draft-ietf-ippm-ipdv-00.txt   draft-ietf-ippm-ipdv-01.txt 
Network Working Group C.Demichelis CSELT Network Working Group C.Demichelis CSELT
expires 16 August 1998 expires 16 January 1999
Instantaneous Packet Delay Variation Metric for IPPM Instantaneous Packet Delay Variation Metric for IPPM
<draft-ietf-ippm-ipdv-01.txt>
<draft-ietf-ippm-ipdv-00.txt>
1. Status of this Memo 1. Status of this Memo
This document is an Internet Draft. Internet Drafts are working doc- This document is an Internet Draft. Internet Drafts are working doc-
uments of the Internet Engineering Task Force (IETF), its areas, and uments of the Internet Engineering Task Force (IETF), its areas, and
its working groups. Note that other groups may also distribute work- its working groups. Note that other groups may also distribute work-
ing documents as Internet Drafts. ing documents as Internet Drafts.
Internet Drafts are draft documents valid for a maximum of six Internet Drafts are draft documents valid for a maximum of six
months, and may be updated, replaced, or obsoleted by other documents months, and may be updated, replaced, or obsoleted by other documents
at any time. It is inappropriate to use Internet Drafts as reference at any time. It is inappropriate to use Internet Drafts as reference
material or to cite them other than as ``work in progress''. material or to cite them other than as ``work in progress''.
To learn the current status of any Internet Draft, please check the To learn the current status of any Internet Draft, please check the
``1id-abstracts.txt'' listing contained in the Internet Drafts shadow ``1id-abstracts.txt'' listing contained in the Internet Drafts shadow
directories on ftp.is.co.za (Africa), nic.nordu.net (Europe), directories on ftp.is.co.za (Africa), nic.nordu.net (Europe),
munnari.oz.au (Pacific Rim), ftp.ietf.org (US East Coast), or
munnari.oz.au (Pacific Rim), ds.internic.net (US East Coast), or
ftp.isi.edu (US West Coast). ftp.isi.edu (US West Coast).
This memo provides information for the Internet community. This memo This memo provides information for the Internet community. This memo
does not specify an Internet standard of any kind. Distribution of does not specify an Internet standard of any kind. Distribution of
this memo is unlimited. this memo is unlimited.
2. Abstract 2. Abstract
This memo refers to a metric for variation in delay of packets across This memo refers to a metric for variation in delay of packets across
Internet paths. The metric is based on statistics of the difference Internet paths. The metric is based on statistics of the difference
in One-way Delay of consecutive packets. This particular definition in One-way Delay of consecutive packets. This particular definition
of variation is called ''Instantaneous Packet Delay Variation (ipdv)''. of variation is called "Instantaneous Packet Delay Variation (ipdv)".
The metric is valid for measurements between two hosts both in the The metric is valid for measurements between two hosts both in the
case that they have synchronized clocks and in the case that they are case that they have synchronized clocks and in the case that they are
not synchronized. In the second case it allows an evaluation of the not synchronized. In the second case it allows an evaluation of the
relative skew. Measurements performed on both directions (Two-ways relative skew. Measurements performed on both directions (Two-ways
measurements) allow a better estimation of clock differences. The measurements) allow a better estimation of clock differences. The
precision that can be obtained is evaluated. precision that can be obtained is evaluated.
This memo is intended to have, as much as possible, the structure of This memo is intended to have, as much as possible, the structure of
the ippm draft on one-way delay metric. the ippm draft on one-way delay metric.
I-D Ipdv Metric March 1998 I-D Ipdv Metric July 1998
3. Introduction 3. Introduction
This memo defines a metric for variation in delay of packets that go This memo refers to the Draft-ietf "One-way-delay metric for IPPM" that
supposes as known. Part of the text in this memo is directly taken from
that Draft.
This memo defines a metric for variation in delay of packets that flow
from one host to another one through an IP path. Since the metric is from one host to another one through an IP path. Since the metric is
related to a variation, different definitions are possible according related to a variation, different definitions are possible according
to what the variation is measured against. to what the variation is measured against.
[Editor's Note: This memo refers to the Draft-ietf "One-way-delay metric
for IPPM" that supposes as known. For sake of readability, some text is
directly taken from that Draft. Text taken without modification is mark-
ed with trailing "TTTTTTT" and ending "EEEEEEE". These marks will be re-
moved in next versions]
3.1. Definition 3.1. Definition
The Instantaneous Packet Delay Variation of an IP packet, inside a The Instantaneous Packet Delay Variation of an IP packet, inside a
stream of packets, going from the measurement point MP1 to the measu- stream of packets, going from the measurement point MP1 to the measu-
rement point MP2, is the difference of the One-Way Delay of that packet
rement point MP2, is the difference of the One-Way Delay of that pac- and the One-Way Delay of preceding packet in the stream.
ket and the One-Way Delay of preceding packet in the stream.
3.2. Motivation 3.2. Motivation
A number of services that can be supported by IP are sensitive to the A number of services that can be supported by IP are sensitive to the
regular delivery of packets and can be disturbed by instantaneous va- regular delivery of packets and can be disturbed by instantaneous va-
riations in delay, while they are not disturbed by slow variations, riations in delay, while they are not disturbed by slow variations,
that can last a relatively long time. A specific metric for quick va- that can last a relatively long time. A specific metric for quick va-
riations is therefore desirable. Metrics that can be derived from the
riations is therefore desirable. analysis of statistics of ipdv can also be used for buffer
dimensioning, but this memo is not intended in that sense. The scope
is to provide a way for measurement of the quality delivered by a
path.
In addition, this type of metric is particularly robust with respect In addition, this type of metric is particularly robust with respect
differences and variations of the clocks of the two hosts. This allow differences and variations of the clocks of the two hosts. This allow
the use of the metric even if the two hosts that support the measure- the use of the metric even if the two hosts that support the measure-
ment points are not synchronized. The related precision is comparable ment points are not synchronized. The related precision is comparable
with the one that can be achieved with synchronized clocks. This will with the one that can be achieved with synchronized clocks. This will
be discussed below. be discussed below.
3.3. General Issues Regarding Time 3.3. General Issues Regarding Time
All what is contained in the paragraph 2.2. of the Draft ippm on one- All what is contained in the paragraph 2.2. of the Draft ippm on one-
way delay metric (2.2. General Issues Regarding Time) applies also in way delay metric (2.2. General Issues Regarding Time) applies also in
this case. this case.
In addition, it is here considered that the relative skew of the two In addition, it is here considered that the relative skew of the two
clocks can be decomposed into two parts: clocks can be decomposed into two parts:
* A fixed one, called in this context "skew", given, for example, by * A fixed one, called in this context "skew", given, for example, by
tolerances in physical dimension of crystals. tolerances in physical dimension of crystals.
I-D Ipdv Metric March 1998 I-D Ipdv Metric July 1998
* A variable one, called in this context "drift", given, for example, * A variable one, called in this context "drift", given, for example,
by changes in temperature or other conditions of operation. by changes in temperature or other conditions of operation.
Both of this components are part of the term "skew" as defined in the Both of this components are part of the term "skew" as defined in the
referenced Draft and in the Framework document. referenced Draft and in the Framework document.
4. Structure of this memo 4. Structure of this memo
The metric will be defined as applicable to a stream of packets that The metric will be defined as applicable to a stream of packets that
flow from a source host to a destination host (one-way ipdv). The ini flow from a source host to a destination host (one-way ipdv). The ini
-tial assumption is that source and destination hosts have synchronized
-tial assumption is that source and destination hosts have synchroni- clocks.
zed clocks.
The definition of a singleton of one-way ipdv metric is first consi- The definition of a singleton of one-way ipdv metric is first consi-
dered, and then a definition of samples for ipdv will be given. dered, and then a definition of samples for ipdv will be given.
Then the case of application to not synchronized hosts will be dis- Then the case of application to not synchronized hosts will be dis-
cussed, and the precision will be compared with the one of the previous
cussed, and the precision will be compared with the one of the pre- case.
vious case.
A bidirectional ipdv metric will be defined, and the methodology for A bidirectional ipdv metric will be defined, and the methodology for
error corrections. This will not be a two-ways metric, but a "paired" error corrections. This will not be a two-ways metric, but a "paired"
one-way in opposite directions. Some statistics describing the IP one-way in opposite directions. Some statistics describing the IP
path's behavior will be proposed.
path behavior will be proposed.
5. A singleton definition of a One-way ipdv metric 5. A singleton definition of a One-way ipdv metric
This definition makes use of the corresponding definition of type-P- This definition makes use of the corresponding definition of type-P-
One-way-delay, that is supposed to be known. This section makes use One-way-delay, that is supposed to be known. This section makes use
of those parts of the One-way-delay Draft that directly apply to the of those parts of the One-way-delay Draft that directly apply to the
One-way-ipdv metric, or makes direct references to that Draft. One-way-ipdv metric, or makes direct references to that Draft.
5.1. Metric name 5.1. Metric name
Type-P-One-way-ipdv Type-P-One-way-ipdv
5.2. Metric parameters 5.2. Metric parameters
+ Scr, the IP address of a host + Scr, the IP address of a host
+ Dst, the IP address of a host + Dst, the IP address of a host
+ T1, a time + T1, a time
+ T2, a time. It is explicitly noted that also the difference T2-T1
+ T2, a time is a parameter of the measurement though this is already implicit,
since the times T1 and T2 exactly define the time conditions in which
TTTTTTT the measurement takes place.
+ Path, the path from Src to Dst; in cases where there is only one + Path, the path from Src to Dst; in cases where there is only one
path from Src to Dst, this optional parameter can be omitted. I-D Ipdv Metric July 1998
path from Src to Dst, this optional parameter can be omitted.
{Comment: the presence of path is motivated by cases such as with {Comment: the presence of path is motivated by cases such as with
Merit's NetNow setup, in which a Src on one NAP can reach a Dst on Merit's NetNow setup, in which a Src on one NAP can reach a Dst on
I-D Ipdv Metric March 1998
another NAP by either of several different backbone networks. Gener- another NAP by either of several different backbone networks. Gener-
ally, this optional parameter is useful only when several different ally, this optional parameter is useful only when several different
routes are possible from Src to Dst. Using the loose source route IP routes are possible from Src to Dst. Using the loose source route IP
option is avoided since it would often artificially worsen the per- option is avoided since it would often artificially worsen the per-
formance observed, and since it might not be supported along some formance observed, and since it might not be supported along some
paths.} paths.}
EEEEEEE
5.2. Metric unit 5.2. Metric unit
The value of a Type-P-One-way-ipdv is either a real number of seconds The value of a Type-P-One-way-ipdv is either a real number of seconds
(positive, zero or negative) or an undefined number of seconds.
or an undefined number of seconds
5.3. Definition 5.3. Definition
Type-P-One-way-ipdv is defined for two consecutive packets from Src Type-P-One-way-ipdv is defined for two (consecutive) packets from Src
to Dst, as the difference between the value of the type-P-One-way- to Dst, as the difference between the value of the type-P-One-way-
delay from Src to Dst at T2 [via path] and the value of the type-P- delay from Src to Dst at T2 [via path] and the value of the type-P-
One-way-delay from Src to Dst at T1 [via path]. T1 is the wire-time One-way-delay from Src to Dst at T1 [via path]. T1 is the wire-time
at which Scr sent the first bit of the first packet, and T2 is the at which Scr 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 therefore ideally derived from the One-Way-Delay metric.
wire-time at which Src sent the first bit of the second packet. NOTE: The requirement of "consecutive" packets is not essential. The
measured value is anyway the difference in one-way-delay at the times
T1 and T2, which is meaningful by itself, as long as the times T1 and
T2 are such to describe the investigated characteristics. These times
will be better defined later.
Therefore, for a real number ddT "The type-P-one-way-ipdv from Src to Therefore, for a real number ddT "The type-P-one-way-ipdv from Src to
Dst at T1, T2 [via path] is ddT" means that Src sent two consecutive Dst at T1, T2 [via path] is ddT" means that Src sent two consecutive
packets whose the first at wire-time T1 (first bit), and the second packets whose the first at wire-time T1 (first bit), and the second
wire-time T2 (first bit) and the packets were received by Dst at wire wire-time T2 (first bit) and the packets were received by Dst at wire
-time dT1+T1 (last bit of the first packet), and, respectively, at
-time dT1+T1 (last bit of the first packet), and at wire-time dT2+T2 wire-time dT2+T2 (last bit of the second packet), and that dT2-dT1=ddT.
(last bit of the second packet), and that dT2-dT1=ddT.
"The type-P-one-way-ipdv from Src to Dst at T1,T2 [via path] is unde- "The type-P-one-way-ipdv from Src to Dst at T1,T2 [via path] is unde-
fined" means that Src sent the first bit of a packet at T1 and the fined" means that Src sent the first bit of a packet at T1 and the
first bit of a second packet at T2 and that Dst did not receive one first bit of a second packet at T2 and that Dst did not receive one
or both packets. or both packets.
5.4. Discussion 5.4. Discussion
Type-P-One-way-ipdv is a metric that makes use of the same measure- Type-P-One-way-ipdv is a metric that makes use of the same measurement
methods provided for delay metrics.
ment methods provided for delay metrics. I-D Ipdv Metric July 1998
The following practical issues have to be considered: The following practical issues have to be considered:
+ Being a differential measurement, this metric is less sensitive + Being a differential measurement, this metric is less sensitive
to clock synchronization problems. This issue will be more care- to clock synchronization problems. This issue will be more care-
fully examined in section 6. of this memo. It is pointed out fully examined in section 6. of this memo. It is pointed out
that, if the reciprocal clock conditions change in time, the ac- that, if the reciprocal clock conditions change in time, the ac-
curacy of the measurement will depend on the time interval T2-T1 curacy of the measurement will depend on the time interval T2-T1
and the amount of possible errors will be discussed below. and the amount of possible errors will be discussed below.
I-D Ipdv Metric March 1998
TTTTTTT
+ A given methodology will have to include a way to deter- + A given methodology will have to include a way to deter-
mine whether a delay value is infinite or whether it is mere- mine whether a delay value is infinite or whether it is mere-
ly very large (and the packet is yet to arrive at Dst). ly very large (and the packet is yet to arrive at Dst).
As noted by Mahdavi and Paxson, simple upper bounds (such as the As noted by Mahdavi and Paxson, simple upper bounds (such as the
255 seconds theoretical upper bound on the lifetimes of IP 255 seconds theoretical upper bound on the lifetimes of IP
packets [Postel: RFC 791]) could be used, but good engineering, packets [Postel: RFC 791]) could be used, but good engineering,
including an understanding of packet lifetimes, will be nee- including an understanding of packet lifetimes, will be nee-
ded in practice. {Comment: Note that, for many applications of ded in practice. {Comment: Note that, for many applications of
these metrics, the harm in treating a large delay as infinite these metrics, the harm in treating a large delay as infinite
might be zero or very small. A TCP data packet, for example, might be zero or very small. A TCP data packet, for example,
that arrives only after several multiples of the RTT may as well that arrives only after several multiples of the RTT may as well
have been lost.} have been lost.}
+ Usually a path is such that if the first packet is largely delayed,
it can "stop" the second packet of the pair and vary its delay.
This is not a problem for the definition since is, in any case,
part of the description of the path's behavior.
+ As with other 'type-P' metrics, the value of the metric may de- + As with other 'type-P' metrics, the value of the metric may de-
pend on such properties of the packet as protocol,(UDP or TCP) pend on such properties of the packet as protocol,(UDP or TCP)
port number, size, and arrangement for special treatment (as port number, size, and arrangement for special treatment (as
with IP precedence or with RSVP). with IP precedence or with RSVP).
+ If the packet is duplicated along the path (or paths!) so that + If the packet is duplicated along the path (or paths!) so that
multiple non-corrupt copies arrive at the destination, then the multiple non-corrupt copies arrive at the destination, then the
packet is counted as received, and the first copy to arrive packet is counted as received, and the first copy to arrive
determines the packet's one-way delay. determines the packet's one-way delay.
+ If the packet is fragmented and if, for whatever reason, reas- + If the packet is fragmented and if, for whatever reason, reas-
sembly does not occur, then the packet will be deemed lost. sembly does not occur, then the packet will be deemed lost.
EEEEEEE
5.5. Methodologies 5.5. Methodologies
TTTTTTT
As with other Type-P-* metrics, the detailed methodology will depend As with other Type-P-* metrics, the detailed methodology will depend
on the Type-P (e.g., protocol number, UDP/TCP port number, size, on the Type-P (e.g., protocol number, UDP/TCP port number, size,
precedence). precedence).
Generally, for a given Type-P, the methodology would proceed as fol- Generally, for a given Type-P, the methodology would proceed as fol-
lows: lows:
EEEEEEE
+ The need of synchronized clocks for Src and Dst will be discus- + The need of synchronized clocks for Src and Dst will be discus-
sed later. Here a methodology is supposed that is based on
sed later. Here a methodology is supposed that is bases on
synchronized clocks. synchronized clocks.
TTTTTTT I-D Ipdv Metric July 1998
+ At the Src host, select Src and Dst IP addresses, and form a
test packet of Type-P with these addresses. Any 'padding' por-
+ At the Src host, select Src and Dst IP addresses, and form two
test packets of Type-P with these addresses. Any 'padding' por-
tion of the packet needed only to make the test packet a given tion of the packet needed only to make the test packet a given
size should be filled with randomized bits to avoid a situation size should be filled with randomized bits to avoid a situation
in which the measured delay is lower than it would otherwise in which the measured delay is lower than it would otherwise
be due to compression techniques along the path. be due to compression techniques along the path.
I-D Ipdv Metric March 1998
+ Optionally, select a specific path and arrange for Src to send + Optionally, select a specific path and arrange for Src to send
the packets to that path. {Comment: This could be done, for
the packet to that path. {Comment: This could be done, for
example, by installing a temporary host-route for Dst in Src's example, by installing a temporary host-route for Dst in Src's
routing table.} routing table.}
+ At the Dst host, arrange to receive the packets.
+ At the Dst host, arrange to receive the packet. + At the Src host, place a timestamp in the prepared first
Type-P packet, and send it towards Dst [via path].
+ At the Src host, place a timestamp in the prepared Type-P pac-
ket, and send it towards Dst [via path].
+ If the packet arrives within a reasonable period of time, take a + If the packet arrives within a reasonable period of time, take a
timestamp as soon as possible upon the receipt of the packet. By timestamp as soon as possible upon the receipt of the packet. By
subtracting the two timestamps, an estimate of one-way delay can subtracting the two timestamps, an estimate of one-way delay can
be computed. be computed.
+ Record this first delay value.
EEEEEEE + At the Src host, place a timestamp in the prepared second
Type-P packet, and send it towards Dst [via path].
Record this first delay value. + If the packet arrives within a reasonable period of time, take a
timestamp as soon as possible upon the receipt of the packet. By
+ Repeat the procedure with the same parameters and record the se- subtracting the two timestamps, an estimate of one-way delay can
be computed.
cond delay value. By subtracting the second value from the first + By subtracting the second value of one-way-delay from the first value
the ipdv value of the pair of packets is obtained.
the ipdv value is obtained.
+ If one or both packets fail to arrive within a reasonable period + If one or both packets fail to arrive within a reasonable period
of time, the ipdv is taken to be undefined.
ot time, the ipdv is taken to be undefined.
5.6. Errors and Uncertainties 5.6. Errors and Uncertainties
In the singleton metric of ipdv, factors that affect the measurement In the singleton metric of ipdv, factors that affect the measurement
are the same that can affect the one-way delay measurement, even if, are the same that can affect the one-way delay measurement, even if,
in this case, the influence is different. in this case, the influence is different.
TTTTTTT
The Framework document provides general guidance on this point, but The Framework document provides general guidance on this point, but
we note here the following specifics related to delay metrics: we note here the following specifics related to delay metrics:
+ Errors/uncertainties due to uncertainties in the clocks of the + Errors/uncertainties due to uncertainties in the clocks of the
Src and Dst hosts. Src and Dst hosts.
+ Errors/uncertainties due to the difference between 'wire time' + Errors/uncertainties due to the difference between 'wire time'
and 'host time'. and 'host time'.
Each of these are discussed in more detail below. Each of these are discussed in more detail below.
EEEEEEE
5.6.1. Errors/Uncertainties related to Clocks 5.6.1. Errors/Uncertainties related to Clocks
If, as a first approximation, the error that affects the first measu- If, as a first approximation, the error that affects the first measu-
rement of one-way delay were the same of the one affecting the second rement of one-way delay were the same of the one affecting the second
measurement, they will cancel each other when calculating ipdv. The I-D Ipdv Metric July 1998
measurement, they will cancel each other when calculating ipdv. The
residual error related to clocks is the difference of the said errors residual error related to clocks is the difference of the said errors
that are supposed to change from the time T1, at which the first that are supposed to change from the time T1, at which the first
measurement is performed, to the time T2 at which the second measure- measurement is performed, to the time T2 at which the second measure-
ment is performed. Synchronization, skew, accuracy and resolution are ment is performed. Synchronization, skew, accuracy and resolution are
here considered with the following notes: here considered with the following notes:
+ Errors in synchronization between source and destination clocks + Errors in synchronization between source and destination clocks
contribute to errors in both of the delay measurements required contribute to errors in both of the delay measurements required
for calculating ipdv. for calculating ipdv.
I-D Ipdv Metric March 1998
+ If the synchronization error is Tsync, and it is a linear func- + If the synchronization error is Tsync, and it is a linear func-
tion of time, through the skew value, at time T1 the error will tion of time, through the skew value, at time T1 the error will
be Tsync1 and at time T2 the error will be Tsync2. The ipdv mea- be Tsync1 and at time T2 the error will be Tsync2. The ipdv mea-
surement will be affected by the error Tsync2-Tsync1, depending surement will be affected by the error Tsync2-Tsync1, depending
from skew and T2-T1. To minimize this error it is possible to from skew and T2-T1. To minimize this error it is possible to
reduce the time interval T2-T1, but this could limit the genera- reduce the time interval T2-T1, but this could limit the genera-
lity of the metric. Methods for evaluating the synchronization lity of the metric. Methods for evaluating the synchronization
error will be discussed below, since they come from a statistic error will be discussed below, since they come from a statistic
over a significant sample.
of a significant sample.
+ As far as accuracy and resolution are concerned, what is noted + As far as accuracy and resolution are concerned, what is noted
in the above referenced Draft on one-way delay at section 3.7.1, in the above referenced Draft on one-way delay at section 3.7.1,
applies also in this case, with the further consideration, about applies also in this case, with the further consideration, about
resolution, that in this case the uncertainty introduced is two resolution, that in this case the uncertainty introduced is two
times the one of a single delay measurement. times the one of a single delay measurement.
5.6.2. Errors/uncertainties related to Wire-time vs Host-time 5.6.2. Errors/uncertainties related to Wire-time vs Host-time
The content of sec. 3.7.2 of the above referenced Draft applies also The content of sec. 3.7.2 of the above referenced Draft applies also
in this case, with the following further consideration: in this case, with the following further consideration:
The difference between Host-time and Wire-time can be in general de- The difference between Host-time and Wire-time can be in general de-
composed into two components, whose one is constant and the other is composed into two components, whose one is constant and the other is
variable around zero. Only the variable components will produce measu-
variable aroud zero. Only the variable components will produce measu- rement errors, while the constant one will be canceled while calcu-
rement errors, while the constant one will be cancelled while calcu-
lating ipdv. lating ipdv.
6. Definitions for Samples of One-way ipdv 6. Definitions for Samples of One-way ipdv
Starting from the definition of the singleton metric of one-way ipdv, Starting from the definition of the singleton metric of one-way ipdv,
some ways of building a sample of such singletons are here described some ways of building a sample of such singletons are here described
that have to be further analyzed in order to find the best way of con-
that have to be further anlyzed in order to find the best way of con-
sidering all the related problems. In the following, the two packets sidering all the related problems. In the following, the two packets
needed for a singleton measurement will be called a "pair". needed for a singleton measurement will be called a "pair".
I-D Ipdv Metric July 1998
6.1. A "discontinuous" definition 6.1. A "discontinuous" definition
A general definition can be the following: A general definition can be the following:
Given particular binding of the parameters Src, Dst, path, and Given particular binding of the parameters Src, Dst, path, and
Type-P, a sample of values of parameters T1 and T2 is defined. Type-P, a sample of values of parameters T1 and T2 is defined.
The means for defining the values of T1 is to select a beginning The means for defining the values of T1 is to select a beginning
time T0, a final time Tf, and an average rate lambda, then time T0, a final time Tf, and an average rate lambda, then
define a pseudo-random Poisson arrival process of rate lambda, define a pseudo-random Poisson arrival process of rate lambda,
whose values fall between T0 and Tf. The time interval between whose values fall between T0 and Tf. The time interval between
successive values of T1 will then average 1/lambda. Another si- successive values of T1 will then average 1/lambda. Another si-
milar, but independent, pseudo-random Poisson arrival process milar, but independent, pseudo-random Poisson arrival process
based on T0', Tf' and lambda', will produce a series of t'
values. The time interval between successive t' values will then
average 1/lambda'. For each T1 value that has been obtained
by the first process, it is then possible to calculate the
successive T2 values as the successive T1 values plus the
successive intervals of t'.
based on T0', Tf' and lambda', for each T1 value that has been The result is shown in figure 1.
obtained by the first process, is used for obtaining the inter-
I-D Ipdv Metric March 1998
val T2-T1, that falls between T0' and Tf' with an average of
1/lambda' |<- average interval 1/lambda ->|
| |
|<- av.int. | |<- av.int. |
|1/lambda'->| | 1/lambda'->|
_____|___________|___________________|_____________|________
pair i pair i+1
Figure 1
This general definition is likely go give problems, if no limits are This general definition is likely go give problems, if no limits are
considered for the obtained values. For example, the emission
considered for the values T0, Tf, T0', Tf'. For example, the emission
time of the first packet of a pair, could fall before the emission time of the first packet of a pair, could fall before the emission
time of the second packet of the preceding pair. Probably this could time of the second packet of the preceding pair. Probably this could
be acceptable (provided that there are means to recognize pairs -e.g. be acceptable (provided that there are means to recognize pairs -e.g.
use of sequence numbers-), but the concept itself of ipdv would be,at use of sequence numbers-), but the concept itself of ipdv would be,at
least, slightly changed. A way for avoiding this type of philosophical
least, slightly changed. A way for avoiding problems can be to give problems can be to give some rules on the values T0, Tf, lambda,
T0', Tf', lambda', without changing the meaning of the metric.
some rules on the values T0, Tf, lambda, T0', Tf', lambda', without
changing the meaning of the metric. For example it can be required
that Tf'<T0 in order to assure that pairs of packets consist of two
consecutive packets.
6.2. A "continuous" definition 6.2. A "continuous" definition
A way to naturally avoid the previous problem is to adopt the following
definition.
A continuous stream of test packets can be supposed, where the second A continuous stream of test packets can be supposed, where the second
packet of a pair is, at the same time, the first packet of the next packet of a pair is, at the same time, the first packet of the next
pair. Therefore the preceding definition becomes: pair. Therefore the preceding definition becomes:
+ Given particular binding of the parameters Src, Dst, path, and I-D Ipdv Metric July 1998
+ Given particular binding of the parameters Src, Dst, path, and
Type-P, a sample of values of parameter T1 is defined. Type-P, a sample of values of parameter T1 is defined.
The means for defining the values of T1 is to select a beginning The means for defining the values of T1 is to select a beginning
time T0, a final time Tf, and an average rate lambda, then time T0, a final time Tf, and an average rate lambda, then
define a pseudo-random Poisson arrival process of rate lambda, define a pseudo-random Poisson arrival process of rate lambda,
whose values fall between T0 and Tf. The time interval between whose values fall between T0 and Tf. The time interval between
successive values of T1 will then average 1/lambda. From the successive values of T1 will then average 1/lambda. From the
second value on, T1 value of the pair n coincides with T2 of the second value on, T1 value of the pair n coincides with T2 of the
pair n-1, and the first packet of pair n coincides with the se- pair n-1, and the first packet of pair n coincides with the se-
cond packet of the pair n-1. cond packet of the pair n-1.
For the moment, in the following, this second definition will be con- For the moment, in the following, this second definition will be con-
sidered. Further refinement is required and is for further discussion.
sidered. Further refinement is required and is for further discussion
6.3. Metric name 6.3. Metric name
Type-P-One-way-ipdv-stream Type-P-One-way-ipdv-stream
6.4. Parameters 6.4. Parameters
+ Src, the IP address of a host + Src, the IP address of a host
+ Dst, the IP address of a host + Dst, the IP address of a host
+ Path, the path* from Src to Dst; in cases where there is only + Path, the path* from Src to Dst; in cases where there is only
one path from Src to Dst, this optional parameter can be omitted one path from Src to Dst, this optional parameter can be omitted
+ T0, a time + T0, a time
+ Tf, a time + Tf, a time
+ lambda, a rate in reciprocal seconds + lambda, a rate in reciprocal seconds
I-D Ipdv Metric March 1998
6.5. Metric Units: 6.5. Metric Units:
A sequence of triads whose elements are: A sequence of triads whose elements are:
+ T, a time + T, a time
+ Ti, a time interval. + Ti, a time interval.
+ dT a real number or an undefined number of seconds + dT a real number or an undefined number of seconds
6.6. Definition 6.6. Definition
A pseudo-random Poisson process is defined such that ir begins at or A pseudo-random Poisson process is defined such that it begins at or
before T0, with average arrival rate lambda, and ends at or after Tf. before T0, with average arrival rate lambda, and ends at or after Tf.
Those time values Ti greater than or equal to T0 and less than or Those time values Ti greater than or equal to T0 and less than or
equal to Tf are then selected. Starting from time T, at each pair of
times T(i), T(i+1)of this process a value of Type-P-One-way-ipdv is
obtained. The value of the sample is the sequence made up of the
resulting <time, time interval, ipdv> triad, where the time interval
is given by T(i+1)-T(i). Each obtained time T(i), excluding the first
and the last, is therefore at the same time the the second time of
pair i and the first time of pair i+1. The result is shown in figure 2
equal to Tf are then selected. Starting from time T, at each time Ti |T(i-2) |T(i-1) |T(i) |T(i+1)
_____|__________|___________________|__________|________
of this process a value of Type-P-One-way-ipdv is obtained, and the pair i-1 pair i pair i+1
Figure 2
time T becomes T = T+Ti. The value of the sample is the sequence made
up of the resulting <time, time interval, ipdv> triad. I-D Ipdv Metric July 1998
6.7. Discussion 6.7. Discussion
TTTTTTT
Note first that, since a pseudo-random number sequence is employed, Note first that, since a pseudo-random number sequence is employed,
the sequence of times, and hence the value of the sample, is not the sequence of times, and hence the value of the sample, is not
fully specified. Pseudo-random number generators of good quality fully specified. Pseudo-random number generators of good quality
will be needed to achieve the desired qualities. will be needed to achieve the desired qualities.
The sample is defined in terms of a Poisson process both to avoid the The sample is defined in terms of a Poisson process both to avoid the
effects of self-synchronization and also capture a sample that is effects of self-synchronization and also capture a sample that is
statistically as unbiased as possible. {Comment: there is, of statistically as unbiased as possible. {Comment: there is, of
course, no claim that real Internet traffic arrives according to a course, no claim that real Internet traffic arrives according to a
Poisson arrival process.} Poisson arrival process.}
EEEEEEE
6.8. Methodology 6.8. Methodology
Since packets can be lost or duplicated or can arrive in a different Since packets can be lost or duplicated or can arrive in a different
order with respect the one of emission, in order to recognize the order with respect the one of emission, in order to recognize the
pairs of test packets, they should be marked with a Sequence Number pairs of test packets, they should be marked with a Sequence Number
or make use of any other tool suitable to the scope. For duplicated or make use of any other tool suitable to the scope. For duplicated
packets only the first received copy should be considered. If a pac- packets only the first received copy should be considered. If a pac-
ket is lost, two values of ipdv will be undefined, since each packet, ket is lost, two values of ipdv will be undefined, since each packet,
in the supposed "continuous" definition, is common to two pairs. in the supposed "continuous" definition, is common to two pairs.
Steps for measurement can be the following: Steps for measurement can be the following:
+ Starting from a given time T, Src generates a test packet as for + Starting from a given time T, Src generates a test packet as for
a singleton metrics, inserts in the packet a Sequence Number
a singleton metrics, adding also a Sequence Number, and sorts a and the transmission Time Stamp Tx,then sorts the time Ti at
which the next packet has to be sent.
Ti interval to determine the time at wich the next packet has to + At time Ti, Src repeats the previous step, unless T(i) > Tf.
+ On reception of the first packet, or the first packet after a SN
be sent. error, Dst records SN and Tx timestamp that are contained in
the packet and the reception time Rx as "old values".
I-D Ipdv Metric March 1998 + On reception of the other packets Dst verifies the SN and if it is
correct, by using the "old values" and the newly received ones,
+ On reception of the packet, Dst verifies the Sequence Number SN, a value of ipdv is computed. Then Dst records the new SN, Tx
and Rx timestamps as "old values".
and records SN and Tx timestamp that are contained in the packet
and the Rx timestamp.
+ if the packet is not the first received and the SN is correct,
ipdv is computed and Ti is recorded. Then Dst records SN, Tx
and Rx timestamps as "old" values.
6.9. Errors and uncertainties 6.9. Errors and uncertainties
The same considerations apply that have been made about the single- The same considerations apply that have been made about the single-
ton metric. An additional error can be introduced by the pseudo-ran- ton metric. An additional error can be introduced by the pseudo-ran-
dom Poisson process as focused in the above referenced Draft.
dom Poisson process as focushed in the above referenced Draft.
Further considerations will be made in section 7. Further considerations will be made in section 7.
I-D Ipdv Metric July 1998
6.10 Some statistics for One-way-ipdv 6.10 Some statistics for One-way-ipdv
Some statistics are here considered, that can provide useful informa- Some statistics are here considered, that can provide useful informa-
tion in analyzing the behavior of the packets flowing from Src to Dst tion in analyzing the behavior of the packets flowing from Src to Dst
These statistics are given having in mind a practical use of them. The
These statistics are given having in mind a practical use of them. focus is on the instantaneous behavior of the connection, while buffer
dimensioning is not in the scope of this document.
Other statistics can be defined if needed. Other statistics can be defined if needed.
6.10.1. Type-P-One-way-ipdv-inverse-percentile 6.10.1. Type-P-One-way-ipdv-inverse-percentile
Given a Type-P-One-way-ipdv-Stream and a time threshold, that can be Given a Type-P-One-way-ipdv-Stream and a time threshold, that can be
either positive or negative, the fraction of all the ipdv values in
either positive or negative, the fraction of all the dT values in the the Stream less than or equal to the threshold, if the threshold is
positive, or greater or equal to the threshold if the threshold is ne-
Stream less than or equal to the threshold, if the threshold is po-
sitive, or greater or equal to the threshold if the threshold is ne-
gative. gative.
For many real-time services that require a regular delivery of the For many real-time services that require a regular delivery of the
packets, this statistics can give the amount of packets received
packets, this statistics can give the amount of packets beyond accep- beyond acceptable limits.
table limits.
6.10.2 Type-P-One-way-ipdv-standard-deviation 6.10.2 Type-P-One-way-ipdv-standard-deviation
Given a Type-P-One-way-ipdv-Stream, the distribution of ipdv values Given a Type-P-One-way-ipdv-Stream, the distribution of ipdv values
is considered and the Standard Deviation can be calculated as an is considered and the Standard Deviation can be calculated as an
indication of regularity of delivery. For practical purposes it can indication of regularity of delivery. For practical purposes it can
useful to define a total standard deviation, computed over the com- useful to define a total standard deviation, computed over the com-
plete set of value, and a standard deviation computed over the sub- plete set of value, and a standard deviation computed over the sub-
set of those values that do not exceed given positive and negative
set of those values that do not exceede given positive and negative
thresholds. This allows a more accurate description of the performan- thresholds. This allows a more accurate description of the performan-
ce experienced by packets. ce experienced by packets.
6.10.3 Type-P-One-way-ipdv-average 6.10.3 Type-P-One-way-ipdv-average
This statistic should tend to a value of ZERO for a number of ipdv This statistic should tend to a value of ZERO for a number of ipdv
I-D Ipdv Metric March 1998
values that tend to infinite. The behavior of Type-P-One-way-ipdv- values that tend to infinite. The behavior of Type-P-One-way-ipdv-
average, and its meaning, are issues for the next section 7.
average is an issue for the next section 7.
7. Discussion on clock synchronization 7. Discussion on clock synchronization
This section gives some considerations about the need of having syn- This section gives some considerations about the need of having syn-
chronized clocks at Src and Dst. These considerations are given as a chronized clocks at Src and Dst. These considerations are given as a
basis for discussion, they require further investigation. We start basis for discussion, they require further investigation. We start
from the analysis of the mean value of the ipdv distribution related from the analysis of the mean value of the ipdv distribution related
to a "continuous" sample. to a "continuous" sample.
I-D Ipdv Metric July 1998
7.1. Mean value of ipdv distribution. 7.1. Mean value of ipdv distribution.
If D(i) is the delay of packet "i", and ipdv(i) is the i-th value of If D(i) is the delay of packet "i", and ipdv(i) is the i-th value of
ipdv in the distribution of a sample of "n" values, collected with ipdv in the distribution of a sample of "n" values, collected with
the described methodology, we can write: the described methodology, we can write:
ipdv(1) = D1 - D0 ipdv(1) = D1 - D0
.......... ..........
ipdv(i) = D(i) - D(i-1) ipdv(i) = D(i) - D(i-1)
.......... ..........
ipdv(n) = D(n) - D(n-1) ipdv(n) = D(n) - D(n-1)
The mean value of ipdv distribution will result in The mean value of ipdv distribution will result in
E(ipdv) = (D(n) - D(0))/n E(ipdv) = (D(n) - D(0))/n
If an actual measurement is performed, that lasts a period of time If an actual measurement is performed, that lasts a period of time
long enough to contain a number "n" sufficiently large and, supposing long enough to contain a number "n" sufficiently large and, supposing
synchronized clocks, such that the network conditions (traffic) allow synchronized clocks, such that the network conditions (traffic) allow
to find a D(n) not too different from D(0), e.g. a time of
to find a D(n) not too diferent from D(0), e.g. a time of 24 hours, n x 24 hours, E(ipdv) will tend to zero, since the difference
D(n) - D(0) will remain finite.
E(ipdv) will tend to zero.
7.2. Effects of a varying traffic 7.2. Effects of a varying traffic
If the mean values of delay D are changing inside a given period of If the mean values of delay D are changing inside a given period of
time, for example they are increasing due to an increment of traffic, time, for example they are increasing due to an increment of traffic,
we can consider, as a first approximation, the ipdv values as decom- we can consider, as a first approximation, the ipdv values as decom-
posed into two components, one being instantaneous and another one posed into two components, one being instantaneous and another one
as having a constant rate dD and corresponding to the increment "per as having a constant rate dD and corresponding to the increment "per
interval" of the mean value of D. The mean value of the distribution interval" of the mean value of D. The mean value of the distribution
will be shifted of the value dD corresponding to the mean value of will be shifted of the value dD corresponding to the mean value of
the interval between test packets. When the conditions will come back the interval between test packets. When the conditions will come back
to the initial ones, the distribution will resume a mean value around to the initial ones, the distribution will resume a mean value around
zero. At any time the distribution will correctly describe the zero. At any time the distribution will correctly describe the
effects of the path on the packet flow.
behavior of the packet flow. 7.3. Effects of synchronization errors
I-D Ipdv Metric March 1998
7.3. Effects of syncronization errors
We refer here to the two components that can generate this type of We refer here to the two components that can generate this type of
errors that are the relative "skew" and "drift" of the Src and Dst errors that are the relative "skew" and "drift" of the Src and Dst
clocks. It is first of all noted that the variable component "drift" clocks. It is first of all noted that the variable component "drift"
is physically limited and its effects can be interpreted by saying is physically limited and its effects can be interpreted by saying
that the total skew of the two clocks can vary, ranging from a min that the total skew of the two clocks can vary, ranging from a min
to a max value in the time. This type of variation takes place very to a max value in the time. This type of variation takes place very
slowly being mostly connected to variations in temperature.
slowly being most connected to variations in temperature. I-D Ipdv Metric July 1998
We suppose to perform a measurement between a Src and a Dst that have We suppose to perform a measurement between a Src and a Dst that have
a reciprocal, initial skew of "ts1" and a reciprocal drift such that, a reciprocal, initial skew of "ts1" and a reciprocal drift such that,
after the time T the total skew is "ts2". It is not here a limitation after the time T the total skew is "ts2". It is not here a limitation
to consider that at the beginning of time T the two clocks indicate to consider that at the beginning of time T the two clocks indicate
the same time T0. In order to analyze the effects produced by this the same time T0. In order to analyze the effects produced by this
situation we suppose that packets are transferred, from Src to Dst, situation we suppose that packets are transferred, from Src to Dst,
with a constant delay D. In this conditions the measured ipdv should
with a consatant delay D. In this conditions the measured ipdv should
always be zero, and what is actually measured is the error. always be zero, and what is actually measured is the error.
An ipdv value is measured at the beginning of time T with two packets An ipdv value is measured at the beginning of time T with two packets
having an interval of Ti(1).Another ipdv value is measured at the end having an interval of Ti(1).Another ipdv value is measured at the end
of T with two packets having a time interval Ti(2). of T with two packets having a time interval Ti(2).
On our purposes other errors (like wire-time vs host-time) are not On our purposes other errors (like wire-time vs host-time) are not
considered since they are not relevant in this analysis. considered since they are not relevant in this analysis.
It is then possible to calculate the values of the Tx and Rx time- It is then possible to calculate the values of the Tx and Rx time-
stamps as they are seen by the two clocks, and the related values of stamps as they are seen by the two clocks, and the related values of
the two ipdv values. the two ipdv values.
The first ipdv value will be: ipdv1 = ts1*Ti(1) + ((ts2-ts1)/T)*Ti(1) The first ipdv value will be: ipdv1 = ts1*Ti(1) + ((ts2-ts1)/T)*Ti(1)
The second ipdv value will be: ipdv2 = ts2*Ti(2) +((ts2-ts1)/T)*Ti(2) The second ipdv value will be: ipdv2 = ts2*Ti(2) +((ts2-ts1)/T)*Ti(2)
The error is given by the amount of variation during the time inter- The error is given by the amount of variation during the time inter-
val Ti(i) between the two packets of the pair, and a second order
val Ti(i) between the two packets of the pair, and a second orded
term due to the variation of that variation in the same interval. term due to the variation of that variation in the same interval.
If, as in practical cases, the drift can be considered zero, then
ts1 = ts2, and the error is not depending on the time at which the
measurement is done.
7.4. Related precision 7.4. Related precision
This means that: This means that:
1) + If the skew is constant and is = ts all the ipdv(i) values are 1) + If the skew is constant and is = ts all the ipdv(i) values are
increased by the quantity Ti(i)*ts with respect the actual value. increased by the quantity Ti(i)*ts with respect the actual value.
2) + Considering the total skew as subdivided into a fixed part and a 2) + Considering the total skew as subdivided into a fixed part and a
variable part (skew and drift),respectively, ts and + or - td, and variable part (skew and drift),respectively, ts and + or - td, and
a minimum time T in which the drift can go from -td to +td or vice a minimum time T in which the drift can go from -td to +td or vice
-versa, each ipdv(i) value will be increased of the fixed quantity -versa, each ipdv(i) value will be increased of the fixed quantity
Ti(i)*ts plus or minus, as a maximum, the quantity 2*td*Ti(i)/T Ti(i)*ts plus or minus, as a maximum, the quantity 2*td*Ti(i)/T
I-D Ipdv Metric March 1998 I-D Ipdv Metric July 1998
3) + If the duration of the measurement is such that it is possible 3) + If the duration of the measurement is such that it is possible
to consider that the effect of the items at points 7.1 and 7.2, to consider that the effect of the items at points 7.1 and 7.2,
and the effect of the drift are negligible (related average ten-
and the effect of the drift are negligeables (related average ten-
ding to zero), the mean value of the ipdv distribution will have ding to zero), the mean value of the ipdv distribution will have
the value of the skew multiplied by the mean value of the emission the value of the skew multiplied by the mean value of the emission
interval. interval.
4) + We observe that the displacement due to the skew does not change
4) + We observe that the displacemet due to the skew does not change
the shape of the distribution, and, for example the Standard Devi- the shape of the distribution, and, for example the Standard Devi-
ation remains the same. What introduces a distortion is the effect ation remains the same. What introduces a distortion is the effect
of the drift, even if the mean value of this effect is zero at the of the drift, even if the mean value of this effect is zero at the
end of the measurement. The value of this distortion is limited to
end of the measurement. This is, anyway, a "second order" effect. the effect of the total skew variation on the emission interval.
If, for example, a drift of 30 parts per million (ppm) takes place
along a time of 4 hours, and the used Ti(i) interval ranges from
200 ms to 1200 ms, with an average of 700 ms, the maximum error on
ipdv(i) values will be in the order of:
Ti(i)*td/(4*3600)= 2.25 E -9 seconds
8. Definition for a bidirectional ipdv metric 8. Definition for a bidirectional ipdv metric
We now consider that the action of the skew on one direction is the We now consider that the action of the skew on one direction is the
same, with opposite sign, of the action on the other direction. The same, with opposite sign, of the action on the other direction. The
idea of performing at the same time two independent measurements in idea of performing at the same time two independent measurements in
the two directions is suggested by this fact. the two directions is suggested by this fact.
If, after a long measurement, the variable conditions of the system If, after a long measurement, the variable conditions of the system
under test have reached the situation of a contribution close to zero under test have reached the situation of a contribution close to zero
to the mean value of the ipdv distribution, it is expected that only to the mean value of the ipdv distribution, it is expected that only
the fixed action of the skew has modified the measured mean value. It the fixed action of the skew has modified the measured mean value. It
is therefore expected that on one direction that value is equal and is therefore expected that on one direction that value is equal and
opposite to the one measured in the other direction. opposite to the one measured in the other direction.
A bidirectional measurement can be defined not only as twin one-way This fact offers the possibility of defining a theoretical reference
measurement duration in the following way:
independent metrics that take place (nearly) at the same time, but The reference duration of a bidirectional ipdv measurement between
an host E and an host W is reached at time Tf such that for each time
T > Tf the expression ABS(E(ipdv E-W) - E(ipdv W-E))< epsilon, where
epsilon is what we can consider as zero, is always verified.
A bidirectional measurement can be defined not only as twin one-way
independent metrics that take place (nearly) at the same time, but
also as a two-ways metric making use of packets looped back at one also as a two-ways metric making use of packets looped back at one
end. This metric, that can be object of further study/Draft, would be end. This metric, that can be object of further study/Draft, would be
able to measure also the Round Trip Delay and its variations. able to measure also the Round Trip Delay and its variations.
I-D Ipdv Metric July 1998
9. References 9. References
V.Paxon, G.Almes, J.Mahdavi, M.Mathis - "Framework for IP Performance V.Paxon, G.Almes, J.Mahdavi, M.Mathis - "Framework for IP Performance
Metrics", Internet Draft <draft-ietf-ippm-framework-01.txt> Feb. 1998 Metrics", Internet Draft <draft-ietf-ippm-framework-01.txt> Feb. 1998
G.Almes, S.Kalidindi - "A One-way Delay Metric for IPPM", Internet G.Almes, S.Kalidindi - "A One-way Delay Metric for IPPM", Internet
Draft <draft-ietf-ippm-delay-01.txt> Nov. 1997 Draft <draft-ietf-ippm-delay-01.txt> Nov. 1997
I-D Ipdv Metric March 1998
10. Author's Address 10. Author's Address
Carlo Demichelis <carlo.demichelis@cselt.it> Carlo Demichelis <carlo.demichelis@cselt.it>
CSELT - Centro Studi E Laboratori Telecomunicazioni S.p.A
CSELT - Centro Studi E Laburatori Telecomunicazioni S.p.A
Via G. Reiss Romoli 274 Via G. Reiss Romoli 274
10148 - TORINO 10148 - TORINO
Italy Italy
Phone +39 11 228 5057 Phone +39 11 228 5057
Fax. +39 11 228 5069 Fax. +39 11 228 5069
 End of changes. 

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