draft-ietf-bmwg-benchres-term-05.txt   draft-ietf-bmwg-benchres-term-06.txt 
Benchmarking Working Group Gabor Feher, BUTE Benchmarking Working Group Gabor Feher, BUTE
INTERNET-DRAFT Krisztian Nemeth, BUTE INTERNET-DRAFT Krisztian Nemeth, BUTE
Expiration Date: July 2005 Andras Korn, BUTE Expiration Date: January 2006 Andras Korn, BUTE
Istvan Cselenyi, TeliaSonera Istvan Cselenyi, TeliaSonera
January 2005 July 2005
Benchmarking Terminology for Routers Supporting Resource Reservation Benchmarking Terminology for Resource Reservation Capable Routers
<draft-ietf-bmwg-benchres-term-05.txt> <draft-ietf-bmwg-benchres-term-06.txt>
Status of this Memo Status of this Memo
By submitting this Internet-Draft, each author represents that any
applicable patent or other IPR claims of which he or she is aware
have been or will be disclosed, and any of which he or she becomes
aware will be disclosed, in accordance with Section 6 of BCP 79.
Internet-Drafts are working documents of the Internet Engineering Internet-Drafts are working documents of the Internet Engineering
Task Force (IETF), its areas, and its working groups. Note that Task Force (IETF), its areas, and its working groups. Note that
other groups may also distribute working documents as Internet- other groups may also distribute working documents as Internet-
Drafts. Drafts.
Internet-Drafts are draft documents valid for a maximum of six Internet-Drafts are draft documents valid for a maximum of six
months and may be updated, replaced, or obsoleted by other documents months and may be updated, replaced, or obsoleted by other documents
at any time. It is inappropriate to use Internet-Drafts as at any time. It is inappropriate to use Internet-Drafts as
reference material or to cite them other than as "work in progress." reference material or to cite them other than as "work in progress."
The list of current Internet-Drafts can be accessed at The list of current Internet-Drafts can be accessed at
http://www.ietf.org/1id-abstracts.html http://www.ietf.org/1id-abstracts.html
The list of Internet-Draft Shadow Directories can be accessed at The list of Internet-Draft Shadow Directories can be accessed at
http://www.ietf.org/shadow.html http://www.ietf.org/shadow.html
By submitting this Internet-Draft, I certify that any applicable
patent or other IPR claims of which I am aware have been disclosed,
or will be disclosed, and any of which I become aware will be
disclosed, in accordance with RFC 3668.
Table of contents Table of contents
Abstract...........................................................2 Abstract...........................................................2
1. Introduction....................................................3 1. Introduction....................................................2
2. Existing definitions............................................3 2. Existing definitions............................................3
3. Definition of Terms.............................................4 3. Definition of Terms.............................................3
3.1 Traffic Flow Types..........................................4 3.1 Traffic Flow Types..........................................3
3.1.1 Data Flow..............................................4 3.1.1 Data Flow..............................................3
3.1.2 Distinguished Data Flow................................4 3.1.2 Distinguished Data Flow................................4
3.1.3 Best-Effort Data Flow..................................5 3.1.3 Best-Effort Data Flow..................................4
3.2 Resource Reservation Protocol Basics........................5 3.2 Resource Reservation Protocol Basics........................5
3.2.1 QoS Session............................................5 3.2.1 QoS Session............................................5
3.2.2 Resource Reservation Protocol..........................6 3.2.2 Resource Reservation Protocol..........................6
3.2.3 Resource Reservation Capable Router....................7 3.2.3 Resource Reservation Capable Router....................6
3.2.4 Reservation State......................................7 3.2.4 Reservation State......................................6
3.2.5 Resource Reservation Protocol Orientation..............8 3.2.5 Resource Reservation Protocol Orientation..............7
3.3 Router Load Factors.........................................9 3.3 Router Load Factors.........................................9
3.3.1 Best-Effort Traffic Load Factor........................9 3.3.1 Best-Effort Traffic Load Factor........................9
3.3.2 Distinguished Traffic Load Factor......................9 3.3.2 Distinguished Traffic Load Factor.....................10
Feher, Nemeth, Korn, Cselenyi Expires January 2006 [Page 1]
3.3.3 Session Load Factor...................................10 3.3.3 Session Load Factor...................................10
3.3.4 Signaling Intensity Load Factor.......................10 3.3.4 Signaling Intensity Load Factor.......................11
3.3.5 Signaling Burst Load Factor...........................11 3.3.5 Signaling Burst Load Factor...........................11
3.4 Performance Metrics........................................11 3.4 Performance Metrics........................................12
3.4.1 Signaling Message Handling Time.......................11 3.4.1 Signaling Message Handling Time.......................12
3.4.2 Distinguished Traffic Delay...........................12 3.4.2 Distinguished Traffic Delay...........................13
3.4.3 Best-effort Traffic Delay.............................13 3.4.3 Best-effort Traffic Delay.............................14
3.4.4 Signaling Message Loss................................13 3.4.4 Signaling Message Deficit.............................14
3.4.5 Session Maintenance Capacity..........................14 3.4.5 Session Maintenance Capacity..........................15
3.5 Scalability Limit..........................................15 3.5 Router Load Conditions and Scalability Limit...............16
4. Security Considerations........................................16 3.5.1 Loss-Free Condition...................................16
5. IANA Considerations............................................16 3.5.2 Lossy Condition.......................................17
6. Acknowledgements...............................................16 3.5.3 Scalability Limit.....................................17
7. References.....................................................16 4. Security Considerations........................................19
7.1 Normative References.......................................16 5. IANA Considerations............................................19
7.2 Informative References.....................................16 6. Acknowledgements...............................................19
Authors' Addresses................................................17 7. References.....................................................19
Disclaimer of Validity............................................17 7.1 Normative References.......................................19
Copyright Notice..................................................18 7.2 Informative References.....................................19
Disclaimer........................................................18 Authors' Addresses................................................20
Disclaimer of Validity............................................20
Copyright Notice..................................................21
Disclaimer........................................................21
Abstract Abstract
The purpose of this document is to define terminology specific to
the benchmarking of resource reservation signaling of Integrated The primary purpose of this document is to define terminology
Services IP routers. These terms can be used in additional documents specific to the benchmarking of resource reservation signaling of
that define benchmarking methodologies for routers that support Integrated Services IP routers. These terms can be used in
resource reservation or reporting formats for the benchmarking additional documents that define benchmarking methodologies for
measurements. routers that support resource reservation or reporting formats for
the benchmarking measurements.
1. Introduction 1. Introduction
Signaling based resource reservation (e.g. via RSVP [3]) is an Signaling based resource reservation (e.g. via RSVP [3]) is an
important part of the different QoS provisioning approaches. important part of the different QoS provisioning approaches.
Therefore network operators who are planning to deploy signaling Therefore network operators who are planning to deploy signaling
based resource reservation may want to scrutinize the scalability based resource reservation may want to examine the scalability
limitations of reservation capable routers and the impact of limitations of reservation capable routers and the impact of
signaling on their data forwarding performance. signaling on their data forwarding performance.
An objective way of quantifying the scalability constraints of QoS An objective way of quantifying the scalability constraints of QoS
signaling is to perform measurements on routers that are capable of signaling is to perform measurements on routers that are capable of
resource reservation. This document defines terminology for a resource reservation. This document defines terminology for a
specific set of tests that vendors or network operators can carry specific set of tests that vendors or network operators can carry
out to measure and report the signaling performance characteristics out to measure and report the signaling performance characteristics
of router devices that support resource reservation protocols. The of router devices that support resource reservation protocols. The
results of these tests provide comparable data for different results of these tests provide comparable data for different
products, and thus support the decision process before purchase. products, and thus support the decision-making process before
Moreover, these measurements provide input characteristics for the purchase. Moreover, these measurements provide input characteristics
dimensioning of a network in which resources are provisioned for the dimensioning of a network in which resources are provisioned
dynamically by signaling. Finally, the tests are applicable for dynamically by signaling. Finally, the tests are applicable for
Feher, Nemeth, Korn, Cselenyi Expires January 2006 [Page 2]
characterizing the impact of the resource reservation signaling on characterizing the impact of the resource reservation signaling on
the forwarding performance of the routers. the forwarding performance of the routers.
This benchmarking terminology document is based on the knowledge This benchmarking terminology document is based on the knowledge
gained by examination of (and experimentation with) different gained by examination of (and experimentation with) different
resource reservation protocols: the IETF standard RSVP [3] and resource reservation protocols: the IETF standard RSVP [3] and
several experimental ones, such as YESSIR [5], ST2+ [6], SDP [7], several experimental ones, such as YESSIR [5], ST2+ [6], SDP [7],
Boomerang [8] and Ticket [9]. Some of these protocols are also Boomerang [8] and Ticket [9]. Some of these protocols are also
analyzed in an IETF NSIS working group draft [10]. Although at the analyzed in an IETF NSIS working group draft [10]. Although at the
moment the authors are only aware of resource reservation capable moment the authors are only aware of resource reservation capable
router products that interpret RSVP, this document defines terms router products that interpret RSVP, this document defines terms
that are valid in general and not restricted to any of the above that are valid in general and not restricted to any of the above
listed protocols. listed protocols.
In order to avoid any confusion we would like to emphasize that this In order to avoid any confusion we would like to emphasize that this
terminology considers only signaling protocols that provide IntServ terminology considers only signaling protocols that provide IntServ
resource reservation; the DiffServ world, for example, is out of our resource reservation; for example, techniques in the DiffServ
scope. toolbox are predominantly beyond our scope.
2. Existing definitions 2. Existing definitions
RFC 1242 "Benchmarking Terminology for Network Interconnect RFC 1242 "Benchmarking Terminology for Network Interconnect
Devices" [1] and RFC 2285 "Benchmarking Terminology for LAN Devices" [1] and RFC 2285 "Benchmarking Terminology for LAN
Switching Devices" [2] contain discussions and definitions for a Switching Devices" [2] contain discussions and definitions for a
number of terms relevant to the benchmarking of signaling number of terms relevant to the benchmarking of signaling
performance of reservation capable routers and should be consulted performance of reservation capable routers and should be consulted
before attempting to make use of this document. before attempting to make use of this document.
skipping to change at page 4, line 30 skipping to change at line 162
This group of definitions describes traffic flow types forwarded by This group of definitions describes traffic flow types forwarded by
resource reservation capable routers. resource reservation capable routers.
3.1.1 Data Flow 3.1.1 Data Flow
Definition: Definition:
A data flow is a stream of data packets from one sender to one or A data flow is a stream of data packets from one sender to one or
more receivers, where each packet has a flow identifier unique to more receivers, where each packet has a flow identifier unique to
the flow. the flow.
Feher, Nemeth, Korn, Cselenyi Expires January 2006 [Page 3]
Discussion: Discussion:
The flow identifier can be an arbitrary subset of the packet The flow identifier can be an arbitrary subset of the packet
header fields that uniquely distinguishes the flow from others. header fields that uniquely distinguishes the flow from others.
For example, the 5-tuple "source address; source port; destination For example, the 5-tuple "source address; source port; destination
address; destination port; protocol number" is commonly used for address; destination port; protocol number" is commonly used for
this purpose (where port number are applicable). It is also this purpose (where port numbers are applicable). It is also
possible to take advantage of the Flow Label field of IPv6 possible to take advantage of the Flow Label field of IPv6
packets. For more comment on flow identification refer to [4]. packets. For more comment on flow identification refer to [4].
The flow identification can be time- and/or resource-consuming,
but this can sometimes be avoided as routers do not necessarily
have to classify each packet. Instead, packets that should be
classified by routers can be marked with special flags that
routers understand. One existing marking approach is to use the
Type of Service (IPv4)/Traffic Class (IPv6) field of the IP
header. Naturally, unmarked packets are not classified by routers
and this way valuable resources can be saved.
3.1.2 Distinguished Data Flow 3.1.2 Distinguished Data Flow
Definition: Definition:
Distinguished data flows are flows that resource reservation Distinguished data flows are flows that resource reservation
capable routers intentionally treat better or worse than capable routers intentionally treat better or worse than best-
"ordinary" data flows, according to a QoS agreement defined for effort data flows, according to a QoS agreement defined for the
the distinguished flow. distinguished flow.
Discussion: Discussion:
Packets of distinguished data flows are marked so that the routers Routers classify the packets of distinguished data flows and
that forward them know they require differentiated treatment. identify the data flow they belong to.
Routers classify these incoming packets and identify the data flow
they belong to.
The most common usage of the distinguished data flow is to get The most common usage of the distinguished data flow is to get
higher priority treatment than that of best-effort data flows (see higher priority treatment than that of best-effort data flows (see
the next definition). In these cases, a distinguished data flow is the next definition). In these cases, a distinguished data flow is
sometimes referred to as a "premium data flow". Nevertheless sometimes referred to as a "premium data flow". Nevertheless
theoretically it is possible to require worse treatment than that theoretically it is possible to require worse treatment than that
of best-effort flows. of best-effort flows.
3.1.3 Best-Effort Data Flow 3.1.3 Best-Effort Data Flow
skipping to change at page 5, line 31 skipping to change at line 204
Best-effort data flows are flows that are not treated in any Best-effort data flows are flows that are not treated in any
special manner by resource reservation capable routers; thus, special manner by resource reservation capable routers; thus,
their packets are served (forwarded) in some default way. their packets are served (forwarded) in some default way.
Discussion: Discussion:
"Best-effort" means that the router makes its best effort to "Best-effort" means that the router makes its best effort to
forward the data packet quickly and safely, but does not guarantee forward the data packet quickly and safely, but does not guarantee
anything (e.g. delay or loss probability). This type of traffic is anything (e.g. delay or loss probability). This type of traffic is
the most common in today's Internet. the most common in today's Internet.
The packets belonging to the best-effort data flows are not Packets that belong to best-effort data flows need not be
specially marked and thus they are not classified by the routers. classified by the routers; that is, the routers don't need to find
a related reservation session in order to find out what treatment
the packet is entitled to.
Feher, Nemeth, Korn, Cselenyi Expires January 2006 [Page 4]
3.2 Resource Reservation Protocol Basics 3.2 Resource Reservation Protocol Basics
This group of definitions applies to signaling based resource This group of definitions applies to signaling based resource
reservation protocols implemented by IP router devices. reservation protocols implemented by IP router devices.
3.2.1 QoS Session 3.2.1 QoS Session
Definition: Definition:
A QoS session is an application layer concept, shared between a A QoS session is an application layer concept, shared between a
skipping to change at page 6, line 36 skipping to change at line 264
network resource in a router can be shared among many traffic network resource in a router can be shared among many traffic
sources from the same multicast group (c.f. multicast reservation sources from the same multicast group (c.f. multicast reservation
styles in the case of RSVP). styles in the case of RSVP).
Issues: Issues:
Even though QoS sessions are considered to be unique, resource Even though QoS sessions are considered to be unique, resource
reservation capable routers might aggregate them and allocate reservation capable routers might aggregate them and allocate
network resources to these aggregated sessions at once. The network resources to these aggregated sessions at once. The
aggregation can be based on similar data flow attributes (e.g. aggregation can be based on similar data flow attributes (e.g.
similar destination addresses) or it can combine arbitrary similar destination addresses) or it can combine arbitrary
Feher, Nemeth, Korn, Cselenyi Expires January 2006 [Page 5]
sessions as well. While reservation aggregation significantly sessions as well. While reservation aggregation significantly
lightens the signaling processing task of a resource reservation lightens the signaling processing task of a resource reservation
capable router, it also requires the administration of the capable router, it also requires the administration of the
aggregated QoS sessions and might also lead to the violation of aggregated QoS sessions and might also lead to the violation of
the quality guaranties referring to individual data flows within the quality guaranties referring to individual data flows within
an aggregation [11]. an aggregation [11].
3.2.2 Resource Reservation Protocol 3.2.2 Resource Reservation Protocol
Definition: Definition:
skipping to change at page 7, line 8 skipping to change at line 292
that carry the information related to QoS sessions. This that carry the information related to QoS sessions. This
information includes a session identifier, the actual QoS information includes a session identifier, the actual QoS
parameters, and possibly flow descriptors. parameters, and possibly flow descriptors.
The message processing rules of the signaling protocols ensure The message processing rules of the signaling protocols ensure
that signaling messages reach all network nodes concerned. Some that signaling messages reach all network nodes concerned. Some
resource reservation protocols (e.g. RSVP) are only concerned with resource reservation protocols (e.g. RSVP) are only concerned with
this, i.e. carrying the QoS-related information to all the this, i.e. carrying the QoS-related information to all the
appropriate network nodes, without being aware of its content. appropriate network nodes, without being aware of its content.
This latter approach allows changing the way the QoS parameters This latter approach allows changing the way the QoS parameters
are described, and different kind of provisioning can be realized are described, and different kinds of provisioning can be realized
without the need to change the protocol itself. without the need to change the protocol itself.
3.2.3 Resource Reservation Capable Router 3.2.3 Resource Reservation Capable Router
Definition: Definition:
A router is resource reservation capable (it supports resource A router is resource reservation capable (it supports resource
reservation) if it is able to interpret signaling messages of a reservation) if it is able to interpret signaling messages of a
resource reservation protocol, and based on these messages is able resource reservation protocol, and based on these messages is able
to adjust the management of its flow classifiers and network to adjust the management of its flow classifiers and network
resources so as to conform with the content of the messages. resources so as to conform to the content of the signaling
messages.
Discussion: Discussion:
Routers capture signaling messages and manipulate reservation Routers capture signaling messages and manipulate reservation
states and/or reserved network resources according to the content states and/or reserved network resources according to the content
of the messages. This ensures that the flows are treated as their of the messages. This ensures that the flows are treated as their
specified QoS requirements indicate. specified QoS requirements indicate.
3.2.4 Reservation State 3.2.4 Reservation State
Definition: Definition:
A reservation state is the set of entries in the router's memory A reservation state is the set of entries in the router's memory
that contain all relevant information about a given QoS session that contain all relevant information about a given QoS session
registered with the router. registered with the router.
Feher, Nemeth, Korn, Cselenyi Expires January 2006 [Page 6]
Discussion: Discussion:
States are needed because IntServ related resource reservation States are needed because IntServ related resource reservation
protocols require the routers to keep track of QoS session and protocols require the routers to keep track of QoS session and
data-flow-related metadata. The reservation state includes the data-flow-related metadata. The reservation state includes the
parameters of the QoS treatment; the description of how and where parameters of the QoS treatment; the description of how and where
to forward the incoming signaling messages; refresh timing to forward the incoming signaling messages; refresh timing
information; etc. information; etc.
Based on how reservation states are stored in a reservation Based on how reservation states are stored in a reservation
capable router, the routers can be categorized into two classes: capable router, the routers can be categorized into two classes:
skipping to change at page 8, line 6 skipping to change at line 345
There are also soft-state resource reservation capable routers, There are also soft-state resource reservation capable routers,
where there are no permanent reservation states, and each state where there are no permanent reservation states, and each state
has to be regularly refreshed by appropriate refresh signaling has to be regularly refreshed by appropriate refresh signaling
messages. If no refresh signaling message arrives during a certain messages. If no refresh signaling message arrives during a certain
period then the router stops the maintenance of the QoS session period then the router stops the maintenance of the QoS session
assuming that the end-points do not intend to keep the session up assuming that the end-points do not intend to keep the session up
any longer or the communication lines are broken somewhere along any longer or the communication lines are broken somewhere along
the data path. This feature makes soft-state resource reservation the data path. This feature makes soft-state resource reservation
capable routers more robust than hard-state routers, since no capable routers more robust than hard-state routers, since no
failures can cause resources to stay permanently stuck in the failures can cause resources to stay permanently stuck in the
routers. (Note, it is still possible to have an explicit teardown routers. (Note that it is still possible to have an explicit
message in soft-state protocols for quicker resource release.) teardown message in soft-state protocols for quicker resource
release.)
Issues: Issues:
Based on the initiating point of the refresh messages, soft-state Based on the initiating point of the refresh messages, soft-state
resource reservation protocols can be divided into two groups. resource reservation protocols can be divided into two groups.
First, there are protocols where it is the responsibility of the First, there are protocols where it is the responsibility of the
end-points or their proxies to initiate refresh messages. These end-points or their proxies to initiate refresh messages. These
messages are forwarded along the path of the data flow refreshing messages are forwarded along the path of the data flow refreshing
the corresponding reservation states in each router affected by the corresponding reservation states in each router affected by
the flow. Secondly, there are other protocols, where routers and the flow. Secondly, there are other protocols, where routers and
end-points have their own schedule for the reservation state end-points have their own schedule for the reservation state
skipping to change at page 8, line 31 skipping to change at line 371
3.2.5 Resource Reservation Protocol Orientation 3.2.5 Resource Reservation Protocol Orientation
Definition: Definition:
The orientation of a resource reservation protocol tells which end The orientation of a resource reservation protocol tells which end
of the protocol communication initiates the allocation of the of the protocol communication initiates the allocation of the
network resources. Thus, the protocol can be sender or receiver network resources. Thus, the protocol can be sender or receiver
initiated, depending on the location of the data flow source initiated, depending on the location of the data flow source
(sender) and destination (receiver) compared to the reservation (sender) and destination (receiver) compared to the reservation
initiator. initiator.
Feher, Nemeth, Korn, Cselenyi Expires January 2006 [Page 7]
Discussion: Discussion:
In the case of sender-initiated protocols the resource reservation In the case of sender-initiated protocols the resource reservation
propagates the same directions as of the data flow. Consequently, propagates the same directions as of the data flow. Consequently,
in the case of receiver-initiated protocols the signaling messages in the case of receiver-initiated protocols the signaling messages
reserving resources are forwarded backward on the path of the data reserving resources are forwarded backward on the path of the data
flow. Due to the asymmetric routing nature of the Internet, in flow. Due to the asymmetric routing nature of the Internet, in
this latter case, the path of the desired data flow should be this latter case, the path of the desired data flow should be
known before the reservation initiator would be able to send the known before the reservation initiator would be able to send the
resource allocation messages. For example in the case of RSVP, the resource allocation messages. For example in the case of RSVP, the
RSVP PATH message, traveling from the data flow sources towards RSVP PATH message, traveling from the data flow sources towards
the destinations, first marks the path of the data flow on which the destinations, first marks the path of the data flow on which
the resource allocation messages will travel backward. the resource allocation messages will travel backward.
This definition considers only protocols that reserve resources This definition considers only protocols that reserve resources
for just one data flow between the end-nodes. The reservation for just one data flow between the end-nodes. The reservation
orientation of protocols reserving more than one data flow is not orientation of protocols that reserve more than one data flow is
defined here. not defined here.
Issues: Issues:
The location of the reservation initiator affects the basics of The location of the reservation initiator affects the basics of
the resource reservation protocols and therefore it is an the resource reservation protocols and therefore is an important
important design decision. In the case of multicast QoS sessions, aspect of characterization. Most importantly, in the case of
the sender-oriented protocols require the traffic sources to multicast QoS sessions, the sender-oriented protocols require the
maintain a list of receivers and send their allocation messages traffic sources to maintain a list of receivers and send their
considering the different requirements of the receivers. Using allocation messages considering the different requirements of the
multicast QoS sessions, the receiver-oriented protocols give the receivers. Using multicast QoS sessions, the receiver-oriented
chance to the receivers to manage their own resource allocation protocols enable the receivers to manage their own resource
requests and thus ease the task of the sources. allocation requests and thus ease the task of the sources.
Feher, Nemeth, Korn, Cselenyi Expires January 2006 [Page 8]
3.3 Router Load Factors 3.3 Router Load Factors
The router load expressing the utilization of the device naturally When a router is under "load", it means that there are tasks its
affects the performance of the router. During the benchmarking CPU(s) must attend to; and/or that its memory contains data it must
process several load conditions have to be examined. keep track of; and/or that its interface buffers are utilized to
some extent; etc. Unfortunately, we cannot assume that the full
internal state of a router can be monitored during a benchmark;
rather, we must consider the router to be a black box.
This group of definitions describes different load components that We need to look at router "load" in a way that makes this "load"
impact only a specific part of the resource reservation capable measurable and controllable. Instead of focusing on the internal
router. processes of a router, we will consider the external, and therefore
observable, measurable and controllable processes that result in
"load".
In this chapter we introduce several ways of creating "load" on a
router; we will refer to these as "load factors" henceforth. These
load factors are defined so that they each impact the performance of
the router in a different way (or by different means), by utilizing
different components of a resource reservation capable router as
separately as possible.
During a benchmark, the performance of the device under test will
have to be measured under different controlled load conditions, that
is, with different values of these load factors.
3.3.1 Best-Effort Traffic Load Factor 3.3.1 Best-Effort Traffic Load Factor
Definition: Definition:
The best-effort traffic load factor is defined as the volume of The best-effort traffic load factor is defined as the number and
the best-effort data traffic that traverses the router in a length of equal-sized best-effort data packets that traverses the
second. router in a second.
Discussion: Discussion:
Forwarding the best-effort data packets, which requires obtaining Forwarding the best-effort data packets, which requires obtaining
the routing information and transferring the data packet between the routing information and transferring the data packet between
network interfaces, requires processing power, which is related to network interfaces, requires processing power. This load factor
this load factor. creates load on the CPU(s) and buffers of the router.
For the purpose of benchmarking we define a traffic flow as a
stream of equal-sized packets with even interpacket delay. It is
possible to specify traffic with varying packet sizes as a
superposition of multiple best-effort traffic flows as they are
defined here.
Issues: Issues:
The same amount of data segmented into differently sized packets The same amount of data segmented into differently sized packets
causes different amounts of load on the router, which has to be causes different amounts of load on the router, which has to be
considered during the benchmarking measurements. considered during benchmarking measurements. The measurement unit
of this load factor reflects this as well.
Feher, Nemeth, Korn, Cselenyi Expires January 2006 [Page 9]
Measurement unit: Measurement unit:
bits per second (bps) This load factor has a composite unit of [packets per second
(pps); bytes]. For example, [5 pps; 100 bytes] means five pieces
of one-hundred-byte packets per second.
3.3.2 Distinguished Traffic Load Factor 3.3.2 Distinguished Traffic Load Factor
Definition: Definition:
The distinguished traffic load factor is defined as the volume of The distinguished traffic load factor is defined as the number and
the distinguished data traffic that traverses the router in a length of the distinguished data packets that traverses the router
second. in a second.
Discussion: Discussion:
Similarly to the best-effort data, forwarding the distinguished Similarly to the best-effort data, forwarding the distinguished
data packets requires obtaining the routing information and data packets requires obtaining the routing information and
transferring the data packet between network interfaces. However, transferring the data packet between network interfaces. However,
in this case packets have to be classified as well, which requires in this case packets have to be classified as well, which requires
additional processing capacity. additional processing capacity.
For the purpose of benchmarking we define a traffic flow as a
stream of equal-sized packets with even interpacket delay. It is
possible to specify traffic with varying packet sizes as a
superposition of multiple distinguished traffic flows as they are
defined here.
Issues: Issues:
Just as in the best-effort case, the same amount of data segmented Just as in the best-effort case, the same amount of data segmented
into differently sized packets causes different amounts of load on into differently sized packets causes different amounts of load on
the router, which has to be considered during the benchmarking the router, which has to be considered during the benchmarking
measurements. measurements. The measurement unit of this load factor reflects
this as well.
Measurement unit: Measurement unit:
bits per second (bps) This load factor has a composite unit of [packets per second
(pps); bytes]. For example, [5 pps; 100 bytes] means five pieces
of one-hundred-byte packets per second.
3.3.3 Session Load Factor 3.3.3 Session Load Factor
Definition: Definition:
The session load factor is the number of QoS sessions the router The session load factor is the number of QoS sessions the router
is keeping track of. is keeping track of.
Discussion: Discussion:
Resource reservation capable routers maintain reservation states Resource reservation capable routers maintain reservation states
keeping track of the QoS sessions. Obviously, the more reservation to keep track of QoS sessions. Obviously, the more reservation
states are registered with the router, the more complex the states are registered with the router, the more complex the
traffic classification becomes, and the longer time it takes to traffic classification becomes, and the more time it takes to look
look up the corresponding resource reservation sate. Moreover, not up the corresponding resource reservation state. Moreover, not
only the traffic flows, but also the signaling messages that only the traffic flows, but also the signaling messages that
control the reservation states have to be identified first, before control the reservation states have to be identified first, before
taking any other action, and this kind of classification also taking any other action, and this kind of classification also
means extra work for the router. means extra work for the router.
Feher, Nemeth, Korn, Cselenyi Expires January 2006 [Page 10]
In the case of soft-state resource reservation protocols, the In the case of soft-state resource reservation protocols, the
session load also affects reservation state maintenance. For session load also affects reservation state maintenance. For
example, the supervision of timers that watchdog the reservation example, the supervision of timers that watchdog the reservation
state refreshes may cause further load on the router. state refreshes may cause further load on the router.
This load factor utilizes the CPU(s), the main memory and the
session management logic (e.g. content addressable memory), if
any, of the resource reservation capable router.
Measurement unit: Measurement unit:
This factor is measured by the number of QoS sessions impacting This load component is measured by the number of QoS sessions that
the router, thus it has no unit. impact the router.
3.3.4 Signaling Intensity Load Factor 3.3.4 Signaling Intensity Load Factor
Definition: Definition:
The signaling intensity load factor is defined as the number of The signaling intensity load factor is the number of signaling
signaling messages that hit the router during one second. messages that are presented at the input interfaces of the router
during one second.
Discussion: Discussion:
The processing of signaling messages requires processor power that The processing of signaling messages requires processor power that
raises the load on the control plane of the router. raises the load on the control plane of the router.
In routers where the control plane and the data plane are not In routers where the control plane and the data plane are not
totally independent (e.g. certain parts of the tasks are served by totally independent (e.g. certain parts of the tasks are served by
the same processor; or the architecture has common memory buffers, the same processor; or the architecture has common memory buffers,
transfer buses or any other resources) the signaling load can have transfer buses or any other resources) the signaling load can have
an impact on the router's packet forwarding performance as well. an impact on the router's packet forwarding performance as well.
Naturally, just as everywhere else in this document, the term Naturally, just as everywhere else in this document, the term
"signaling messages" refer only to the resource reservation "signaling messages" refer only to the resource reservation
protocol related primitives. protocol related primitives.
Issues: Issues:
Most of the resource reservation protocols have several protocol Most resource reservation protocols have several protocol
primitives realized by different signaling message types. Each of primitives realized by different signaling message types. Each of
these message types may require a different amount of processing these message types may require a different amount of processing
power from the router. This fact has to be considered during the power from the router. This fact has to be considered during the
benchmarking measurements. benchmarking measurements.
Measurement unit: Measurement unit:
The unit of this factor is 1/second. The unit of this factor is signaling messages/second.
3.3.5 Signaling Burst Load Factor 3.3.5 Signaling Burst Load Factor
Definition: Definition:
The signaling burst load factor is defined as the number of The signaling burst load factor is defined as the number of
signaling messages that arrive to one input port of the router signaling messages that arrive to one input port of the router
back-to-back ([1]), causing persistent load on the signaling back-to-back ([1]), causing persistent load on the signaling
message handler. message handler.
Feher, Nemeth, Korn, Cselenyi Expires January 2006 [Page 11]
Discussion: Discussion:
The definition focuses on one input port only and does not The definition focuses on one input port only and does not
consider the traffic arriving at the other input ports. consider the traffic arriving at the other input ports.
As a consequence, a set of messages arriving at different ports, As a consequence, a set of messages arriving at different ports,
but with such a timing that would be a burst if the messages but with such a timing that would be a burst if the messages
arrived at the same port, is not considered to be a burst. The arrived at the same port, is not considered to be a burst. The
reason for this is that it is not guaranteed at a black-box test reason for this is that it is not guaranteed in a black-box test
that this would have the same effect on the router as a burst that this would have the same effect on the router as a burst
(incoming at the same interface) has. (incoming at the same interface) has.
This definition conforms to the burst definition given in [2]. This definition conforms to the burst definition given in [2].
Issues: Issues:
Most of the resource reservation protocols have several protocol Most of the resource reservation protocols have several protocol
primitives realized by different signaling message types. Bursts primitives realized by different signaling message types. Bursts
built up of different messages may have a different effect on the built up of different messages may have a different effect on the
router. Consequently, during measurements the content of the burst router. Consequently, during measurements the content of the burst
has to be considered as well. has to be considered as well.
Likewise, the first one of multiple idempotent signaling messages
that each accomplish exactly the same end will probably not take
the same amount of time to be processed as subsequent ones.
Benchmarking methodology will have to consider the intended effect
of the signaling messages, as well as the state of the router at
the time of their arrival.
Measurement unit: Measurement unit:
This load factor is measured by the number of messages in the This load factor is characterized by the number of messages in the
burst, thus it has no unit. burst.
3.4 Performance Metrics 3.4 Performance Metrics
This group of definitions is a collection of measurable quantities This group of definitions is a collection of measurable quantities
that describe the impact the different load components have on the that describe the performance impact the different load components
router. have on the router.
During a benchmark, the values of these metrics will have to be
measured under different load conditions.
3.4.1 Signaling Message Handling Time 3.4.1 Signaling Message Handling Time
Definition: Definition:
The signaling message handling time (or, in short, signal handling The signaling message handling time (or, in short, signal handling
time) is the latency ([1]) of a signaling message passing through time) is the latency ([1], for store-and-forward devices) of a
the router. signaling message passing through the router.
Discussion: Discussion:
The router interprets the signaling messages, acts based on their The router interprets the signaling messages, acts based on their
content and usually forwards them in an unmodified or modified content and usually forwards them in an unmodified or modified
form. Thus the message handling time is usually longer than the form. Thus the message handling time is usually longer than the
forwarding time of data packets of the same size. forwarding time of data packets of the same size.
Feher, Nemeth, Korn, Cselenyi Expires January 2006 [Page 12]
There might be signaling message primitives, however, that are There might be signaling message primitives, however, that are
drained or generated by the router, like certain refresh messages. drained or generated by the router, like certain refresh messages.
In this case the signal handling time is immeasurable, therefore In this case the signal handling time is not necessarily
it is not defined for such messages. measureable, therefore it is not defined for such messages.
In the case of signaling messages that carry information In the case of signaling messages that carry information
pertaining to multicast flows, the router might issue multiple pertaining to multicast flows, the router might issue multiple
signaling messages after processing them. In this case, by signaling messages after processing them. In this case, by
definition, the signal handling time is the latency between the definition, the signal handling time is the latency between the
incoming signaling message and the last outgoing signaling message incoming signaling message and the last outgoing signaling message
related to the received one. related to the received one.
The signal handling time is an important characteristic as it The signal handling time is an important characteristic as it
directly affects the setup time of a QoS session. directly affects the setup time of a QoS session.
Issues: Issues:
The signal handling time may be dependent on the type of the The signal handling time may be dependent on the type of the
signaling message. For example, it usually takes a shorter time signaling message. For example, it usually takes a shorter time
for the router to remove a reservation state than to set it up. for the router to remove a reservation state than to set it up.
This fact has to be considered during the benchmarking process. This fact has to be considered during the benchmarking process.
As noted above, the first one of multiple idempotent signaling
messages that each accomplish exactly the same end will probably
not take the same amount of time to be processed as subsequent
ones. Benchmarking methodology will have to consider the intended
effect of the signaling messages, as well as the state of the
router at the time of their arrival.
Measurement unit: Measurement unit:
The unit of the signaling message handling time is the second. The unit of the signaling message handling time is the second.
3.4.2 Distinguished Traffic Delay 3.4.2 Distinguished Traffic Delay
Definition: Definition:
Distinguished traffic delay is the latency ([1]) of a Distinguished traffic delay is the latency ([1], for store-and-
distinguished data packet passing through the tested router forward devices) of a distinguished data packet passing through
device. the tested router device.
Discussion: Discussion:
Distinguished traffic packets must be classified first in order to Distinguished traffic packets must be classified first in order to
assign the network resources dedicated to the flow. The time of assign the network resources dedicated to the flow. The time of
the classification is added to the usual forwarding time the classification is added to the usual forwarding time
(including the queuing) that a router would spend on the packet (including the queuing) that a router would spend on the packet
without any resource reservation capability. This classification without any resource reservation capability. This classification
procedure might be quite time consuming in routers with vast procedure might be quite time consuming in routers with vast
amounts of reservation states. amounts of reservation states.
There are routers where the processing power is shared between the There are routers where the processing power is shared between the
control plane and the data plane. This means that the processing control plane and the data plane. This means that the processing
of signaling messages may have an impact on the data forwarding of signaling messages may have an impact on the data forwarding
performance of the router. In this case the distinguished traffic performance of the router. In this case the distinguished traffic
delay metric also indicates the influence the two planes have on delay metric also indicates the influence the two planes have on
each other. each other.
Feher, Nemeth, Korn, Cselenyi Expires January 2006 [Page 13]
Issues: Issues:
Queuing of the incoming data packets in routers can bias this Queuing of the incoming data packets in routers can bias this
metric, so the measurement procedures have to consider this metric, so the measurement procedures have to consider this
effect. effect.
Measurement unit: Measurement unit:
The unit of the distinguished traffic delay is the second. The unit of the distinguished traffic delay is the second.
3.4.3 Best-effort Traffic Delay 3.4.3 Best-effort Traffic Delay
skipping to change at page 13, line 34 skipping to change at line 700
indicator of the influence the two planes have on each other. indicator of the influence the two planes have on each other.
Issues: Issues:
Queuing of the incoming data packets in routers can bias this Queuing of the incoming data packets in routers can bias this
metric as well, so measurement procedures have to consider this metric as well, so measurement procedures have to consider this
effect. effect.
Measurement unit: Measurement unit:
The unit of the best-effort traffic delay is the second. The unit of the best-effort traffic delay is the second.
3.4.4 Signaling Message Loss 3.4.4 Signaling Message Deficit
Definition: Definition:
Signaling message loss is the ratio of the actual and the expected Signaling message deficit is one minus the ratio of the actual and
number of signaling messages leaving a resource reservation the expected number of signaling messages leaving a resource
capable router, subtracted from one. reservation capable router.
Discussion: Discussion:
This definition gives the same value as the ratio of the lost and This definition gives the same value as the ratio of the lost
the expected messages. The reason for choosing the given (that is, not forwarded or not generated) and the expected
definition is that the number of lost messages cannot be measured messages. The above calculation must be used because the number of
directly. lost messages cannot be measured directly.
There are certain types of signaling messages that are required to There are certain types of signaling messages that reservation
be forwarded by reservation capable routers as soon as their capable routers are required to forward as soon as their
processing is finished. However, due to the high router load or processing is finished. However, due to lack of resources or other
for other reasons, the forwarding or even the processing of these reasons, the forwarding or even the processing of these signaling
signaling messages might be canceled. There are other kinds of messages might not take place.
signaling messages, that should have been generated by the router,
without any corresponding incoming message. In case of high router Certain other kinds of signaling messages must be generated by the
load, it is possible that such a message never leaves the router. router in the absence of any corresponding incoming message. It is
possible that an overloaded router does not have the resources
necessary to generate such a message.
Feher, Nemeth, Korn, Cselenyi Expires January 2006 [Page 14]
To characterize these situations we introduce the signaling To characterize these situations we introduce the signaling
message loss metric expressing the ratio of the signaling messages message deficit metric that expresses the ratio of the signaling
that actually have left the router and those ones that were messages that have actually left the router and those ones that
expected to leave the router. were expected to leave the router. We subtract this ratio from one
in order to obtain a loss-type metric instead of a "message
survival metric".
Since the most frequent reason for signaling message loss is high Since the most frequent reason for signaling message deficit is
router load, this metric is suitable for sounding out the high router load, this metric is suitable for sounding out the
scalability limits of resource reservation capable routers. scalability limits of resource reservation capable routers.
During the measurements one must be able to determine whether a During the measurements one must be able to determine whether a
signaling message is still in the queues of the router or if it signaling message is still in the queues of the router or if it
has already been dropped. For this reason we define a signaling has already been dropped. For this reason we define a signaling
message as lost if no forwarded signaling message is emitted message as lost if no forwarded signaling message is emitted
within a reasonably long time period. This period is defined along within a reasonably long time period. This period is defined along
with the benchmarking methodology. with the benchmarking methodology.
Measurement unit: Measurement unit:
This measure has no unit; it is expressed as a real number, which This measure has no unit; it is expressed as a real number, which
is between zero and one, including the limits. is between zero and one, including the limits.
3.4.5 Session Maintenance Capacity 3.4.5 Session Maintenance Capacity
Definition: Definition:
The session maintenance capacity metric is used in the case of The session maintenance capacity metric is used in the case of
soft-state resource reservation protocols only. It is defined as soft-state resource reservation protocols only. It is defined as
the ratio of the number of QoS sessions actually maintained and the ratio of the number of QoS sessions actually being maintained
the number of QoS sessions that should have been maintained during and the number of QoS sessions that should have been maintained
one refresh period. during one refresh period.
Discussion: Discussion:
For soft-state protocols maintaining a QoS session means For soft-state protocols maintaining a QoS session means
refreshing the reservation states associated with it. refreshing the reservation states associated with it.
When a soft-state resource reservation capable router is When a soft-state resource reservation capable router is
overloaded, it may happen that the router is not able to refresh overloaded, it may happen that the router is not able to refresh
all the registered reservation states, because it does not have all the registered reservation states, because it does not have
the time to run the state refresh task. In this case sooner or the time to run the state refresh task. In this case sooner or
later some QoS sessions will be lost even if the endpoints still later some QoS sessions will be lost even if the endpoints still
require their maintenance. require their maintenance.
The session maintenance capacity sounds out the maximal number of The session maintenance capacity sounds out the maximal number of
QoS sessions that the router is capable of maintaining. QoS sessions that the router is capable of maintaining.
Issues: Issues:
The actual process of session maintenance is protocol and The actual process of session maintenance is protocol and
implementation dependent, so is the method to examine that a implementation dependent, thus so is the method to examine whether
session is maintained or not. a session is maintained or not.
In the case of soft-state resource reservation protocols a router In the case of soft-state resource reservation protocols a router
that fails to maintain a QoS session may not emit refresh that fails to maintain a QoS session may not emit refresh
Feher, Nemeth, Korn, Cselenyi Expires January 2006 [Page 15]
signaling messages either. This has direct consequences on the signaling messages either. This has direct consequences on the
signaling message loss metric. signaling message deficit metric.
Measurement unit: Measurement unit:
This measure has no unit; it is expressed as a real number, which This measure has no unit; it is expressed as a real number, which
is between zero and one (including the limits). is between zero and one (including the limits).
3.5 Scalability Limit 3.5 Router Load Conditions and Scalability Limit
Depending mainly, but not exclusively, on the overall load of a
router, it can be in exactly of the following two conditions at a
time: loss-free or lossy. These conditions are defined below, along
with the scalability limit, which is the 'boundary' between them.
3.5.1 Loss-Free Condition
Definition: Definition:
The scalability limit of the router is the critical load A router is in loss-free condition, or loss-free state, if the
condition, when the router is still in the steady state but the extent to which its internal resources are utilized interferes
smallest amount of additional load would drive it to the with neither the correctness nor the timeliness of its operation.
overloaded state.
Discussion: Discussion:
All existing routers have finite buffer memory and finite All existing routers have finite buffer memory and finite
processing power. In the steady state of the router, the buffer processing power. If a router is in loss-free state, the buffers
memories are not fully utilized and the processing power is enough of the router still contain enough free space to accommodate the
to cope with all tasks running on the router. As the router load next incoming packet when it arrives. Also, the router has enough
increases the buffers are starting to fill up and/or the router processing power to cope with all its tasks, thus all required
has to postpone more and more tasks. However, there is a certain operations are carried out within the time the protocol
point where no more buffer memory is available, or a task cannot specification allows; or, if this time is not specified by the
be postponed any longer; thus the router is forced to drop a protocol, then in "reasonable time" (which is then defined in the
packet or an activity. This is the overloaded state of the benchmarks). Similar considerations can be applied to other
resource reservation capable router, which can be recognized by resources a router may have, if any; in loss-free states, the
the fact that some kind of data (signaling or packet) or task utilization of these resources still allows the router to carry
(e.g. QoS session maintenance) loss occurs. out its tasks in accordance with applicable protocol
specifications and in "reasonable time".
Note that loss-free states as defined above are not related to the
reservation states of resource reservation protocols. The word
"state" is used to mean "condition".
Also note that it is irrelevant what internal reason causes a
router to fail to perform in accordance with protocol
specifications or in "reasonable time"; if it is not high load but
-- for example -- an implementation error that causes the device
to perform inadequately, it still cannot be said to be in a loss-
free state. The same applies to the random early dropping of
packets in order to prevent congestion. In a black-box measurement
it is impossible to determine whether a packet was dropped as part
of a congestion control mechanism or because the router was unable
to forward it; therefore, if packet loss is observed, the router
is by definition in lossy state (lossy condition).
Feher, Nemeth, Korn, Cselenyi Expires January 2006 [Page 16]
Related definitions:
Lossy Condition
Scalability Limit
3.5.2 Lossy Condition
Definition:
A router is in lossy condition, or lossy state, if it cannot
perform its duties adequately for some reason; that is, if it
doesn't meet protocol specifications, or -- if time-related
specifications are missing -- doesn't complete some operations in
"reasonable time" (which is then defined in the benchmarks).
Discussion:
A router may be in a lossy state for several reasons, including
but not necessarily limited to the following:
a) Buffer memory has run out, so either an incoming or a buffered
packet has to be dropped.
b) The router doesn't have enough processing power to cope with
all its duties. Some required operations are skipped, aborted
or suffer unacceptable delays.
c) Some other finite internal resource is exhausted.
d) The router runs a defective (non-conforming) protocol
implementation.
e) Hardware malfunction.
Related definitions:
Loss-Free Condition (especially the discussion of congestion
control mechanisms that cause packet loss)
Scalability Limit
3.5.3 Scalability Limit
Definition:
The scalability limits of a router are the boundary load
conditions where the router is still in a loss-free state but the
smallest amount of additional load would drive it to a lossy
state.
Discussion:
An unloaded router that operates correctly is in loss-free state.
As load increases, the resources of the router are becoming more
and more utilized. There is a certain point where the router
leaves the loss-free state and enters the lossy state. Note that
such a point may be impossible to reach in some cases (for
example, the bandwidth of the physical medium prevents increasing
the traffic load any further).
A particular load condition can be identified by the corresponding
values of the load factors (as defined in 3.3 Router Load Factors)
impacting the router. These values can be represented as a 7-tuple
of numbers (5 is the number of load factors, but two of them have
Feher, Nemeth, Korn, Cselenyi Expires January 2006 [Page 17]
composite units and thus require two numbers each to express). We
can think of these tuples as vectors that correspond either to
loss-free state or to lossy state. The scalability limit of the
router is, then, the boundary between the sets of vectors
corresponding to loss-free and lossy states. Finding these
boundary points if one of the objectives of benchmarking.
Related definitions:
Loss-Free Condition
Lossy Condition
Feher, Nemeth, Korn, Cselenyi Expires January 2006 [Page 18]
4. Security Considerations 4. Security Considerations
As this document only provides terminology and describes neither a As this document only provides terminology and describes neither a
protocol nor an implementation or a procedure, there are no security protocol nor an implementation or a procedure, there are no security
considerations associated with it. considerations associated with it.
5. IANA Considerations 5. IANA Considerations
This document has no actions for IANA. This document requires no IANA actions.
6. Acknowledgements 6. Acknowledgements
We would like to thank the following individuals for their help in We would like to thank the following individuals for their help in
the research and development work, which contributed to form this the research and development work which contributed to the creation
document: Joakim Bergkvist and Norbert Vegh from Telia Research AB, of this document: Joakim Bergkvist and Norbert Vegh from Telia
Sweden; Balazs Szabo, Gabor Kovacs and Peter Vary from the High Research AB, Sweden; Balazs Szabo, Gabor Kovacs and Peter Vary from
Speed Networks Laboratory, Budapest University of Technology and the High Speed Networks Laboratory, Department of Telecommunication
and Mediainformatics, Budapest University of Technology and
Economics, Hungary. Economics, Hungary.
7. References 7. References
7.1 Normative References 7.1 Normative References
[1] S. Bradner, "Benchmarking Terminology for Network [1] S. Bradner, "Benchmarking Terminology for Network
Interconnection Devices", RFC 1242, July 1991 Interconnection Devices", RFC 1242, July 1991
[2] R. Mandeville, "Benchmarking Terminology for LAN Switching [2] R. Mandeville, "Benchmarking Terminology for LAN Switching
Devices", RFC 2285, February 1998 Devices", RFC 2285, February 1998
7.2 Informative References 7.2 Informative References
[3] B. Braden, Ed., et. al., "Resource Reservation Protocol (RSVP) [3] B. Braden, Ed., et. al., "Resource Reservation Protocol (RSVP)
- Version 1 Functional Specification", RFC 2205, September - Version 1 Functional Specification", RFC 2205, September
1997. 1997.
[4] R. Hancock, et al., "Next Steps in Signaling: Framework" [4] R. Hancock, et al., "Next Steps in Signaling (NSIS):
(draft-ietf-nsis-fw-07.txt) (Internet draft: work in progress), Framework", RFC4080, June 2005
November 2004
[5] P. Pan, H. Schulzrinne, "YESSIR: A Simple Reservation Mechanism [5] P. Pan, H. Schulzrinne, "YESSIR: A Simple Reservation Mechanism
for the Internet", Computer Communication Review, on-line for the Internet", Computer Communication Review, on-line
version, volume 29, number 2, April 1999 version, volume 29, number 2, April 1999
[6] L. Delgrossi, L. Berger, "Internet Stream Protocol Version 2 [6] L. Delgrossi, L. Berger, "Internet Stream Protocol Version 2
(ST2) Protocol Specification - Version ST2+", RFC 1819, August (ST2) Protocol Specification - Version ST2+", RFC 1819, August
1995 1995
[7] P. White, J. Crowcroft, "A Case for Dynamic Sender-Initiated [7] P. White, J. Crowcroft, "A Case for Dynamic Sender-Initiated
Reservation in the Internet", Journal on High Speed Networks, Reservation in the Internet", Journal on High Speed Networks,
Special Issue on QoS Routing and Signaling, Vol. 7 No. 2, 1998 Special Issue on QoS Routing and Signaling, Vol. 7 No. 2, 1998
Feher, Nemeth, Korn, Cselenyi Expires January 2006 [Page 19]
[8] J. Bergkvist, D. Ahlard, T. Engborg, K. Nemeth, G. Feher, I. [8] J. Bergkvist, D. Ahlard, T. Engborg, K. Nemeth, G. Feher, I.
Cselenyi, M. Maliosz, "Boomerang : A Simple Protocol for Cselenyi, M. Maliosz, "Boomerang : A Simple Protocol for
Resource Reservation in IP Networks", Vancouver, IEEE Real-Time Resource Reservation in IP Networks", Vancouver, IEEE Real-Time
Technology and Applications Symposium, June 1999 Technology and Applications Symposium, June 1999
[9] A. Eriksson, C. Gehrmann, "Robust and Secure Light-weight [9] A. Eriksson, C. Gehrmann, "Robust and Secure Light-weight
Resource Reservation for Unicast IP Traffic", International WS Resource Reservation for Unicast IP Traffic", International WS
on QoS'98, IWQoS'98, May 18-20, 1998 on QoS'98, IWQoS'98, May 18-20, 1998
[10] J. Manner, X. Fu, "Analysis of Existing Quality of Service [10] J. Manner, X. Fu, "Analysis of Existing Quality of Service
Signaling Protocols" (draft-ietf-nsis-signalling-analysis- Signaling Protocols", RFC4094, May 2005
05.txt) (Internet draft: work in progress), December 2004
[11] F. Baker, C. Iturralde, F. Le Faucheur, B. Davie, "Aggregation [11] F. Baker, C. Iturralde, F. Le Faucheur, B. Davie, "Aggregation
of RSVP for IPv4 and IPv6 Reservations", RFC 3175, September of RSVP for IPv4 and IPv6 Reservations", RFC 3175, September
2001 2001
Authors' Addresses Authors' Addresses
Gabor Feher Gabor Feher
Budapest University of Technology and Economics Budapest University of Technology and Economics
Department of Telecommunications and Mediainformatics Department of Telecommunications and Mediainformatics
skipping to change at page 17, line 39 skipping to change at line 985
Krisztian Nemeth Krisztian Nemeth
Budapest University of Technology and Economics Budapest University of Technology and Economics
Department of Telecommunications and Mediainformatics Department of Telecommunications and Mediainformatics
Magyar Tudosok krt. 2, H-1117, Budapest, Hungary Magyar Tudosok krt. 2, H-1117, Budapest, Hungary
Phone: +36 1 463-1565 Phone: +36 1 463-1565
Email: Krisztian.Nemeth@tmit.bme.hu Email: Krisztian.Nemeth@tmit.bme.hu
Andras Korn Andras Korn
Budapest University of Technology and Economics Budapest University of Technology and Economics
Institute of Mathematics, Department of Analysis Department of Telecommunication and Mediainformatics
Egry Jozsef u. 2, H-1111 Budapest, Hungary Magyar Tudosok krt. 2, H-1117, Budapest, Hungary
Phone: +36 1 463-2475 Phone: +36 1 463-2664
Email: Korn@math.bme.hu Email: andras.korn@tmit.bme.hu
Istvan Cselenyi Istvan Cselenyi
TeliaSonera International Carrier TeliaSonera International Carrier
Vaci ut 22-24, H-1132 Budapest, Hungary Vaci ut 22-24, H-1132 Budapest, Hungary
Phone: +36 1 412-2705 Phone: +36 1 412-2705
Email: Istvan.Cselenyi@teliasonera.com Email: Istvan.Cselenyi@teliasonera.com
Disclaimer of Validity Disclaimer of Validity
The IETF takes no position regarding the validity or scope of any The IETF takes no position regarding the validity or scope of any
Intellectual Property Rights or other rights that might be claimed Intellectual Property Rights or other rights that might be claimed
to pertain to the implementation or use of the technology to pertain to the implementation or use of the technology
described in this document or the extent to which any license described in this document or the extent to which any license
under such rights might or might not be available; nor does it under such rights might or might not be available; nor does it
represent that it has made any independent effort to identify any represent that it has made any independent effort to identify any
such rights. Information on the IETF's procedures with respect to
rights in IETF Documents can be found in BCP 78 and BCP 79. Feher, Nemeth, Korn, Cselenyi Expires January 2006 [Page 20]
such rights. Information on the procedures with respect to
rights in RFC documents can be found in BCP 78 and BCP 79.
Copies of IPR disclosures made to the IETF Secretariat and any Copies of IPR disclosures made to the IETF Secretariat and any
assurances of licenses to be made available, or the result of an assurances of licenses to be made available, or the result of an
attempt made to obtain a general license or permission for the use attempt made to obtain a general license or permission for the use
of such proprietary rights by implementers or users of this of such proprietary rights by implementers or users of this
specification can be obtained from the IETF on-line IPR repository specification can be obtained from the IETF on-line IPR repository
at http://www.ietf.org/ipr. at http://www.ietf.org/ipr.
The IETF invites any interested party to bring to its attention The IETF invites any interested party to bring to its attention
any copyrights, patents or patent applications, or other any copyrights, patents or patent applications, or other
skipping to change at line 866 skipping to change at line 1039
Disclaimer Disclaimer
This document and the information contained herein are provided This document and the information contained herein are provided
on an "AS IS" basis and THE CONTRIBUTOR, THE ORGANIZATION HE/SHE on an "AS IS" basis and THE CONTRIBUTOR, THE ORGANIZATION HE/SHE
REPRESENTS OR IS SPONSORED BY (IF ANY), THE INTERNET SOCIETY AND REPRESENTS OR IS SPONSORED BY (IF ANY), THE INTERNET SOCIETY AND
THE INTERNET ENGINEERING TASK FORCE DISCLAIM ALL WARRANTIES, THE INTERNET ENGINEERING TASK FORCE DISCLAIM ALL WARRANTIES,
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTY THAT EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTY THAT
THE USE OF THE INFORMATION HEREIN WILL NOT INFRINGE ANY RIGHTS OR THE USE OF THE INFORMATION HEREIN WILL NOT INFRINGE ANY RIGHTS OR
ANY IMPLIED WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A ANY IMPLIED WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A
PARTICULAR PURPOSE. PARTICULAR PURPOSE.
Feher, Nemeth, Korn, Cselenyi Expires January 2006 [Page 21]
 End of changes. 

This html diff was produced by rfcdiff 1.25, available from http://www.levkowetz.com/ietf/tools/rfcdiff/