue delay estimate.
o qdelay_old_. The previous queue delay estimate
o burst_allowance_. Countdown for burst protection, initialize to 0 o burst_allowance_. Countdown for burst protection, initialize to 0
o burst_reset_. counter to reset burst o burst_reset_. Counter to reset burst
o aqm_state_. AQM activity state encoding 3 states: o aqm_state_. AQM activity state encoding 3 states:
INACTIVE - queue staying below 1/3 full, suppress AQM drops INACTIVE - Queue staying below 1/3 full, suppress AQM drops
QUIESCENT - transition state QUIESCENT - Transition state
ACTIVE - normal AQM drops (after burst protection period) ACTIVE - Normal AQM drops (after burst protection period)
o queue_. Holds the pending packets. o queue_. Holds the pending packets
A.1.4. Public/system functions: A.1.4. Public/System Functions
o drop(packet). Drops/discards a packet o drop(packet). Drops/discards a packet
o random(). Returns a uniform r.v. in the range 0 ~ 1 o random(). Returns a uniform random value in the range 0 ~ 1
o queue_.is_full(). Returns true if queue_ is full o queue_.is_full(). Returns true if queue_ is full
o queue_.byte_length(). Returns current queue_ length in bytes, o queue_.byte_length(). Returns current queue_ length in bytes,
including all MAC PDU bytes without DOCSIS MAC overhead including all MAC PDU bytes without DOCSIS MAC overhead
o queue_.enque(packet). Adds packet to tail of queue_ o queue_.enque(packet). Adds packet to tail of queue_
o msrtokens(). Returns current token credits (in bytes) from the o msrtokens(). Returns current token credits (in bytes) from the
Max Sust. Traffic Rate token bucket Maximum Sustained Traffic Rate token bucket
o packet.size(). Returns size of packet o packet.size(). Returns size of packet
A.2. DOCSIS-PIE AQM Control Path A.2. DOCSIS-PIE AQM Control Path
The DOCSIS-PIE control path performs the following: The DOCSIS-PIE control path performs the following:
o Calls control_path_init() at service flow creation o Calls control_path_init() at Service Flow creation
o Calls calculate_drop_prob() at a regular INTERVAL (16ms) o Calls calculate_drop_prob() at a regular INTERVAL (16 ms)
================ ================
// Initialization function // Initialization function
control_path_init() { control_path_init() {
drop_prob_ = 0; drop_prob_ = 0;
qdelay_old_ = 0; qdelay_old_ = 0;
burst_reset_ = 0; burst_reset_ = 0;
aqm_state_ = INACTIVE; aqm_state_ = INACTIVE;
} }
// Background update, occurs every INTERVAL // Background update, occurs every INTERVAL
calculate_drop_prob() { calculate_drop_prob() {
skipping to change at page 13, line 15 skipping to change at page 14, line 32
drop_prob_ *= 0.98; // exponential decay drop_prob_ *= 0.98; // exponential decay
} else if (qdelay > LATENCY_HIGH) { } else if (qdelay > LATENCY_HIGH) {
drop_prob_ += 0.02; // ramp up quickly drop_prob_ += 0.02; // ramp up quickly
} }
drop_prob_ = max(0, drop_prob_); drop_prob_ = max(0, drop_prob_);
drop_prob_ = min(drop_prob_, \ drop_prob_ = min(drop_prob_, \
PROB_LOW * MEAN_PKTSIZE/MIN_PKTSIZE); PROB_LOW * MEAN_PKTSIZE/MIN_PKTSIZE);
} }
// check if all is quiet // Check if all is quiet
quiet = (qdelay < 0.5 * LATENCY_TARGET) quiet = (qdelay < 0.5 * LATENCY_TARGET)
&& (qdelay_old_ < 0.5 * LATENCY_TARGET) && (qdelay_old_ < 0.5 * LATENCY_TARGET)
&& (drop_prob_ == 0) && (drop_prob_ == 0)
&& (burst_allowance_ == 0); && (burst_allowance_ == 0);
// Update AQM state based on quiet or !quiet // Update AQM state based on quiet or !quiet
if ((aqm_state_ == ACTIVE) && quiet) { if ((aqm_state_ == ACTIVE) && quiet) {
aqm_state_ = QUIESCENT; aqm_state_ = QUIESCENT;
burst_reset_ = 0; burst_reset_ = 0;
} else if (aqm_state_ == QUIESCENT) { } else if (aqm_state_ == QUIESCENT) {
skipping to change at page 14, line 51 skipping to change at page 16, line 20
accu_prob_ += p1; accu_prob_ += p1;
// Suppress AQM drops in certain situations // Suppress AQM drops in certain situations
if ( (qdelay_old_ < 0.5 * LATENCY_TARGET && drop_prob_ < 0.2) if ( (qdelay_old_ < 0.5 * LATENCY_TARGET && drop_prob_ < 0.2)
|| (queue_.byte_length() <= 2 * MEAN_PKTSIZE) ) { || (queue_.byte_length() <= 2 * MEAN_PKTSIZE) ) {
return FALSE; return FALSE;
} }
if (accu_prob_ < PROB_LOW) { // avoid dropping too fast due if (accu_prob_ < PROB_LOW) { // avoid dropping too fast due
return FALSE; // to bad luck of coin tosses... return FALSE; // to bad luck of coin tosses...
} else if (accu_prob_ >= PROB_HIGH) { // ...and avoid droppping } else if (accu_prob_ >= PROB_HIGH) { // ...and avoid dropping
drop = TRUE; // too slowly drop = TRUE; // too slowly
} else { //Random drop } else { //Random drop
double u = random(); // 0 ~ 1 double u = random(); // 0 ~ 1
if (u > p1) if (u > p1)
return FALSE; return FALSE;
else else
drop = TRUE; drop = TRUE;
} }
// at this point, drop == TRUE, so packet will be dropped. // At this point, drop == TRUE, so packet will be dropped.
// reset accu_prob_ // Reset accu_prob_
accu_prob_ = 0; accu_prob_ = 0;
// If in QUIESCENT state, packet drop triggers // If in QUIESCENT state, packet drop triggers
// ACTIVE state and start of burst protection // ACTIVE state and start of burst protection
if (aqm_state_ == QUIESCENT) { if (aqm_state_ == QUIESCENT) {
aqm_state_ = ACTIVE; aqm_state_ = ACTIVE;
burst_allowance_ = MAX_BURST; burst_allowance_ = MAX_BURST;
} }
return TRUE; return TRUE;
} }
Authors' Addresses Authors' Addresses
Greg White Greg White
CableLabs CableLabs
858 Coal Creek Circle 858 Coal Creek Circle
Louisville, CO 80027-9750 Louisville, CO 80027-9750
USA United States of America
Email: g.white@cablelabs.com Email: g.white@cablelabs.com
Rong Pan Rong Pan
Cisco Systems Cisco Systems
510 McCarthy Blvd 510 McCarthy Blvd
Milpitas, CA 95134 Milpitas, CA 95134
USA United States of America
Email: ropan@cisco.com Email: ropan@cisco.com
 End of changes. 94 change blocks. 
216 lines changed or deleted 225 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/