draft-ietf-bmwg-benchres-term-01.txt   draft-ietf-bmwg-benchres-term-02.txt 
Network Working Group Gabor Feher, BUTE Benchmarking Working Group Gabor Feher, BUTE
INTERNET-DRAFT Istvan Cselenyi, TRAB INTERNET-DRAFT Istvan Cselenyi, TRAB
Expiration Date: May 2002 Andras Korn, BUTE Expiration Date: May 2003 Andras Korn, BUTE
November 2001 November 2002
Benchmarking Terminology for Routers Supporting Resource Reservation Benchmarking Terminology for Routers Supporting Resource Reservation
<draft-ietf-bmwg-benchres-term-01.txt> <draft-ietf-bmwg-benchres-term-02.txt>
1. Status of this Memo 1. Status of this Memo
This document is an Internet-Draft and is in full conformance with This document is an Internet-Draft and is in full conformance with
all provisions of Section 10 of RFC2026. all provisions of Section 10 of RFC2026.
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 other Task Force (IETF), its areas, and its working groups. Note that other
groups may also distribute working documents as Internet- groups may also distribute working documents as Internet-
Drafts. Drafts.
skipping to change at page 1, line 46 skipping to change at line 45
2. Table of contents 2. Table of contents
1. Status of this Memo.............................................1 1. Status of this Memo.............................................1
2. Table of contents...............................................1 2. Table of contents...............................................1
3. Abstract........................................................2 3. Abstract........................................................2
4. Introduction....................................................2 4. Introduction....................................................2
5. Existing definitions............................................3 5. Existing definitions............................................3
6. Definition of Terms.............................................3 6. Definition of Terms.............................................3
6.1 Resource Reservation Protocol Basics........................3 6.1 Resource Reservation Protocol Basics........................3
6.1.1 Resource Reservation Session...........................3 6.1.1 Unicast Resource Reservation Session...................3
6.1.2 Multicast Resource Reservation Session.................4 6.1.2 Multicast Resource Reservation Session.................4
6.1.3 Resource Reservation Capable Router....................4 6.1.3 Resource Reservation Capable Router....................4
6.1.4 Signaling End-point....................................5 6.1.4 Signaling End-point....................................5
6.1.5 Reservation Initiator..................................5 6.1.5 Reservation Orientation................................5
6.1.6 Reservation Session Maintenance........................6 6.1.6 Reservation Session State..............................6
6.1.7 Signaling Path.........................................7 6.1.7 Signaling Path.........................................7
6.2 Traffic Types...............................................8 6.2 Traffic Types...............................................8
6.2.1 Premium Traffic........................................8 6.2.1 Best-Effort Data Packets...............................8
6.2.2 Best-Effort Traffic....................................8
Feher, Cselenyi, Korn Expires May 2003 [Page 1]
6.2.2 Premium Data Packets...................................8
6.3 Router Load Types...........................................9 6.3 Router Load Types...........................................9
6.3.1 Traffic Load...........................................9 6.3.1 Traffic Load...........................................9
6.3.2 Session Load...........................................9 6.3.2 Session Load...........................................9
6.3.3 Signaling Load........................................10 6.3.3 Signaling Load........................................10
6.3.4 Signaling Burst.......................................11 6.3.4 Signaling Burst.......................................11
6.4 Performance Metrics........................................11 6.4 Performance Metrics........................................11
6.4.1 Signaling Message Handling Time.......................11 6.4.1 Signaling Message Handling Time.......................11
6.4.2 Premium Traffic Delay.................................12 6.4.2 Premium Traffic Delay.................................12
6.4.3 Best-effort Traffic Delay.............................13 6.4.3 Best-effort Traffic Delay.............................12
6.4.4 Signaling Message Loss................................13 6.4.4 Signaling Message Loss................................13
6.4.5 Session Refreshing Capacity...........................14 6.4.5 Session Refreshing Capacity...........................13
6.4.6 Scalability Limit.....................................14 6.4.6 Scalability Limit.....................................14
7. Acknowledgement................................................15 7. Security Considerations........................................14
8. References.....................................................15 8. Acknowledgement................................................15
9. Authors' Addresses:............................................15 9. References.....................................................15
10. Authors' Addresses............................................16
3. Abstract 3. Abstract
The purpose of this document is to define terminology specific to the The purpose of this document is to define terminology specific to the
performance benchmarking of the resource reservation signaling of IP benchmarking of the resource reservation signaling of IP routers.
routers. These terms are used in additional documents that define These terms can be used in additional documents that define
benchmarking methodologies for routers supporting resource benchmarking methodologies for routers supporting resource
reservation and define reporting formats for the benchmarking reservation and define reporting formats for the benchmarking
measurements. measurements.
4. Introduction 4. Introduction
The IntServ over DiffServ framework [1] outlines a heterogeneous The IntServ over DiffServ framework [1] outlines a heterogeneous
Quality of Service (QoS) architecture for multi domain Internet Quality of Service (QoS) architecture for multi domain Internet
services. Signaling based resource reservation (e.g. via RSVP [2]) is services. Signaling based resource reservation (e.g. via RSVP [2]) is
an integral part of that model. While this significantly lightens the an integral part of that model. While this approach significantly
load on most of the core routers, the performance of border routers lightens the load on most of the core routers, the performance of
that handle the QoS signaling is still crucial. Therefore network border routers that handle QoS signaling is still crucial. Therefore
operators, who are planning to deploy this model, shall scrutinize network operators, who are planning to deploy this model, shall
the scalability limitations in reservation capable routers and the scrutinize the scalability limitations of reservation capable routers
impact of signaling on the forwarding performance of the routers. and the impact of signaling on the forwarding performance of the
routers.
An objective way for quantifying the scalability constraints of QoS An objective way for 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 specific resource reservation. This document defines terminology for specific
set of tests that vendors or network operators can use to measure and set of tests that vendors or network operators can use to measure and
report the signaling performance characteristics of router devices report the signaling performance characteristics of router devices
that support resource reservation protocols. The results of these that support resource reservation protocols. The results of these
tests provide comparable data for different products supporting the tests provide comparable data for different products supporting the
decision process before purchase. Moreover, these measurements decision process before purchase. Moreover, these measurements
provide input characteristics for the dimensioning of a network in provide input characteristics for the dimensioning of a network in
which resources are provisioned dynamically by signaling. Finally, which resources are provisioned dynamically by signaling. Finally,
the tests are applicable for characterizing the impact of the control the tests are applicable for characterizing the impact of the
plane signaling on the forwarding performance of routers. resource reservation signaling on the forwarding performance of the
routers.
Feher, Cselenyi, Korn Expires May 2003 [Page 2]
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) several very gained by examination of (and experimentation with) several very
different resource reservation protocols: RSVP [2], Boomerang [5], different resource reservation protocols: RSVP [2], Boomerang [5],
YESSIR [6], ST2+ [7], SDP [8] and Ticket [9]. Nevertheless, this YESSIR [6], ST2+ [7], SDP [8] and Ticket [9]. Nevertheless, this
document aspires to compose terms that are valid in general and not document defines terms that are valid in general and not restricted
restricted to these protocols. to these protocols.
5. Existing definitions 5. Existing definitions
RFC 1242 [3] "Benchmarking Terminology for Network Interconnect RFC 1242 [3] "Benchmarking Terminology for Network Interconnect
Devices" and RFC 2285 [4] "Benchmarking Terminology for LAN Switching Devices" and RFC 2285 [4] "Benchmarking Terminology for LAN Switching
Devices" contains discussions and definitions for a number of terms Devices" contains discussions and definitions for a number of terms
relevant to the benchmarking of signaling performance of reservation relevant to the benchmarking of signaling performance of reservation
capable routers and should be consulted before attempting to make use capable routers and should be consulted before attempting to make use
of this document. of this document.
For the sake of clarity and continuity this document adopts the For the sake of clarity and continuity this document adopts the
template for definitions set out in Section 2 of RFC 1242. template for definitions set out in Section 2 of RFC 1242.
Definitions are indexed and grouped together in sections for ease of Definitions are indexed and grouped together into different sections
reference. for ease of reference.
6. Definition of Terms 6. Definition of Terms
6.1 Resource Reservation Protocol Basics 6.1 Resource Reservation Protocol Basics
This group of definitions applies to various signaling based resource This group of definitions applies to various signaling based resource
reservation protocols implemented on IP router devices. reservation protocols implemented on IP router devices.
6.1.1 Resource Reservation Session 6.1.1 Unicast Resource Reservation Session
Definition: Definition:
A resource reservation session (or shortly reservation) expresses The term unicast resource reservation session (or shortly
that routers along the data path between two network nodes apply reservation session) expresses that two end-nodes explicitly
special QoS treatment to a certain traffic flow. request the network nodes, which forward their data flow, to
assign special QoS treatment for data packets belonging to the
flow.
Discussion: Discussion:
The QoS treatment is specified by giving the amount of networking The QoS treatment is defined by specifying the amount of
resources that are dedicated to the traffic flow during the length networking resources that should be dedicated to the data flow
of the reservation session. Depending on the protocol, there are during the length of the reservation session. There are different
different approaches to define the network resource requirement of approaches, how to specify the network resource requirement of a
a traffic flow. It can be described by high-level parameters, like data flow. It can be described by high-level parameters, like the
the required bandwidth, service class or the maximum traffic required bandwidth or the maximum data delay; or it can be low-
delay; or it can be low-level information, like the parameters of level information, such as the parameters of a leaky-bucket model
a leaky-bucket model of the traffic flow [10]. describing the data flow [10].
Issues: Reservation sessions must be uniquely registered in network nodes
There are resource reservation protocols, where resource assuring the QoS treatments. Practically, the transport address of
dedications in a router are unique for each resource reservation the destination end-node and the transport protocol of the
session. However, in this case the number of resource dedications communication are sufficient to distinguish the reservations,
grows along with the number of sessions and working with huge
number of resource dedications raise problems (see Reservation Feher, Cselenyi, Korn Expires May 2003 [Page 3]
Session Maintenance). Therefore, many resource reservation however in extreme cases the transport address of the source
protocols allow to bunch different reservation sessions into one should be included as well.
aggregated session, which takes only one aggregated resource
allocation for the whole bunch. The aggregation can be based on
the similar attributes of the flows, (e.g. aggregation using
DiffServ code-points [11]) or it can combine arbitrary sessions as
well.
See Also: See Also:
Reservation Session Maintenance Reservation Session State
6.1.2 Multicast Resource Reservation Session 6.1.2 Multicast Resource Reservation Session
Definition: Definition:
A multicast resource reservation session (or, in short, multicast A multicast resource reservation session (or, in short, multicast
reservation) denotes that certain QoS treatment is applied to the reservation session) denotes that end-nodes forming a multicast
packets of every traffic flow related to a multicast group. group ask the network nodes, which forward the data packets of the
multicast group, to assign a certain QoS treatment to their data
traffic.
Discussion: Discussion:
Usually, there are several traffic sources and destinations in a In a multicast group there can be several data traffic sources and
multicast group. In order to be able to guarantee the QoS destinations. The required QoS treatment is specified the same way
parameters for each packet of the multicast flow, every router as in the case of the unicast resource reservation sessions. In
that forwards the multicast traffic must dedicate resources to the the case of multicast reservations, however, unlike in the case of
flow. unicast reservations, the amount of reserved network resources
does not have to be the same on each network node forwarding the
multicast data traffic. Multicast reservations must be registered
in network nodes forwarding the associated data traffic similarly
as it happens in the unicast case.
Generally, there are two types of multicast resource reservations: Generally, there are two types of multicast resource reservations:
many-to-many and one-to-many multicast reservations. Those of the many-to-many and one-to-many. Those of the first type allow
first type allow traffic to be originated from several sources, multicast data traffic to be originated from several sources,
while those of the second type permit only one traffic source in while those of the second type permit only one fix data traffic
the whole multicast group and this source should not change during source in the whole multicast group that must not change during
the lifetime of the session. Additionally, in several cases, a the lifetime of the session.
many-to-many multicast reservation session does not require the
same amount of resources reserved in every involved router.
Depending on the resource reservation protocol, the traffic
destinations of the multicast group may request different QoS
parameters. Furthermore, the protocols may describe more than one
reservation styles expressing the resource reservation
distribution method among the involved routers. (e.g. RSVP
SE/WF/FF [2])
Issues:
Naturally, many-to-many multicast reservation capable protocols
are bound to be more complex than one-to-many or non-multicast
protocols. Usually, the router has to be aware of the location of
the traffic sources and destinations participating in the
multicast reservation in the aspect of its network interfaces,
plus the resource requirements of the traffic destinations in
order to be able to calculate the right amount of resources
dedicated to the session.
6.1.3 Resource Reservation Capable Router 6.1.3 Resource Reservation Capable Router
Definition: Definition:
By definition, a router is resource reservation capable - supports A router is resource reservation capable -- supports resource
resource reservation - if it understands a resource reservation reservation -- if it understands a resource reservation protocol
protocol that signals the set-up, tear-down and modification of that signals the set-up, tear-down and modification of resource
resource reservation sessions. reservation sessions.
Discussion: Discussion:
Resource reservation protocols define signaling messages that are Resource reservation protocols define signaling messages that are
interpreted by resource reservation capable routers. The router interpreted by resource reservation capable routers. The router
captures the signaling message and manipulates resource captures the signaling message and manipulates the resource
reservation sessions according to the content of the message. In reservation sessions and/or the reserved network resources
addition, the protocol might declare to forward the same or a according to the content of the message.
modified signaling message to other routers as well.
Issues: Issues:
There are resource reservation protocols where routers are Despite that resource reservation sessions are considered to be
required to initiate signaling messages besides the signaling unique, resource reservation capable routers might aggregate them
message forwarding. The benefits of such protocols are that and allocate network resources to these aggregated sessions at
changes in resource reservation sessions can be signaled to other once. The aggregation can be based on similar flow attributes
routers immediately, even if the change is not caused by signaling
messages directly. In contrast, the message initiation takes time Feher, Cselenyi, Korn Expires May 2003 [Page 4]
that slows down the signaling message processing, so there are (e.g. aggregation using DiffServ code-points [11]) or it can
protocols declaring instant responses, where all the signaling combine arbitrary sessions as well. While reservation aggregation
messages are forwarded to other routers immediately, avoiding the significantly lightens the signaling processing task of a resource
signaling message initiation. reservation capable router, it also requires the administration of
the aggregated flows and might also lead to the violation of the
quality guaranties of individual reservations within an
aggregation.
6.1.4 Signaling End-point 6.1.4 Signaling End-point
Definition: Definition:
A signaling end-point is a network node capable of initiating and A signaling end-point is a network node capable of initiating and
terminating resource reservation sessions. terminating resource reservation sessions.
Discussion: Discussion:
Typically, signaling end-points have a separate protocol stack Besides traditional end-systems, there is also another type of
that is capable of generating and understanding the signaling signaling end-point: the reservation gateways. Reservation
messages. However, in some special cases, the resource reservation gateways translate the signaling messages of one resource
initiation is carried out without the notice of the signaling reservation protocol into messages of another resource reservation
terminating node. For example, the Boomerang resource reservation protocol. Thus the reservation gateway represents two signaling
protocol encapsulates the reservation requests in an ICMP Echo end-points in one, as it is both a signaling terminator and a
message. This message is bounced back from the signaling signaling initiator.
terminating network node and as a result the node becomes a
signaling end-point without understanding the reservation
protocol.
There are reservation gateways that translate the signaling Issues:
messages of one resource reservation protocol into messages of Typically, signaling end-points have a dedicated protocol stack,
another resource reservation protocol. Thus the reservation which interprets and generates the signaling messages. However, in
gateway represents two signaling end-points in one, as it is both some special cases, the resource reservation initiation is carried
a signaling terminator and a signaling initiator. out without the notice of the signaling terminating node. For
example, the Boomerang resource reservation protocol encapsulates
the reservation requests in an ICMP Echo message. This message is
bounced back from the signaling terminating network node ("Far-End
Node") and as a result the node becomes a signaling end-point
without understanding the reservation protocol.
6.1.5 Reservation Initiator 6.1.5 Reservation Orientation
Definition: Definition:
The reservation initiator is the signaling end-point that The reservation orientation tells which signaling end-point(s)
initiates the resource reservation session setup. initiates the network resources allocation to obtain special QoS
treatment for the data traffic of the reservation session.
Discussion: Discussion:
Resource reservation protocols can be classified into two groups
depending on the relationship between the reservation initiators
and their role in the data traffic flow. First, there are sender-
oriented protocols, where the source(s) of the reservation
sessionĘs data traffic initiates the network resource allocation
message. Second, in the case of the receiver-oriented protocols,
the receiver(s) of the reservation sessionĘs data traffic
initiates the resource allocation messages. Due to the asymmetric
routing nature of the Internet, in the latter case, the
receiver(s) should know the route(s) of the desired data traffic
before it would be able to send the resource allocation
Resource reservation protocols can be classified depending on the Feher, Cselenyi, Korn Expires May 2003 [Page 5]
relationship between the reservation initiators and their role in message(s). For this reason, even in the second case, the first
the traffic flow. signaling message(s) establishing the reservation session comes
from the source(s) of the data traffic marking the route(s) on
In the case of receiver-oriented protocols, the traffic which the resource allocation message(s) might travel backward.
destinations, which are the receivers of the data traffic,
initiate the reservation session setup, unlike the sender-oriented
protocols where this is done by traffic sources. Moreover, there
are protocols where both the traffic source and destination can
act as the reservation initiator.
The importance of the reservation initiator orientation is only
dominant in case of multicast reservation sessions. Generally, in
multicast groups the number of traffic destinations changes more
frequently than the number of traffic sources. In this case, the
receiver-oriented protocols do not require the traffic sources to
change their states generating signaling messages when a new
traffic destination joins or an existing one leaves the group,
since the reservation session is managed by the traffic
destinations.
Issues: Issues:
Receiver-oriented resource reservation protocols often require two The orientation of the reservation initiator affects the basics of
pass to setup the reservation session. Since the resource the resource reservation protocols and therefore it is an
dedication should take place on all the routers that are on the important design decision. In the case of multicast reservation
path from the sources to the destinations, thus the reservation sessions, the sender-oriented protocols require the traffic
initiator must have a method to reach every such router. In the sources to maintain a list of receivers and send their allocation
case of the sender-oriented protocols this method is assured by messages considering the requirements of the receivers. A less
sending the signaling traffic same way as the data traffic, which polite, but less demanding solution is when the sources ignore the
guarantees that signaling messages goes through the same routers QoS requirements of the receivers and send the allocation requests
as the data traffic. However, in the case of the receiver-oriented at will. Using multicast reservation sessions, the receiver-
protocols the reservation initiation requests go from the oriented protocols give the chance to the receivers to place their
destinations to the sources, which is the opposite direction own resource allocation requests and thus ease the task of the
compared to the data traffic. Thus, receiver-oriented protocols sources. However, in this case the resource allocations must be
must provide a mechanism that at first discovers all the routers preceded by the marking of the data routes of the reservation
along the path of the data traffic (RSVP PATH message [2]), before session (c.f. RSVP PATH message [2]). In case of large multicast
the second pass, where the traffic destinations are ready to groups, enabling the receivers to specify their QoS requirements,
initiate resource reservation requests. the receiver-oriented approach seems to be a better choice,
however in other cases the sender-oriented protocols promise less
complexity.
6.1.6 Reservation Session Maintenance 6.1.6 Reservation Session State
Definition: Definition:
Soft-state resource reservation protocols require the routers to A reservation session state is a holder for all the relevant
maintain the resource reservation sessions from the initiation information about the corresponding reservation session registered
until the teardown of the session. This maintenance often involves in the resource reservation capable router.
the regular checking and refreshing of the session.
Discussion: Discussion:
Based on the approach of reservation session maintenance, resource Resource reservation capable routers maintain reservation session
reservation protocols can be divided into two categories: soft- states to store information about the reservation session. This
state protocols and hard-state protocols. information might include the QoS treatment that the reservation
session requires; the description of how and where to forward the
incoming signaling messages; policies regarding the QoS treatment
or the reservation session; timing information about the
reservation session; etc.
In the case of hard-state protocols (e.g. ST2 [7]), the resource Based on how reservation session states are stored in a
reservation session established by a set-up signaling primitive is reservation capable router, the routers can be categorized into
permanent and is cancelled only when the corresponding tear-down three classes:
signaling primitive arrives to the router. Contrary, in the case
of the soft-state protocols there are no permanent resource
reservations. The resource reservation session have to be
regularly refreshed by appropriate signaling messages. No refresh
signaling message arrived during a certain period is assumed as
the indication that the resource reservation session is not
maintained by the signaling end-points any longer. In such case,
the router tears the session down waiting for no explicit request.
For this reason, soft-state protocols exhibit more robust behavior
than hard-state protocols, since no failures can cause permanent
resource stuck in the routers.
Issues: Hard-state resource reservation capable routers (e.g. ST2 capable
Although soft-state protocols are more robust than hard-state routers [7]) store the reservation session states permanently,
protocols, the frequent processing of refresh signaling messages established by a set-up signaling primitive, until a corresponding
might cause serious increase in the router load. Moreover, session tear-down signaling primitive arrives or until the router is
maintenance mechanisms often use timers to watch the refresh informed that the reservation session canceled.
period expirations of the sessions. The maintenance of such timers
and the actions due to the expiration of such timers also
contributes to the router load.
In order to reduce the large number of refresh signaling message There are also soft-state resource reservation capable routers,
processing overhead, the resource reservation protocol may support where there are no permanent reservation session states, but each
various mechanisms to pack several refresh signaling messages into
one signaling message. Feher, Cselenyi, Korn Expires May 2003 [Page 6]
state have to be regularly refreshed by appropriate refresh
signaling messages. If no refresh signaling message arrives during
a certain period then the router cancels the reservation session
assuming that the signaling end-points do not intend to keep up
the reservation session any longer or the communication lines are
broken somewhere along the data path. This feature makes soft-
state resource reservation capable routers more robust than hard-
state routers, since no failures can cause permanent resource
stuck in the routers.
Finally, there are stateless resource reservation capable routers
storing no information about the individual reservation sessions.
Without reservation session states the resource reservation
capabilities of such routers are limited, e.g. there is no support
for many-to-many multicast resource reservation sessions; and the
reservation session must be sender oriented.
Issues:
Although soft-state reservation capable routers are more robust
than hard-state ones, the frequent processing of refresh signaling
messages or the detection of the missing reservation session state
refreshes might cause serious increase in the router load, which
can be a base of the scalability problems. In order to decrease
the number of refresh signaling messages, the resource reservation
capable router might support various mechanisms to pack several
refresh signaling messages into one larger message.
6.1.7 Signaling Path 6.1.7 Signaling Path
Definition: Definition:
A signaling path is a sequence of network nodes and links along A signaling path is a sequence of network nodes and links along
which signaling messages travel from one signaling end-point to which signaling messages travel from one signaling end-point to
the other. the other.
Discussion: Discussion:
The resource reservation protocol must provide that each router, Resource reservation capable routers must assure that all other
which is responsible to handle a signaling message, truly receives router, which is responsible for handling the actual signaling
the signaling message. Usually it is assured by passing through message, really receives that message. Therefore, routers forward
the signaling messages along the signaling path, which involves the signaling messages along the signaling path and each router,
every router affected by the resource reservation session. affected by the message, processes it.
Resource reservation protocol must be also prepared that there are Usually signaling messages are immediately forwarded by resource
routers forwarding the data traffic of a resource reservation reservation capable routers towards the destination(s), spreading
session that do not support the actual resource reservation the information as fast as possible. However, there might be
protocol. In this case the signaling traffic must be tunneled protocol messages that do not affect all the routers along the
through the zones of the routers that can not interpret the signaling path, but only a subset of it (e.g. refresh messages in
signaling messages in order to keep the continuity of the RSVP). These kinds of signaling messages are terminated by routers
signaling path. when they are not necessary anymore.
Issues: Issues:
Resource reservation capable routers must be prepared that there
are other routers along the signaling path unable to interpret the
actual resource reservation protocol. Even in this case the
It is not unusual for routers to change their routing from time to Feher, Cselenyi, Korn Expires May 2003 [Page 7]
time. One reason for the change can be a failure of a neighboring signaling messages must be delivered to all corresponding resource
router or link. In case of route changes the data traffic will be reservation capable routers (usually using some kind of
forwarded along a different path than the signaling messages used tunneling).
in establishing the resource dedications for the reservation
session. In order to properly handle this situation, hard-state
protocols have to be much more sophisticated in order to detect
the route change and to re-reserve the resources on the new path.
However, soft-state protocols do not have to worry about such
situation, since the refresh messages can be used to set up the
reservation on the new path and the dedicated resources will
eventually disappear from routers of the obsoleted path.
6.2 Traffic Types 6.2 Traffic Types
This group of definitions defines traffic types forwarded by resource This group of definitions defines traffic types forwarded by resource
reservation capable routers. reservation capable routers.
6.2.1 Premium Traffic 6.2.1 Best-Effort Data Packets
Definition: Definition:
Premium traffic is a traffic type that the router distinguishes Best-effort data packet is a packet that has no associated
from best-effort traffic (to be defined later) and forwards its resource reservation session in the routers and thus it is served
packets according to a QoS agreement. in the "default" way.
Discussion: Discussion:
Traffic that corresponds to a resource reservation session in the Data packets that do not require QoS guarantees along their path
router is premium traffic. The QoS treatment is defined in the are considered to be best-effort packets. "Best-effort" means that
associated flow descriptor that is established by the signaling the router makes its best effort to forward the data packet
messages during the reservation session setup. quickly and safely, but does not guarantee anything (e.g. delay or
loss probability). This type of traffic is the most common type in
The router may distinguish several types of premium traffic (e.g. today's Internet. (There may be scenarios where resource
delay sensitive traffic, loss sensitive traffic, etc.). Different reservation is done even for best-effort traffic too, but those
types of premium traffic may receive different QoS treatment. are outside of the focus of this memo.) We will refer to the
traffic of the best-effort data packets shortly as best-effort
Issues: traffic.
The router has to identify every packet whether it has dedicated
resource or not. This can be done by either multi-field
classification [11] using the IP 5-tuple or behavior-aggregate
classification using the DSCP field. However, if a packet claims
that it has an associated resource reservation session in the
router, the router has to find the flow descriptor, which might be
time consuming in routers with vast amounts of resource
reservation sessions.
6.2.2 Best-Effort Traffic 6.2.2 Premium Data Packets
Definition: Definition:
Best-effort traffic is a traffic type that has no reservation Premium data packets are the packets that the resource reservation
entry in the router. capable router distinguishes from best-effort packets and forwards
them according to a QoS agreement.
Discussion: Discussion:
Data packets that correspond to a resource reservation session in
the router are premium data packets. The QoS treatment is defined
in the associated resource reservation state (e.g. flow
descriptor) that is established by signaling messages during the
reservation session setup.
Traffic flows that do not require QoS guarantees along their path The router may distinguish several types of premium. Data packets
are considered to be best-effort traffic. "Best-effort" means that belonging to different types of premium traffic may receive
the router makes its best effort to forward every data packet, but different QoS treatment. We will refer to the traffic of the
does not guarantee anything. This is the most common type of premium data packets shortly as premium traffic.
traffic on today's Internet. (There may be scenarios where
resource reservation is done for BE traffic too, but those are Issues:
outside of the focus of this memo.) The router has to identify every packet whether it belongs to any
resource reservation session or not. This can be done by either
multi-field classification [11] using the IP 5-tuple or the ToS
field in the header of the IP packet. However, if a packet has an
associated resource reservation session in the router, then the
Feher, Cselenyi, Korn Expires May 2003 [Page 8]
corresponding resource reservation states describing the QoS
treatment has to be looked up. This look up procedure might be
quite time consuming in routers with vast amounts of resource
reservation sessions.
6.3 Router Load Types 6.3 Router Load Types
This group of definitions describes different load component types This group of definitions describes different load component types
that impact only a specific part of the resource reservation capable that impact only a specific part of the resource reservation capable
router. Categorizing the router load is crucial, since the router. Categorizing the router load is crucial, since the
conventional router load metric expressing the processing power conventional router load metric expressing the processing power
utilization of the router does not characterize perfectly the utilization of the router does not characterize precisely enough a
resource reservation capable router. In the case of routers the resource reservation capable router. In the case of routers
supporting resource reservations it is also important to know the supporting resource reservations it is also important to know the
source of the processing power utilization. source of the processing power utilization.
6.3.1 Traffic Load 6.3.1 Traffic Load
Definition: Definition:
Traffic load is the load that is raised by forwarding data traffic Usually traffic load means the load that is raised by the data
on the router. traffic forwarding task of the router. However, we define the
traffic load as the volume of the input data traffic that causes
the router to be loaded.
Discussion: Discussion:
It is obvious that forwarding the data packets, which requires It is obvious that forwarding the data packets, which requires
obtaining the routing information and transferring the data packet obtaining the routing information and transferring the data packet
between network interfaces, requires processing power. Speaking of between network interfaces, requires processing power. In general
general router measurements only this type of load is considered router benchmarking measurements only this type of load is
as the source of the processing power utilization expressed by the considered as the source of the processing power utilization.
router load metric. Although the traffic load is the dominant load Although the traffic load is the dominant load component,
component, benchmarking routers supporting resource reservations benchmarking routers supporting resource reservations must
must consider other load components also in line with the resource consider other load components also in line with the resource
reservation handling. reservation handling.
Measurement unit: Measurement unit:
The amount of the traffic load is represented by the volume of the The amount of the traffic load is represented by the volume of the
data traffic. The volume is measured with the transferred bits data traffic. The volume is measured by the transferred bits
during a specified time unit, which is typically bit per seconds during a second, i.e. the measurement unit is bit per seconds
(bps). (bps).
6.3.2 Session Load 6.3.2 Session Load
Definition: Definition:
Session load is the load that manifests itself as the excess Similar to the traffic load, we define the session load as the
processing power required to keep track of reservation sessions. number of reservation sessions in the router.
Discussion: Discussion:
All signaling based resource reservation protocol implementation Each resource reservation capable router that employs a packet
employ a packet classifier algorithm that distinguishes the flows classifier algorithm distinguishing the flows referring to
having reservations in the router from the others that do not. reservation sessions maintains resource reservation session states
Therefore each implementation maintains a list of reservation keeping track of the resource reservation dedication. Obviously,
session descriptors that is instrumental in keeping track of the the more reservation session states are set up on the router, the
resource reservation dedication. Obviously, the more reservation
sessions are set up on the router, the more complex traffic Feher, Cselenyi, Korn Expires May 2003 [Page 9]
classification becomes, and the more time it takes for the more complex the traffic classification becomes, and the longer
classification algorithm to identify the session descriptor list. time it takes to look up the corresponding resource reservation
session sate.
Moreover, in most protocols, not only the traffic flows, but also Moreover, in most protocols, not only the traffic flows, but also
signaling messages that manipulate resource reservations on the the signaling messages that manipulate resource reservation
router have to identify themselves first, before taking any other sessions on the router have to identify themselves first, before
actions. This kind of classification gives extra work for the taking any other actions. This kind of classification also gives
router. extra work to the router.
Session load also involves the duties related to reservation Issues:
session maintenance. The maintenance of timers that watchdog the In the case of soft-state resource reservation capable routers,
reservation session refreshes and the signaling of the reservation the session load also affects reservation session maintenance. The
session refresh may cause severe load on the router. Based on the maintenance of timers that watchdog the reservation session
initiating point of the refresh messages, resource reservation refreshes and the refresh signaling messages may cause severe load
protocols can be divided into two groups. First, there are on the router. Based on the initiating point of the refresh
protocols where it is the responsibility of the signaling end- messages, resource reservation protocols can be divided into two
points to initiate refresh messages, which messages are forwarded groups. First, there are protocols where it is the responsibility
by the routers along the signaling path refreshing the of the signaling end-points to initiate refresh messages and these
corresponding session. Second, there are other protocols, where messages are forwarded along the whole signaling path refreshing
the session refresh happens between the two peering network nodes the corresponding resource reservation session. Second, there are
from the signaling path only. In this latter case, the routers and other protocols, where the reservation session refresh happens
signaling end-points have their own schedule for the refresh only between the two peering network nodes of the signaling path.
message initiation. The first approach lightens the load of the In this latter case, the routers and signaling end-points have
session maintenance task; however, the second approach bears the their own schedule for the refresh message initiation. The first
ability to adjust the signaling message traffic intensity along approach lightens the load of the session maintenance task;
the signaling path. however, the second approach bears the ability to adjust the
signaling intensity along the signaling path.
Measurement unit: Measurement unit:
The session load is represented by the number of reservation The session load is measured by the number of reservation sessions
sessions in the router. in the router.
6.3.3 Signaling Load 6.3.3 Signaling Load
Definition: Definition:
Signaling load is the load that manifests itself as the time Similarly to the previous load types, the signaling load is
required to process the incoming signaling messages. determined by the incoming signaling message intensity.
Discussion: Discussion:
The processing of signaling messages requires processing power The processing of signaling messages requires processor power that
that raises load on the control plane of the router. In the case raises the load on the control plane of the router. In routers
of routers where the control plane and the data plane are not where the control plane and the data plane are not totally
totally independent (e.g. certain parts of the tasks are served by independent (e.g. certain parts of the tasks are served by the
the same processor; or the architecture has common memory buffers same processor; or the architecture has common memory buffers or
or transfer buses) the signaling load can have an impact on the transfer buses) the signaling load can have an impact on the
router's packet forwarding performance as well. router's packet forwarding performance as well.
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. 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. power from the router.
Feher, Cselenyi, Korn Expires May 2003 [Page 10]
Measurement unit: Measurement unit:
The signaling load is characterized by the signaling intensity, The signaling load is characterized by the signaling intensity,
which expresses how many signaling messages arrive to the router which expresses how many signaling messages arrive to the router
within a time unit. The typical unit of the signaling intensity is within a second. Thus the unit of the signaling intensity is
[1/s], which is the number of signaling messages that arrive [1/s].
within one second.
6.3.4 Signaling Burst 6.3.4 Signaling Burst
Definition: Definition:
The signaling burst denotes a certain number of signaling messages The signaling burst denotes a certain number of signaling messages
that arrive to the input port(s) of the router without that arrive to the input port(s) of the router back-to-back,
interruption, causing persistent load on the signaling message causing persistent load on the signaling message handler.
handler.
Discussion: Discussion:
Back-to-back signaling messages on one port of the router form a Back-to-back signaling messages on one port of the router form a
typical signaling burst. However, other cases are imaginable, for typical signaling burst. However, other cases are imaginable, for
example when signaling messages arrive on different ports example when signaling messages arrive on different ports
simultaneously or with an overlap in time (i.e. when the tail of simultaneously or with an overlap in time (i.e. when the tail of
one signaling message is behind the head of another one arriving one signaling message is behind the head of another one arriving
on another port). on another port).
Measurement unit: Measurement unit:
The signaling burst is characterized by its length, which is the The signaling burst is characterized by its length, which is the
number of messages that have arrived during the burst. number of messages that have arrived within the burst.
6.4 Performance Metrics 6.4 Performance Metrics
This group of definitions is the collection of the measurable impacts This group of definitions is the collection of the measurable impacts
that a resource reservation protocol has over the tested router that a resource reservation protocol has over the tested router
device it is running on. device it is running on.
6.4.1 Signaling Message Handling Time 6.4.1 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 time that a signaling message spends inside the time) is the time that a signaling message spends inside the
router before it is forwarded to the next node on the signaling router before it is forwarded to the next node on the signaling
path. path.
Discussion: Discussion:
Depending on the type of the signaling message, the router also Depending on the type of the signaling message, the router also
interprets the signaling messages, acts on them and forwards an interprets the signaling messages, acts on them and usually
extended signaling message, which might contain information about forwards a modified signaling message. Thus the message handling
the result of the message processing. Thus the message handling
time is usually longer than forwarding time of data packets of the time is usually longer than forwarding time of data packets of the
same size. In addition, there might be also signaling message same size. In addition, there might be also signaling message
primitives that are drained or generated by the router. Thus, the primitives that are drained or generated by the router. Thus, the
signal handling time is defined as the time difference between the signal handling time is defined as the time difference between the
time when a signaling message is received and the time the time when a signaling message is received and the time the
corresponding processed signaling message is transmitted. If a corresponding processed signaling message is transmitted. If a
message is not forwarded on the router, the signal handling time signaling message is not forwarded on the router (see Signaling
is immeasurable; therefore it is not defined for such messages. Path), the signal handling time is immeasurable; therefore it is
not defined for such messages.
Feher, Cselenyi, Korn Expires May 2003 [Page 11]
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. In this case, by definition, signaling messages after processing. In this case, by definition,
the signal handling time is the time interval elapsed between the the signal handling time is the time interval elapsed between the
arrival of the incoming signaling message and the departure of the arrival of the incoming signaling message and the departure of the
last signaling message related to the received one. last signaling message related to the received one.
This metric depends on the load on the router, as other tasks may This metric depends on the load on the router, as other tasks may
limit the processing power available to signaling message limit the processing power available to signaling message
handling. In addition to the router load, the signal handling time handling. In addition to the router load, the signal handling time
may also be dependent on the type of the signaling message. For may also be dependent on the type of the signaling message. For
example, it usually takes a shorter time for the router to tear example, it usually takes a shorter time for the router to tear
down a resource reservation session than to set it up. down a resource reservation session than to set it up.
Issues: The signal handling time is an important characteristic as it
In the case of soft-state protocols, where refresh messages are directly affects the setup time of a session.
exchanged between peering network nodes only (see Reservation
Session Maintenance) the incoming refresh messages are drained by
the router making impossible to measure the signaling message
handling time on them.
Signal handling time is an important characteristic as it directly
affects the setup time of a session.
Measurement unit: Measurement unit:
The typical unit of the signaling message handling time is The unit of the signaling message handling time is the second.
microsecond.
6.4.2 Premium Traffic Delay 6.4.2 Premium Traffic Delay
Definition: Definition:
Premium traffic delay is the forwarding time of a packet that Premium traffic delay is the forwarding time of a premium data
belongs to a premium traffic flow passing through a resource packet passing through a resource reservation capable router.
reservation capable router.
Discussion: Discussion:
Premium traffic packets must be classified first in order to find Premium traffic packets must be classified first in order to
the resources dedicated to the flow. The time of the assign the network resources dedicated to the flow. The time of
classification is added to the usual forwarding time that a router the classification is added to the usual forwarding time
would spend on the packet without any resource reservation (including the queuing) that a router would spend on the packet
capability. without any resource reservation capability.
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 premium traffic delay performance of the router. In this case the premium traffic delay
metric reflects the influence the two planes have on each other. metric reflects the influence the two planes have on each other.
Measurement unit: Measurement unit:
The typical unit of the premium traffic delay is the microsecond. The unit of the premium traffic delay is the second.
6.4.3 Best-effort Traffic Delay 6.4.3 Best-effort Traffic Delay
Definition: Definition:
Best-effort traffic delay is the forwarding time of a packet that Best-effort traffic delay is the forwarding time of a best-effort
does not belong to any premium traffic flow passing through a packet passing through a resource reservation capable router.
resource reservation capable router.
Discussion: Discussion:
It looks trivial that the classification algorithms do not have Marking the premium traffic packets also marks the best-effort
any influence on the best-effort traffic. However, the processing traffic packets via the lack of marking. In this case the
power sharing between the control and data plane may cause delays detection of the best-effort packets is straightforward, so the
in the forwarding procedure of each packet. classification algorithms do not have any influence on the best-
Feher, Cselenyi, Korn Expires May 2003 [Page 12]
effort traffic. However, the processing power sharing between the
control and data plane might still cause delays in the forwarding
procedure of each packet.
Measurement unit: Measurement unit:
The typical unit of the best-effort traffic delay is microsecond. The unit of the best-effort traffic delay is the second.
6.4.4 Signaling Message Loss 6.4.4 Signaling Message Loss
Definition: Definition:
Signaling message loss is the ratio of the actual and the expected Signaling message loss is the ratio of the actual and the expected
number of signaling messages leaving a resource reservation number of signaling messages leaving a resource reservation
capable router subtracted from one. capable router subtracted from one.
Discussion: Discussion:
There are certain types of signaling messages, which are required There are certain types of signaling messages required to be
to be forwarded by the router immediately when their processing is forwarded by the resource reservation capable router immediately
finished. However, due to the high router load or for other when their processing is finished. However, due to the high router
reasons, the forwarding or even the processing of the signaling load or for other reasons, the forwarding or even the processing
message might be canceled. To characterize such situations we of these signaling messages might be canceled. To characterize
introduce the signaling message loss metric, which expresses the such situations we introduce the signaling message loss metric
ratio of the signaling messages that actually have left the router expressing the ratio of the signaling messages that actually have
and those ones that were expected to leave the router as a result left the router and those ones that were expected to leave the
of the incoming sequence of signaling messages. router as a result of the incoming sequence of signaling messages.
Since the most frequent reason for the signaling message loss is Since the most frequent reason for the signaling message loss is
the high router load, therefore this metric is suitable for the high router load, therefore this metric is suitable for
sounding out the scalability limits of resource reservation sounding out the scalability limits of resource reservation
capable routers. capable routers.
Issues: Issues:
In the case of routers where network packets are queued in several Sometimes it may be hard to determine whether a signaling message
places, we have to be aware of that a signaling message may be is still in the queues of the router or whether it has already
delayed seriously. Therefore, it may be hard or impossible to been dropped. For this reason we define that a signaling message
determine whether the signaling message is still in the queues or is lost if there is no appearing forwarded signaling message
whether it was already dropped. By definition we say that a within a reasonable long time period. This time period should be
signaling message is lost if there is no appearing forwarded adjusted to the actual resource reservation protocol and might
signaling message within a reasonable long time period. This time also depend on the type of the message, too. For example, in the
period should be adjusted to the actual resource reservation case of soft-state resource reservation capable routers the
protocol (e.g. soft-state protocols may wait as much as the measurer may wait as much as the refresh period to detect the loss
refresh period to determine the loss of a signaling message). of a signaling message.
Measurement unit: Measurement unit:
This measure has no unit; it is expressed by a real number, which
Usually, we measure the signaling message loss over a longer is between zero and one (including the limits).
period of time and then we express it as a percentage value.
Besides, in many cases it is enough to know that there was
signaling loss.
6.4.5 Session Refreshing Capacity 6.4.5 Session Refreshing Capacity
Definition: Definition:
The session refreshing capacity is the ratio of the truly The session refreshing capacity metric is applied for soft-state
refreshed sessions and the number of session that have to be resource reservation capable routers only and tells the ratio of
refreshed during one refresh period. This metric is applied for the truly refreshed reservation sessions and the number of
soft-state routers only. sessions that should be refreshed during one refresh period.
Feher, Cselenyi, Korn Expires May 2003 [Page 13]
Discussion: Discussion:
The session refreshing capacity informs about condition of the When a soft-state resource reservation capable router is
session maintenance. When the router is overloaded it may happen overloaded, it may happen that the router is not able to refresh
that the router is not capable to refresh all the allocated all the registered reservation sessions having no time to run the
reservation sessions due to other tasks with higher priorities. In session refresh task. In this case sooner or later the resource
this case sooner or later the resource reservation sessions over reservation sessions over the session refresh capacity are dropped
the session refresh capacity are dropped even if the resource even if the resource reservation end-points are still refreshing
reservation end-points are still refreshing them. them.
The session refreshing capacity sounds out the limit of resource The session refreshing capacity sounds out the limit of the
reservation session number that the router is capable to maintain. resource reservation session number that the router is capable to
maintain.
Measurement unit: Measurement unit:
The session refreshing capacity is expressed as a percentage This measure has no unit; it is expressed by a real number, which
value. is between zero and one (including the limits).
6.4.6 Scalability Limit 6.4.6 Scalability Limit
Definition: Definition:
The scalability limit is the threshold between the steady state The scalability limit is the threshold between the steady state
and the overloaded state of the device under test. and the overloaded state of the device under test.
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. In the steady state of the router, the buffer
memories are not fully utilized and the processing power is enough memories are not fully utilized and the processing power is enough
to cope with all tasks running on the router. As the router load to cope with all tasks running on the router. As the router load
increases the router has to postpone more and more tasks. These increases the router has to postpone more and more tasks. These
tasks (e.g. forwarding certain packets) are queued in the buffers, tasks (e.g. forwarding certain packets) are queued in the buffers,
and processed later. However, there is a certain point where no and processed later. However, there is a certain point where no
more buffer memory is available; thus, the router becomes more buffer memory is available or a task cannot be postponed any
overloaded and it is unable to store any more tasks for future longer; thus, the router is forced to drop the packet or the
processing, so it is forced to drop them. Therefore the overloaded activity. This way the overloaded state of the resource
state of the router can be recognized by the fact that some kind reservation capable router can be recognized by the fact that some
of data (signaling or packet) loss occurs. A resource reservation kind of data (signaling or packet) or task (e.g. refreshing) loss
capable router may drop signaling messages, data packets or entire occurs.
resource reservation sessions.
The critical load condition when the router is still in the steady The critical load condition when the router is still in the steady
state but the smallest amount of constant load increase would state but the smallest amount of constant load increase would
drive it to the overloaded state is the scalability limit of the drive it to the overloaded state is the scalability limit of the
router. router.
7. Acknowledgement 7. Security Considerations
As this document is solely for providing terminology and describes
neither a protocol nor an implementation, there are no security
considerations associated with this document.
Feher, Cselenyi, Korn Expires May 2003 [Page 14]
8. Acknowledgement
We would like to thank the following individuals for their help in We would like to thank the following individuals for their help in
forming this document: Joakim Bergkvist and Norbert Vegh from Telia forming this document: Joakim Bergkvist and Norbert Vegh from Telia
Research AB, Sweden, Krisztian Nemeth, Balazs Szabo, Gabor Kovacs and Research AB, Sweden, Krisztian Nemeth, Balazs Szabo, Gabor Kovacs and
Peter Vary from High Speed Networks Laboratory of Budapest University Peter Vary from the High Speed Networks Laboratory, Budapest
of Technology and Economics, Hungary. University of Technology and Economics, Hungary.
8. References 9. References
[1] Y. Bernet, et. al., "A Framework for Integrated Services [1] Y. Bernet, et. al., "A Framework for Integrated Services
Operation over Diffserv Networks", RFC 2998, November 2000 Operation over Diffserv Networks", RFC 2998, November 2000
[2] B. Braden, Ed., et. al., "Resource Reservation Protocol (RSVP) - [2] B. Braden, Ed., et. al., "Resource Reservation Protocol (RSVP) -
Version 1 Functional Specification", RFC 2205, September 1997. Version 1 Functional Specification", RFC 2205, September 1997.
[3] S. Bradner, "Benchmarking Terminology for Network [3] S. Bradner, "Benchmarking Terminology for Network
Interconnection Devices", RFC 1242, July 1991 Interconnection Devices", RFC 1242, July 1991
skipping to change at page 15, line 55 skipping to change at line 811
[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. Wroclawski, "The Use of RSVP with IETF Integrated Services", [10] J. Wroclawski, "The Use of RSVP with IETF Integrated Services",
RFC 2210, September 1997 RFC 2210, September 1997
[11] K. Nichols et al., " Definition of the Differentiated Services [11] K. Nichols et al., " Definition of the Differentiated Services
Field (DS Field) in the IPv4 and IPv6 Headers ", RFC 2474 Field (DS Field) in the IPv4 and IPv6 Headers ", RFC 2474
9. Authors' Addresses: [12] Deering, S. and R. Hinden, "Internet Protocol, Version 6 (IPv6)
Specification", RFC 2460, December 1998
[13] Postel, J., Editor, "Internet Protocol", STD 5, RFC 791,
September 1981
Feher, Cselenyi, Korn Expires May 2003 [Page 15]
10. Authors' Addresses
Gabor Feher Gabor Feher
Budapest University of Technology and Economics (BUTE) Budapest University of Technology and Economics (BUTE)
Department of Telecommunications and Telematics Department of Telecommunications and Telematics
Pazmany Peter Setany 1/D, H-1117, Budapest, Hungary Magyar Tudosok krt. 2, H-1117, Budapest, Hungary
Phone: +36 1 463-3110 Phone: +36 1 463-1538
Email: feher@ttt-atm.ttt.bme.hu Email: feher@ttt-atm.ttt.bme.hu
Istvan Cselenyi Istvan Cselenyi
Telia Research AB Telia Research AB
Vitsandsgatan 9B Vitsandsgatan 9B
SE 12386, Farsta SE 12386, Farsta
SWEDEN, SWEDEN,
Phone: +46 8 713-8173 Phone: +46 8 713-8173
Email: istvan.i.cselenyi@telia.se Email: istvan.i.cselenyi@telia.se
Andras Korn Andras Korn
Budapest University of Technology and Economics (BUTE) Budapest University of Technology and Economics (BUTE)
Institute of Mathematics, Department of Analysis Institute of Mathematics, Department of Analysis
Egry Jozsef u. 2, H-1111 Budapest, Hungary Egry Jozsef u. 2, H-1111 Budapest, Hungary
Phone: +36 1 463-2475 Phone: +36 1 463-2475
Email: korn@math.bme.hu Email: korn@math.bme.hu
Feher, Cselenyi, Korn Expires May 2003 [Page 16]
 End of changes. 

This html diff was produced by rfcdiff 1.23, available from http://www.levkowetz.com/ietf/tools/rfcdiff/