IP Performance Metrics
(IPPM) for spatial and multicastFrance Telecom Division
R&D2 avenue Pierre MarzinLannionF-22307+33 2 96 05 18 52emile.stephan@orange-ftgroup.comCCSR, University of
SurreyGuildfordSurreyGU2 7XH+44 1483 683641L.Liang@surrey.ac.uk200 Laurel Ave. SouthMiddletownNJ07748USA+1 732 420 1571acmorton@att.comThe IETF IP Performance Metrics (IPPM) working group has standardized
metrics for measuring end-to-end performance between two points. This
memo defines two new categories of metrics that extend the coverage to
multiple measurement points. It defines spatial metrics for measuring
the performance of segments of a source to destination path, and metrics
for measuring the performance between a source and many destinations in
multiparty communications (e.g., a multicast tree).The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT",
"SHOULD", "SHOULD NOT", "RECOMMENDED", "MAY", and "OPTIONAL" in this
document are to be interpreted as described in RFC 2119.The IETF IP Performance Metrics (IPPM) working group has standardized
metrics for measuring end-to-end performance between two points. This
memo defines two new categories of metrics that extend the coverage to
multiple measurement points. It defines spatial metrics for measuring
the performance of segments of a source to destination path, and metrics
for measuring the performance between a source and many destinations in
multiparty communications (e.g., a multicast tree).The purpose of the memo is to define metrics to fulfill the new
requirements of measurement involving multiple measurement points.
Spatial metrics are defined to measure the performance of each segments
along a path while the one-to-group metrics are aiming to provide a
ruler to measure the performance of a group of users. These metrics are
derived from one-way end-to-end metrics defined by IETF and follow the
criteria described in the IPPM framework .New terms are introduced to extend the terminology of the IPPM
framework to spatial metrics and one-to-group metrics. Then a section
motivates the need of defining each category of metrics. After, each
category is defined in a separate section. Then the memo discusses the
impact of the measurement methods on the scalability and proposes an
information model for reporting the measurements. Finally the document
discusses security aspects related to measurement and registers the
metrics in the IANA IP Performance Metrics Registry .Note that all these metrics are based on observations of packets
dedicated to testing, a process which is called Active measurement.
Purely passive spatial measurement (for example, a spatial metric based
on the observation of user traffic) is beyond the scope of this
memo.Following is a summary of the metrics defined.This memo firstly defines metrics for spatial measurement based on
the decomposition of standard end-to-end metrics defined by IETF in
[, , , . Seven metrics
are defined including their names, parameters, units and measurement
methodologies. Each definion includes a specific section discussing
measurements constraints and issues, and proposing guidance to increase
results accucacy. These spatial metrics are:A 'Vector', called Type-P-Spatial-One-way-Delay-Vector, will be
introduced to divide an end-to-end Type-P-One-way-Delay into a spatial sequence of one-way delay
metrics.A 'Vector', called Type-P-Spatial-One-way-Packet-Loss-Vector,
will be introduced to divide an end-to-end
Type-P-One-way-Packet-Loss in a
spatial sequence of packet loss metrics.Using the Type-P-Spatial-One-way-Delay-Vector metric, a 'vector',
called Type-P-Spatial-One-way-ipdv-Vector, will be introduced to
divide an end-to-end Type-P-One-way-ipdv in a spatial sequence of
ipdv metrics.Using the Type-P-Spatial-One-way-Delay-Vector metric, a 'sample',
called Type-P-Segment-One-way-Delay-Stream, will be introduced to
collect one-way delay metrics over time between two points of
interest of the path;Using the Type-P-Spatial-Packet-Loss-Vector metric, a 'sample',
called Type-P-Segment-Packet-Loss-Stream, will be introduced to
collect packet loss metrics over time between two points of interest
of the path;Using the Type-P-Spatial-One-way-Delay-Vector metric, a 'sample',
called Type-P-Segment-ipdv-prev-Stream, will be introduced to
compute ipdv metrics over time between two points of interest of the
path using the previous packet selection function;Using the Type-P-Spatial-One-way-Delay-Vector metric, a 'sample',
called Type-P-Segment-ipdv-min-Stream, will be introduced to compute
ipdv metrics over time between two points of interest of the path
using the shortest delay selection function;Then the memo defines one-to-group metrics and one-to-group
statistics.Three one-to-group metrics are defined to measure the one-way
performance between a source and a group of receivers. Definitions
derive from one-way metrics definitions of RFCs in , , , : A 'Vector', called Type-P-One-to-Group-One-way-Delay-Vector, will
be introduced to collect the set of Type-P-one-way-delay singletons
between one sender and N receivers;A 'Vector', called
Type-P-One-to-Group-One-way-Packet-Loss-Vector, will be introduced
to collect the set of Type-P-One-way-Packet-Loss singletons between
one sender and N receivers;A 'Vector', called Type-P-One-to-Group-One-way-ipdv-Vector, will
be introduced to collect the set of Type-P-One-way-ipdv singletons
between one sender and N receivers.Then, based on the One-to-group vector metrics listed above,
statistics are defined to capture single receiver performance, group
performance and relative performance situation inside a multiparty
communication for each packet sent during the test interval between one
sender and N receivers: Using the Type-P-One-to-Group-One-way-Delay-Vector, a metric
called Type-P-One-to-Group-Receiver-n-Mean-Delay will be introduced
to present the mean of delays between one sender and a receiver 'n'.
Then, based on this definition, 3 metrics will be defined to
characterize the mean delay over the entire group during this
interval:a metric called Type-P-One-to-Group-Mean-Delay, will be
introduced to present the mean of delays;a metric called Type-P-One-to-Group-Range-Mean-Delay will be
introduced to present the range of mean delays;a metric called Type-P-One-to-Group-Max-Mean-Delay will be
introduced to present the maximum of mean delays;Using the Type-P-one-to-group-One-way-Packet-Loss-Vector, a
metric called Type-P-One-to-Group-Receiver-n-Loss-Ratio will be
introduced to capture packet loss ratio between one sender and a
receiver 'n'. Then based on this definition, 2 metrics will be
defined to characterize packet loss over the entire group during
this interval:a metric called Type-P-One-to-Group-Loss-Ratio will be
introduced to capture packet loss ratio overall over the entire
group or all receivers;a metric called Type-P-One-to-Group-Range-Loss-Ratio will be
introduced to present comparative packet loss ratio for each
packet during the test interval between one sender and N
Receivers.Using Type-P-one-to-group-One-way-ipdv-Vector, a metric called
Type-P-One-to-Group-Range-Delay-Variation will be introduced to
present the range of delay variation between one sender and a group
of receivers.The list of the hosts on a path from the source to the
destination.A metric is said to be multiparty if the topology involves more
than one measurement collection point. All multiparty metrics define a
set of hosts called "points of interest", where one host is the source
and other hosts are the measurement collection points. For example, if
the set of points of interest is < ha, hb, hc, ..., hn >, where
ha is the source and < hb, hc, ..., hn > are the destinations,
then measurements may be conducted between < ha, hb>, < ha,
hc>, ..., <ha, hn >.For the purposes of this memo (reflecting the scope of a single
source), the only multiparty metrics are one-to-group metrics.A metric is said to be spatial if one of the hosts (measurement
collection points) involved is neither the source nor a destination of
the measured packet.A metric is said to be one-to-group if the measured packet is sent
by one source and (potentially) received by several destinations.
Thus, the topology of the communication group can be viewed as a
centre-distributed or server-client topology with the source as the
centre/server in the topology.Points of interest are the hosts* (as per RFC2330 definition, that
includes routing nodes) that are measurement collection points, a
sub-set of the set of hosts involved in the delivery of the packets
(in addition to the source itself). Note that the points of interest
are a possibly arbitrary sub-set of all the hosts involved in the
path.Points of interest of one-to-group metrics are the intended
destination hosts for packets from the source (in addition to the
source itself).A candidate point of interest for spatial metrics is a host from
the set of hosts involved in the delivery of the packets from the
source.A reference point is defined as the server where the statistical
calculations will be carried out. A centre/server in the multimetrics
measurement that is controlled by a network operator is a good example
of a reference point, where measurement data can be collected for
further processing. However, the actual measurements have to be
carried out at all points of interest.A Vector is a set of singletons, which are a set of results of the
observation of the behaviour of the same packet at different places of
a network at different times. For instance, if one-way delay
singletons observed at N receivers for Packet P sent by the source Src
are dT1, dT2,…, dTN, it can be say that a vector V with N
elements can be organized as {dT1, dT2,…, dTN}. The elements in
one vector are singletons distinct with each other in terms of both
measurement point and sending time. Given the vector V as an example,
the element dT1 is distinct from all others as the singleton at
receiver 1 in response to a packet sent from the source at time T1.
The complete Vector gives information over the dimension of space.Several vectors form a Matrix, which contains results observed in a
sampling interval at different places in a network at different times.
For instance, given One-way delay vectors V1={dT11, dT12,..., dT1N},
V2={dT21, dT22,…, dT2N},…, Vm={dTm1, dTm2,…,
dTmN} for Packet P1, P2,…,Pm, we can have a One-way delay
Matrix {V1, V2,…,Vm}. Additional to the information given by a
Vector, a Matrix is more powerful to present network performance in
both space and time dimensions. It normally corresponds to a sample in
simple point-to-point measurement.The relation among Singleton, Vector and Matrix can be shown in the
following .All IPPM metrics are defined for end-to-end (source to destination)
measurement of point-to-point paths. It is a logical extension to define
metrics for multiparty measurements such as one to one trajectory
metrics and one to multipoint metrics.Decomposition of instantaneous end-to-end measures is needed: Decomposing the performance of interdomain path is desirable to
quantify the per-AS contribution to the performance. It is
valuable to define standard spatial metrics before pursuing
inter-domain path performance specifications.Traffic engineering and troubleshooting applications benefit
from spatial views of one-way delay and ipdv consumption, and
identification of the location of the lost of packets.Monitoring the performance of a multicast tree composed of MPLS
point-to-multipoint and inter-domain communication require spatial
decomposition of the one-way delay, ipdv, and packet loss.Composition of metrics is needed to help measurement systems
reach large scale coverage. Spatial measures typically give the
individual performance of an intra domain segment and provide an
elementary piece of information needed to estimate interdomain
performance based on composition of metrics.While the node-to-node based spatial measures can provide very
useful data in the view of each connection, we also need measures to
present the performance of a multiparty communication topology. A
simple one-way metric cannot completely describe the multiparty
situation. New one-to-group metrics assess performance of all the
paths for further statistical analysis. The new metrics proposed in
this stage are named one-to-group performance metrics, and they are
based on the unicast metrics defined in IPPM WG. One-to-group metrics
are one-way metrics from one source to a group of destinations. The
metrics are helpful for judging the network performance of multiparty
communications and can also be used to describe the variation of
performance delivered to a group of destination hosts and their
users.One-to-group performance metrics are needed for several
reasons:For designing and engineering multicast trees and MPLS
point-to-multipoint LSP;For evaluating and controlling of the quality of the multicast
services;For controlling the performance of the inter domain multicast
services;For presenting and evaluating the performance requirements for
multiparty communications and overlay multicast.To understand the packet transfer performance between one
source and any one receiver in the multiparty communication group, we
need to collect instantaneous end-to-end metrics, or singletons. It
will give a very detailed insight into each branch of the multicast
tree in terms of end-to-end absolute performance. This detail can
provide clear and helpful information for engineers to identify the
sub-path with problems in a complex multiparty routing tree.The one-to-group metrics described in this memo introduce the
multiparty topology to the IPPM working group; the goal is to measure
the performance delivered to a group of users who are receiving
packets from the same source. The concept extends the "path" in the
one-way measurement to "path tree" to cover both one-to-one and
one-to-many communications. If applied to one-to-one communications,
the one-to-group metrics provide exactly the same results as the
corresponding one-to-one metrics.We note that points of interest can also be selected to define
measurements on group-to-one and group-to-group topologies. These
topologies are currently beyond the scope of this memo, because they
would involve multiple packets launched from different sources.
However, we can give some clues here on these two cases.The measurements for group-to-one topology can be easily derived
from the one-to-group measurement. The measurement point is the
reference point that is acting as a receiver while all of
clients/receivers defined for one-to-group measurement act as sources
in this case.For the group-to-group connection topology, it is difficult to
define the reference point and therefore it is difficult to define the
measurement points. However, we can always avoid this confusion by
treating the connections as one-to-group or group-to-one in our
measurements without consideration on how the real communication will
be carried out. For example, if one group of hosts < ha, hb, hc,
..., hn > are acting as sources to send data to another group of
hosts < Ha, Hb, Hc, ..., Hm >, we can always decompose them into
n one-to-group communications as < ha, Ha, Hb, Hc, ..., Hm >,
< hb, Ha, Hb, Hc, ..., Hm >, <hc, Ha, Hb, Hc, ..., Hm >,
..., < hn, Ha, Hb, Hc, ..., Hm >.This section defines vectors for the decomposition of end-to-end
singleton metrics over a path.Spatial vectors metrics are based on the decomposition of standard
end-to-end metrics defined by the IPPM WG in , , and .Definitions are coupled with the corresponding end-to-end metrics.
Methodology specificities are common to all the vectors defined and are
consequently discussed in a common section.This section is coupled with the definition of Type-P-One-way-Delay
of the section 3 of . When a parameter
of this definition is first used in this section, it will be tagged
with a trailing asterisk.Sections 3.5 to 3.8 of give
requirements and applicability statements for end-to-end one-way-delay
measurements. They are applicable to each point of interest Hi
involved in the measure. Spatial one-way-delay measurement SHOULD be
respectful of them, especially those related to methodology, clock,
uncertainties and reporting.Type-P-Spatial-One-way-Delay-VectorSrc*, the IP address of the sender.Dst*, the IP address of the receiver.i, An integer in the ordered list <1,2,...,n> of hosts
in the path.Hi, A host* of the path digest.T*, a time, the sending (or initial observation) time for a
measured packet.dT*, a delay, the one-way delay for a measured packet.<dT1,..., dTn> a list of delay.P*, the specification of the packet type.<H1, H2,..., Hn>, hosts path digest.The value of Type-P-Spatial-One-way-Delay-Vector is a sequence of
times.Given a Type-P packet sent by the sender Src at wire-time (first
bit) T to the receiver Dst in the path <H1, H2,..., Hn>. Given
the sequence of values <T+dT1,T+dT2,...,T+dTn,T+dT> such that
dT is the Type-P-One-way-Delay from Src to Dst and such that for
each Hi of the path, T+dTi is either a real number corresponding to
the wire-time the packet passes (last bit received) Hi, or undefined
if the packet never passes Hi.Type-P-Spatial-One-way-Delay-Vector metric is defined for the
path <Src, H1, H2,..., Hn, Dst> as the sequence of values
<T,dT1,dT2,...,dTn,dT>.Following are specific issues which may occur: the delay looks to decrease: dTi > DTi+1. This may occur
despite it does not make sense per definition:This is frequently due to some clock synchronization
issue. This point is discussed in the section 3.7.1. "Errors
or uncertainties related to Clocks" of . Consequently, times of a measure
at different hosts do not guaranty the ordering of the hosts
on the path of a measure.During some change of routes the order of 2 hosts may
change on the main path;The location of the point of interest in the device
influences the result. If the packet is not observed
directly on the input interface the delay includes buffering
time and consequently an uncertainty due to the difference
between 'wire time' and 'host time'This section is coupled with the definition of
Type-P-One-way-Packet-Loss. Then when a parameter from the section 2
of is first used in this section, it
will be tagged with a trailing asterisk.Sections 2.5 to 2.8 of give
requirements and applicability statements for end-to-end one-way
packet loss measurements. They are applicable to each point of
interest Hi involved in the measure. Spatial packet loss measurement
SHOULD be respectful of them, especially those related to methodology,
clock, uncertainties and reporting.Following we define the spatial metric, then we adapt some of the
points above and introduce points specific to spatial measurement.Type-P-Spatial-One-way-Packet-Loss-VectorSrc*, the IP address of the sender.Dst*, the IP address of the receiver.i, an integer which ordered the hosts in the path.Hi, points of interests of the path digest.T*, a time, the sending time for a measured packet.<dT1,..., dTn, dT>, a list of delay.P*, the specification of the packet type.<H1, H2,..., Hn>, hosts path digest.<L1, L2, ...,Ln>, a list of Boolean values.The value of Type-P-Spatial-One-way-Packet-Loss-Vector is a
sequence of Boolean values.Given a Type-P packet sent by the sender Src at time T to the
receiver Dst in the path <H1, H2, ..., Hn>. Given the sequence
of times <T+dT1,T+dT2,...,T+dTn> the packet passes in <H1,
H2 ..., Hn>, we define Type-P-One-way-Packet-Lost-Vector metric
as the sequence of values <L1, L2, ..., Ln> such that for each
Hi of the path, a value of 0 for Li means that dTi is a finite
value, and a value of 1 means that dTi is undefined.Following are specific issues which may occur: The result includes the sequence 1,0. This may occur under
specific situations:During some change of routes a packet may be seen by a
host but not by it successor on the main path;A packet may not be observed in a host due to some buffer
or CPU overflow in the point of interest;This section uses parameters from the definition of
Type-P-One-way-ipdv. When a parameter from section 2 of is first used in this section, it will be
tagged with a trailing asterisk.In the following we adapt some of them and introduce points
specific to spatial measurement.Type-P-Spatial-One-way-ipdv-VectorSrc*, the IP address of the sender.Dst*, the IP address of the receiver.i, An integer in the ordered list <1,2,...,n> of hosts
in the path.Hi, A host* of the path digest.T1*, a time, the sending time for a first measured
packet.T2*, a time, the sending time for a second measured
packet.dT*, a delay, the one-way delay for a measured packet.P*, the specification of the packets type.P1, the first packet sent at time T1.P2, the second packet sent at time T2.<H1, H2,..., Hn>, hosts path digest.<T1,dT1.1, dT1.2,..., dT1.n,dT1>, the
Type-P-Spatial-One-way-Delay-Vector for packet sent at time
T1.<T2,dT2.1, dT2.2,..., dT2.n,dT2>, the
Type-P-Spatial-One-way-Delay-Vector for packet sent at time
T2.L*, a packet length in bits. The packets of a Type P packet
stream from which the Type-P-Spatial-One-way-Delay-Vector metric
is taken MUST all be of the same length.The value of Type-P-Spatial-One-way-ipdv-Vector is a sequence of
times.Given P1 the Type-P packet sent by the sender Src at wire-time
(first bit) T1 to the receiver Dst and <T1, dT1.1, dT1.2,...,
dT1.n, dT1> its Type-P-Spatial-One-way-Delay-Vector over the path
<H1, H2,..., Hn>.Given P2 the Type-P packet sent by the sender Src at wire-time
(first bit) T2 to the receiver Dst and <T2, dT2.1, dT2.2,...,
dT2.n, dT2> its Type-P-Spatial-One-way-Delay-Vector over the same
path.Type-P-Spatial-One-way-ipdv-Vector metric is defined as the
sequence of values <T2-T1, dT2.1-dT1.1, dT2.2-dT1.2 ,...,
dT2.n-dT1.n, dT2-dT1> such that for each Hi of the path <H1,
H2,..., Hn>, dT2.i-dT1.i is either a real number if the packets
P1 and P2 passe Hi at wire-time (last bit) dT1.i, respectively
dT2.i, or undefined if at least one of them never passes Hi. T2-T1
is the inter-packet emission interval and dT2-dT1 is ddT* the
Type-P-One-way-ipdv at T1,T2*.Methodology, reporting and uncertainties points specified in
section 3 of applies to each point of
interest Hi measuring a element of a spatial delay vector.Methodology, reporting and uncertainties points specified in
section 2 of applies to each point of
interest Hi measuring a element of a spatial packet loss vector.Sections 3.5 to 3.7 of give
requirements and applicability statements for end-to-end One-way ipdv
measurements. They are applicable to each point of interest Hi
involved in the measure. Spatial One-way ipdv measurement SHOULD be
respectful of methodology, clock, uncertainties and reporting aspects
given in this section.Generally, for a given Type-P of length L, in a given Hi, the
methodology for spatial vector metrics may proceed as follows:At each Hi, points of interest prepare to capture the packet
sent a time T, take a timestamp Ti', determine the internal delay
correction dTi' (See section 3.7.1. "Errors or uncertainties
related to Clocks" of ),Each Hi extracts the path ordering information from the packet
(e.g. time-to-live);Each Hi compute the wiretime from Src to Hi: Ti = Ti' - dTi'.
This arrival time is undefined (infinite) if the packet is not
detected after the 'loss threshold' duration;Each Hi extracts the timestamp T from the packet;Each Hi computes the one-way-delay from Src to Hi: dTi = Ti -
T;The reference point gathers the result of each Hi and order
them according to the path ordering information received to build
the type-P spatial one-way vector (e.g.
Type-P-Spatial-One-way-Delay-Vector metric <T, dT1, dT2,...,
dTn, dT> ) over the path <Src, H1, H2,..., Hn, Dst> at
time T.Loss threshold is the centrality of any methodology because it
determines the presence the packet in the measurement process of the
point of interest and consequently determines any ground truth
metric result. It determines the presence of an effective delay, and
bias the measure of ipdv, of packet loss and of the statistics.This is consistent for end-to-end but impacts spatial measure:
depending on the consistency of the loss threshold among the points
of interest, a packet may be considered loss a one host but present
in another one, or may be observed by the last host (last hop) of
the path but considered lost by Dst. The analysis of such results is
not deterministic: Has the path change? Does the packet arrive at
destination or was it lost during the last mile? The same applies,
of course, for one-way-delay measures: a delay measured may be
infinite at one host but a real value in another one, or may be
measured as a real value by the last host of the path but observed
as infinite by Dst. The loss threshold should be set up with the
same value in each host of the path and in the destination. The loss
threshold must be systematically reported to permit careful
introspection and to avoid the introduction of any contradiction in
the statistic computation process.The methodology given above relies on the order of the points of
interest over the path to one's.A test packets may cross several times the same host resulting in
the repetition of one or several hosts in the Path Digest.As an example. This occurs typically during rerouting phases
which introduce temporary micro loops. During such an event the host
path digest for a packet crossing Ha and Hb may include the pattern
<Hb, Ha, Hb, Ha, Hb> meaning that Ha ended the computation of
the new path before Hb and that the initial path wath from Ha to Hb
and that the new path is from Hb to Ha.Consequently, duplication of hosts in the Path Digest of a
vectors MUST be identified before statistics computation to avoid
corrupted results' production.This section defines samples to measure the performance of a segment
of a path over time. Definitions rely on matrix of the spatial vector
metrics defined above.Firstly it defines a sample of one-way delay,
Type-P-Segment-One-way-Delay-Stream, and a sample of packet loss,
Type-P-segment-Packet-loss-Stream.Then it defines 2 different samples of ipdv. The first metric,
Type-P-Segment-One-way-ipdv-prev-Stream, uses the previous packet as the
selection function. The second metric,
Type-P-Segment-One-way-ipdv-min-Stream, uses the minimum delay as the
selection.This metric defines a sample of One-way delays over time between a
pair of hosts of a path.As its semantic is very close to the metric
Type-P-Packet-loss-Stream defined in section 4 of , sections 4.5 to 4.8 of are part of the current definition.Type-P-Segment-One-way-Delay-StreamSrc*, the IP address of the sender.Dst*, the IP address of the receiver.P*, the specification of the packet type.i, an integer in the ordered list <1,2,...,n> of hosts
in the path.k, an integer which orders the packets sent.a and b, 2 integers where b > a.Hi, a host* of the path digest.<H1,..., Ha, ..., Hb, ...., Hn>, hosts path digest.<T1, T2, ..., Tm>, a list of times.The value of a Type-P-Segment-One-way-Delay-Stream is a pair
oflist of times <T1, T2, ..., Tm>;sequence of delays.Given 2 hosts, Ha and Hb, of the path <H1, H2,..., Ha, ...,
Hb, ..., Hn>, given the matrix of
Type-P-Spatial-One-way-Delay-Vector for the packets sent from Src to
Dst at times <T1, T2, ..., Tm-1, Tm> :<T1, dT1.1, dT1.2, ..., dT1.a, ..., dT1.b,..., dT1.n,
dT1>;<T2, dT2.1, dT2.2, ..., dT2.a, ..., dT2.b,..., dT2.n,
dT2>;...<Tm, dTm.1, dTm.2, ..., dTm.a, ..., dTm.b,..., dTm.n,
dTm>.We define the sample Type-P-segment-One-way-Delay-Stream as the
sequence <dT1.ab, dT2.ab, ..., dTk.ab, ..., dTm.ab> such that
for each time Tk, 'dTk.ab' is either the real number 'dTk.b - dTk.a'
if the packet send a time Tk passes Ha and Hb or undefined if this
packet never passes Ha or (inclusive) never passes Hb.Following are specific issues which may occur: the delay looks to decrease: dTi > DTi+1:This is typically due to clock synchronization issue.
this point is discussed in the section 3.7.1. "Errors or
uncertainties related to Clocks" of of ;This may occurs too when the clock resolution of one
probe is bigger than the minimum delay of a path. As an
example this happen when measuring the delay of a path which
is 500 km long with one probe synchronized using NTP having
a clock resolution of 8ms.The metric can not be performed on < T1 , T2, ..., Tm-1,
Tm> in the following cases: Ha or Hb disappears from the path due to some change of
routes;The order of Ha and Hb changes in the path;This metric defines a sample of packet lost over time between a
pair of hosts of a path. As its semantic is very close to the metric
Type-P-Packet-loss-Stream defined in section 3 of , sections 3.5 to 3.8 of are part of the current definition.Type-P-segment-Packet-loss-StreamSrc*, the IP address of the sender.Dst*, the IP address of the receiver.P*, the specification of the packet type.k, an integer which orders the packets sent.n, an integer which orders the hosts on the path.a and b, 2 integers where b > a.<H1, H2, ..., Ha, ..., Hb, ...,Hn>, hosts path
digest.Hi, exchange points of the path digest.<T1, T2, ..., Tm>, a list of times.<L1, L2, ..., Ln> a list of boolean values.The value of a Type-P-segment-Packet-loss-Stream is a pair
ofThe list of times <T1, T2, ..., Tm>;a sequence of booleans.Given 2 hosts, Ha and Hb, of the path <H1, H2,..., Ha, ...,
Hb, ..., Hn>, given the matrix of
Type-P-Spatial-Packet-loss-Vector for the packets sent from Src to
Dst at times <T1, T2, ..., Tm-1, Tm> : <L1.1, L1.2,..., L1.a, ..., L1.b, ..., L1.n, L>,<L2.1, L2.2,..., L2.a, ..., L2.b, ..., L2.n, L>,...,<Lm.1, Lm.2,..., Lma, ..., Lm.b, ..., Lm.n, L>.We define the value of the sample
Type-P-segment-Packet-Lost-Stream from Ha to Hb as the sequence of
booleans <L1.ab, L2.ab,..., Lk.ab, ..., Lm.ab> such that for
each Tk:A value of Lk of 0 means that Ha and Hb observed the packet
sent at time Tk (Lk.a and Lk.b have a value of 0);A value of Lk of 1 means that Ha observed the packet sent at
time Tk (Lk.a has a value of 0) and that Hb did not observed the
packet sent at time Tk (Lk.b have a value of 1);The value of Lk is undefined when Neither Ha or Hb observe
the packet;Unlike Type-P-Packet-loss-Stream,
Type-P-Segment-Packet-loss-Stream relies on the stability of the
host path digest. The metric can not be performed on < T1 , T2,
..., Tm-1, Tm> in the following cases: Ha or Hb disappears from the path due to some change of
routes;the order of Ha and Hb changes in the path;Lk.a or Lk.b is undefined;Lk.a has the value 1 (not observed) and Lk.b has the value 0
(observed);L has the value 0 (the packet was received by Dst) and Lk.ab
has the value 1 (the packet was lost between Ha and Hb).This metric defines a sample of ipdv
over time between a pair of hosts using the previous packet as the
selection function.Type-P-Segment-One-way-ipdv-prev-StreamSrc*, the IP address of the sender.Dst*, the IP address of the receiver.P*, the specification of the packet type.k, an integer which orders the packets sent.n, an integer which orders the hosts on the path.a and b, 2 integers where b > a.<H1, H2, ..., Ha, ..., Hb, ...,Hn>, the hosts path
digest.<T1, T2, ..., Tm-1, Tm>, a list of times.<Tk, dTk.1, dTk.2, ..., dTk.a, ..., dTk.b,..., dTk.n,
dTk>, a Type-P-Spatial-One-way-Delay-Vector.The value of a Type-P-Segment-One-way-ipdv-prev-Stream is a pair
of:The list of <T1, T2, ..., Tm-1, Tm>;A list of pairs of interval of times and delays;Given 2 hosts, Ha and Hb, of the path <H1, H2,..., Ha, ...,
Hb, ..., Hn>, given the matrix of
Type-P-Spatial-One-way-Delay-Vector for the packets sent from Src to
Dst at times <T1, T2, ..., Tm-1, Tm> :<T1, dT1.1, dT1.2, ..., dT1.a, ..., dT1.b,..., dT1.n,
dT1>,<T2, dT2.1, dT2.2, ..., dT2.a, ..., dT2.b,..., dT2.n,
dT2>,...<Tm, dTm.1, dTm.2, ..., dTm.a, ..., dTm.b,..., dTm.n,
dTm>.We define the Type-P-Segment-One-way-ipdv-prev-Stream as the
sequence of pair of packet intervals and delay variations
<(dT2_1.a , dT2.ab - dT1.ab) ,..., (dTk_k-1.a, dTk.ab -
dTk-1.ab), ..., (dTm_m-1.a, dTm.ab - dTm-1.ab)> such that for
each Tk:dTk_k-1.a is either undefined if the delay dTk.a or the delay
dTk-1.a is undefined, or the interval of time, 'dTk.a -
dTk-1.a', between the 2 packets at Ha;dTk_k-1.ab, is either undefined if one of the delays dTk.b,
dTk.a, dTk-1.b or dTk-1.a is undefined, or , (dTk.b - dTk.a) -
(dTk-1.b - dTk-1.a), the delay variation from Ha to Hb between
the 2 packets sent at time Tk and Tk-1.This metric belongs to the family of inter packet delay variation
metrics (IPDV in upper case) which results can be extremely
sensitive to the inter-packet interval.The inter-packet interval of a end-to-end IPDV metric is under
the control of the ingress point of interest which corresponds
exactly to the Source of the packet. Unlikely, the inter-packet
interval of a segment IPDV metric is not under the control the
ingress point of interest of the measure, Ha. However, the interval
will vary if there is delay variation between the Source and Ha.
Therefore, the actual inter-packet interval must be known at Ha in
order to fully comprehend the delay variation between Ha and Hb.This metric defines a sample of ipdv
over time between a pair of hosts of a path using the shortest delay
as the selection function.Type-P-Segment-One-way-ipdv-min-StreamSrc*, the IP address of the sender.Dst*, the IP address of the receiver.P*, the specification of the packet type.k, an integer which orders the packets sent.i, an integer which identifies a packet sent.n, an integer which orders the hosts on the path.a and b, 2 integers where b > a.<H1, H2, ..., Ha, ..., Hb, ...,Hn>, the hosts path
digest.<T1, T2, ..., Tm-1, Tm>, a list of times.<Tk, dTk.1, dTk.2, ..., dTk.a, ..., dTk.b,..., dTk.n,
dTk>, a Type-P-Spatial-One-way-Delay-Vector.The value of a Type-P-Segment-One-way-ipdv-min-Stream is a pair
of:The list of <T1, T2, ..., Tm-1, Tm>;A list of times;Given 2 hosts, Ha and Hb, of the path <H1, H2,..., Ha, ...,
Hb, ..., Hn>, given the matrix of
Type-P-Spatial-One-way-Delay-Vector for the packets sent from Src to
Dst at times <T1, T2, ..., Tm-1, Tm> :<T1, dT1.1, dT1.2, ..., dT1.a, ..., dT1.b,..., dT1.n,
dT1>,<T2, dT2.1, dT2.2, ..., dT2.a, ..., dT2.b,..., dT2.n,
dT2>,...<Tm, dTm.1, dTm.2, ..., dTm.a, ..., dTm.b,..., dTm.n,
dTm>.We define the Type-P-Segment-One-way-ipdv-min-Stream as the
sequence of times <dT1.ab - min(dTi.ab) ,..., dTk.ab -
min(dTi.ab), ..., dTm.ab - min(dTi.ab)> such that:min(dTi.ab) is the minimum value of the tuples (dTk.b -
dTk.a);for each time Tk, dTk.ab is undefined if dTk.a or (inclusive)
dTk.b is undefined, or the real number (dTk.b - dTk.a).This metric belongs to the family of packet delay variation
metrics (PDV). PDV distributions are less sensitive to inter-packet
interval variations than IPDV results.In principle, the PDV distribution reflects the variation over
many different inter-packet intervals, from the smallest
inter-packet interval, up to the length of the evaluation interval,
Tm - T1. Therefore, when delay variation occurs and disturbs the
packet spacing observed at Ha, the PDV results will likely compare
favorably to a PDV measurement where the source is Ha and the
destination is Hb.This metric defines metrics to measure the performance between a
source and a group of receivers.This metric defines a metric to measure one-way delay between a
source and a group of receivers.Type-P-One-to-group-One-way-Delay-VectorSrc, the IP address of a host acting as the source.Recv1,..., RecvN, the IP addresses of the N hosts acting as
receivers.T, a time.dT1,...,dTn a list of time.P, the specification of the packet type.Gr, the receiving group identifier. The parameter Gr is the
multicast group address if the measured packets are transmitted
over IP multicast. This parameter is to differentiate the measured
traffic from other unicast and multicast traffic. It is optional
in the metric to avoid losing any generality, i.e. to make the
metric also applicable to unicast measurement where there is only
one receiver.The value of a Type-P-One-to-group-One-way-Delay-Vector is a set
of Type-P-One-way-Delay singletons .Given a Type P packet sent by the source Src at Time T, given the
N hosts { Recv1,...,RecvN } which receive the packet at the time {
T+dT1,...,T+dTn }, a Type-P-One-to-group-One-way-Delay-Vector is
defined as the set of the Type-P-One-way-Delay singleton between Src
and each receiver with value of { dT1, dT2,...,dTn }.Type-P-One-to-group-One-way-Packet-Loss-VectorSrc, the IP address of a host acting as the source.Recv1,..., RecvN, the IP addresses of the N hosts acting as
receivers.T, a time.T1,...,Tn a list of time.P, the specification of the packet type.Gr, the receiving group identifier.The value of a Type-P-One-to-group-One-way-Packet-Loss-Vector is
a set of Type-P-One-way-Packet-Loss singletons .Given a Type P packet sent by the source Src at T and the N
hosts, Recv1,...,RecvN, which should receive the packet at
T1,...,Tn, a Type-P-One-to-group-One-way-Packet-Loss-Vector is
defined as a set of the Type-P-One-way-Packet-Loss singleton between
Src and each of the receivers {<T1,0|1>,<T2,0|1>,...,
<Tn,0|1>}.Type-P-One-to-group-One-way-ipdv-VectorSrc, the IP address of a host acting as the source.Recv1,..., RecvN, the IP addresses of the N hosts acting as
receivers.T1, a time.T2, a time.ddT1, ...,ddTn, a list of time.P, the specification of the packet type.F, a selection function defining unambiguously the two
packets from the stream selected for the metric.Gr, the receiving group identifier. The parameter Gr is the
multicast group address if the measured packets are transmitted
over IP multicast. This parameter is to differentiate the
measured traffic from other unicast and multicast traffic. It is
optional in the metric to avoid losing any generality, i.e. to
make the metric also applicable to unicast measurement where
there is only one receiver.The value of a Type-P-One-to-group-One-way-ipdv-Vector is a set
of Type-P-One-way-ipdv singletons .Given a Type P packet stream,
Type-P-One-to-group-One-way-ipdv-Vector is defined for two packets
from the source Src to the N hosts {Recv1,...,RecvN },which are
selected by the selection function F, as the difference between the
value of the Type-P-One-to-group-One-way-Delay-Vector from Src to {
Recv1,..., RecvN } at time T1 and the value of the
Type-P-One-to-group-One-way-Delay-Vector from Src to {
Recv1,...,RecvN } at time T2. T1 is the wire-time at which Src sent
the first bit of the first packet, and T2 is the wire-time at which
Src sent the first bit of the second packet. This metric is derived
from the Type-P-One-to-group-One-way-Delay-Vector metric.Therefore, for a set of real number
{ddT1,...,ddTn},Type-P-One-to-group-One-way-ipdv-Vector from Src to
{ Recv1,...,RecvN } at T1, T2 is {ddT1,...,ddTn} means that Src sent
two packets, the first at wire-time T1 (first bit), and the second
at wire-time T2 (first bit) and the packets were received by {
Recv1,...,RecvN } at wire-time {dT1+T1,...,dTn+T1}(last bit of the
first packet), and at wire-time {dT'1+T2,...,dT'n+T2} (last bit of
the second packet), and that {dT'1-dT1,...,dT'n-dTn}
={ddT1,...,ddTn}.The defined one-to-group metrics above can all be directly achieved
from the relevant unicast one-way metrics. They collect all unicast
measurement results of one-way metrics together in one profile and sort
them by receivers and packets in a receiving group. They provide
sufficient information regarding the network performance in terms of
each receiver and guide engineers to identify potential problem happened
on each branch of a multicast routing tree. However, these metrics
cannot be directly used to conveniently present the performance in terms
of a group and neither to identify the relative performance
situation.From the performance point of view, the multiparty communication
services not only require the absolute performance support but also the
relative performance. The relative performance means the difference
between absolute performance of all users. Directly using the one-way
metrics cannot present the relative performance situation. However, if
we use the variations of all users one-way parameters, we can have new
metrics to measure the difference of the absolute performance and hence
provide the threshold value of relative performance that a multiparty
service might demand. A very good example of the high relative
performance requirement is the online gaming. A very light difference in
delay might result in failure in the game. We have to use multicast
specific statistic metrics to define exactly how small the relative
delay the online gaming requires. There are many other services, e.g.
online biding, online stock market, etc., that require multicast metrics
in order to evaluate the network against their requirements. Therefore,
we can see the importance of new, multicast specific, statistic metrics
to feed this need.We might also use some one-to-group statistic conceptions to present
and report the group performance and relative performance to save the
report transmission bandwidth. Statistics have been defined for One- way
metrics in corresponding RFCs. They provide the foundation of definition
for performance statistics. For instance, there are definitions for
minimum and maximum One-way delay in [RFC2679]. However, there is a
dramatic difference between the statistics for one-to-one communications
and for one-to-many communications. The former one only has statistics
over the time dimension while the later one can have statistics over
both time and space dimensions. This space dimension is introduced by
the Matrix concept as illustrated in . For a Matrix M each row is a set of
One-way singletons spreading over the time dimension and each column is
another set of One-way singletons spreading over the space
dimension.In Matrix M, each element is a one-way delay singleton. Each column
is a delay vector contains the One-way delays of the same packet
observed at M points of interest. It implies the geographical factor of
the performance within a group. Each row is a set of One-way delays
observed during a sampling interval at one of the points of interest. It
presents the delay performance at a receiver over the time
dimension.Therefore, one can either calculate statistics by rows over the space
dimension or by columns over the time dimension. It's up to the
operators or service provides which dimension they are interested in.
For example, a TV broadcast service provider might want to know the
statistical performance of each user in a long term run to make sure
their services are acceptable and stable. While for an online gaming
service provider, he might be more interested to know if all users are
served fairly by calculating the statistics over the space dimension.
This memo does not intend to recommend which of the statistics are
better than the other.To save the report transmission bandwidth, each point of interest can
send statistics in a pre-defined time interval to the reference point
rather than sending every one-way singleton it observed. As long as an
appropriate time interval is decided, appropriate statistics can
represent the performance in a certain accurate scale. How to decide the
time interval and how to bootstrap all points of interest and the
reference point depend on applications. For instance, applications with
lower transmission rate can have the time interval longer and ones with
higher transmission rate can have the time interval shorter. However,
this is out of the scope of this memo.Moreover, after knowing the statistics over the time dimension, one
might want to know how this statistics distributed over the space
dimension. For instance, a TV broadcast service provider had the
performance Matrix M and calculated the One-way delay mean over the time
dimension to obtain a delay Vector as {V1,V2,..., VN}. He then
calculated the mean of all the elements in the Vector to see what level
of delay he has served to all N users. This new delay mean gives
information on how good the service has been delivered to a group of
users during a sampling interval in terms of delay. It needs twice
calculation to have this statistic over both time and space dimensions.
We name this kind of statistics 2-level statistics to distinct with
those 1-level statistics calculated over either space or time dimension.
It can be easily prove that no matter over which dimension a 2-level
statistic is calculated first, the results are the same. I.e. one can
calculate the 2-level delay mean using the Matrix M by having the
1-level delay mean over the time dimension first and then calculate the
mean of the obtained vector to find out the 2-level delay mean. Or, he
can do the 1-level statistic calculation over the space dimension first
and then have the 2-level delay mean. Both two results will be exactly
the same. Therefore, when define a 2-level statistic, there is no need
to specify in which procedure the calculation should follow.Comment: The above statement depends on whether the order of
operations has any affect on the outcome.Many statistics can be defined for the proposed one-to-group metrics
over either the space dimension or the time dimension or both. This memo
treats the case where a stream of packets from the Source results in a
sample at each of the Receivers in the Group, and these samples are each
summarized with the usual statistics employed in one-to-one
communication. New statistic definitions are presented, which summarize
the one-to-one statistics over all the Receivers in the Group.The packet loss does have effects on one-way metrics and their
statistics. For example, the lost packet can result an infinite
one-way delay. It is easy to handle the problem by simply ignoring the
infinite value in the metrics and in the calculation of the
corresponding statistics. However, the packet loss has so strong
impact on the statistics calculation for the one-to-group metrics that
it can not be solved by the same method used for one-way metrics. This
is due to the complex of building a Matrix, which is needed for
calculation of the statistics proposed in this memo.The situation is that measurement results obtained by different end
users might have different packet loss pattern. For example, for
User1, packet A was observed lost. And for User2, packet A was
successfully received but packet B was lost. If the method to overcome
the packet loss for one-way metrics is applied, the two singleton sets
reported by User1 and User2 will be different in terms of the
transmitted packets. Moreover, if User1 and User2 have different
number of lost packets, the size of the results will be different.
Therefore, for the centralized calculation, the reference point will
not be able to use these two results to build up the group Matrix and
can not calculate the statistics. In an extreme situation, no single
packet arrives all users in the measurement and the Matrix will be
empty. One of the possible solutions is to replace the
infinite/undefined delay value by the average of the two adjacent
values. For example, if the result reported by user1 is { R1dT1 R1dT2
R1dT3 … R1dTK-1 UNDEF R1dTK+1… R1DM } where
“UNDEF” is an undefined value, the reference point can
replace it by R1dTK = {(R1dTK-1)+( R1dTK+1)}/2. Therefore, this result
can be used to build up the group Matrix with an estimated value
R1dTK. There are other possible solutions such as using the overall
mean of the whole result to replace the infinite/undefined value, and
so on. However this is out of the scope of this memo.For the distributed calculation, the reported statistics might have
different “weight” to present the group performance, which
is especially true for delay and ipdv relevant metrics. For example,
User1 calculates the Type-P-Finite-One-way-Delay-Mean R1DM as shown in
Figure. 8 without any packet loss and User2 calculates the R2DM with
N-2 packet loss. The R1DM and R2DM should not be treated with equal
weight because R2DM was calculated only based on 2 delay values in the
whole sample interval. One possible solution is to use a weight factor
to mark every statistic value sent by users and use this factor for
further statistic calculation.Src, the IP address of a host;G, the receiving group identifier;N, the number of Receivers (Recv1, Recv2, ... RecvN);T, a time (start of test interval);Tf, a time (end of test interval);K, the number of packets sent from the source during the test
interval;J[n], the number of packets received at a particular Receiver,
n, where 1<=n<=N;lambda, a rate in reciprocal seconds (for Poisson Streams);incT, the nominal duration of inter-packet interval, first bit
to first bit (for Periodic Streams);T0, a time that MUST be selected at random from the interval
[T, T+I] to start generating packets and taking measurements (for
Periodic Streams);TstampSrc, the wire time of the packet as measured at MP(Src)
(the Source Measurement Point);TstampRecv, the wire time of the packet as measured at
MP(Recv), assigned to packets that arrive within a "reasonable"
time;Tmax, a maximum waiting time for packets at the destination,
set sufficiently long to disambiguate packets with long delays
from packets that are discarded (lost), thus the distribution of
delay is not truncated;dT, shorthand notation for a one-way delay singleton value;L, shorthand notation for a one-way loss singleton value,
either zero or one, where L=1 indicates loss and L=0 indicates
arrival at the destination within TstampSrc + Tmax, may be indexed
over n Receivers;DV, shorthand notation for a one-way delay variation singleton
value;This section defines the overall one-way delay statistics for a
receiver and for an entire group as illustrated by the matrix
below.Statistics are computed on the finite One-way delays of the matrix
above.All One-to-group delay statistics are expressed in seconds with
sufficient resolution to convey 3 significant digits.This section defines Type-P-One-to-Group-Receiver-n-Mean-Delay
the Delay Mean at each Receiver N, also named RnDM.We obtain the value of Type-P-One-way-Delay singleton for all
packets sent during the test interval at each Receiver
(Destination), as per . For each
packet that arrives within Tmax of its sending time, TstampSrc, the
one-way delay singleton (dT) will be the finite value TstampRecv[i]
- TstampSrc[i] in units of seconds. Otherwise, the value of the
singleton is Undefined.where all packets i= 1 through J[n] have finite singleton
delays.This section defines Type-P-One-to-Group-Mean-Delay, the Mean
One-way delay calculated over the entire Group, also named GMD.Note that the Group Mean Delay can also be calculated by summing
the Finite one-way Delay singletons in the Matrix, and dividing by
the number of Finite One-way Delay singletons.This section defines a metric for the range of mean delays over
all N receivers in the Group, (R1DM, R2DM,...RnDM).Type-P-One-to-Group-Range-Mean-Delay = GRMD = max(RnDM) -
min(RnDM)This section defines a metric for the maximum of mean delays over
all N receivers in the Group, (R1DM, R2DM,...RnDM).Type-P-One-to-Group-Max-Mean-Delay = GMMD = max(RnDM)This section defines the overall one-way loss statistics for a
receiver and for an entire group as illustrated by the matrix
below.Statistics are computed on the sample of Type-P-One-way-Packet-Loss
of the matrix above.All loss ratios are expressed in units of packets lost to total
packets sent.Given a Matrix of loss singletons as illustrated above, determine
the Type-P-One-way-Packet-Loss-Average for the sample at each
receiver, according to the definitions and method of . The Type-P-One-way-Packet-Loss-Average and
the Type-P-One-to-Group-Receiver-n-Loss-Ratio, also named RnLR, are
equivalent metrics. In terms of the parameters used here, these
metrics definitions can be expressed asUsually, the number of packets sent is used in the denominator of
packet loss ratio metrics. For the comparative metrics defined here,
the denominator is the maximum number of packets received at any
receiver for the sample and test interval of interest.The Comparative Loss Ratio, also named, RnCLR, is defined
asType-P-One-to-Group-Loss-Ratio, the overall Group loss ratio,
also named GLR, is defined asThe One-to-Group Loss Ratio Range is defined as:Type-P-One-to-Group-Range-Loss-Ratio = max(RnLR) - min(RnLR)It is most effective to indicate the range by giving both the max
and minimum loss ratios for the Group, rather than only reporting
the difference between them.This section defines one-way delay variation (DV) statistics for an
entire group as illustrated by the matrix below.Statistics are computed on the sample of
Type-P-One-way-Delay-Variation singletons of the group delay variation
matrix above where RnddTk is the Type-P-One-way-Delay-Variation
singleton evaluated at Receiver n for the packet k and where RnDV is
the point-to-point one-way packet delay variation for Receiver n.All One-to-group delay variation statistics are expressed in
seconds with sufficient resolution to convey 3 significant digits.This section defines a metric for the range of delays variation
over all N receivers in the Group.Maximum DV and minimum DV over all receivers summarize the
performance over the Group (where DV is a point-to-point metric).
For each receiver, the DV is usually expressed as the 1-10^(-3)
quantile of one-way delay minus the minimum one-way delay.Type-P-One-to-Group-Delay-Variation-Range = GDVR == max(RnDV) – min(RnDV) for all n receiversThis range is determined from the minimum and maximum values of
the point-to-point one-way IP Packet Delay Variation for the set of
Destinations in the group and a population of interest, using the
Packet Delay Variation expressed as the 1-10^-3 quantile of one-way
delay minus the minimum one-way delay. If a more demanding service
is considered, one alternative is to use the 1-10^-5 quantile, and
in either case the quantile used should be recorded with the
results. Both the minimum and the maximum delay variation are
recorded, and both values are given to indicate the location of the
range.Virtually all the guidance on measurement processes supplied by the
earlier IPPM RFCs (such as and ) for one-to-one scenarios is applicable here in
the spatial and multiparty measurement scenario. The main difference is
that the spatial and multiparty configurations require multiple points
of interest where a stream of singletons will be collected. The amount
of information requiring storage grows with both the number of metrics
and the points of interest, so the scale of the measurement architecture
multiplies the number of singleton results that must be collected and
processed.It is possible that the architecture for results collection involves
a single reference point with connectivity to all the points of
interest. In this case, the number of points of interest determines both
storage capacity and packet transfer capacity of the host acting as the
reference point. However, both the storage and transfer capacity can be
reduced if the points of interest are capable of computing the summary
statistics that describe each measurement interval. This is consistent
with many operational monitoring architectures today, where even the
individual singletons may not be stored at each point of interest.In recognition of the likely need to minimize form of the results for
storage and communication, the Group metrics above have been constructed
to allow some computations on a per-Receiver basis. This means that each
Receiver's statistics would normally have an equal weight with all other
Receivers in the Group (regardless of the number of packets
received).The scalability issue can be raised when there are thousands of
points of interest in a group who are trying to send back the
measurement results to the reference point for further processing and
analysis. The points of interest can send either the whole measured
sample or only the calculated statistics. The former one is a
centralized statistic calculation method and the latter one is a
distributed statistic calculation method. The sample should include
all metrics parameters, the values and the corresponding sequence
numbers. The transmission of the whole sample can cost much more
bandwidth than the transmission of the statistics that should include
all statistic parameters specified by policies and the additional
information about the whole sample, such as the size of the sample,
the group address, the address of the point of interest, the ID of the
sample session, and so on. Apparently, the centralized calculation
method can require much more bandwidth than the distributed
calculation method when the sample size is big. This is especially
true when the measurement has huge number of the points of interest.
It can lead to a scalability issue at the reference point by over load
the network resources. The distributed calculation method can save
much more bandwidth and release the pressure of the scalability issue
at the reference point side. However, it can result in the lack of
information because not all measured singletons are obtained for
building up the group matrix. The performance over time can be hidden
from the analysis. For example, the loss pattern can be missed by
simply accepting the loss ratio as well as the delay pattern. This
tradeoff between the bandwidth consuming and the information acquiring
has to be taken into account when design the measurement campaign to
optimize the measurement results delivery. The possible solution could
be to transit the statistic parameters to the reference point first to
obtain the general information of the group performance. If the detail
results are required, the reference point should send the requests to
the points of interest, which could be particular ones or the whole
group. This procedure can happen in the off peak time and can be well
scheduled to avoid delivery of too many points of interest at the same
time. Compression techniques can also be used to minimize the
bandwidth required by the transmission. This could be a measurement
protocol to report the measurement results. However, this is out of
the scope of this memo.To prevent any bias in the result, the configuration of a
one-to-many measure must take in consideration that implicitly more
packets will to be routed than send and selects a test packets rate
that will not impact the network performance.This section presents the impact of the aggregation order on the
scalability of the reporting and of the computation. It makes the
hypothesis that receivers are managed remotely and not co-located.multimetrics samples represented a matrix as illustrated below2 methods are available to compute statistics on the resulting
matrix: metric is computed over time and then over space;metric is computed over space and then over time.They differ only by the order of the time and of the space
aggregation. View as a matrix this order is neutral as does not impact
the result, but the impact on a measurement deployment is
critical.In both cases the volume of data to report is proportional to the
number of probes. But there is a major difference between these 2
methods: method2: In space and time aggregation mode the volume of data
to collect is proportional to the number of test packets received;
Each received packet RiSi triggers out a block of data that must
be reported to a common place for computing the stat over
space;method1: In time and space aggregation mode the volume of data
to collect is proportional to the period of aggregation, so it
does not depend on the number of packet received;Method 2 property has severe drawbacks in terms of security and
dimensioning: The increasing of the rate of the test packets may result in a
sort of DoS toward the computation points;The dimensioning of a measurement system is quite impossible to
validate.The time aggregation interval provides the reporting side with a
control of various collecting aspects such as bandwidth and
computation and storage capacities. So this draft defines metrics
based on method 1.Note: In some specific cases one may need sample of singletons over
space. To address this need it is suggested firstly to limit the
number of test and the number of test packets per seconds. Then
reducing the size of the sample over time to one packet give sample of
singleton over space..2 methods are available to compute spatial statistics: method 1: spatial segment metrics and statistics are
preferably computed over time by each points of interest;method 2: Vectors metrics are intrinsically instantaneous
space metrics which must be reported using method2 whenever
instantaneous metrics information is needed.2 methods are available to compute group statistics: method1: and illustrate the method chosen: the
one-to-one statistic is computed per interval of time before the
computation of the mean over the group of receivers;method2: presents
the second one, metric is computed over space and then over
time.Usually IPPM WG documents defines each metric reporting within its
definition. This document defines the reporting of all the metrics
introduced in a single section to provide consistent information, to
avoid repetitions and to conform to IESG recommendation of gathering
manageability considerations in a dedicated section.Information models of spatial metrics and of one-to-group metrics are
similar excepted that points of interests of spatial vectors must be
ordered.The complexity of the reporting relies on the number of points of
interests.The reporting of spatial metrics shares a lot of aspects with
RFC2679-80. New ones are common to all the definitions and are mostly
related to the reporting of the path and of methodology parameters
that may bias raw results analysis. This section presents these
specific parameters and then lists exhaustively the parameters that
shall be reported.End-to-end metrics can't determine the path of the measure
despite IPPM RFCs recommend it to be reported (See Section 3.8.4 of
). Spatial metrics vectors provide
this path. The report of a spatial vector must include the points of
interests involved: the sub set of the hosts of the path
participating to the instantaneous measure.A spatial vector must order the points of interest according to
their order in the path. It is highly suggested to use the TTL in
IPv4, the Hop Limit in IPv6 or the corresponding information in
MPLS.The report of a spatial vector must include the ordered list of
the hosts involved in the instantaneous measure.The location of the point of interest inside a node influences
the timestamping skew and accuracy. As an example, consider that
some internal machinery delays the timestamping up to 3 milliseconds
then the minimal uncertainty reported be 3 ms if the internal delay
is unknown at the time of the timestamping.The report of a spatial vector must include the uncertainty of
the timestamping compared to wire time.The reporting includes information to report for one-way-delay as
the Section 3.6 of . The same apply
for packet loss and ipdv.All reporting rules described in RFC2679-80 apply to the
corresponding One-to-group metrics. Following are specific parameters
that should be reported.As suggested by the RFC2679-80, the path traversed by the packet
SHOULD be reported, if possible. For One-to-group metrics, there is
a path tree SHOULD be reported rather than A path. This is even more
impractical. If, by anyway, partial information is available to
report, it might not be as valuable as it is in the one-to-one case
because the incomplete path might be difficult to identify its
position in the path tree. For example, how many points of interest
are reached by the packet traveled through this incomplete path?The group size should be reported as one of the critical
management parameters. Unlike the spatial metrics, there is no need
of order of points of interests.It is the same as described in section 9.1.3.It is the same as described in section 9.1.4.As explained in section 8, the measurement method will have
impact on the analysis of the measurement result. Therefore, it
should be reported.IANA assigns each metric defined by the IPPM WG with a unique
identifier as per in the
IANA-IPPM-METRICS-REGISTRY-MIB.This section presents the elements of information and the usage of
the information reported for network performance analysis. It is out
of the scope of this section to define how the information is
reported.The information model is build with pieces of information
introduced and explained in one-way delay definitions , in packet loss definitions and in IPDV definitions of and . It
includes not only information given by "Reporting the metric" sections
but by sections "Methodology" and "Errors and Uncertainties"
sections.Following are the elements of information taken from end-to-end
definitions referred in this memo and from spatial and multicast
metrics it defines:Packet_type, The Type-P of test packets (Type-P);Packet_length, a packet length in bits (L);Src_host, the IP address of the sender;Dst_host, the IP address of the receiver;Hosts_serie: <H1, H2,..., Hn>, a list of points of
interest;Loss_threshold: The threshold of infinite delay;Systematic_error: constant delay between wire time and
timestamping;Calibration_error: maximal uncertainty;Src_time, the sending time for a measured packet;Dst_time, the receiving time for a measured packet;Result_status : an indicator of usability of a result 'Resource
exhaustion' 'infinite', 'lost';Delays_serie: <dT1,..., dTn> a list of delays;Losses_serie: <B1, B2, ..., Bi, ..., Bn>, a list of
Boolean values (spatial) or a set of Boolean values
(one-to-group);Result_status_serie: a list of results status;dT: a delay;Singleton_number: a number of singletons;Observation_duration: An observation duration;metric_identifier.Following is the information of each vector that should be
available to compute samples:Packet_type;Packet_length;Src_host, the sender of the packet;Dst_host, the receiver of the packet, apply only for spatial
vectors;Hosts_serie: not ordered for one-to-group;Src_time, the sending time for the measured packet;dT, the end-to-end one-way delay for the measured packet, apply
only for spatial vectors;Delays_serie: apply only for delays and ipdv vector, not
ordered for one-to-group;Losses_serie: apply only for packets loss vector, not ordered
for one-to-group;Result_status_serie;Observation_duration: the difference between the time of the
last singleton and the time of the first singleton.Following is the context information (measure, points of
interests) that should be available to compute samples :Loss threshold;Systematic error: constant delay between wire time and
timestamping;Calibration error: maximal uncertainty;A spatial or a one-to-group sample is a collection of singletons
giving the performance from the sender to a single point of interest.
Following is the information that should be available for each sample
to compute statistics:Packet_type;Packet_length;Src_host, the sender of the packet;Dst_host, the receiver of the packet;Start_time, the sending time of the first packet;Delays_serie: apply only for delays and ipdv samples;Losses_serie: apply only for packets loss samples;Result_status_serie;Observation_duration: the difference between the time of the
last singleton of the last sample and the time of the first
singleton of the first sample.Following is the context information (measure, points of
interests) that should be available to compute statistics :Loss threshold;Systematic error: constant delay between wire time and
timestamping;Calibration error: maximal uncertainty;Following is the information of each statistic that should be
reported:Result;Start_time;Duration;Result_status;Singleton_number, the number of singletons the statistic is
computed on;Spatial and one-to-group metrics are defined on the top of end-to-end
metrics. Security considerations discussed in One-way delay metrics
definitions of , in packet loss metrics
definitions of and in IPDV metrics
definitions of and apply to metrics defined in this memo.Malicious generation of packets with spoofing addresses may corrupt
the results without any possibility to detect the spoofing.Malicious generation of packets which match systematically the hash
function used to detect the packets may lead to a DoS attack toward
the point of reference.Reporting of measurement results from a huge number of probes may
overload reference point ressources (network, network interfaces,
computation capacities ...).The configuration of a measurement must take in consideration that
implicitly more packets will to be routed than send and selects a test
packets rate accordingly. Collecting statistics from a huge number of
probes may overload any combination of the network where the
measurement controller is attached to, measurement controller network
interfaces and measurement controller computation capacities.One-to-group metrics measurement should consider using source
authentication protocols, standardized in the MSEC group, to avoid
fraud packet in the sampling interval. The test packet rate could be
negotiated before any measurement session to avoid deny of service
attacks.Lei would like to acknowledge Prof. Zhili Sun from CCSR, University
of Surrey, for his instruction and helpful comments on this work.Metrics defined in this memo Metrics defined in this memo are
designed to be registered in the IANA IPPM METRICS REGISTRY as described
in initial version of the registry :IANA is asked to register the following metrics in the
IANA-IPPM-METRICS-REGISTRY-MIB :ietfSpatialOneWayDelayVector OBJECT-IDENTITYSTATUS currentDESCRIPTION"Type-P-Spatial-One-way-Delay-Vector"REFERENCE"Reference "RFCyyyy, section 4.1."-- RFC Ed.: replace yyyy with actual RFC number & remove
this note := { ianaIppmMetrics nn } -- IANA assigns nnietfSpatialPacketLossVector OBJECT-IDENTITYSTATUS currentDESCRIPTION"Type-P-Spatial-Packet-Loss-Vector"REFERENCE"Reference "RFCyyyy, section 4.2."-- RFC Ed.: replace yyyy with actual RFC number & remove
this note := { ianaIppmMetrics nn } -- IANA assigns nnietfSpatialOneWayIpdvVector OBJECT-IDENTITYSTATUS currentDESCRIPTION"Type-P-Spatial-One-way-ipdv-Vector"REFERENCE"Reference "RFCyyyy, section 4.3."-- RFC Ed.: replace yyyy with actual RFC number & remove
this note := { ianaIppmMetrics nn } -- IANA assigns nnietfSegmentOneWayDelayStream OBJECT-IDENTITYSTATUS currentDESCRIPTION"Type-P-Segment-One-way-Delay-Stream"REFERENCE"Reference "RFCyyyy, section 5.1."-- RFC Ed.: replace yyyy with actual RFC number & remove
this note := { ianaIppmMetrics nn } -- IANA assigns nnietfSegmentPacketLossStream OBJECT-IDENTITYSTATUS currentDESCRIPTION"Type-P-Segment-Packet-Loss-Stream"REFERENCE"Reference "RFCyyyy, section 5.2."-- RFC Ed.: replace yyyy with actual RFC number & remove
this note := { ianaIppmMetrics nn } -- IANA assigns nnietfSegmentOneWayIpdvPrevStream OBJECT-IDENTITYSTATUS currentDESCRIPTION"Type-P-Segment-One-way-ipdv-prev-Stream"REFERENCE"Reference "RFCyyyy, section 5.3."-- RFC Ed.: replace yyyy with actual RFC number & remove
this note := { ianaIppmMetrics nn } -- IANA assigns nnietfSegmentOneWayIpdvMinStream OBJECT-IDENTITYSTATUS currentDESCRIPTION"Type-P-Segment-One-way-ipdv-min-Stream"REFERENCE"Reference "RFCyyyy, section 5.4."-- RFC Ed.: replace yyyy with actual RFC number & remove
this note := { ianaIppmMetrics nn } -- IANA assigns nn-- One-to-group metricsietfOneToGroupOneWayDelayVector OBJECT-IDENTITYSTATUS currentDESCRIPTION"Type-P-One-to-group-One-way-Delay-Vector"REFERENCE"Reference "RFCyyyy, section 6.1."-- RFC Ed.: replace yyyy with actual RFC number & remove
this note := { ianaIppmMetrics nn } -- IANA assigns nnietfOneToGroupOneWayPktLossVector OBJECT-IDENTITYSTATUS currentDESCRIPTION"Type-P-One-to-Group-One-way-Packet-Loss-Vector"REFERENCE"Reference "RFCyyyy, section 6.2."-- RFC Ed.: replace yyyy with actual RFC number & remove
this note := { ianaIppmMetrics nn } -- IANA assigns nnietfOneToGroupOneWayIpdvVector OBJECT-IDENTITYSTATUS currentDESCRIPTION"Type-P-One-to-Group-One-way-ipdv-Vector"REFERENCE"Reference "RFCyyyy, section 6.3."-- RFC Ed.: replace yyyy with actual RFC number & remove
this note := { ianaIppmMetrics nn } -- IANA assigns nn-- One to group statistics--ietfOnetoGroupReceiverNMeanDelay OBJECT-IDENTITYSTATUS currentDESCRIPTION"Type-P-One-to-Group-Receiver-n-Mean-Delay"REFERENCE"Reference "RFCyyyy, section 7.3.1."-- RFC Ed.: replace yyyy with actual RFC number & remove
this note := { ianaIppmMetrics nn } -- IANA assigns nnietfOneToGroupMeanDelay OBJECT-IDENTITYSTATUS currentDESCRIPTION"Type-P-One-to-Group-Mean-Delay"REFERENCE"Reference "RFCyyyy, section 7.3.2."-- RFC Ed.: replace yyyy with actual RFC number & remove
this note := { ianaIppmMetrics nn } -- IANA assigns nnietfOneToGroupRangeMeanDelay OBJECT-IDENTITYSTATUS currentDESCRIPTION"Type-P-One-to-Group-Range-Mean-Delay"REFERENCE"Reference "RFCyyyy, section 7.3.3."-- RFC Ed.: replace yyyy with actual RFC number & remove
this note := { ianaIppmMetrics nn } -- IANA assigns nnietfOneToGroupMaxMeanDelay OBJECT-IDENTITYSTATUS currentDESCRIPTION"Type-P-One-to-Group-Max-Mean-Delay"REFERENCE"Reference "RFCyyyy, section 7.3.4."-- RFC Ed.: replace yyyy with actual RFC number & remove
this note := { ianaIppmMetrics nn } -- IANA assigns nnietfOneToGroupReceiverNLossRatio OBJECT-IDENTITYSTATUS currentDESCRIPTION"Type-P-One-to-Group-Receiver-n-Loss-Ratio"REFERENCE"Reference "RFCyyyy, section 7.4.1."-- RFC Ed.: replace yyyy with actual RFC number & remove
this note := { ianaIppmMetrics nn } -- IANA assigns nn--ietfOneToGroupReceiverNCompLossRatio OBJECT-IDENTITYSTATUS currentDESCRIPTION"Type-P-One-to-Group-Receiver-n-Comp-Loss-Ratio"REFERENCE"Reference "RFCyyyy, section 7.4.2."-- RFC Ed.: replace yyyy with actual RFC number & remove
this note := { ianaIppmMetrics nn } -- IANA assigns nnietfOneToGroupLossRatio OBJECT-IDENTITYSTATUS currentDESCRIPTION"Type-P-One-to-Group-Loss-Ratio"REFERENCE"Reference "RFCyyyy, section 7.4.3."-- RFC Ed.: replace yyyy with actual RFC number & remove
this note := { ianaIppmMetrics nn } -- IANA assigns nn--ietfOneToGroupRangeLossRatio OBJECT-IDENTITYSTATUS currentDESCRIPTION"Type-P-One-to-Group-Range-Loss-Ratio"REFERENCE"Reference "RFCyyyy, section 7.4.4."-- RFC Ed.: replace yyyy with actual RFC number & remove
this note := { ianaIppmMetrics nn } -- IANA assigns nnietfOneToGroupRangeDelayVariation OBJECT-IDENTITYSTATUS currentDESCRIPTION"Type-P-One-to-Group-Range-Delay-Variation"REFERENCE"Reference "RFCyyyy, section 7.5.1."-- RFC Ed.: replace yyyy with actual RFC number & remove
this note := { ianaIppmMetrics nn } -- IANA assigns nn--