rfc9320.original   rfc9320.txt 
DetNet N. Finn Internet Engineering Task Force (IETF) N. Finn
Internet-Draft Huawei Technologies Co. Ltd Request for Comments: 9320 Huawei Technologies Co. Ltd
Intended status: Informational J-Y. Le Boudec Category: Informational J.-Y. Le Boudec
Expires: 10 October 2022 E. Mohammadpour ISSN: 2070-1721 E. Mohammadpour
EPFL EPFL
J. Zhang J. Zhang
Huawei Technologies Co. Ltd Huawei Technologies Co. Ltd
B. Varga B. Varga
Ericsson Ericsson
8 April 2022 November 2022
DetNet Bounded Latency Deterministic Networking (DetNet) Bounded Latency
draft-ietf-detnet-bounded-latency-10
Abstract Abstract
This document presents a timing model for sources, destinations, and This document presents a timing model for sources, destinations, and
DetNet transit nodes. Using the model, it provides a methodology to Deterministic Networking (DetNet) transit nodes. Using the model, it
compute end-to-end latency and backlog bounds for various queuing provides a methodology to compute end-to-end latency and backlog
methods. The methodology can be used by the management and control bounds for various queuing methods. The methodology can be used by
planes and by resource reservation algorithms to provide bounded the management and control planes and by resource reservation
latency and zero congestion loss for the DetNet service. algorithms to provide bounded latency and zero congestion loss for
the DetNet service.
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 https://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 candidates for any level of Internet
Standard; see Section 2 of RFC 7841.
This Internet-Draft will expire on 10 October 2022. Information about the current status of this document, any errata,
and how to provide feedback on it may be obtained at
https://www.rfc-editor.org/info/rfc9320.
Copyright Notice Copyright Notice
Copyright (c) 2022 IETF Trust and the persons identified as the Copyright (c) 2022 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 (https://trustee.ietf.org/ Provisions Relating to IETF Documents
license-info) in effect on the date of publication of this document. (https://trustee.ietf.org/license-info) in effect on the date of
Please review these documents carefully, as they describe your rights publication of this document. Please review these documents
and restrictions with respect to this document. Code Components carefully, as they describe your rights and restrictions with respect
extracted from this document must include Revised BSD License text as to this document. Code Components extracted from this document must
described in Section 4.e of the Trust Legal Provisions and are include Revised BSD License text as described in Section 4.e of the
provided without warranty as described in the Revised BSD License. Trust Legal Provisions and are provided without warranty as described
in the Revised BSD License.
Table of Contents Table of Contents
1. Introduction . . . . . . . . . . . . . . . . . . . . . . . . 3 1. Introduction
2. Terminology and Definitions . . . . . . . . . . . . . . . . . 4 2. Terminology and Definitions
3. DetNet bounded latency model . . . . . . . . . . . . . . . . 4 3. DetNet Bounded Latency Model
3.1. Flow admission . . . . . . . . . . . . . . . . . . . . . 4 3.1. Flow Admission
3.1.1. Static latency-calculation . . . . . . . . . . . . . 5 3.1.1. Static Latency Calculation
3.1.2. Dynamic latency-calculation . . . . . . . . . . . . . 6 3.1.2. Dynamic Latency Calculation
3.2. Relay node model . . . . . . . . . . . . . . . . . . . . 7 3.2. Relay Node Model
4. Computing End-to-end Delay Bounds . . . . . . . . . . . . . . 9 4. Computing End-to-End Delay Bounds
4.1. Non-queuing delay bound . . . . . . . . . . . . . . . . . 9 4.1. Non-queuing Delay Bound
4.2. Queuing delay bound . . . . . . . . . . . . . . . . . . . 10 4.2. Queuing Delay Bound
4.2.1. Per-flow queuing mechanisms . . . . . . . . . . . . . 11 4.2.1. Per-Flow Queuing Mechanisms
4.2.2. Aggregate queuing mechanisms . . . . . . . . . . . . 11 4.2.2. Aggregate Queuing Mechanisms
4.3. Ingress considerations . . . . . . . . . . . . . . . . . 12 4.3. Ingress Considerations
4.4. Interspersed DetNet-unaware transit nodes . . . . . . . . 13 4.4. Interspersed DetNet-Unaware Transit Nodes
5. Achieving zero congestion loss . . . . . . . . . . . . . . . 13 5. Achieving Zero Congestion Loss
6. Queuing techniques . . . . . . . . . . . . . . . . . . . . . 14 6. Queuing Techniques
6.1. Queuing data model . . . . . . . . . . . . . . . . . . . 15 6.1. Queuing Data Model
6.2. Frame Preemption . . . . . . . . . . . . . . . . . . . . 17 6.2. Frame Preemption
6.3. Time-Aware Shaper . . . . . . . . . . . . . . . . . . . . 17 6.3. Time-Aware Shaper
6.4. Credit-Based Shaper with Asynchronous Traffic Shaping . . 18 6.4. Credit-Based Shaper with Asynchronous Traffic Shaping
6.4.1. Delay Bound Calculation . . . . . . . . . . . . . . . 20 6.4.1. Delay Bound Calculation
6.4.2. Flow Admission . . . . . . . . . . . . . . . . . . . 21 6.4.2. Flow Admission
6.5. Guaranteed-Service IntServ . . . . . . . . . . . . . . . 22 6.5. Guaranteed Service
6.6. Cyclic Queuing and Forwarding . . . . . . . . . . . . . . 23 6.6. Cyclic Queuing and Forwarding
7. Example application on DetNet IP network . . . . . . . . . . 24 7. Example Application on DetNet IP Network
8. Security considerations . . . . . . . . . . . . . . . . . . . 26 8. Security Considerations
9. IANA considerations . . . . . . . . . . . . . . . . . . . . . 27 9. IANA considerations
10. Acknowledgement . . . . . . . . . . . . . . . . . . . . . . . 27 10. References
11. Contributors . . . . . . . . . . . . . . . . . . . . . . . . 27 10.1. Normative References
12. References . . . . . . . . . . . . . . . . . . . . . . . . . 27 10.2. Informative References
12.1. Normative References . . . . . . . . . . . . . . . . . . 27 Acknowledgments
12.2. Informative References . . . . . . . . . . . . . . . . . 28 Contributors
Authors' Addresses . . . . . . . . . . . . . . . . . . . . . . . 30 Authors' Addresses
1. Introduction 1. Introduction
The ability for IETF Deterministic Networking (DetNet) or IEEE 802.1 The ability for IETF Deterministic Networking (DetNet) or IEEE 802.1
Time-Sensitive Networking [IEEE8021TSN] to provide the DetNet Time-Sensitive Networking [IEEE8021TSN] to provide the DetNet
services of bounded latency and zero congestion loss depends upon services of bounded latency and zero congestion loss depends upon
A) configuring and allocating network resources for the exclusive A. configuring and allocating network resources for the exclusive
use of DetNet flows; use of DetNet flows;
B) identifying, in the data plane, the resources to be utilized by B. identifying, in the data plane, the resources to be utilized by
any given packet; any given packet; and
C) the detailed behavior of those resources, especially C. the detailed behavior of those resources, especially transmission
transmission queue selection, so that latency bounds can be queue selection, so that latency bounds can be reliably assured.
reliably assured.
As explained in [RFC8655], DetNet flows are notably characterized by As explained in [RFC8655], DetNet flows are notably characterized by
1. a maximum bandwidth, guaranteed either by the transmitter or by 1. a maximum bandwidth, guaranteed either by the transmitter or by
strict input metering; strict input metering, and
2. a requirement for a guaranteed worst-case end-to-end latency. 2. a requirement for a guaranteed worst-case end-to-end latency.
That latency guarantee, in turn, provides the opportunity for the That latency guarantee, in turn, provides the opportunity for the
network to supply enough buffer space to guarantee zero congestion network to supply enough buffer space to guarantee zero congestion
loss. It is assumed in this document that the paths of DetNet flows loss. In this document, it is assumed that the paths of DetNet flows
are fixed. Before the transmission of a DetNet flow, it is possible are fixed. Before the transmission of a DetNet flow, it is possible
to calculate end-to-end latency bounds and the amount of buffer space to calculate end-to-end latency bounds and the amount of buffer space
required at each hop to ensure zero congestion loss; this can be used required at each hop to ensure zero congestion loss; this can be used
by the applications identified in [RFC8578]. by the applications identified in [RFC8578].
This document presents a timing model for sources, destinations, and This document presents a timing model for sources, destinations, and
the DetNet transit nodes; using this model, it provides a methodology the DetNet transit nodes; using this model, it provides a methodology
to compute end-to-end latency and backlog bounds for various queuing to compute end-to-end latency and backlog bounds for various queuing
mechanisms that can be used by the management and control planes to mechanisms that can be used by the management and control planes to
provide DetNet qualities of service. The methodology used in this provide DetNet qualities of service. The methodology used in this
document account for the possibility of packet reordering within a document accounts for the possibility of packet reordering within a
DetNet node. The bounds on the amount of packet reordering is out of DetNet node. The bounds on the amount of packet reordering is out of
the scope of this document and can be found in the scope of this document and can be found in
[PacketReorderingBounds]. Moreover, this document references [PacketReorderingBounds]. Moreover, this document references
specific queuing mechanisms, mentioned in [RFC8655], as proofs of specific queuing mechanisms, mentioned in [RFC8655], as proofs of
concept that can be used to control packet transmission at each concept that can be used to control packet transmission at each
output port and achieve the DetNet quality of service. output port and achieve the DetNet quality of service (QoS).
Using the model presented in this document, it is possible for an Using the model presented in this document, it is possible for an
implementer, user, or standards development organization to select a implementer, user, or standards development organization to select a
set of queuing mechanisms for each device in a DetNet network, and to set of queuing mechanisms for each device in a DetNet network and to
select a resource reservation algorithm for that network, so that select a resource reservation algorithm for that network so that
those elements can work together to provide the DetNet service. those elements can work together to provide the DetNet service.
Section 7 provides an example application of the timing model Section 7 provides an example application of the timing model
introduced in this document on a DetNet IP network with a combination introduced in this document on a DetNet IP network with a combination
of different queuing mechanisms. of different queuing mechanisms.
This document does not specify any resource reservation protocol or This document does not specify any resource reservation protocol or
control plane function. It does not describe all of the requirements control plane function. It does not describe all of the requirements
for that protocol or control plane function. It does describe for that protocol or control plane function. It does describe
requirements for such resource reservation methods, and for queuing requirements for such resource reservation methods and for queuing
mechanisms that, if met, will enable them to work together. mechanisms that, if met, will enable them to work together.
2. Terminology and Definitions 2. Terminology and Definitions
This document uses the terms defined in [RFC8655]. Moreover, the This document uses the terms defined in [RFC8655]. Moreover, the
following terms are used in this document: following terms are used in this document:
T-SPEC T-SPEC
TrafficSpecification as defined in Section 5.5 of [RFC9016]. TrafficSpecification, as defined in Section 5.5 of [RFC9016].
arrival curve arrival curve
An arrival curve function alpha(t) is an upper bound on the number An arrival curve function alpha(t) is an upper bound on the number
of bits seen at an observation point within any time interval t. of bits seen at an observation point within any time interval t.
CQF CQF
Cyclic Queuing and Forwarding. Cyclic Queuing and Forwarding.
CBS CBS
Credit-based Shaper. Credit-Based Shaper.
TSN TSN
Time-Sensitive Networking. Time-Sensitive Networking.
PREOF PREOF
A collective name for Packet Replication, Elimination, and A collective name for Packet Replication, Elimination, and
Ordering Functions. Ordering Functions.
Packet Ordering Function (POF) POF
A function that reorders packets within a DetNet flow that are A Packet Ordering Function is a function that reorders packets
received out of order. This function can be implemented by a within a DetNet flow that are received out of order. This
DetNet edge node, a DetNet relay node, or an end system. function can be implemented by a DetNet edge node, a DetNet relay
node, or an end system.
3. DetNet bounded latency model 3. DetNet Bounded Latency Model
3.1. Flow admission 3.1. Flow Admission
This document assumes that the following paradigm is used to admit This document assumes that the following paradigm is used to admit
DetNet flows: DetNet flows:
1. Perform any configuration required by the DetNet transit nodes in 1. Perform any configuration required by the DetNet transit nodes in
the network for aggregates of DetNet flows. This configuration the network for aggregates of DetNet flows. This configuration
is done beforehand, and not tied to any particular DetNet flow. is done beforehand and not tied to any particular DetNet flow.
2. Characterize the new DetNet flow, particularly in terms of 2. Characterize the new DetNet flow, particularly in terms of
required bandwidth. required bandwidth.
3. Establish the path that the DetNet flow will take through the 3. Establish the path that the DetNet flow will take through the
network from the source to the destination(s). This can be a network from the source to the destination(s). This can be a
point-to-point or a point-to-multipoint path. point-to-point or a point-to-multipoint path.
4. Compute the worst-case end-to-end latency for the DetNet flow, 4. Compute the worst-case end-to-end latency for the DetNet flow
using one of the methods, below (Section 3.1.1, Section 3.1.2). using one of the methods below (Sections 3.1.1 and 3.1.2). In
In the process, determine whether sufficient resources are the process, determine whether sufficient resources are available
available for the DetNet flow to guarantee the required latency for the DetNet flow to guarantee the required latency and to
and to provide zero congestion loss. provide zero congestion loss.
5. Assuming that the resources are available, commit those resources 5. Assuming that the resources are available, commit those resources
to the DetNet flow. This may or may not require adjusting the to the DetNet flow. This may require adjusting the parameters
parameters that control the filtering and/or queuing mechanisms that control the filtering and/or queuing mechanisms at each hop
at each hop along the DetNet flow's path. along the DetNet flow's path.
This paradigm can be implemented using peer-to-peer protocols or This paradigm can be implemented using peer-to-peer protocols or
using a central controller. In some situations, a lack of resources using a central controller. In some situations, a lack of resources
can require backtracking and recursing through the above list. can require backtracking and recursing through the above list.
Issues such as service preemption of a DetNet flow in favor of Issues, such as service preemption of a DetNet flow in favor of
another, when resources are scarce, are not considered here. Also another, when resources are scarce, are not considered here. Also
not addressed is the question of how to choose the path to be taken not addressed is the question of how to choose the path to be taken
by a DetNet flow. by a DetNet flow.
3.1.1. Static latency-calculation 3.1.1. Static Latency Calculation
The static problem: The static problem:
Given a network and a set of DetNet flows, compute an end-to- Given a network and a set of DetNet flows, compute an end-to-
end latency bound (if computable) for each DetNet flow, and end latency bound (if computable) for each DetNet flow and
compute the resources, particularly buffer space, required in compute the resources, particularly buffer space, required in
each DetNet transit node to achieve zero congestion loss. each DetNet transit node to achieve zero congestion loss.
In this calculation, all of the DetNet flows are known before the In this calculation, all of the DetNet flows are known before the
calculation commences. This problem is of interest to relatively calculation commences. This problem is of interest to relatively
static networks, or static parts of larger networks. It provides static networks or static parts of larger networks. It provides
bounds on latency and buffer size. The calculations can be extended bounds on latency and buffer size. The calculations can be extended
to provide global optimizations, such as altering the path of one to provide global optimizations, such as altering the path of one
DetNet flow in order to make resources available to another DetNet DetNet flow in order to make resources available to another DetNet
flow with tighter constraints. flow with tighter constraints.
This calculation may be more difficult to perform than the dynamic This calculation may be more difficult to perform than the dynamic
calculation (Section 3.1.2), because the DetNet flows passing through calculation (Section 3.1.2) because the DetNet flows passing through
one port on a DetNet transit node affect each other's latency. The one port on a DetNet transit node affect each other's latency. The
effects can even be circular, from a node A to B to C and back to A. effects can even be circular, from node A to B to C and back to A.
On the other hand, the static calculation can often accommodate On the other hand, the static calculation can often accommodate
queuing methods, such as transmission selection by strict priority, queuing methods, such as transmission selection by strict priority,
that are unsuitable for the dynamic calculation. that are unsuitable for the dynamic calculation.
3.1.2. Dynamic latency-calculation 3.1.2. Dynamic Latency Calculation
The dynamic problem: The dynamic problem:
Given a network whose maximum capacity for DetNet flows is Given a network whose maximum capacity for DetNet flows is
bounded by a set of static configuration parameters applied bounded by a set of static configuration parameters applied
to the DetNet transit nodes, and given just one DetNet flow, to the DetNet transit nodes and given just one DetNet flow,
compute the worst-case end-to-end latency that can be compute the worst-case end-to-end latency that can be
experienced by that flow, no matter what other DetNet flows experienced by that flow, no matter what other DetNet flows
(within the network's configured parameters) might be created (within the network's configured parameters) might be created
or deleted in the future. Also, compute the resources, or deleted in the future. Also, compute the resources,
particularly buffer space, required in each DetNet transit particularly buffer space, required in each DetNet transit
node to achieve zero congestion loss. node to achieve zero congestion loss.
This calculation is dynamic, in the sense that DetNet flows can be This calculation is dynamic, in the sense that DetNet flows can be
added or deleted at any time, with a minimum of computation effort, added or deleted at any time, with a minimum of computation effort
and without affecting the guarantees already given to other DetNet and without affecting the guarantees already given to other DetNet
flows. flows.
Dynamic latency-calculation can be done based on the static one Dynamic latency calculation can be done based on the static one
described in Section 3.1.1; when a new DetNet flow is created or described in Section 3.1.1; when a new DetNet flow is created or
deleted, the entire calculation for all DetNet flows is repeated. If deleted, the entire calculation for all DetNet flows is repeated. If
an already-established DetNet flow would be pushed beyond its latency an already-established DetNet flow would be pushed beyond its latency
requirements by the new DetNet flow request, then the new DetNet flow requirements by the new DetNet flow request, then the new DetNet flow
request can be refused, or some other suitable action taken. request can be refused or some other suitable action can be taken.
The choice of queuing methods is critical to the applicability of the The choice of queuing methods is critical to the applicability of the
dynamic calculation. Some queuing methods (e.g., CQF, Section 6.6) dynamic calculation. Some queuing methods (e.g., CQF, Section 6.6)
make it easy to configure bounds on the network's capacity, and to make it easy to configure bounds on the network's capacity and to
make independent calculations for each DetNet flow. Some other make independent calculations for each DetNet flow. Some other
queuing methods (e.g., strict priority with the credit-based shaper queuing methods (e.g., strict priority with the credit-based shaper
defined in [IEEE8021Q] section 8.6.8.2) can be used for dynamic defined in Section 8.6.8.2 of [IEEE8021Q]) can be used for dynamic
DetNet flow creation, but yield poorer latency and buffer space DetNet flow creation but yield poorer latency and buffer space
guarantees than when that same queuing method is used for static guarantees than when that same queuing method is used for static
DetNet flow creation (Section 3.1.1). DetNet flow creation (Section 3.1.1).
3.2. Relay node model 3.2. Relay Node Model
A model for the operation of a DetNet transit node is required, in A model for the operation of a DetNet transit node is required in
order to define the latency and buffer calculations. In Figure 1 we order to define the latency and buffer calculations. In Figure 1, we
see a breakdown of the per-hop latency experienced by a packet see a breakdown of the per-hop latency experienced by a packet
passing through a DetNet transit node, in terms that are suitable for passing through a DetNet transit node in terms that are suitable for
computing both hop-by-hop latency and per-hop buffer requirements. computing both hop-by-hop latency and per-hop buffer requirements.
DetNet transit node A DetNet transit node B DetNet transit node A DetNet transit node B
+-------------------------+ +------------------------+ +-------------------------+ +------------------------+
| Queuing | | Queuing | | Queuing | | Queuing |
| Regulator subsystem | | Regulator subsystem | | Regulator subsystem | | Regulator subsystem |
| +-+-+-+-+ +-+-+-+-+ | | +-+-+-+-+ +-+-+-+-+ | | +-+-+-+-+ +-+-+-+-+ | | +-+-+-+-+ +-+-+-+-+ |
-->+ | | | | | | | | | + +------>+ | | | | | | | | | + +---> -->+ | | | | | | | | | + +------>+ | | | | | | | | | + +--->
| +-+-+-+-+ +-+-+-+-+ | | +-+-+-+-+ +-+-+-+-+ | | +-+-+-+-+ +-+-+-+-+ | | +-+-+-+-+ +-+-+-+-+ |
| | | | | | | |
+-------------------------+ +------------------------+ +-------------------------+ +------------------------+
|<->|<------>|<------->|<->|<---->|<->|<------>|<------>|<->|<-- |<->|<------>|<------->|<->|<---->|<->|<------>|<------>|<->|<--
2,3 4 5 6 1 2,3 4 5 6 1 2,3 2,3 4 5 6 1 2,3 4 5 6 1 2,3
1: Output delay 4: Processing delay 1: Output delay 4: Processing delay
2: Link delay 5: Regulation delay 2: Link delay 5: Regulation delay
3: Frame preemption delay 6: Queuing delay 3: Frame preemption delay 6: Queuing subsystem delay
Figure 1: Timing model for DetNet or TSN Figure 1: Timing Model for DetNet or TSN
In Figure 1, we see two DetNet transit nodes that are connected via a In Figure 1, we see two DetNet transit nodes that are connected via a
link. In this model, the only queues, that we deal with explicitly, link. In this model, the only queues that we deal with explicitly
are attached to the output port; other queues are modeled as are attached to the output port; other queues are modeled as
variations in the other delay times (e.g., an input queue could be variations in the other delay times (e.g., an input queue could be
modeled as either a variation in the link delay (2) or the processing modeled as either a variation in the link delay (2) or the processing
delay (4).) There are six delays that a packet can experience from delay (4)). There are six delays that a packet can experience from
hop to hop. hop to hop.
1. Output delay 1. Output delay
The time taken from the selection of a packet for output from a
queue to the transmission of the first bit of the packet on the This is the time taken from the selection of a packet for output
physical link. If the queue is directly attached to the physical from a queue to the transmission of the first bit of the packet
port, output delay can be a constant. But, in many on the physical link. If the queue is directly attached to the
implementations, the queuing mechanism in a forwarding ASIC is physical port, output delay can be a constant. However, in many
separated from a multi-port MAC/PHY, in a second ASIC, by a implementations, a multiplexed connection separates the queuing
multiplexed connection. This causes variations in the output mechanism from a multi-port Network Interface Card (NIC). This
delay that are hard for the forwarding node to predict or control. causes variations in the output delay that are hard for the
forwarding node to predict or control.
2. Link delay 2. Link delay
The time taken from the transmission of the first bit of the
packet to the reception of the last bit, assuming that the This is the time taken from the transmission of the first bit of
transmission is not suspended by a frame preemption event. This the packet to the reception of the last bit, assuming that the
delay has two components, the first-bit-out to first-bit-in delay transmission is not suspended by a frame preemption event. This
and the first-bit-in to last-bit-in delay that varies with packet delay has two components: the first-bit-out to first-bit-in delay
size. The former is typically measured by the Precision Time and the first-bit-in to last-bit-in delay that varies with packet
Protocol and is constant (see [RFC8655]). However, a virtual size. The former is typically constant. However, a virtual
"link" could exhibit a variable link delay. "link" could exhibit a variable link delay.
3. Frame preemption delay 3. Frame preemption delay
If the packet is interrupted in order to transmit another packet
or packets, (e.g., [IEEE8023] clause 99 frame preemption) an If the packet is interrupted in order to transmit another packet
arbitrary delay can result. or packets (e.g., frame preemption, as in [IEEE8023], clause 99),
an arbitrary delay can result.
4. Processing delay 4. Processing delay
This delay covers the time from the reception of the last bit of
the packet to the time the packet is enqueued in the regulator
(queuing subsystem, if there is no regulator) as shown in
Figure 1. This delay can be variable, and depends on the details
of the operation of the forwarding node.
5. Regulator delay This delay covers the time from the reception of the last bit of
A regulator, also known as shaper in [RFC2475], delays some or all the packet to the time the packet is enqueued in the regulator
of the packets in a traffic stream in order to bring the stream (queuing subsystem if there is no regulator), as shown in
into compliance with an arrival curve; an arrival curve 'alpha(t)' Figure 1. This delay can be variable and depends on the details
is an upper bound on the number of bits observed within any of the operation of the forwarding node.
interval t. The regulator delay is the time spent from the
insertion of the last bit of a packet into a regulation queue 5. Regulator queuing delay
until the time the packet is declared eligible according to its
regulation constraints. We assume that this time can be A regulator, also known as shaper in [RFC2475], delays some or
calculated based on the details of regulation policy. If there is all of the packets in a traffic stream in order to bring the
no regulation, this time is zero. stream into compliance with an arrival curve; an arrival curve
'alpha(t)' is an upper bound on the number of bits observed
within any interval t. The regulator delay is the time spent
from the insertion of the last bit of a packet into a regulation
queue until the time the packet is declared eligible according to
its regulation constraints. We assume that this time can be
calculated based on the details of regulation policy. If there
is no regulation, this time is zero.
6. Queuing subsystem delay 6. Queuing subsystem delay
This is the time spent for a packet from being declared eligible
until being selected for output on the next link. We assume that This is the time spent for a packet from being declared eligible
this time is calculable based on the details of the queuing until being selected for output on the next link. We assume that
mechanism. If there is no regulation, this time is from the this time is calculable based on the details of the queuing
insertion of the packet into a queue until it is selected for mechanism. If there is no regulation, this time is from the
output on the next link. insertion of the packet into a queue until it is selected for
output on the next link.
Not shown in Figure 1 are the other output queues that we presume are Not shown in Figure 1 are the other output queues that we presume are
also attached to that same output port as the queue shown, and also attached to that same output port as the queue shown, and
against which this shown queue competes for transmission against which this shown queue competes for transmission
opportunities. opportunities.
In this analysis, the measurement is from the point at which a packet In this analysis, the measurement is from the point at which a packet
is selected for output in a node to the point at which it is selected is selected for output in a node to the point at which it is selected
for output in the next downstream node (that is the definition of a for output in the next downstream node (i.e., the definition of a
"hop"). In general, any queue selection method that is suitable for "hop"). In general, any queue selection method that is suitable for
use in a DetNet network includes a detailed specification as to use in a DetNet network includes a detailed specification as to
exactly when packets are selected for transmission. Any variations exactly when packets are selected for transmission. Any variations
in any of the delay times 1-4 result in a need for additional buffers in any of the delay times 1-4 result in a need for additional buffers
in the queue. If all delays 1-4 are constant, then any variation in in the queue. If all delays 1-4 are constant, then any variation in
the time at which packets are inserted into a queue depends entirely the time at which packets are inserted into a queue depends entirely
on the timing of packet selection in the previous node. If the on the timing of packet selection in the previous node. If delays
delays 1-4 are not constant, then additional buffers are required in 1-4 are not constant, then additional buffers are required in the
the queue to absorb these variations. Thus: queue to absorb these variations. Thus:
* Variations in output delay (1) require buffers to absorb that * Variations in the output delay (1) require buffers to absorb that
variation in the next hop, so the output delay variations of the variation in the next hop, so the output delay variations of the
previous hop (on each input port) must be known in order to previous hop (on each input port) must be known in order to
calculate the buffer space required on this hop. calculate the buffer space required on this hop.
* Variations in processing delay (4) require additional output * Variations in the processing delay (4) require additional output
buffers in the queues of that same DetNet transit node. Depending buffers in the queues of that same DetNet transit node. Depending
on the details of the queuing subsystem delay (6) calculations, on the details of the queuing subsystem delay (6) calculations,
these variations need not be visible outside the DetNet transit these variations need not be visible outside the DetNet transit
node. node.
4. Computing End-to-end Delay Bounds 4. Computing End-to-End Delay Bounds
4.1. Non-queuing delay bound 4.1. Non-queuing Delay Bound
End-to-end latency bounds can be computed using the delay model in End-to-end latency bounds can be computed using the delay model in
Section 3.2. Here, it is important to be aware that for several Section 3.2. Here, it is important to be aware that, for several
queuing mechanisms, the end-to-end latency bound is less than the sum queuing mechanisms, the end-to-end latency bound is less than the sum
of the per-hop latency bounds. An end-to-end latency bound for one of the per-hop latency bounds. An end-to-end latency bound for one
DetNet flow can be computed as DetNet flow can be computed as
end_to_end_delay_bound = non_queuing_delay_bound + end_to_end_delay_bound = non_queuing_delay_bound +
queuing_delay_bound queuing_delay_bound
The two terms in the above formula are computed as follows. The two terms in the above formula are computed as follows.
First, at the h-th hop along the path of this DetNet flow, obtain an First, at the h-th hop along the path of this DetNet flow, obtain an
upper-bound per-hop_non_queuing_delay_bound[h] on the sum of the upper-bound per-hop_non_queuing_delay_bound[h] on the sum of the
bounds over the delays 1,2,3,4 of Figure 1. These upper bounds are bounds over delays 1, 2, 3, and 4 of Figure 1. These upper bounds
expected to depend on the specific technology of the DetNet transit are expected to depend on the specific technology of the DetNet
node at the h-th hop but not on the T-SPEC of this DetNet flow transit node at the h-th hop but not on the T-SPEC of this DetNet
[RFC9016]. Then set non_queuing_delay_bound = the sum of per- flow [RFC9016]. Then, set non_queuing_delay_bound = the sum of per-
hop_non_queuing_delay_bound[h] over all hops h. hop_non_queuing_delay_bound[h] over all hops h.
Second, compute queuing_delay_bound as an upper bound to the sum of Second, compute queuing_delay_bound as an upper bound to the sum of
the queuing delays along the path. The value of queuing_delay_bound the queuing delays along the path. The value of queuing_delay_bound
depends on the information on the arrival curve of this DetNet flow depends on the information on the arrival curve of this DetNet flow
and possibly of other flows in the network, as well as the specifics and possibly of other flows in the network, as well as the specifics
of the queuing mechanisms deployed along the path of this DetNet of the queuing mechanisms deployed along the path of this DetNet
flow. Note that arrival curve of DetNet flow at source is flow. Note that arrival curve of the DetNet flow at the source is
immediately specified by the T-SPEC of this flow. The computation of immediately specified by the T-SPEC of this flow. The computation of
queuing_delay_bound is described in Section 4.2 as a separate queuing_delay_bound is described in Section 4.2 as a separate
section. section.
4.2. Queuing delay bound 4.2. Queuing Delay Bound
For several queuing mechanisms, queuing_delay_bound is less than the For several queuing mechanisms, queuing_delay_bound is less than the
sum of upper bounds on the queuing delays (5,6) at every hop. This sum of upper bounds on the queuing delays (5 and 6) at every hop.
occurs with (1) per-flow queuing, and (2) aggregate queuing with This occurs with (1) per-flow queuing and (2) aggregate queuing with
regulators, as explained in Section 4.2.1, Section 4.2.2, and regulators, as explained in Sections 4.2.1, 4.2.2, and 6. For other
Section 6. For other queuing mechanisms the only available value of queuing mechanisms, the only available value of queuing_delay_bound
queuing_delay_bound is the sum of the per-hop queuing delay bounds. is the sum of the per-hop queuing delay bounds.
The computation of per-hop queuing delay bounds must account for the The computation of per-hop queuing delay bounds must account for the
fact that the arrival curve of a DetNet flow is no longer satisfied fact that the arrival curve of a DetNet flow is no longer satisfied
at the ingress of a hop, since burstiness increases as one flow at the ingress of a hop, since burstiness increases as one flow
traverses one DetNet transit node. If a regulator is placed at a traverses one DetNet transit node. If a regulator is placed at a
hop, an arrival curve of a DetNet flow at the entrance of the queuing hop, an arrival curve of a DetNet flow at the entrance of the queuing
subsystem of this hop is the one configured at the regulator (also subsystem of this hop is the one configured at the regulator (also
called shaping curve in [NetCalBook]); otherwise, an arrival curve of called shaping curve in [NetCalBook]); otherwise, an arrival curve of
the flow can be derived using the delay-jitter of the flow from the the flow can be derived using the delay jitter of the flow from the
last regulation point (the last regulator in the path of the flow if last regulation point (the last regulator in the path of the flow if
there is any, otherwise the source of the flow) to the ingress of the there is any, otherwise the source of the flow) to the ingress of the
hop; more formally, assume a DetNet flow has arrival curve at the hop; more formally, assume a DetNet flow has an arrival curve at the
last regulation point equal to 'alpha(t)', and the delay-jitter from last regulation point equal to 'alpha(t)' and the delay jitter from
the last regulation point to the ingress of the hop is 'V'. Then, the last regulation point to the ingress of the hop is 'V'. Then,
the arrival curve at the ingress of the hop is 'alpha(t+V)'. the arrival curve at the ingress of the hop is 'alpha(t+V)'.
For example, consider a DetNet flow with T-SPEC "Interval: tau, For example, consider a DetNet flow with T-SPEC "Interval: tau,
MaxPacketsPerInterval: K, MaxPayloadSize: L" at source. Then, a MaxPacketsPerInterval: K, MaxPayloadSize: L" at the source. Then, a
leaky-bucket arrival curve for such flow at source is alpha(t)=r * t+ leaky-bucket arrival curve for such flow at the source is alpha(t)=r
b, t>0; alpha(0)=0, where r is the rate and b is the bucket size, * t+ b, t>0; alpha(0)=0, where r is the rate and b is the bucket
computed as size, computed as
r = K * (L+L') / tau, r = K * (L+L') / tau,
b = K * (L+L'). b = K * (L+L').
where L' is the size of any added networking technology-specific where L' is the size of any added networking technology-specific
encapsulation (e.g., MPLS label(s), UDP, and IP headers). Now, if encapsulation (e.g., MPLS label(s), UDP, or IP headers). Now, if the
the flow has delay-jitter of 'V' from the last regulation point to flow has a delay jitter of 'V' from the last regulation point to the
the ingress of a hop, an arrival curve at this point is r * t + b + r ingress of a hop, an arrival curve at this point is r * t + b + r *
* V, implying that the burstiness is increased by r*V. A more V, implying that the burstiness is increased by r*V. More detailed
detailed information on arrival curves is available in [NetCalBook]. information on arrival curves is available in [NetCalBook].
4.2.1. Per-flow queuing mechanisms 4.2.1. Per-Flow Queuing Mechanisms
With such mechanisms, each flow uses a separate queue inside every With such mechanisms, each flow uses a separate queue inside every
node. The service for each queue is abstracted with a guaranteed node. The service for each queue is abstracted with a guaranteed
rate and a latency. For every DetNet flow, a per-node latency bound rate and a latency. For every DetNet flow, a per-node latency bound,
as well as an end-to-end latency bound can be computed from the as well as an end-to-end latency bound, can be computed from the
traffic specification of this DetNet flow at its source and from the traffic specification of this DetNet flow at its source and from the
values of rates and latencies at all nodes along its path. An values of rates and latencies at all nodes along its path. An
instance of per-flow queuing is IntServ's Guaranteed-Service, for instance of per-flow queuing is Guaranteed Service [RFC2212], for
which the details of latency bound calculation are presented in which the details of latency bound calculation are presented in
Section 6.5. Section 6.5.
4.2.2. Aggregate queuing mechanisms 4.2.2. Aggregate Queuing Mechanisms
With such mechanisms, multiple flows are aggregated into macro-flows With such mechanisms, multiple flows are aggregated into macro-flows
and there is one FIFO queue per macro-flow. A practical example is and there is one FIFO queue per macro-flow. A practical example is
the credit-based shaper defined in section 8.6.8.2 of [IEEE8021Q] the credit-based shaper defined in Section 8.6.8.2 of [IEEE8021Q],
where a macro-flow is called a "class". One key issue in this where a macro-flow is called a "class". One key issue in this
context is how to deal with the burstiness cascade: individual flows context is how to deal with the burstiness cascade; individual flows
that share a resource dedicated to a macro-flow may see their that share a resource dedicated to a macro-flow may see their
burstiness increase, which may in turn cause increased burstiness to burstiness increase, which may in turn cause increased burstiness to
other flows downstream of this resource. Computing delay upper other flows downstream of this resource. Computing delay upper
bounds for such cases is difficult, and in some conditions impossible bounds for such cases is difficult and, in some conditions,
[CharnyDelay][BennettDelay]. Also, when bounds are obtained, they impossible [CharnyDelay] [BennettDelay]. Also, when bounds are
depend on the complete configuration, and must be recomputed when one obtained, they depend on the complete configuration and must be
flow is added. (The dynamic calculation, Section 3.1.2.) recomputed when one flow is added (i.e., the dynamic calculation in
Section 3.1.2).
A solution to deal with this issue for the DetNet flows is to reshape A solution to deal with this issue for the DetNet flows is to reshape
them at every hop. This can be done with per-flow regulators (e.g., them at every hop. This can be done with per-flow regulators (e.g.,
leaky bucket shapers), but this requires per-flow queuing and defeats leaky-bucket shapers), but this requires per-flow queuing and defeats
the purpose of aggregate queuing. An alternative is the interleaved the purpose of aggregate queuing. An alternative is the interleaved
regulator, which reshapes individual DetNet flows without per-flow regulator, which reshapes individual DetNet flows without per-flow
queuing ([SpechtUBS], [IEEE8021Qcr]). With an interleaved regulator, queuing [SpechtUBS] [IEEE8021Qcr]. With an interleaved regulator,
the packet at the head of the queue is regulated based on its (flow) the packet at the head of the queue is regulated based on its (flow)
regulation constraints; it is released at the earliest time at which regulation constraints; it is released at the earliest time at which
this is possible without violating the constraint. One key feature this is possible without violating the constraint. One key feature
of per-flow or interleaved regulator is that, it does not increase of a per-flow or interleaved regulator is that it does not increase
worst-case latency bounds [LeBoudecTheory]. Specifically, when an worst-case latency bounds [LeBoudecTheory]. Specifically, when an
interleaved regulator is appended to a FIFO subsystem, it does not interleaved regulator is appended to a FIFO subsystem, it does not
increase the worst-case delay of the latter; in Figure 1, when the increase the worst-case delay of the latter. In Figure 1, when the
order of packets from output of queuing subsystem at node A to the order of packets from the output of a queuing subsystem at node A to
entrance of regulator at node B is preserved, then the regulator does the entrance of a regulator at node B is preserved, then the
not increase the worst-case latency bounds; this is made possible if regulator does not increase the worst-case latency bounds. This is
all the systems are FIFO or a DetNet packet-ordering function (POF) made possible if all the systems are FIFO or a DetNet Packet Ordering
is implemented just before the regulator. This property does not Function (POF) is implemented just before the regulator. This
hold if packet reordering occurs from the output of a queuing property does not hold if packet reordering occurs from the output of
subsystem to the entrance of next downstream interleaved regulator, a queuing subsystem to the entrance of the next downstream
e.g., at a non-FIFO switching fabric. interleaved regulator, e.g., at a non-FIFO switching fabric.
Figure 2 shows an example of a network with 5 nodes, aggregate Figure 2 shows an example of a network with 5 nodes, an aggregate
queuing mechanism and interleaved regulators as in Figure 1. An end- queuing mechanism, and interleaved regulators, as in Figure 1. An
to-end delay bound for DetNet flow f, traversing nodes 1 to 5, is end-to-end delay bound for DetNet flow f, traversing nodes 1 to 5, is
calculated as follows: calculated as follows:
end_to_end_latency_bound_of_flow_f = C12 + C23 + C34 + S4 end_to_end_latency_bound_of_flow_f = C12 + C23 + C34 + S4
In the above formula, Cij is a bound on the delay of the queuing In the above formula, Cij is a bound on the delay of the queuing
subsystem in node i and interleaved regulator of node j, and S4 is a subsystem in node i and interleaved regulator of node j, and S4 is a
bound on the delay of the queuing subsystem in node 4 for DetNet flow bound on the delay of the queuing subsystem in node 4 for DetNet flow
f. In fact, using the delay definitions in Section 3.2, Cij is a f. In fact, using the delay definitions in Section 3.2, Cij is a
bound on sum of the delays 1,2,3,6 of node i and 4,5 of node j. bound on a sum of delays 1, 2, 3, and 6 of node i and delays 4 and 5
Similarly, S4 is a bound on sum of the delays 1,2,3,6 of node 4. A of node j. Similarly, S4 is a bound on sum of delays 1, 2, 3, and 6
practical example of queuing model and delay calculation is presented of node 4. A practical example of the queuing model and delay
Section 6.4. calculation is presented Section 6.4.
f f
-----------------------------> ----------------------------->
+---+ +---+ +---+ +---+ +---+ +---+ +---+ +---+ +---+ +---+
| 1 |---| 2 |---| 3 |---| 4 |---| 5 | | 1 |---| 2 |---| 3 |---| 4 |---| 5 |
+---+ +---+ +---+ +---+ +---+ +---+ +---+ +---+ +---+ +---+
\__C12_/\__C23_/\__C34_/\_S4_/ \__C12_/\__C23_/\__C34_/\_S4_/
Figure 2: End-to-end delay computation example Figure 2: End-to-End Delay Computation Example
REMARK: If packet reordering does not occur, the end-to-end latency If packet reordering does not occur, the end-to-end latency bound
bound calculation provided here gives a tighter latency upper-bound calculation provided here gives a tighter latency upper bound than
than would be obtained by adding the latency bounds of each node in would be obtained by adding the latency bounds of each node in the
the path of a DetNet flow [TSNwithATS]. path of a DetNet flow [TSNwithATS].
4.3. Ingress considerations 4.3. Ingress Considerations
A sender can be a DetNet node which uses exactly the same queuing A sender can be a DetNet node that uses exactly the same queuing
methods as its adjacent DetNet transit node, so that the latency and methods as its adjacent DetNet transit node so that the latency and
buffer bounds calculations at the first hop are indistinguishable buffer bounds calculations at the first hop are indistinguishable
from those at a later hop within the DetNet domain. On the other from those at a later hop within the DetNet domain. On the other
hand, the sender may be DetNet-unaware, in which case some hand, the sender may be DetNet unaware; in which case, some
conditioning of the DetNet flow may be necessary at the ingress conditioning of the DetNet flow may be necessary at the ingress
DetNet transit node. DetNet transit node. The ingress conditioning typically consists of
the regulators described in Section 3.2.
This ingress conditioning typically consists of a FIFO with an output
regulator that is compatible with the queuing employed by the DetNet
transit node on its output port(s). For some queuing methods, this
simply requires added buffer space in the queuing subsystem. Ingress
conditioning requirements for different queuing methods are mentioned
in the sections, below, describing those queuing methods.
4.4. Interspersed DetNet-unaware transit nodes 4.4. Interspersed DetNet-Unaware Transit Nodes
It is sometimes desirable to build a network that has both DetNet- It is sometimes desirable to build a network that has both DetNet-
aware transit nodes and DetNet-unaware transit nodes, and for a aware transit nodes and DetNet-unaware transit nodes and for a DetNet
DetNet flow to traverse an island of DetNet-unaware transit nodes, flow to traverse an island of DetNet-unaware transit nodes while
while still allowing the network to offer delay and congestion loss still allowing the network to offer delay and congestion loss
guarantees. This is possible under certain conditions. guarantees. This is possible under certain conditions.
In general, when passing through a DetNet-unaware island, the island In general, when passing through a DetNet-unaware island, the island
may cause delay variation in excess of what would be caused by DetNet may cause delay variation in excess of what would be caused by DetNet
nodes. That is, the DetNet flow might be "lumpier" after traversing nodes. That is, the DetNet flow might be "lumpier" after traversing
the DetNet-unaware island. DetNet guarantees for delay and buffer the DetNet-unaware island. DetNet guarantees for delay and buffer
requirements can still be calculated and met if and only if the requirements can still be calculated and met if and only if the
following are true: following are true:
1. The latency variation across the DetNet-unaware island must be 1. The latency variation across the DetNet-unaware island must be
bounded and calculable. bounded and calculable.
2. An ingress conditioning function (Section 4.3) is required at the 2. An ingress conditioning function (Section 4.3) is required at the
re-entry to the DetNet-aware domain. This will, at least, reentry to the DetNet-aware domain. This will, at least, require
require some extra buffering to accommodate the additional delay some extra buffering to accommodate the additional delay
variation, and thus further increases the latency bound. variation and thus further increases the latency bound.
The ingress conditioning is exactly the same problem as that of a The ingress conditioning is exactly the same problem as that of a
sender at the edge of the DetNet domain. The requirement for bounds sender at the edge of the DetNet domain. The requirement for bounds
on the latency variation across the DetNet-unaware island is on the latency variation across the DetNet-unaware island is
typically the most difficult to achieve. Without such a bound, it is typically the most difficult to achieve. Without such a bound, it is
obvious that DetNet cannot deliver its guarantees, so a DetNet- obvious that DetNet cannot deliver its guarantees, so a DetNet-
unaware island that cannot offer bounded latency variation cannot be unaware island that cannot offer bounded latency variation cannot be
used to carry a DetNet flow. used to carry a DetNet flow.
5. Achieving zero congestion loss 5. Achieving Zero Congestion Loss
When the input rate to an output queue exceeds the output rate for a When the input rate to an output queue exceeds the output rate for a
sufficient length of time, the queue must overflow. This is sufficient length of time, the queue must overflow. This is
congestion loss, and this is what deterministic networking seeks to congestion loss, and this is what DetNet seeks to avoid.
avoid.
To avoid congestion losses, an upper bound on the backlog present in To avoid congestion losses, an upper bound on the backlog present in
the regulator and queuing subsystem of Figure 1 must be computed the regulator and queuing subsystem of Figure 1 must be computed
during resource reservation. This bound depends on the set of flows during resource reservation. This bound depends on the set of flows
that use these queues, the details of the specific queuing mechanism that use these queues, the details of the specific queuing mechanism,
and an upper bound on the processing delay (4). The queue must and an upper bound on the processing delay (4). The queue must
contain the packet in transmission plus all other packets that are contain the packet in transmission, plus all other packets that are
waiting to be selected for output. A conservative backlog bound, waiting to be selected for output. A conservative backlog bound that
that applies to all systems, can be derived as follows. applies to all systems can be derived as follows.
The backlog bound is counted in data units (bytes, or words of The backlog bound is counted in data units (bytes or words of
multiple bytes) that are relevant for buffer allocation. For every multiple bytes) that are relevant for buffer allocation. For every
flow or an aggregate of flows, we need one buffer space for the flow or an aggregate of flows, we need one buffer space for the
packet in transmission, plus space for the packets that are waiting packet in transmission, plus space for the packets that are waiting
to be selected for output. to be selected for output.
Let Let
* total_in_rate be the sum of the line rates of all input ports that * total_in_rate be the sum of the line rates of all input ports that
send traffic to this output port. The value of total_in_rate is send traffic to this output port. The value of total_in_rate is
in data units (e.g., bytes) per second. in data units (e.g., bytes) per second.
* nb_input_ports be the number input ports that send traffic to this * nb_input_ports be the number of input ports that send traffic to
output port this output port.
* max_packet_length be the maximum packet size for packets that may * max_packet_length be the maximum packet size for packets that may
be sent to this output port. This is counted in data units. be sent to this output port. This is counted in data units.
* max_delay456 be an upper bound, in seconds, on the sum of the * max_delay456 be an upper bound, in seconds, on the sum of the
processing delay (4) and the queuing delays (5,6) for any packet processing delay (4) and the queuing delays (5 and 6) for any
at this output port. packet at this output port.
Then a bound on the backlog of traffic in the queue at this output Then, a bound on the backlog of traffic in the queue at this output
port is port is
backlog_bound = (nb_input_ports * max_packet_length) + backlog_bound = (nb_input_ports * max_packet_length) +
(total_in_rate * max_delay456) (total_in_rate * max_delay456)
The above bound is over the backlog caused by the traffic entering The above bound is over the backlog caused by the traffic entering
the queue from the input ports of a DetNet node. If the DetNet node the queue from the input ports of a DetNet node. If the DetNet node
also generates packets (e.g., creation of new packets, replication of also generates packets (e.g., creation of new packets or replication
arriving packets), the bound must accordingly incorporate the of arriving packets), the bound must accordingly incorporate the
introduced backlog. introduced backlog.
6. Queuing techniques 6. Queuing Techniques
In this section, we present a general queuing data model as well as In this section, we present a general queuing data model, as well as
some examples of queuing mechanisms. For simplicity of latency bound some examples of queuing mechanisms. For simplicity of latency bound
computation, we assume leaky-bucket arrival curve for each DetNet computation, we assume a leaky-bucket arrival curve for each DetNet
flow at source. Also, at each DetNet transit node, the service for flow at the source. Also, at each DetNet transit node, the service
each queue is abstracted with a minimum guaranteed rate and a latency for each queue is abstracted with a minimum guaranteed rate and a
[NetCalBook]. latency [NetCalBook].
6.1. Queuing data model 6.1. Queuing Data Model
Sophisticated queuing mechanisms are available in Layer 3 (L3, see, Sophisticated queuing mechanisms are available in Layer 3 (L3) (e.g.,
e.g., [RFC7806] for an overview). In general, we assume that "Layer see [RFC7806] for an overview). In general, we assume that "Layer 3"
3" queues, shapers, meters, etc., are precisely the "regulators" queues, shapers, meters, etc., are precisely the "regulators" shown
shown in Figure 1. The "queuing subsystems" in this figure are FIFO. in Figure 1. The "queuing subsystems" in this figure are FIFO. They
They are not the province solely of bridges; they are an essential are not the province solely of bridges; they are an essential part of
part of any DetNet transit node. As illustrated by numerous any DetNet transit node. As illustrated by numerous implementation
implementation examples, some of the "Layer 3" mechanisms described examples, some of the "Layer 3" mechanisms described in documents,
in documents such as [RFC7806] are often integrated, in an such as [RFC7806], are often integrated in an implementation, with
implementation, with the "Layer 2" mechanisms also implemented in the the "Layer 2" mechanisms also implemented in the same node. An
same node. An integrated model is needed in order to successfully integrated model is needed in order to successfully predict the
predict the interactions among the different queuing mechanisms interactions among the different queuing mechanisms needed in a
needed in a network carrying both DetNet flows and non-DetNet flows. network carrying both DetNet flows and non-DetNet flows.
Figure 3 shows the general model for the flow of packets through the Figure 3 shows the general model for the flow of packets through the
queues of a DetNet transit node. The DetNet packets are mapped to a queues of a DetNet transit node. The DetNet packets are mapped to a
number of regulators. Here, we assume that the PREOF (Packet number of regulators. Here, we assume that the Packet Replication,
Replication, Elimination and Ordering Functions) are performed before Elimination, and Ordering Functions (PREOF) are performed before the
the DetNet packets enter the regulators. All Packets are assigned to DetNet packets enter the regulators. All packets are assigned to a
a set of queues. Packets compete for the selection to be passed to set of queues. Packets compete for the selection to be passed to
queues in the queuing subsystem. Packets again are selected for queues in the queuing subsystem. Packets again are selected for
output from the queuing subsystem. output from the queuing subsystem.
| |
+--------------------------------V----------------------------------+ +--------------------------------V----------------------------------+
| Queue assignment | | Queue assignment |
+--+------+----------+---------+-----------+-----+-------+-------+--+ +--+------+----------+---------+-----------+-----+-------+-------+--+
| | | | | | | | | | | | | | | |
+--V-+ +--V-+ +--V--+ +--V--+ +--V--+ | | | +--V-+ +--V-+ +--V--+ +--V--+ +--V--+ | | |
|Flow| |Flow| |Flow | |Flow | |Flow | | | | |Flow| |Flow| |Flow | |Flow | |Flow | | | |
skipping to change at page 16, line 32 skipping to change at line 702
|queue| |queue| |queue| |queue| |queue| |queue| |queue| |queue| |queue| |queue|
| 1 | | 2 | | 3 | | 4 | | 5 | | 1 | | 2 | | 3 | | 4 | | 5 |
+--+--+ +--+--+ +--+--+ +--+--+ +--+--+ +--+--+ +--+--+ +--+--+ +--+--+ +--+--+
| | | | | | | | | |
+----------V----------------------V--------------V-------V-------V--+ +----------V----------------------V--------------V-------V-------V--+
| Transmission selection | | Transmission selection |
+---------------------------------+---------------------------------+ +---------------------------------+---------------------------------+
| |
V V
Figure 3: IEEE 802.1Q Queuing Model: Data flow Figure 3: IEEE 802.1Q Queuing Model: Data Flow
Some relevant mechanisms are hidden in this figure, and are performed Some relevant mechanisms are hidden in this figure and are performed
in the queue boxes: in the queue boxes:
* Discarding packets because a queue is full. * discarding packets because a queue is full
* Discarding packets marked "yellow" by a metering function, in * discarding packets marked "yellow" by a metering function in
preference to discarding "green" packets [RFC2697]. preference to discarding "green" packets [RFC2697]
Ideally, neither of these actions are performed on DetNet packets. Ideally, neither of these actions are performed on DetNet packets.
Full queues for DetNet packets occurs only when a DetNet flow is Full queues for DetNet packets occur only when a DetNet flow is
misbehaving, and the DetNet QoS does not include "yellow" service for misbehaving, and the DetNet QoS does not include "yellow" service for
packets in excess of committed rate. packets in excess of a committed rate.
The queue assignment function can be quite complex, even in a bridge The queue assignment function can be quite complex, even in a bridge
[IEEE8021Q], since the introduction of per-stream filtering and [IEEE8021Q], because of the introduction of per-stream filtering and
policing ([IEEE8021Q] clause 8.6.5.1). In addition to the Layer 2 policing ([IEEE8021Q], clause 8.6.5.1). In addition to the Layer 2
priority expressed in the 802.1Q VLAN tag, a DetNet transit node can priority expressed in the 802.1Q VLAN tag, a DetNet transit node can
utilize the information from the non-exhaustive list below to assign utilize the information from the non-exhaustive list below to assign
a packet to a particular queue: a packet to a particular queue:
* Input port. * input port
* Selector based on a rotating schedule that starts at regular, * selector based on a rotating schedule that starts at regular,
time-synchronized intervals and has nanosecond precision. time-synchronized intervals and has nanosecond precision
* MAC addresses, VLAN ID, IP addresses, Layer 4 port numbers, DSCP * MAC addresses, VLAN ID, IP addresses, Layer 4 port numbers, and
[RFC8939], [RFC8964]. Differentiated Services Code Point (DSCP) [RFC8939] [RFC8964]
* The queue assignment function can contain metering and policing * the queue assignment function can contain metering and policing
functions. functions
* MPLS and/or pseudo-wire labels [RFC6658]. * MPLS and/or pseudowire labels [RFC6658]
The "Transmission selection" function decides which queue is to The "Transmission selection" function decides which queue is to
transfer its oldest packet to the output port when a transmission transfer its oldest packet to the output port when a transmission
opportunity arises. opportunity arises.
6.2. Frame Preemption 6.2. Frame Preemption
In [IEEE8021Q] and [IEEE8023], the transmission of a frame can be In [IEEE8021Q] and [IEEE8023], the transmission of a frame can be
interrupted by one or more "express" frames, and then the interrupted interrupted by one or more "express" frames; then, the interrupted
frame can continue transmission. The frame preemption is modeled as frame can continue transmission. The frame preemption is modeled as
consisting of two MAC/PHY stacks, one for packets that can be consisting of two MAC/PHY stacks: one for packets that can be
interrupted, and one for packets that can interrupt the interruptible interrupted and one for packets that can interrupt the interruptible
packets. Only one layer of frame preemption is supported -- a packets. Only one layer of frame preemption is supported -- a
transmitter cannot have more than one interrupted frame in progress. transmitter cannot have more than one interrupted frame in progress.
DetNet flows typically pass through the interrupting MAC. For those DetNet flows typically pass through the interrupting MAC. For those
DetNet flows with T-SPEC, latency bounds can be calculated by the DetNet flows with T-SPEC, latency bounds can be calculated by the
methods provided in the following sections that account for the methods provided in the following sections that account for the
effect of frame preemption, according to the specific queuing effect of frame preemption, according to the specific queuing
mechanism that is used in DetNet nodes. Best-effort queues pass mechanism that is used in DetNet nodes. Best-effort queues pass
through the interruptible MAC, and can thus be preempted. through the interruptible MAC and can thus be preempted.
6.3. Time-Aware Shaper 6.3. Time-Aware Shaper
In [IEEE8021Q], the notion of time-scheduling queue gates is In [IEEE8021Q], the notion of time-scheduling queue gates is
described in section 8.6.8.4. On each node, the transmission described in Section 8.6.8.4. On each node, the transmission
selection for packets is controlled by time-synchronized gates; each selection for packets is controlled by time-synchronized gates; each
output queue is associated with a gate. The gates can be either open output queue is associated with a gate. The gates can be either open
or closed. The states of the gates are determined by the gate or closed. The states of the gates are determined by the gate
control list (GCL). The GCL specifies the opening and closing times control list (GCL). The GCL specifies the opening and closing times
of the gates. The design of GCL must satisfy the requirement of of the gates. The design of the GCL must satisfy the requirement of
latency upper bounds of all DetNet flows; therefore, those DetNet latency upper bounds of all DetNet flows; therefore, those DetNet
flows that traverse a network that uses this kind of shaper must have flows that traverse a network that uses this kind of shaper must have
bounded latency, if the traffic and nodes are conformant. bounded latency if the traffic and nodes are conformant.
Note that scheduled traffic service relies on a synchronized network Note that scheduled traffic service relies on a synchronized network
and coordinated GCL configuration. Synthesis of GCL on multiple and coordinated GCL configuration. Synthesis of the GCL on multiple
nodes in network is a scheduling problem considering all DetNet flows nodes in a network is a scheduling problem considering all DetNet
traversing the network, which is a non-deterministic polynomial-time flows traversing the network, which is a nondeterministic polynomial-
hard (NP-hard) problem [Sch8021Qbv]. Also, at this writing, time hard (NP-hard) problem [Sch8021Qbv]. Also, at the time of
scheduled traffic service supports no more than eight traffic queues, writing, scheduled traffic service supports no more than eight
typically using up to seven priority queues and at least one best traffic queues, typically using up to seven priority queues and at
effort. least one best effort.
6.4. Credit-Based Shaper with Asynchronous Traffic Shaping 6.4. Credit-Based Shaper with Asynchronous Traffic Shaping
In this queuing model, it is assumed that the DetNet nodes are FIFO. In this queuing model, it is assumed that the DetNet nodes are FIFO.
We consider the four traffic classes (Definition 3.268 of We consider the four traffic classes (Definition 3.268 of
[IEEE8021Q]): control-data traffic (CDT), class A, class B, and best [IEEE8021Q]): control-data traffic (CDT), class A, class B, and best
effort (BE) in decreasing order of priority. Flows of classes A and effort (BE) in decreasing order of priority. Flows of classes A and
B are DetNet flows that are less critical than CDT (such as studio B are DetNet flows that are less critical than CDT (such as studio
audio and video traffic, as in IEEE 802.1BA Audio-Video-Bridging). audio and video traffic, as in IEEE 802.1BA Audio-Video-Bridging).
This model is a subset of Time-Sensitive Networking as described This model is a subset of Time-Sensitive Networking, as described
next. next.
Based on the timing model described in Figure 1, contention occurs Based on the timing model described in Figure 1, contention occurs
only at the output port of a DetNet transit node; therefore, the only at the output port of a DetNet transit node; therefore, the
focus of the rest of this subsection is on the regulator and queuing focus of the rest of this subsection is on the regulator and queuing
subsystem in the output port of a DetNet transit node. The input subsystem in the output port of a DetNet transit node. The input
flows are identified using the information in (Section 5.1 of flows are identified using the information in (Section 5.1 of
[RFC8939]). Then they are aggregated into eight macro flows based on [RFC8939]). Then, they are aggregated into eight macro-flows based
their service requirements; we refer to each macro flow as a class. on their service requirements; we refer to each macro-flow as a
The output port performs aggregate scheduling with eight queues class. The output port performs aggregate scheduling with eight
(queuing subsystems): one for CDT, one for class A flows, one for queues (queuing subsystems): one for CDT, one for class A flows, one
class B flows, and five for BE traffic denoted as BE0-BE4. The for class B flows, and five for BE traffic denoted as BE0-BE4. The
queuing policy for each queuing subsystem is FIFO. In addition, each queuing policy for each queuing subsystem is FIFO. In addition, each
node output port also performs per-flow regulation for class A and B node output port also performs per-flow regulation for class A and B
flows using an interleaved regulator (IR), called Asynchronous flows using an interleaved regulator (IR). This regulation is called
Traffic Shaper [IEEE8021Qcr]. Thus, at each output port of a node, asynchronous traffic shaping [IEEE8021Qcr]. Thus, at each output
there is one interleaved regulator per-input port and per-class; the port of a node, there is one interleaved regulator per input port and
interleaved regulator is mapped to the regulator depicted in per class; the interleaved regulator is mapped to the regulator
Figure 1. The detailed picture of scheduling and regulation depicted in Figure 1. The detailed picture of scheduling and
architecture at a node output port is given by Figure 4. The packets regulation architecture at a node output port is given by Figure 4.
received at a node input port for a given class are enqueued in the The packets received at a node input port for a given class are
respective interleaved regulator at the output port. Then, the enqueued in the respective interleaved regulator at the output port.
packets from all the flows, including CDT and BE flows, are enqueued Then, the packets from all the flows, including CDT and BE flows, are
in queuing subsystem; there is no regulator for CDT and BE flows. enqueued in a queuing subsystem; there is no regulator for CDT and BE
flows.
+--+ +--+ +--+ +--+ +--+ +--+ +--+ +--+
| | | | | | | | | | | | | | | |
|IR| |IR| |IR| |IR| |IR| |IR| |IR| |IR|
| | | | | | | | | | | | | | | |
+-++XXX++-+ +-++XXX++-+ +-++XXX++-+ +-++XXX++-+
| | | | | | | |
| | | | | | | |
+---+ +-v-XXX-v-+ +-v-XXX-v-+ +-----+ +-----+ +-----+ +-----+ +-----+ +---+ +-v-XXX-v-+ +-v-XXX-v-+ +-----+ +-----+ +-----+ +-----+ +-----+
| | | | | | |Class| |Class| |Class| |Class| |Class| | | | | | | |Class| |Class| |Class| |Class| |Class|
skipping to change at page 19, line 28 skipping to change at line 837
| +-v-+ +-v-+ | | | | | | +-v-+ +-v-+ | | | | |
| |CBS| |CBS| | | | | | | |CBS| |CBS| | | | | |
| +-+-+ +-+-+ | | | | | | +-+-+ +-+-+ | | | | |
| | | | | | | | | | | | | | | |
+-v--------v-----------v---------v-------V-------v-------v-------v--+ +-v--------v-----------v---------v-------V-------v-------v-------v--+
| Strict Priority selection | | Strict Priority selection |
+--------------------------------+----------------------------------+ +--------------------------------+----------------------------------+
| |
V V
Figure 4: The architecture of an output port inside a relay node with Figure 4: The Architecture of an Output Port inside a Relay Node with
interleaved regulators (IRs) and credit-based shaper (CBS) Interleaved Regulators (IRs) and a Credit-Based Shaper (CBS)
Each of the queuing subsystems for classes A and B, contains a Each of the queuing subsystems for classes A and B contains a credit-
Credit-Based Shaper (CBS). The CBS serves a packet from a class based shaper (CBS). The CBS serves a packet from a class according
according to the available credit for that class. As described in to the available credit for that class. As described in
Section 8.6.8.2 and Annex L.1 of [IEEE8021Q], the credit for each Section 8.6.8.2 and Annex L.1 of [IEEE8021Q], the credit for each
class A or B increases based on the idle slope (as guaranteed rate), class A or B increases based on the idle slope (as guaranteed rate)
and decreases based on the sendslope (typically equal to the and decreases based on the sendslope (typically equal to the
difference between the guaranteed and the output link rates), both of difference between the guaranteed and the output link rates), both of
which are parameters of the CBS. The CDT and BE0-BE4 flows are which are parameters of the CBS. The CDT and BE0-BE4 flows are
served by separate queuing subsystems. Then, packets from all flows served by separate queuing subsystems. Then, packets from all flows
are served by a transmission selection subsystem that serves packets are served by a transmission selection subsystem that serves packets
from each class based on its priority. All subsystems are non- from each class based on its priority. All subsystems are non-
preemptive. Guarantees for classes A and B traffic can be provided preemptive. Guarantees for class A and B traffic can be provided
only if CDT traffic is bounded; it is assumed that the CDT traffic only if CDT is bounded. It is assumed that the CDT has a leaky-
has a leaky bucket arrival curve with two parameters r_h as rate and bucket arrival curve with two parameters: r_h as rate and b_h as
b_h as bucket size, i.e., the amount of bits entering a node within a bucket size. That is, the amount of bits entering a node within a
time interval t is bounded by r_h * t + b_h. time interval t is bounded by r_h * t + b_h.
Additionally, it is assumed that the classes A and B flows are also Additionally, it is assumed that the class A and B flows are also
regulated at their source according to a leaky bucket arrival curve. regulated at their source according to a leaky-bucket arrival curve.
At the source, the traffic satisfies its regulation constraint, i.e., At the source, the traffic satisfies its regulation constraint, i.e.,
the delay due to interleaved regulator at the source is ignored. the delay due to interleaved regulator at the source is ignored.
At each DetNet transit node implementing an interleaved regulator, At each DetNet transit node implementing an interleaved regulator,
packets of multiple flows are processed in one FIFO queue; the packet packets of multiple flows are processed in one FIFO queue. The
at the head of the queue is regulated based on its leaky bucket packet at the head of the queue is regulated based on its leaky-
parameters; it is released at the earliest time at which this is bucket parameters. It is released at the earliest time at which this
possible without violating the constraint. is possible without violating the constraint.
The regulation parameters for a flow (leaky bucket rate and bucket The regulation parameters for a flow (leaky-bucket rate and bucket
size) are the same at its source and at all DetNet transit nodes size) are the same at its source and at all DetNet transit nodes
along its path in the case where all clocks are perfect. However, in along its path in the case where all clocks are perfect. However, in
reality there is clock non-ideality throughout the DetNet domain even reality, there is clock non-ideality throughout the DetNet domain,
with clock synchronization. This phenomenon causes inaccuracy in the even with clock synchronization. This phenomenon causes inaccuracy
rates configured at the regulators that may lead to network in the rates configured at the regulators that may lead to network
instability. To avoid that, when configuring the regulators, the instability. To avoid instability, the rates are set as the source
rates are set as the source rates with some positive margin. rates with some positive margin when configuring regulators.
[ThomasTime] describes and provides solutions to this issue. [ThomasTime] describes and provides solutions to this issue.
6.4.1. Delay Bound Calculation 6.4.1. Delay Bound Calculation
A delay bound of the queuing subsystem ((4) in Figure 1) of a given A delay bound of the queuing subsystem ((4) in Figure 1) of a given
DetNet node for a flow of classes A or B can be computed if the DetNet node for a flow of class A or B can be computed if the
following condition holds: following condition holds:
sum of leaky bucket rates of all flows of this class at this The sum of leaky-bucket rates of all flows of this class at this
transit node <= R, where R is given below for every class. transit node <= R, where R is given below for every class
If the condition holds, the delay bounds for a flow of class X (A or If the condition holds, the delay bounds for a flow of class X (A or
B) is d_X and calculated as: B) is d_X and calculated as:
d_X = T_X + (b_t_X-L_min_X)/R_X - L_min_X/c d_X = T_X + (b_t_X-L_min_X)/R_X - L_min_X/c
where L_min_X is the minimum packet lengths of class X (A or B); c is where L_min_X is the minimum packet lengths of class X (A or B); c is
the output link transmission rate; b_t_X is the sum of the b term the output link transmission rate; and b_t_X is the sum of the b term
(bucket size) for all the flows of the class X. Parameters R_X and (bucket size) for all the flows of the class X. Parameters R_X and
T_X are calculated as follows for class A and class B, separately: T_X are calculated as follows for class A and B, separately.
If the flow is of class A: If the flow is of class A:
R_A = I_A * (c-r_h)/ c R_A = I_A * (c-r_h)/ c
T_A = (L_nA + b_h + r_h * L_n/c)/(c-r_h) T_A = (L_nA + b_h + r_h * L_n/c)/(c-r_h)
where I_A is the idle slope for class A; L_nA is the maximum packet where I_A is the idle slope for class A; L_nA is the maximum packet
length of class B and BE packets; L_n is the maximum packet length of length of class B and BE packets; L_n is the maximum packet length of
classes A,B, and BE; r_h is the rate and b_h is the bucket size of classes A, B, and BE; and r_h is the rate and b_h is the bucket size
CDT traffic leaky bucket arrival curve. of CDT leaky-bucket arrival curve.
If the flow is of class B: If the flow is of class B:
R_B = I_B * (c-r_h)/ c R_B = I_B * (c-r_h)/ c
T_B = (L_BE + L_A + L_nA * I_A/(c_h-I_A) + b_h + r_h * L_n/ T_B = (L_BE + L_A + L_nA * I_A/(c_h-I_A) + b_h + r_h * L_n/
c)/(c-r_h) c)/(c-r_h)
where I_B is the idle slope for class B; L_A is the maximum packet where I_B is the idle slope for class B; L_A is the maximum packet
length of class A; L_BE is the maximum packet length of class BE. length of class A; and L_BE is the maximum packet length of class BE.
Then, as discussed in Section 4.2.2; an interleaved regulator does Then, as discussed in Section 4.2.2, an interleaved regulator does
not increase the delay bound of the upstream queuing subsystem; not increase the delay bound of the upstream queuing subsystem;
therefore an end-to-end delay bound for a DetNet flow of class X (A therefore, an end-to-end delay bound for a DetNet flow of class X (A
or B) is the sum of d_X_i for all node i in the path the flow, where or B) is the sum of d_X_i for all node i in the path of the flow,
d_X_i is the delay bound of queuing subsystem in node i which is where d_X_i is the delay bound of queuing subsystem in node i, which
computed as above. According to the notation in Section 4.2.2, the is computed as above. According to the notation in Section 4.2.2,
delay bound of queuing subsystem in a node i and interleaved the delay bound of the queuing subsystem in a node i and interleaved
regulator in node j, i.e., Cij, is: regulator in node j, i.e., Cij, is:
Cij = d_X_i Cij = d_X_i
More information of delay analysis in such a DetNet transit node is More information of delay analysis in such a DetNet transit node is
described in [TSNwithATS]. described in [TSNwithATS].
6.4.2. Flow Admission 6.4.2. Flow Admission
The delay bound calculation requires some information about each The delay bound calculation requires some information about each
node. For each node, it is required to know the idle slope of CBS node. For each node, it is required to know the idle slope of the
for each class A and B (I_A and I_B), as well as the transmission CBS for each class A and B (I_A and I_B), as well as the transmission
rate of the output link (c). Besides, it is necessary to have the rate of the output link (c). Besides, it is necessary to have the
information on each class, i.e., maximum packet length of classes A, information on each class, i.e., maximum packet length of classes A,
B, and BE. Moreover, the leaky bucket parameters of CDT (r_h,b_h) B, and BE. Moreover, the leaky-bucket parameters of CDT (r_h, b_h)
must be known. To admit a flow/flows of classes A and B, their delay must be known. To admit a flow or flows of classes A and B, their
requirements must be guaranteed not to be violated. As described in delay requirements must be guaranteed not to be violated. As
Section 3.1, the two problems, static and dynamic, are addressed described in Section 3.1, the two problems (static and dynamic) are
separately. In either of the problems, the rate and delay must be addressed separately. In either of the problems, the rate and delay
guaranteed. Thus, must be guaranteed. Thus,
The static admission control: The static admission control:
The leaky bucket parameters of all class A or B flows are The leaky-bucket parameters of all class A or B flows are
known, therefore, for each class A or B flow f, a delay bound known; therefore, for each flow f of either class A or B, a
can be calculated. The computed delay bound for every class delay bound can be calculated. The computed delay bound for
A or B flow must not be more than its delay requirement. every flow of class A or B must not be more than its delay
Moreover, the sum of the rate of each flow (r_f) must not be requirement. Moreover, the sum of the rate of each flow
more than the rate allocated to each class (R). If these two (r_f) must not be more than the rate allocated to each class
conditions hold, the configuration is declared admissible. (R). If these two conditions hold, the configuration is
declared admissible.
The dynamic admission control: The dynamic admission control:
For dynamic admission control, we allocate to every node and For dynamic admission control, we allocate a static value
class A or B, static value for rate (R) and maximum bucket for rate (R) and a maximum bucket size (b_t) to every node
size (b_t). In addition, for every node and every class A and each class A or B. In addition, for every node and
and B, two counters are maintained: each class A or B, two counters are maintained:
R_acc is equal to the sum of the leaky-bucket rates of all R_acc is equal to the sum of the leaky-bucket rates of all
flows of this class already admitted at this node; At all flows of this class already admitted at this node; at all
times, we must have: times, we must have:
R_acc <=R, (Eq. 1) R_acc <= R, (Eq. 1)
b_acc is equal to the sum of the bucket sizes of all flows b_acc is equal to the sum of the bucket sizes of all flows
of this class already admitted at this node; At all times, of this class already admitted at this node; at all times,
we must have: we must have:
b_acc <=b_t. (Eq. 2) b_acc <= b_t. (Eq. 2)
A new class A or B flow is admitted at this node, if Eqs. (1) A new class A or B flow is admitted at this node if Eqs. (1)
and (2) continue to be satisfied after adding its leaky and (2) continue to be satisfied after adding its leaky-
bucket rate and bucket size to R_acc and b_acc. A class A or bucket rate and bucket size to R_acc and b_acc. A class A or
B flow is admitted in the network, if it is admitted at all B flow is admitted in the network if it is admitted at all
nodes along its path. When this happens, all variables R_acc nodes along its path. When this happens, all variables R_acc
and b_acc along its path must be incremented to reflect the and b_acc along its path must be incremented to reflect the
addition of the flow. Similarly, when a class A or B flow addition of the flow. Similarly, when a class A or B flow
leaves the network, all variables R_acc and b_acc along its leaves the network, all variables R_acc and b_acc along its
path must be decremented to reflect the removal of the flow. path must be decremented to reflect the removal of the flow.
The choice of the static values of R and b_t at all nodes and classes The choice of the static values of R and b_t at all nodes and classes
must be done in a prior configuration phase; R controls the bandwidth must be done in a prior configuration phase: R controls the bandwidth
allocated to this class at this node, b_t affects the delay bound and allocated to this class at this node, and b_t affects the delay bound
the buffer requirement. The value of R must be set such that and the buffer requirement. The value of R must be set such that
R <= I_X*(c-r_h)/c R <= I_X*(c-r_h)/c
where I_X is the idleslope of credit-based shaper for class X={A,B}, where I_X is the idleslope of credit-based shaper for class X={A,B},
c is the transmission rate of the output link and r_h is the leaky- c is the transmission rate of the output link, and r_h is the leaky-
bucket rate of the CDT class. bucket rate of the CDT class.
6.5. Guaranteed-Service IntServ 6.5. Guaranteed Service
Guaranteed-Service Integrated service (IntServ) is an architecture
that specifies the elements to guarantee quality of service (QoS) on
networks [RFC2212].
The flow, at the source, has a leaky bucket arrival curve with two The Guaranteed Service is defined in [RFC2212]. The flow, at the
parameters r as rate and b as bucket size, i.e., the amount of bits source, has a leaky-bucket arrival curve with two parameters: r as
entering a node within a time interval t is bounded by r * t + b. rate and b as bucket size, i.e., the amount of bits entering a node
within a time interval t is bounded by r * t + b.
If a resource reservation on a path is applied, a node provides a If a resource reservation on a path is applied, a node provides a
guaranteed rate R and maximum service latency of T. This can be guaranteed rate R and maximum service latency of T. This can be
interpreted in a way that the bits might have to wait up to T before interpreted in a way that the bits might have to wait up to T before
being served with a rate greater or equal to R. The delay bound of being served with a rate greater or equal to R. The delay bound of
the flow traversing the node is T + b / R. the flow traversing the node is T + b / R.
Consider a Guaranteed-Service IntServ path including a sequence of Consider a Guaranteed Service [RFC2212] path including a sequence of
nodes, where the i-th node provides a guaranteed rate R_i and maximum nodes, where the i-th node provides a guaranteed rate R_i and maximum
service latency of T_i. Then, the end-to-end delay bound for a flow service latency of T_i. Then, the end-to-end delay bound for a flow
on this can be calculated as sum(T_i) + b / min(R_i). on this can be calculated as sum(T_i) + b / min(R_i).
The provided delay bound is based on a simple case of Guaranteed- The provided delay bound is based on a simple case of Guaranteed
Service IntServ where only a guaranteed rate and maximum service Service, where only a guaranteed rate and maximum service latency and
latency and a leaky bucket arrival curve are available. If more a leaky-bucket arrival curve are available. If more information
information about the flow is known, e.g., the peak rate, the delay about the flow is known, e.g., the peak rate, the delay bound is more
bound is more complicated; the details are available in [RFC2212] and complicated; the details are available in [RFC2212] and Section 1.4.1
Section 1.4.1 of [NetCalBook]. of [NetCalBook].
6.6. Cyclic Queuing and Forwarding 6.6. Cyclic Queuing and Forwarding
Annex T of [IEEE8021Q] describes Cyclic Queuing and Forwarding (CQF), Annex T of [IEEE8021Q] describes Cyclic Queuing and Forwarding (CQF),
which provides bounded latency and zero congestion loss using the which provides bounded latency and zero congestion loss using the
time-scheduled gates of [IEEE8021Q] section 8.6.8.4. For a given time-scheduled gates of Section 8.6.8.4 of [IEEE8021Q]. For a given
class of DetNet flows, a set of two or more buffers is provided at class of DetNet flows, a set of two or more buffers is provided at
the output queue layer of Figure 3. A cycle time T_c is configured the output queue layer of Figure 3. A cycle time T_c is configured
for each class of DetNet flows c, and all of the buffer sets in a for each class of DetNet flows c, and all of the buffer sets in a
class of DetNet flows swap buffers simultaneously throughout the class of DetNet flows swap buffers simultaneously throughout the
DetNet domain at that cycle rate, all in phase. In such a mechanism, DetNet domain at that cycle rate, all in phase. In such a mechanism,
the regulator, mentioned in Figure 1, is not required. the regulator, as mentioned in Figure 1, is not required.
In the case of two-buffer CQF, each class of DetNet flows c has two In the case of two-buffer CQF, each class of DetNet flows c has two
buffers, namely buffer1 and buffer2. In a cycle (i) when buffer1 buffers, namely buffer1 and buffer2. In a cycle (i) when buffer1
accumulates received packets from the node's reception ports, buffer2 accumulates received packets from the node's reception ports, buffer2
transmits the already stored packets from the previous cycle (i-1). transmits the already stored packets from the previous cycle (i-1).
In the next cycle (i+1), buffer2 stores the received packets and In the next cycle (i+1), buffer2 stores the received packets and
buffer1 transmits the packets received in cycle (i). The duration of buffer1 transmits the packets received in cycle (i). The duration of
each cycle is T_c. each cycle is T_c.
The cycle time T_c must be carefully chosen; it needs to be large The cycle time T_c must be carefully chosen; it needs to be large
enough to accommodate all the DetNet traffic, plus at least one enough to accommodate all the DetNet traffic, plus at least one
maximum packet (or fragment) size from lower priority queues, which maximum packet (or fragment) size from lower priority queues, which
might be received within a cycle. Also, the value of T_c includes a might be received within a cycle. Also, the value of T_c includes a
time interval, called dead time (DT), which is the sum of the delays time interval, called dead time (DT), which is the sum of delays 1,
1,2,3,4 defined in Figure 1. The value of DT guarantees that the 2, 3, and 4 defined in Figure 1. The value of DT guarantees that the
last packet of one cycle in a node is fully delivered to a buffer of last packet of one cycle in a node is fully delivered to a buffer of
the next node in the same cycle. A two-buffer CQF is recommended if the next node in the same cycle. A two-buffer CQF is recommended if
DT is small compared to T_c. For a large DT, CQF with more buffers DT is small compared to T_c. For a large DT, CQF with more buffers
can be used, and a cycle identification label can be added to the can be used, and a cycle identification label can be added to the
packets. packets.
The per-hop latency is determined by the cycle time T_c: a packet The per-hop latency is determined by the cycle time T_c: a packet
transmitted from a node at a cycle (i), is transmitted from the next transmitted from a node at a cycle (i) is transmitted from the next
node at cycle (i+1). Then, if the packet traverses h hops, the node at cycle (i+1). Then, if the packet traverses h hops, the
maximum latency experienced by the packet is from the beginning of maximum latency experienced by the packet is from the beginning of
cycle (i) to the end of cycle (i+h); also, the minimum latency is cycle (i) to the end of cycle (i+h); also, the minimum latency is
from the end of cycle (i) before the DT, to the beginning of cycle from the end of cycle (i), before the DT, to the beginning of cycle
(i+h). Then, the maximum latency is: (i+h). Then, the maximum latency is:
(h+1) T_c (h+1) T_c
and the minimum latency is: and the minimum latency is:
(h-1) T_c + DT. (h-1) T_c + DT.
Ingress conditioning (Section 4.3) may be required if the source of a Ingress conditioning (Section 4.3) may be required if the source of a
DetNet flow does not, itself, employ CQF. Since there are no per- DetNet flow does not itself employ CQF. Since there are no per-flow
flow parameters in the CQF technique, per-hop configuration is not parameters in the CQF technique, per-hop configuration is not
required in the CQF forwarding nodes. required in the CQF forwarding nodes.
7. Example application on DetNet IP network 7. Example Application on DetNet IP Network
This section provides an example application of the timing model This section provides an example application of the timing model
presented in this document to control the admission of a DetNet flow presented in this document to control the admission of a DetNet flow
on a DetNet-enabled IP network. Consider Figure 5, taken from on a DetNet-enabled IP network. Consider Figure 5, taken from
Section 3 of [RFC8939], that shows a simple IP network: Section 3 of [RFC8939], which shows a simple IP network:
* The end-system 1 implements Guaranteed-Service IntServ as in * End system 1 implements Guaranteed Service [RFC2212], as in
Section 6.5 between itself and relay node 1. Section 6.5, between itself and relay node 1.
* Sub-network 1 is a TSN network. The nodes in subnetwork 1 * Sub-network 1 is a TSN network. The nodes in sub-network 1
implement credit-based shapers with asynchronous traffic shaping implement credit-based shapers with asynchronous traffic shaping,
as in Section 6.4. as in Section 6.4.
* Sub-network 2 is a TSN network. The nodes in subnetwork 2 * Sub-network 2 is a TSN network. The nodes in sub-network 2
implement cyclic queuing and forwarding with two buffers as in implement Cyclic Queuing and Forwarding with two buffers, as in
Section 6.6. Section 6.6.
* The relay nodes 1 and 2 implement credit-based shapers with * The relay nodes 1 and 2 implement credit-based shapers with
asynchronous traffic shaping as in Section 6.4. They also perform asynchronous traffic shaping, as in Section 6.4. They also
the aggregation and mapping of IP DetNet flows to TSN streams perform the aggregation and mapping of IP DetNet flows to TSN
(Section 4.4 of [RFC9023]). streams (Section 4.4 of [RFC9023]).
DetNet IP Relay Relay DetNet IP DetNet IP Relay Relay DetNet IP
End-System Node 1 Node 2 End-System End System Node 1 Node 2 End System
1 2 1 2
+----------+ +----------+ +----------+ +----------+
| Appl. |<------------ End-to-End Service ----------->| Appl. | | Appl. |<------------ End-to-End Service ----------->| Appl. |
+----------+ ............ ........... +----------+ +----------+ ............ ........... +----------+
| Service |<-: Service :-- DetNet flow --: Service :->| Service | | Service |<-: Service :-- DetNet flow --: Service :->| Service |
+----------+ +----------+ +----------+ +----------+ +----------+ +----------+ +----------+ +----------+
|Forwarding| |Forwarding| |Forwarding| |Forwarding| |Forwarding| |Forwarding| |Forwarding| |Forwarding|
+--------.-+ +-.------.-+ +-.---.----+ +-------.--+ +--------.-+ +-.------.-+ +-.---.----+ +-------.--+
: Link : \ ,-----. / \ ,-----. / : Link : \ ,-----. / \ ,-----. /
+......+ +----[ Sub- ]----+ +-[ Sub- ]-+ +......+ +----[ Sub- ]----+ +-[ Sub- ]-+
[Network] [Network] [Network] [Network]
`--1--' `--2--' `--1--' `--2--'
|<--------------------- DetNet IP --------------------->| |<--------------------- DetNet IP --------------------->|
|<--- d1 --->|<--------------- d2_p --------------->|<-- d3_p -->| |<--- d1 --->|<--------------- d2_p --------------->|<-- d3_p -->|
Figure 5: A Simple DetNet-Enabled IP Network, taken from RFC8939 Figure 5: A Simple DetNet-Enabled IP Network, Taken from RFC 8939
Consider a fully centralized control plane for the network of Consider a fully centralized control plane for the network of
Figure 5 as described in Section 3.2 of Figure 5, as described in Section 3.2 of [DETNET-CONTROL-PLANE].
[I-D.ietf-detnet-controller-plane-framework]. Suppose end-system 1 Suppose end system 1 wants to create a DetNet flow with a traffic
wants to create a DetNet flow with traffic specification destined to specification destined to end system 2 with end-to-end delay bound
end-system 2 with end-to-end delay bound requirement D. Therefore, requirement D. Therefore, the control plane receives a flow
the control plane receives a flow establishment request and establishment request and calculates a number of valid paths through
calculates a number of valid paths through the network (Section 3.2 the network (Section 3.2 of [DETNET-CONTROL-PLANE]). To select a
of [I-D.ietf-detnet-controller-plane-framework]). To select a proper proper path, the control plane needs to compute an end-to-end delay
path, the control plane needs to compute an end-to-end delay bound at bound at every node of each selected path p.
every node of each selected path p.
The end-to-end delay bound is d1 + d2_p + d3_p, where d1 is the delay The end-to-end delay bound is d1 + d2_p + d3_p, where d1 is the delay
bound from end-system 1 to the entrance of relay node 1, d2_p is the bound from end system 1 to the entrance of relay node 1, d2_p is the
delay bound for path p from relay node 1 to entrance of the first delay bound for path p from relay node 1 to the entrance of the first
node in sub-network 2, and d3_p the delay bound of path p from the node in sub-network 2, and d3_p is the delay bound of path p from the
first node in sub-network 2 to end-system 2. The computation of d1 first node in sub-network 2 to end system 2. The computation of d1
is explained in Section 6.5. Since the relay node 1, sub-network 1 is explained in Section 6.5. Since the relay node 1, sub-network 1,
and relay node 2 implement aggregate queuing, we use the results in and relay node 2 implement aggregate queuing, we use the results in
Section 4.2.2 and Section 6.4 to compute d2_p for the path p. Sections 4.2.2 and 6.4 to compute d2_p for the path p. Finally, d3_p
Finally, d3_p is computed using the delay bound computation of is computed using the delay bound computation of Section 6.6. Any
Section 6.6. Any path p such that d1 + d2_p + d3_p <= D satisfies path p, such that d1 + d2_p + d3_p <= D, satisfies the delay bound
the delay bound requirement of the flow. If there is no such path, requirement of the flow. If there is no such path, the control plane
the control plane may compute new set of valid paths and redo the may compute a new set of valid paths and redo the delay bound
delay bound computation or reject the DetNet flow. computation or reject the DetNet flow.
As soon as the control plane selects a path that satisfies the delay As soon as the control plane selects a path that satisfies the delay
bound constraint, it allocates and reserves the resources in the path bound constraint, it allocates and reserves the resources in the path
for the DetNet flow (Section 4.2 for the DetNet flow (Section 4.2 of [DETNET-CONTROL-PLANE]).
[I-D.ietf-detnet-controller-plane-framework]).
8. Security considerations 8. Security Considerations
Detailed security considerations for DetNet are cataloged in Detailed security considerations for DetNet are cataloged in
[RFC9055], and more general security considerations are described in [RFC9055], and more general security considerations are described in
[RFC8655]. [RFC8655].
Security aspects that are unique to DetNet are those whose aim is to Security aspects that are unique to DetNet are those whose aim is to
provide the specific QoS aspects of DetNet, specifically bounded end- provide the specific QoS aspects of DetNet, specifically bounded end-
to-end delivery latency and zero congestion loss. Achieving such to-end delivery latency and zero congestion loss. Achieving such
loss rates and bounded latency may not be possible in the face of a loss rates and bounded latency may not be possible in the face of a
highly capable adversary, such as the one envisioned by the Internet highly capable adversary, such as the one envisioned by the Internet
Threat Model of BCP 72 [RFC3552] that can arbitrarily drop or delay Threat Model of BCP 72 [RFC3552], which can arbitrarily drop or delay
any or all traffic. In order to present meaningful security any or all traffic. In order to present meaningful security
considerations, we consider a somewhat weaker attacker who does not considerations, we consider a somewhat weaker attacker who does not
control the physical links of the DetNet domain but may have the control the physical links of the DetNet domain but may have the
ability to control or change the behavior of some resources within ability to control or change the behavior of some resources within
the boundary of the DetNet domain. the boundary of the DetNet domain.
Latency bound calculations use parameters that reflect physical Latency bound calculations use parameters that reflect physical
quantities. If an attacker finds a way to change the physical quantities. If an attacker finds a way to change the physical
quantities, unknown to the control and management planes, the latency quantities, unknown to the control and management planes, the latency
calculations fail and may result in latency violation and/or calculations fail and may result in latency violation and/or
congestion losses. An example of such attacks is to make some congestion losses. An example of such attacks is to make some
traffic sources under the control of the attacker send more traffic traffic sources under the control of the attacker send more traffic
than their assumed T-SPECs. This type of attack is typically avoided than their assumed T-SPECs. This type of attack is typically avoided
by ingress conditioning at the edge of a DetNet domain. However, it by ingress conditioning at the edge of a DetNet domain. However, it
must be insured that such ingress conditioning is done per-flow and must be insured that such ingress conditioning is done per flow and
that the buffers are segregated such that if one flow exceeds its that the buffers are segregated such that if one flow exceeds its
T-SPEC, it does not cause buffer overflow for other flows. T-SPEC, it does not cause buffer overflow for other flows.
Some queuing mechanisms require time synchronization and operate Some queuing mechanisms require time synchronization and operate
correctly only if the time synchronization works correctly. In the correctly only if the time synchronization works correctly. In the
case of CQF, the correct alignments of cycles can fail if an attack case of CQF, the correct alignments of cycles can fail if an attack
against time synchronization fools a node into having an incorrect against time synchronization fools a node into having an incorrect
offset. Some of these attacks can be prevented by cryptographic offset. Some of these attacks can be prevented by cryptographic
authentication as in Annex K of [IEEE1588] for the Precision Time authentication as in Annex K of [IEEE1588] for the Precision Time
Protocol (PTP). However, the attacks that change the physical Protocol (PTP). However, the attacks that change the physical
latency of the links used by the time synchronization protocol are latency of the links used by the time synchronization protocol are
still possible even if the time synchronization protocol is protected still possible even if the time synchronization protocol is protected
by authentication and cryptography [DelayAttack]. Such attacks can by authentication and cryptography [DelayAttack]. Such attacks can
be detected only by their effects on latency bound violations and be detected only by their effects on latency bound violations and
congestion losses, which do not occur in normal DetNet operation. congestion losses, which do not occur in normal DetNet operation.
9. IANA considerations 9. IANA considerations
This document has no IANA actions. This document has no IANA actions.
10. Acknowledgement 10. References
We would like to thank Lou Berger, Tony Przygienda, John Scudder,
Watson Ladd, Yoshifumi Nishida, Ralf Weber, Robert Sparks, Gyan
Mishra, Martin Duke, Eric Vyncke, Lars Eggert, Roman Danyliw, and
Paul Wouters for their useful feedback on this document.
11. Contributors
RFC 7322 limits the number of authors listed on the front page to a
maximum of 5. The editor wishes to thank and acknowledge the
following author for contributing text to this document
Janos Farkas
Ericsson
Email: janos.farkas@ericsson.com
12. References
12.1. Normative References 10.1. Normative References
[IEEE8021Q] [IEEE8021Q]
IEEE 802.1, "IEEE Std 802.1Q-2018: IEEE Standard for Local IEEE, "IEEE Standard for Local and Metropolitan Area
and metropolitan area networks - Bridges and Bridged Networks--Bridges and Bridged Networks", IEEE Std 802.1Q-
Networks", 2018, 2018, DOI 10.1109/IEEESTD.2018.8403927, July 2018,
<https://ieeexplore.ieee.org/document/8403927>. <https://ieeexplore.ieee.org/document/8403927>.
[RFC2212] Shenker, S., Partridge, C., and R. Guerin, "Specification [RFC2212] Shenker, S., Partridge, C., and R. Guerin, "Specification
of Guaranteed Quality of Service", RFC 2212, of Guaranteed Quality of Service", RFC 2212,
DOI 10.17487/RFC2212, September 1997, DOI 10.17487/RFC2212, September 1997,
<https://www.rfc-editor.org/info/rfc2212>. <https://www.rfc-editor.org/info/rfc2212>.
[RFC2475] Blake, S., Black, D., Carlson, M., Davies, E., Wang, Z., [RFC2475] Blake, S., Black, D., Carlson, M., Davies, E., Wang, Z.,
and W. Weiss, "An Architecture for Differentiated and W. Weiss, "An Architecture for Differentiated
Services", RFC 2475, DOI 10.17487/RFC2475, December 1998, Services", RFC 2475, DOI 10.17487/RFC2475, December 1998,
skipping to change at page 28, line 30 skipping to change at line 1239
S., and J. Korhonen, "Deterministic Networking (DetNet) S., and J. Korhonen, "Deterministic Networking (DetNet)
Data Plane: MPLS", RFC 8964, DOI 10.17487/RFC8964, January Data Plane: MPLS", RFC 8964, DOI 10.17487/RFC8964, January
2021, <https://www.rfc-editor.org/info/rfc8964>. 2021, <https://www.rfc-editor.org/info/rfc8964>.
[RFC9016] Varga, B., Farkas, J., Cummings, R., Jiang, Y., and D. [RFC9016] Varga, B., Farkas, J., Cummings, R., Jiang, Y., and D.
Fedyk, "Flow and Service Information Model for Fedyk, "Flow and Service Information Model for
Deterministic Networking (DetNet)", RFC 9016, Deterministic Networking (DetNet)", RFC 9016,
DOI 10.17487/RFC9016, March 2021, DOI 10.17487/RFC9016, March 2021,
<https://www.rfc-editor.org/info/rfc9016>. <https://www.rfc-editor.org/info/rfc9016>.
12.2. Informative References 10.2. Informative References
[BennettDelay] [BennettDelay]
J.C.R. Bennett, K. Benson, A. Charny, W.F. Courtney, and Bennett, J. C. R., Benson, K., Charny, A., Courtney, W.
J.-Y. Le Boudec, "Delay Jitter Bounds and Packet Scale F., and J.-Y. Le Boudec, "Delay jitter bounds and packet
Rate Guarantee for Expedited Forwarding", scale rate guarantee for expedited forwarding",
DOI 10.1109/TNET.2002.801404, August 2002,
<https://dl.acm.org/citation.cfm?id=581870>. <https://dl.acm.org/citation.cfm?id=581870>.
[CharnyDelay] [CharnyDelay]
A. Charny and J.-Y. Le Boudec, "Delay Bounds in a Network Charny, A. and J.-Y. Le Boudec, "Delay Bounds in a Network
with Aggregate Scheduling", <https://link.springer.com/ with Aggregate Scheduling", DOI 10.1007/3-540-39939-9_1,
September 2002, <https://link.springer.com/
chapter/10.1007/3-540-39939-9_1>. chapter/10.1007/3-540-39939-9_1>.
[DelayAttack] [DelayAttack]
S. Barreto, A. Suresh, and J.-Y. Le Boudec, "Cyber-attack Barreto, S., Suresh, A., and J. L. Boudec, "Cyber-attack
on packet-based time synchronization protocols: The on packet-based time synchronization protocols: The
undetectable Delay Box", undetectable Delay Box", DOI 10.1109/I2MTC.2016.7520408,
<https://ieeexplore.ieee.org/document/7520408>. May 2016, <https://ieeexplore.ieee.org/document/7520408>.
[I-D.ietf-detnet-controller-plane-framework] [DETNET-CONTROL-PLANE]
A. Malis, X. Geng, M. Chen, F. Qin, and B. Varga, Malis, A., Geng, A., Ed., Chen, M., Qin, F., and B. Varga,
"Deterministic Networking (DetNet) Controller Plane "Deterministic Networking (DetNet) Controller Plane
Framework draft-ietf-detnet-controller-plane-framework- Framework", Work in Progress, Internet-Draft, draft-ietf-
01", <https://datatracker.ietf.org/doc/html/draft-ietf- detnet-controller-plane-framework-02, 28 June 2022,
detnet-controller-plane-framework>. <https://datatracker.ietf.org/doc/html/draft-ietf-detnet-
controller-plane-framework-02>.
[IEEE1588] IEEE Std 1588-2008, "IEEE Standard for a Precision Clock [IEEE1588] IEEE, "IEEE Standard for a Precision Clock Synchronization
Synchronization Protocol for Networked Measurement and Protocol for Networked Measurement and Control Systems",
Control Systems", 2008, IEEE Std 1588-2008, DOI 10.1109/IEEESTD.2008.4579760, July
<https://ieeexplore.ieee.org/document/4579760>. 2008, <https://ieeexplore.ieee.org/document/4579760>.
[IEEE8021Qcr] [IEEE8021Qcr]
IEEE 802.1, "IEEE P802.1Qcr: Bridges and Bridged Networks IEEE 802.1, "802.1Qcr-2020 - IEEE Standard for Local and
- Amendment: Asynchronous Traffic Shaping", 2017, Metropolitan Area Networks--Bridges and Bridged Networks
<https://1.ieee802.org/tsn/802-1qcr/>. Amendment 34:Asynchronous Traffic Shaping", November 2020,
<https://ieeexplore.ieee.org/document/9253013>.
[IEEE8021TSN] [IEEE8021TSN]
IEEE 802.1, "IEEE 802.1 Time-Sensitive Networking (TSN) IEEE 802.1, "802.1 Time-Sensitive Networking (TSN) Task
Task Group", <http://www.ieee802.org/1/>. Group", <https://1.ieee802.org/tsn/>.
[IEEE8023] IEEE 802.3, "IEEE Std 802.3-2018: IEEE Standard for [IEEE8023] IEEE, "IEEE Standard for Ethernet", IEEE Std 802.3-2018,
Ethernet", 2018, DOI 10.1109/IEEESTD.2018.8457469, August 2018,
<http://ieeexplore.ieee.org/document/8457469>. <http://ieeexplore.ieee.org/document/8457469>.
[LeBoudecTheory] [LeBoudecTheory]
J.-Y. Le Boudec, "A Theory of Traffic Regulators for Le Boudec, J.-Y., "A Theory of Traffic Regulators for
Deterministic Networks with Application to Interleaved Deterministic Networks With Application to Interleaved
Regulators", Regulators", DOI 10.1109/TNET.2018.2875191, November 2018,
<https://ieeexplore.ieee.org/document/8519761>. <https://ieeexplore.ieee.org/document/8519761>.
[NetCalBook] [NetCalBook]
J.-Y. Le Boudec and P. Thiran, "Network calculus: a theory Le Boudec, J.-Y. and P. Thiran, "Network Calculus: A
of deterministic queuing systems for the internet", 2001, Theory of Deterministic Queuing Systems for the Internet",
<https://leboudec.github.io/netcal/>. Springer Science & Business Media, vol. 2050, 2001,
<https://leboudec.github.io/netcal/latex/netCalBook.pdf>.
[PacketReorderingBounds] [PacketReorderingBounds]
E. Mohammadpour, and J.-Y. Le Boudec, "On Packet Mohammadpour, E. and J.-Y. Le Boudec, "On Packet
Reordering in Time-Sensitive Networks", Reordering in Time-Sensitive Networks",
DOI 10.1109/TNET.2021.3129590, December 2021,
<https://ieeexplore.ieee.org/document/9640523>. <https://ieeexplore.ieee.org/document/9640523>.
[RFC2697] Heinanen, J. and R. Guerin, "A Single Rate Three Color [RFC2697] Heinanen, J. and R. Guerin, "A Single Rate Three Color
Marker", RFC 2697, DOI 10.17487/RFC2697, September 1999, Marker", RFC 2697, DOI 10.17487/RFC2697, September 1999,
<https://www.rfc-editor.org/info/rfc2697>. <https://www.rfc-editor.org/info/rfc2697>.
[RFC3552] Rescorla, E. and B. Korver, "Guidelines for Writing RFC [RFC3552] Rescorla, E. and B. Korver, "Guidelines for Writing RFC
Text on Security Considerations", BCP 72, RFC 3552, Text on Security Considerations", BCP 72, RFC 3552,
DOI 10.17487/RFC3552, July 2003, DOI 10.17487/RFC3552, July 2003,
<https://www.rfc-editor.org/info/rfc3552>. <https://www.rfc-editor.org/info/rfc3552>.
skipping to change at page 30, line 26 skipping to change at line 1330
IEEE 802.1 Time-Sensitive Networking (TSN)", RFC 9023, IEEE 802.1 Time-Sensitive Networking (TSN)", RFC 9023,
DOI 10.17487/RFC9023, June 2021, DOI 10.17487/RFC9023, June 2021,
<https://www.rfc-editor.org/info/rfc9023>. <https://www.rfc-editor.org/info/rfc9023>.
[RFC9055] Grossman, E., Ed., Mizrahi, T., and A. Hacker, [RFC9055] Grossman, E., Ed., Mizrahi, T., and A. Hacker,
"Deterministic Networking (DetNet) Security "Deterministic Networking (DetNet) Security
Considerations", RFC 9055, DOI 10.17487/RFC9055, June Considerations", RFC 9055, DOI 10.17487/RFC9055, June
2021, <https://www.rfc-editor.org/info/rfc9055>. 2021, <https://www.rfc-editor.org/info/rfc9055>.
[Sch8021Qbv] [Sch8021Qbv]
S. Craciunas, R. Oliver, M. Chmelik, and W. Steiner, Craciunas, S., Oliver, R., Chmelik, M., and W. Steiner,
"Scheduling Real-Time Communication in IEEE 802.1Qbv Time "Scheduling Real-Time Communication in IEEE 802.1Qbv Time
Sensitive Networks", Sensitive Networks", DOI 10.1145/2997465.2997470, October
<https://dl.acm.org/doi/10.1145/2997465.2997470>. 2016, <https://dl.acm.org/doi/10.1145/2997465.2997470>.
[SpechtUBS] [SpechtUBS]
J. Specht and S. Samii, "Urgency-Based Scheduler for Time- Specht, J. and S. Samii, "Urgency-Based Scheduler for
Sensitive Switched Ethernet Networks", Time-Sensitive Switched Ethernet Networks",
DOI 10.1109/ECRTS.2016.27, July 2016,
<https://ieeexplore.ieee.org/abstract/document/7557870>. <https://ieeexplore.ieee.org/abstract/document/7557870>.
[ThomasTime] [ThomasTime]
L. Thomas and J.-Y. Le Boudec, "On Time Synchronization Thomas, L. and J.-Y. Le Boudec, "On Time Synchronization
Issues in Time-Sensitive Networks with Regulators and Issues in Time-Sensitive Networks with Regulators and
Nonideal Clocks", Nonideal Clocks", DOI 10.1145/3393691.339420, June 2020,
<https://dl.acm.org/doi/10.1145/3393691.3394206>. <https://dl.acm.org/doi/10.1145/3393691.3394206>.
[TSNwithATS] [TSNwithATS]
E. Mohammadpour, E. Stai, M. Mohiuddin, and J.-Y. Le Mohammadpour, E., Stai, E., Mohiuddin, M., and J.-Y. Le
Boudec, "Latency and Backlog Bounds in Time-Sensitive Boudec, "Latency and Backlog Bounds in Time-Sensitive
Networking with Credit Based Shapers and Asynchronous Networking with Credit Based Shapers and Asynchronous
Traffic Shaping", Traffic Shaping", DOI 10.1109/ITC30.2018.10053, September
<https://ieeexplore.ieee.org/document/8493026>. 2018, <https://ieeexplore.ieee.org/document/8493026>.
Acknowledgments
We would like to thank Lou Berger, Tony Przygienda, John Scudder,
Watson Ladd, Yoshifumi Nishida, Ralf Weber, Robert Sparks, Gyan
Mishra, Martin Duke, √Čric Vyncke, Lars Eggert, Roman Danyliw, and
Paul Wouters for their useful feedback on this document.
Contributors
RFC 7322 limits the number of authors listed on the front page to a
maximum of 5. The editor wishes to thank and acknowledge the
following author for contributing text to this document:
Janos Farkas
Ericsson
Email: janos.farkas@ericsson.com
Authors' Addresses Authors' Addresses
Norman Finn Norman Finn
Huawei Technologies Co. Ltd Huawei Technologies Co. Ltd
3101 Rio Way 3101 Rio Way
Spring Valley, California 91977 Spring Valley, California 91977
United States of America United States of America
Phone: +1 925 980 6430 Phone: +1 925 980 6430
Email: nfinn@nfinnconsulting.com Email: nfinn@nfinnconsulting.com
Jean-Yves Le Boudec Jean-Yves Le Boudec
EPFL EPFL
IC Station 14 IC Station 14
CH-1015 Lausanne EPFL CH-1015 Lausanne
Switzerland Switzerland
Email: jean-yves.leboudec@epfl.ch Email: jean-yves.leboudec@epfl.ch
Ehsan Mohammadpour Ehsan Mohammadpour
EPFL EPFL
IC Station 14 IC Station 14
CH-1015 Lausanne EPFL CH-1015 Lausanne
Switzerland Switzerland
Email: ehsan.mohammadpour@epfl.ch Email: ehsan.mohammadpour@epfl.ch
Jiayi Zhang Jiayi Zhang
Huawei Technologies Co. Ltd Huawei Technologies Co. Ltd
Q27, No.156 Beiqing Road Q27, No.156 Beiqing Road
Beijing Beijing
100095 100095
China China
Email: zhangjiayi11@huawei.com Email: zhangjiayi11@huawei.com
 End of changes. 207 change blocks. 
525 lines changed or deleted 528 lines changed or added

This html diff was produced by rfcdiff 1.48.