One document matched: draft-ietf-ippm-testplan-rfc2679-03.xml


<?xml version="1.0" encoding="US-ASCII"?>
<!DOCTYPE rfc SYSTEM "rfc2629.dtd">
<?rfc toc="yes"?>
<?rfc tocompact="yes"?>
<?rfc tocdepth="3"?>
<?rfc tocindent="yes"?>
<?rfc symrefs="yes"?>
<?rfc sortrefs="yes"?>
<?rfc comments="yes"?>
<?rfc inline="yes"?>
<?rfc compact="yes"?>
<?rfc subcompact="no"?>
<rfc category="info" docName="draft-ietf-ippm-testplan-rfc2679-03"
     ipr="pre5378Trust200902">
  <front>
    <title abbrev="Stds Track Tests RFC2679">Test Plan and Results Supporting
    Advancement of RFC 2679 on the Standards Track</title>

    <author fullname="Len Ciavattone" initials="L." surname="Ciavattone">
      <organization>AT&T Labs</organization>

      <address>
        <postal>
          <street>200 Laurel Avenue South</street>

          <city>Middletown</city>

          <region>NJ</region>

          <code>07748</code>

          <country>USA</country>
        </postal>

        <phone>+1 732 420 1239</phone>

        <facsimile></facsimile>

        <email>lencia@att.com</email>

        <uri></uri>
      </address>
    </author>

    <author fullname="Ruediger Geib" initials="R." surname="Geib">
      <organization>Deutsche Telekom</organization>

      <address>
        <postal>
          <street>Heinrich Hertz Str. 3-7</street>

          <!-- Reorder these if your country does things differently -->

          <code>64295</code>

          <city>Darmstadt</city>

          <region></region>

          <country>Germany</country>
        </postal>

        <phone>+49 6151 58 12747</phone>

        <email>Ruediger.Geib@telekom.de</email>

        <!-- uri and facsimile elements may also be added -->
      </address>
    </author>

    <author fullname="Al Morton" initials="A." surname="Morton">
      <organization>AT&T Labs</organization>

      <address>
        <postal>
          <street>200 Laurel Avenue South</street>

          <city>Middletown</city>

          <region>NJ</region>

          <code>07748</code>

          <country>USA</country>
        </postal>

        <phone>+1 732 420 1571</phone>

        <facsimile>+1 732 368 1192</facsimile>

        <email>acmorton@att.com</email>

        <uri>http://home.comcast.net/~acmacm/</uri>
      </address>
    </author>

    <author fullname="Matthias Wieser" initials="M." surname="Wieser">
      <organization>Technical University Darmstadt</organization>

      <address>
        <postal>
          <street></street>

          <!-- Reorder these if your country does things differently -->

          <code></code>

          <city>Darmstadt</city>

          <region></region>

          <country>Germany</country>
        </postal>

        <phone></phone>

        <email>matthias_michael.wieser@stud.tu-darmstadt.de</email>

        <!-- uri and facsimile elements may also be added -->
      </address>
    </author>

    <date day="6" month="September" year="2012" />

    <abstract>
      <t>This memo provides the supporting test plan and results to advance
      RFC 2679 on One-way Delay Metrics along the standards track, following
      the process in RFC 6576. Observing that the metric definitions
      themselves should be the primary focus rather than the implementations
      of metrics, this memo describes the test procedures to evaluate specific
      metric requirement clauses to determine if the requirement has been
      interpreted and implemented as intended. Two completely independent
      implementations have been tested against the key specifications of RFC
      2679. This memo also provides direct input for development of RFC
      2679bis.</t>
    </abstract>

    <note title="Requirements Language">
      <t>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 <xref
      target="RFC2119">RFC 2119</xref>.</t>
    </note>
  </front>

  <middle>
    <section title="Introduction">
      <t>The IETF IP Performance Metrics (IPPM) working group has considered
      how to advance their metrics along the standards track since 2001, with
      the initial publication of Bradner/Paxson/Mankin's memo <xref
      target="I-D.bradner-metricstest"></xref>. The original proposal was to
      compare the performance of metric implementations. This was similar to
      the usual procedures for advancing protocols, which did not directly
      apply. It was found to be difficult to achieve consensus on exactly how
      to compare implementations, since there were many legitimate sources of
      variation that would emerge in the results despite the best attempts to
      keep the network paths equal, and because considerable variation was
      allowed in the parameters (and therefore implementation) of each metric.
      Flexibility in metric definitions, essential for customization and broad
      appeal, made the comparison task quite difficult.</t>

      <t>A renewed work effort investigated ways in which the measurement
      variability could be reduced and thereby simplify the problem of
      comparison for equivalence.</t>

      <t>The consensus process documented in <xref target="RFC6576"></xref> is
      that metric definitions should be the primary focus of evaluation rather
      than the implementations of metrics. Equivalent test results are deemed
      to be evidence that the metric specifications are clear and unambiguous.
      This is now the metric specification equivalent of protocol
      interoperability. The <xref target="RFC6576"></xref> advancement process
      either produces confidence that the metric definitions and supporting
      material are clearly worded and unambiguous, OR, identifies ways in
      which the metric definitions should be revised to achieve clarity.</t>

      <t>The metric RFC advancement process requires documentation of the
      testing and results. <xref target="RFC6576"></xref> retains the testing
      requirement of the original standards track advancement process
      described in <xref target="RFC2026"></xref> and <xref
      target="RFC5657"></xref>, because widespread deployment is insufficient
      to determine whether RFCs that define performance metrics result in
      consistent implementations.</t>

      <t>The process also permits identification of options that were not
      implemented, so that they can be removed from the advancing
      specification (this is a similar aspect to protocol advancement along
      the standards track). All errata must also be considered.</t>

      <t>This memo's purpose is to implement the advancement process of <xref
      target="RFC6576"></xref> for <xref target="RFC2679"></xref>. It supplies
      the documentation that accompanies the protocol action request submitted
      to the Area Director, including description of the test set-up, results
      for each implementation, evaluation of each metric specification, and
      conclusions.</t>

      <t>In particular, this memo documents the consensus on the extent of
      tolerable errors when assessing equivalence in the results. The IPPM
      working group agreed that the test plan and procedures should include
      the threshold for determining equivalence, and that this aspect should
      be decided in advance of cross-implementation comparisons. This memo
      includes procedures for same-implementation comparisons that may
      influence the equivalence threshold.</t>

      <t>Although the conclusion reached through testing is that <xref
      target="RFC2679"></xref> should be advanced on the Standards Track with
      modifications, the revised text of RFC 2679bis is not yet ready for
      review. Therefore, this memo documents the information to support <xref
      target="RFC2679"></xref> advancement, and the approval of RFC2769bis is
      left for future action.</t>
    </section>

    <section title="A Definition-centric metric advancement process">
      <t>The process described in Section 3.5 of <xref
      target="RFC6576"></xref> takes as a first principle that the metric
      definitions, embodied in the text of the RFCs, are the objects that
      require evaluation and possible revision in order to advance to the next
      step on the standards track. This memo follows that process.</t>
    </section>

    <section title="Test configuration">
      <t>One metric implementation used was NetProbe version 5.8.5, (an
      earlier version is used in the AT&T's IP network performance
      measurement system and deployed world-wide <xref target="WIPM"></xref>).
      NetProbe uses UDP packets of variable size, and can produce test streams
      with Periodic <xref target="RFC3432"></xref> or Poisson <xref
      target="RFC2330"></xref> sample distributions.</t>

      <t>The other metric implementation used was Perfas+ version 3.1,
      developed by Deutsche Telekom <xref target="Perfas"></xref>. Perfas+
      uses UDP unicast packets of variable size (but supports also TCP and
      multicast). Test streams with Periodic, Poisson or uniform sample
      distributions may be used.</t>

      <t>Figure 2 shows a view of the test path as each Implementation's test
      flows pass through the Internet and the L2TPv3 tunnel IDs (1 and 2),
      based on Figures 2 and 3 of <xref target="RFC6576"></xref>.</t>

      <t><figure align="center" anchor="L2TPv3_tunnel">
          <preamble />

          <artwork align="center"><![CDATA[        +----+  +----+                                +----+  +----+
        |Imp1|  |Imp1|           ,---.                |Imp2|  |Imp2|  
        +----+  +----+          /     \    +-------+  +----+  +----+  
          | V100 | V200        /       \   | Tunnel|   | V300  | V400
          |      |            (         )  | Head  |   |       |
         +--------+  +------+ |         |__| Router|  +----------+
         |Ethernet|  |Tunnel| |Internet |  +---B---+  |Ethernet  |
         |Switch  |--|Head  |-|         |      |      |Switch    |
         +-+--+---+  |Router| |         |  +---+---+--+--+--+----+
           |__|      +--A---+ (         )  |Network|     |__|     
                               \       /   |Emulat.|         
         U-turn                 \     /    |"netem"|     U-turn 
         V300 to V400            `-+-'     +-------+     V100 to V200        

     
       
        Implementations                  ,---.       +--------+
                            +~~~~~~~~~~~/     \~~~~~~| Remote |
         +------->-----F2->-|          /       \     |->---.  |
         | +---------+      | Tunnel  (         )    |     |  |  
         | | transmit|-F1->-|   ID 1  (         )    |->.  |  |
         | | Imp 1   |      +~~~~~~~~~|         |~~~~|  |  |  |
         | | receive |-<--+           (         )    | F1  F2 |
         | +---------+    |           |Internet |    |  |  |  |
         *-------<-----+  F1          |         |    |  |  |  |
           +---------+ |  | +~~~~~~~~~|         |~~~~|  |  |  |
           | transmit|-*  *-|         |         |    |<-*  |  |
           | Imp 2   |      | Tunnel  (         )    |     |  |
           | receive |-<-F2-|   ID 2   \       /     |<----*  |     
           +---------+      +~~~~~~~~~~~\     /~~~~~~| Switch |
                                         `-+-'       +--------+
        ]]></artwork>

          <postamble>Illustrations of a test setup with a bi-directional
          tunnel. The upper diagram emphasizes the VLAN connectivity and
          geographical location. The lower diagram shows example flows
          traveling between two measurement implementations (for simplicity,
          only two flows are shown).</postamble>
        </figure></t>

      <t>The testing employs the Layer 2 Tunnel Protocol, version 3 (L2TPv3)
      <xref target="RFC3931"></xref> tunnel between test sites on the
      Internet. The tunnel IP and L2TPv3 headers are intended to conceal the
      test equipment addresses and ports from hash functions that would tend
      to spread different test streams across parallel network resources, with
      likely variation in performance as a result.</t>

      <t>At each end of the tunnel, one pair of VLANs encapsulated in the
      tunnel are looped-back so that test traffic is returned to each test
      site. Thus, test streams traverse the L2TP tunnel twice, but appear to
      be one-way tests from the test equipment point of view.</t>

      <t>The network emulator is a host running Fedora 14 Linux <xref
      target="Fedora14"></xref> with IP forwarding enabled and the "netem"
      Network emulator <xref target="netem"></xref> loaded and operating as
      part of the Fedora Kernel 2.6.35.11. Connectivity across the
      netem/Fedora host was accomplished by bridging Ethernet VLAN interfaces
      together with "brctl" commands (e.g., eth1.100 <-> eth2.100). The
      netem emulator was activated on one interface (eth1) and only operates
      on test streams traveling in one direction. In some tests, independent
      netem instances operated separately on each VLAN.</t>

      <t>The links between the netem emulator host and router and switch were
      found to be 100baseTx-HD (100Mbps half duplex) when the testing was
      complete. Use of Half Duplex was not intended, but probably added a
      small amount of delay variation that could have been avoided in full
      duplex mode.</t>

      <t>Each individual test was run with common packet rates (1 pps, 10pps)
      Poisson/Periodic distributions, and IP packet sizes of 64, 340, and 500
      Bytes. These sizes cover a reasonable range while avoiding fragmentation
      and the complexities it causes, and thus complying with the notion of
      "standard formed packets" described in Section 15 of <xref
      target="RFC2330"></xref>.</t>

      <t>For these tests, a stream of at least 300 packets were sent from
      Source to Destination in each implementation. Periodic streams (as per
      <xref target="RFC3432"></xref>) with 1 second spacing were used, except
      as noted.</t>

      <t>With the L2TPv3 tunnel in use, the metric name for the testing
      configured here (with respect to the IP header exposed to Internet
      processing) is:</t>

      <t>Type-IP-protocol-115-One-way-Delay-<StreamType>-Stream</t>

      <t>With (Section 4.2. <xref target="RFC2679"></xref>) Metric
      Parameters:</t>

      <t>+ Src, the IP address of a host (12.3.167.16 or 193.159.144.8)</t>

      <t>+ Dst, the IP address of a host (193.159.144.8 or 12.3.167.16)</t>

      <t>+ T0, a time</t>

      <t>+ Tf, a time</t>

      <t>+ lambda, a rate in reciprocal seconds</t>

      <t>+ Thresh, a maximum waiting time in seconds (see Section 3.8.2 of
      <xref target="RFC2679"></xref>) And (Section 4.3. <xref
      target="RFC2679"></xref>)</t>

      <t>Metric Units: A sequence of pairs; the elements of each pair are:</t>

      <t>+ T, a time, and</t>

      <t>+ dT, either a real number or an undefined number of seconds.</t>

      <t>The values of T in the sequence are monotonic increasing. Note that T
      would be a valid parameter to Type-P-One-way-Delay, and that dT would be
      a valid value of Type-P-One-way-Delay.</t>

      <t>Also, Section 3.8.4 of <xref target="RFC2679"></xref> recommends that
      the path SHOULD be reported. In this test set-up, most of the path
      details will be concealed from the implementations by the L2TPv3
      tunnels, thus a more informative path trace route can be conducted by
      the routers at each location.</t>

      <t>When NetProbe is used in production, a traceroute is conducted in
      parallel with, and at the outset of measurements.</t>

      <t>Perfas+ does not support traceroute.</t>

      <t><figure>
          <preamble></preamble>

          <artwork><![CDATA[IPLGW#traceroute 193.159.144.8

Type escape sequence to abort.
Tracing the route to 193.159.144.8

  1 12.126.218.245 [AS 7018] 0 msec 0 msec 4 msec
  2 cr84.n54ny.ip.att.net (12.123.2.158) [AS 7018] 4 msec 4 msec
    cr83.n54ny.ip.att.net (12.123.2.26) [AS 7018] 4 msec
  3 cr1.n54ny.ip.att.net (12.122.105.49) [AS 7018] 4 msec
    cr2.n54ny.ip.att.net (12.122.115.93) [AS 7018] 0 msec
    cr1.n54ny.ip.att.net (12.122.105.49) [AS 7018] 0 msec
  4 n54ny02jt.ip.att.net (12.122.80.225) [AS 7018] 4 msec 0 msec
    n54ny02jt.ip.att.net (12.122.80.237) [AS 7018] 4 msec
  5 192.205.34.182 [AS 7018] 0 msec
    192.205.34.150 [AS 7018] 0 msec
    192.205.34.182 [AS 7018] 4 msec
  6 da-rg12-i.DA.DE.NET.DTAG.DE (62.154.1.30) [AS 3320] 88 msec 88 msec
88 msec
  7 217.89.29.62 [AS 3320] 88 msec 88 msec 88 msec
  8 217.89.29.55 [AS 3320] 88 msec 88 msec 88 msec
  9  *  *  *
]]></artwork>

          <postamble></postamble>
        </figure></t>

      <t>It was only possible to conduct the traceroute for the measured path
      on one of the tunnel-head routers (the normal trace facilities of the
      measurement systems are confounded by the L2TPv3 tunnel
      encapsulation).</t>
    </section>

    <section title="Error Calibration, RFC 2679">
      <t>An implementation is required to report on its error calibration in
      Section 3.8 of <xref target="RFC2679"></xref> (also required in Section
      4.8 for sample metrics). Sections 3.6, 3.7, and 3.8 of <xref
      target="RFC2679"></xref> give the detailed formulation of the errors and
      uncertainties for calibration. In summary, Section 3.7.1 of <xref
      target="RFC2679"></xref> describes the total time-varying uncertainty
      as:</t>

      <t>Esynch(t)+ Rsource + Rdest</t>

      <t>where:</t>

      <t>Esynch(t) denotes an upper bound on the magnitude of clock
      synchronization uncertainty.</t>

      <t>Rsource and Rdest denote the resolution of the source clock and the
      destination clock, respectively.</t>

      <t>Further, Section 3.7.2 of <xref target="RFC2679"></xref> describes
      the total wire-time uncertainty as</t>

      <t>Hsource + Hdest</t>

      <t>referring to the upper bounds on host-time to wire-time for source
      and destination, respectively.</t>

      <t>Section 3.7.3 of <xref target="RFC2679"></xref> describes a test with
      small packets over an isolated minimal network where the results can be
      used to estimate systematic and random components of the sum of the
      above errors or uncertainties. In a test with hundreds of singletons,
      the median is the systematic error and when the median is subtracted
      from all singletons, the remaining variability is the random error.</t>

      <t>The test context, or Type-P of the test packets, must also be
      reported, as required in Section 3.8 of <xref target="RFC2679"></xref>
      and all metrics defined there. Type-P is defined in Section 13 of <xref
      target="RFC2330"></xref> (as are many terms used below).</t>

      <section title="NetProbe Error and Type-P">
        <t>Type-P for this test was IP-UDP with Best Effort DSCP. These
        headers were encapsulated according to the L2TPv3 specifications <xref
        target="RFC3931"></xref>, and thus may not influence the treatment
        received as the packets traversed the Internet.</t>

        <t>In general, NetProbe error is dependent on the specific version and
        installation details.</t>

        <t>NetProbe operates using host time above the UDP layer, which is
        different from the wire-time preferred in <xref
        target="RFC2330"></xref>, but can be identified as a source of error
        according to Section 3.7.2 of <xref target="RFC2679"></xref>.</t>

        <t>Accuracy of NetProbe measurements is usually limited by NTP
        synchronization performance (which is typically taken as ~+/-1ms error
        or greater), although the installation used in this testing often
        exhibits errors much less than typical for NTP. The primary stratum 1
        NTP server is closely located on a sparsely utilized network
        management LAN, thus it avoids many concerns raised in Section 10
        of<xref target="RFC2330"></xref> (in fact, smooth adjustment,
        long-term drift analysis and compensation, and infrequent adjustment
        all lead to stability during measurement intervals, the main
        concern).</t>

        <t>The resolution of the reported results is 1us (us = microsecond) in
        the version of NetProbe tested here, which contributes to at least
        +/-1us error.</t>

        <t>NetProbe implements a time-keeping sanity check on sending and
        receiving time-stamping processes. When the significant process
        interruption takes place, individual test packets are flagged as
        possibly containing unusual time errors, and are excluded from the
        sample used for all "time" metrics.</t>

        <t>We performed a NetProbe calibration of the type described in
        Section 3.7.3 of <xref target="RFC2679"></xref>, using 64 Byte packets
        over a cross-connect cable. The results estimate systematic and random
        components of the sum of the Hsource + Hdest errors or uncertainties.
        In a test with 300 singletons conducted over 30 seconds (periodic
        sample with 100ms spacing), the median is the systematic error and the
        remaining variability is the random error. One set of results is
        tabulated below:</t>

        <t><figure>
            <preamble>(Results from the "R" software environment for
            statistical computing and graphics - http://www.r-project.org/
            )</preamble>

            <artwork><![CDATA[> summary(XD4CAL) 
      CAL1            CAL2             CAL3          
 Min.   : 89.0   Min.   : 68.00   Min.   : 54.00   
 1st Qu.: 99.0   1st Qu.: 77.00   1st Qu.: 63.00   
 Median :110.0   Median : 79.00   Median : 65.00  
 Mean   :116.8   Mean   : 83.74   Mean   : 69.65   
 3rd Qu.:127.0   3rd Qu.: 88.00   3rd Qu.: 74.00    
 Max.   :205.0   Max.   :177.00   Max.   :163.00    
> ]]></artwork>

            <postamble>NetProbe Calibration with Cross-Connect Cable, one-way
            delay values in microseconds (us)</postamble>
          </figure></t>

        <t>The median or systematic error can be as high as 110 us, and the
        range of the random error is also on the order of 116 us for all
        streams.</t>

        <t>Also, anticipating the Anderson-Darling K-sample (ADK) <xref
        target="ADK"></xref> comparisons to follow, we corrected the CAL2
        values for the difference between means between CAL2 and CAL3 (as
        specified in <xref target="RFC6576"></xref>), and found strong support
        for the (Null Hypothesis that) the samples are from the same
        distribution (resolution of 1 us and alpha equal 0.05 and 0.01)<figure>
            <preamble></preamble>

            <artwork><![CDATA[> XD4CVCAL2 <- XD4CAL$CAL2 - (mean(XD4CAL$CAL2)-mean(XD4CAL$CAL3))
> boxplot(XD4CVCAL2,XD4CAL$CAL3) 
> XD4CV2_ADK <- adk.test(XD4CVCAL2, XD4CAL$CAL3)
> XD4CV2_ADK
Anderson-Darling k-sample test.

Number of samples:  2
Sample sizes: 300 300
Total number of values: 600
Number of unique values: 97

Mean of Anderson Darling Criterion: 1
Standard deviation of Anderson Darling Criterion: 0.75896

T = (Anderson Darling Criterion - mean)/sigma

Null Hypothesis: All samples come from a common population.

                     t.obs P-value extrapolation
not adj. for ties  0.71734 0.17042             0
adj. for ties     -0.39553 0.44589             1
> ]]></artwork>

            <postamble></postamble>
          </figure>using <xref target="Rtool"></xref> and <xref
        target="Radk"></xref>.</t>
      </section>

      <section title="Perfas+ Error and Type-P">
        <t>Perfas+ is configured to use GPS synchronisation and uses NTP
        synchronization as a fall-back or default. GPS synchronisation worked
        throughout this test with the exception of the calibration stated here
        (one implementation was NTP synchronised only). The time stamp
        accuracy typically is 0.1 ms.</t>

        <t>The resolution of the results reported by Perfas+ is 1us (us =
        microsecond) in the version tested here, which contributes to at least
        +/-1us error.</t>

        <t><figure>
            <preamble></preamble>

            <artwork><![CDATA[Port    5001 5002 5003 
Min.    -227 -226  294  
Median  -169 -167  323  
Mean    -159 -157  335  
Max.       6  -52  376 
s        102  102   93]]></artwork>

            <postamble>Perfas+ Calibration with Cross-Connect Cable, one-way
            delay values in microseconds (us)</postamble>
          </figure></t>

        <t>The median or systematic error can be as high as 323 us, and the
        range of the random error is also less than 232 us for all
        streams.</t>
      </section>
    </section>

    <section title="Pre-determined Limits on Equivalence">
      <t>This section provides the numerical limits on comparisons between
      implementations, in order to declare that the results are equivalent and
      therefore, the tested specification is clear. These limits have their
      basis in Section 3.1 of <xref target="RFC6576"></xref> and the Appendix
      of <xref target="RFC2330"></xref>, with additional limits representing
      IPPM consensus prior to publication of results.</t>

      <t>A key point is that the allowable errors, corrections, and confidence
      levels only need to be sufficient to detect mis-interpretation of the
      tested specification resulting in diverging implementations.</t>

      <t>Also, the allowable error must be sufficient to compensate for
      measured path differences. It was simply not possible to measure fully
      identical paths in the VLAN-loopback test configuration used, and this
      practical compromise must be taken into account.</t>

      <t>For Anderson-Darling K-sample (ADK) comparisons, the required
      confidence factor for the cross-implementation comparisons SHALL be the
      smallest of:</t>

      <t><list style="symbols">
          <t>0.95 confidence factor at 1ms resolution, or</t>

          <t>the smallest confidence factor (in combination with resolution)
          of the two same-implementation comparisons for the same test
          conditions.</t>
        </list>A constant time accuracy error of as much as +/-0.5ms MAY be
      removed from one implementation's distributions (all singletons) before
      the ADK comparison is conducted.</t>

      <t>A constant propagation delay error (due to use of different sub-nets
      between the switch and measurement devices at each location) of as much
      as +2ms MAY be removed from one implementation's distributions (all
      singletons) before the ADK comparison is conducted.</t>

      <t>For comparisons involving the mean of a sample or other central
      statistics, the limits on both the time accuracy error and the
      propagation delay error constants given above also apply.</t>
    </section>

    <section title="Tests to evaluate RFC 2679 Specifications">
      <t>This section describes some results from real-world (cross-Internet)
      tests with measurement devices implementing IPPM metrics and a network
      emulator to create relevant conditions, to determine whether the metric
      definitions were interpreted consistently by implementors.</t>

      <t>The procedures are slightly modified from the original procedures
      contained in Appendix A.1 of <xref target="RFC6576"></xref>. The
      modifications include the use of the mean statistic for comparisons.</t>

      <t>Note that there are only five instances of the requirement term
      "MUST" in <xref target="RFC2679"></xref> outside of the boilerplate and
      <xref target="RFC2119"></xref> reference.</t>

      <section title="One-way Delay, ADK Sample Comparison - Same & Cross Implementation">
        <t>This test determines if implementations produce results that appear
        to come from a common delay distribution, as an overall evaluation of
        Section 4 of <xref target="RFC2679"></xref>, "A Definition for Samples
        of One-way Delay". Same-implementation comparison results help to set
        the threshold of equivalence that will be applied to
        cross-implementation comparisons.</t>

        <t>This test is intended to evaluate measurements in sections 3 and 4
        of <xref target="RFC2679"></xref>.</t>

        <t>By testing the extent to which the distributions of one-way delay
        singletons from two implementations of <xref target="RFC2679"></xref>
        appear to be from the same distribution, we economize on comparisons,
        because comparing a set of individual summary statistics (as defined
        in Section 5 of <xref target="RFC2679"></xref>) would require another
        set of individual evaluations of equivalence. Instead, we can simply
        check which statistics were implemented, and report on those
        facts.</t>

        <t><list style="numbers">
            <t>Configure an L2TPv3 path between test sites, and each pair of
            measurement devices to operate tests in their designated pair of
            VLANs.</t>

            <t>Measure a sample of one-way delay singletons with 2 or more
            implementations, using identical options and network emulator
            settings (if used).</t>

            <t>Measure a sample of one-way delay singletons with *four*
            instances of the *same* implementations, using identical options,
            noting that connectivity differences SHOULD be the same as for the
            cross implementation testing.</t>

            <t>Apply the ADK comparison procedures (see Appendix C of <xref
            target="RFC6576"></xref>) and determine the resolution and
            confidence factor for distribution equivalence of each
            same-implementation comparison and each cross-implementation
            comparison.</t>

            <t>Take the coarsest resolution and confidence factor for
            distribution equivalence from the same-implementation pairs, or
            the limit defined in Section 5 above, as a limit on the
            equivalence threshold for these experimental conditions.</t>

            <t>Apply constant correction factors to all singletons of the
            sample distributions, as described and limited in Section 5
            above.</t>

            <t>Compare the cross-implementation ADK performance with the
            equivalence threshold determined in step 5 to determine if
            equivalence can be declared.</t>
          </list></t>

        <t>The common parameters used for tests in this section are:</t>

        <t><list style="symbols">
            <t>IP header + payload = 64 octets</t>

            <t>Periodic sampling at 1 packet per second</t>

            <t>Test duration = 300 seconds (March 29, 2011)</t>
          </list>The netem emulator was set for 100ms average delay, with
        uniform delay variation of +/-50ms. In this experiment, the netem
        emulator was configured to operate independently on each VLAN and thus
        the emulator itself is a potential source of error when comparing
        streams that traverse the test path in different directions.</t>

        <t>In the result analysis of this section:</t>

        <t><list style="symbols">
            <t>All comparisons used 1 microsecond resolution.</t>

            <t>No Correction Factors were applied.</t>

            <t>The 0.95 confidence factor (1.960 for paired stream comparison)
            was used.</t>
          </list></t>

        <section title="NetProbe Same-implementation results">
          <t>A single same-implementation comparison fails the ADK criterion
          (s1 <-> sB). We note that these streams traversed the test
          path in opposite directions, making the live network factors a
          possibility to explain the difference.</t>

          <t>All other pair comparisons pass the ADK criterion.</t>

          <t><figure title="NetProbe ADK Results for same-implementation">
              <preamble></preamble>

              <artwork align="center"><![CDATA[+------------------------------------------------------+
|            |             |             |             |
| ti.obs (P) |     s1      |     s2      |     sA      |
|            |             |             |             |
.............|.............|.............|.............|
|            |             |             |             |
|    s2      | 0.25 (0.28) |             |             |
|            |             |             |             |
...........................|.............|.............|
|            |             |             |             |
|    sA      | 0.60 (0.19) |-0.80 (0.57) |             |
|            |             |             |             |
...........................|.............|.............|
|            |             |             |             |
|    sB      | 2.64 (0.03) | 0.07 (0.31) |-0.52 (0.48) |
|            |             |             |             |
+------------+-------------+-------------+-------------+  ]]></artwork>

              <postamble></postamble>
            </figure></t>

          <t></t>
        </section>

        <section title="Perfas+ Same-implementation results">
          <t>All pair comparisons pass the ADK criterion.</t>

          <t><figure title="Perfas+ ADK Results for same-implementation">
              <preamble></preamble>

              <artwork align="center"><![CDATA[+------------------------------------------------------+
|            |             |             |             |
| ti.obs (P) |     p1      |     p2      |     p3      |
|            |             |             |             |
.............|.............|.............|.............|
|            |             |             |             |
|    p2      | 0.06 (0.32) |             |             |
|            |             |             |             |
.........................................|.............|
|            |             |             |             |
|    p3      | 1.09 (0.12) | 0.37 (0.24) |             |
|            |             |             |             |
...........................|.............|.............|
|            |             |             |             |
|    p4      |-0.81 (0.57) |-0.13 (0.37) | 1.36 (0.09) |
|            |             |             |             |
+------------+-------------+-------------+-------------+]]></artwork>

              <postamble></postamble>
            </figure></t>

          <t></t>
        </section>

        <section title="One-way Delay, Cross-Implementation ADK Comparison">
          <t>The cross-implementation results are compared using a combined
          ADK analysis <xref target="Radk"></xref>, where all NetProbe results
          are compared with all Perfas+ results after testing that the
          combined same-implementation results pass the ADK criterion.</t>

          <t>When 4 (same) samples are compared, the ADK criterion for 0.95
          confidence is 1.915, and when all 8 (cross) samples are compared it
          is 1.85.</t>

          <t><figure>
              <preamble></preamble>

              <artwork><![CDATA[Combination of Anderson-Darling K-Sample Tests.

Sample sizes within each data set:
Data set 1 :  299 297 298 300 (NetProbe)
Data set 2 :  300 300 298 300 (Perfas+)
Total sample size per data set: 1194 1198 
Number of unique values per data set: 1188 1192 
...
Null Hypothesis:
All samples within a data set come from a common distribution.
The common distribution may change between data sets.

NetProbe           ti.obs P-value extrapolation
not adj. for ties 0.64999 0.21355             0
adj. for ties     0.64833 0.21392             0
Perfas+                                         
not adj. for ties 0.55968 0.23442             0
adj. for ties     0.55840 0.23473             0
                                               
Combined Anderson-Darling Criterion: 
                   tc.obs P-value extrapolation
not adj. for ties 0.85537 0.17967             0
adj. for ties     0.85329 0.18010             0
]]></artwork>

              <postamble></postamble>
            </figure>The combined same-implementation samples and the combined
          cross-implementation comparison all pass the ADK criteria at
          P>=0.18 and support the Null Hypothesis (both data sets come from
          a common distribution).</t>

          <t>We also see that the paired ADK comparisons are rather critical.
          Although the NetProbe s1-sB comparison failed, the combined data set
          from 4 streams passed the ADK criterion easily.</t>
        </section>

        <section title="Conclusions on the ADK Results for One-way Delay">
          <t>Similar testing was repeated many times in the months of March
          and April 2011. There were many experiments where a single test
          stream from NetProbe or Perfas+ proved to be different from the
          others in paired comparisons (even same implementation comparisons).
          When the outlier stream was removed from the comparison, the
          remaining streams passed combined ADK criterion. Also, the
          application of correction factors resulted in higher comparison
          success.</t>

          <t>We conclude that the two implementations are capable of producing
          equivalent one-way delay distributions based on their interpretation
          of <xref target="RFC2679"></xref>.</t>
        </section>

        <section title="Additional Investigations">
          <t>On the final day of testing, we performed a series of
          measurements to evaluate the amount of emulated delay variation
          necessary to achieve successful ADK comparisons. The need for
          Correction factors (as permitted by Section 5) and the size of the
          measurement sample (obtained as sub-sets of the complete measurement
          sample) were also evaluated.</t>

          <t>The common parameters used for tests in this section are:</t>

          <t><list style="symbols">
              <t>IP header + payload = 64 octets</t>

              <t>Periodic sampling at 1 packet per second</t>

              <t>Test duration = 300 seconds at each delay variation setting,
              for a total of 1200 seconds (May 2, 2011 at 1720 UTC)</t>
            </list>The netem emulator was set for 100ms average delay, with
          (emulated) uniform delay variation of:</t>

          <t><list style="symbols">
              <t>+/-7.5 ms</t>

              <t>+/-5.0 ms</t>

              <t>+/-2.5 ms</t>

              <t>0 ms</t>
            </list></t>

          <t>In this experiment, the netem emulator was configured to operate
          independently on each VLAN and thus the emulator itself is a
          potential source of error when comparing streams that traverse the
          test path in different directions.</t>

          <t>In the result analysis of this section:</t>

          <t><list style="symbols">
              <t>All comparisons used 1 microsecond resolution.</t>

              <t>Correction Factors *were* applied as noted (under column
              heading "mean adj"). The difference between each sample mean and
              the lowest mean of the NetProbe or Perfas+ stream samples was
              subtracted from all values in the sample. ("raw" indicates no
              correction factors were used.) All correction factors applied
              met the limits described in Section 5.</t>

              <t>The 0.95 confidence factor (1.960 for paired stream
              comparison) was used.</t>
            </list></t>

          <t>When 8 (cross) samples are compared, the ADK criterion for 0.95
          confidence is 1.85. The Combined ADK test statistic ("TC observed")
          must be less than 1.85 to accept the Null Hypothesis (all samples in
          the data set are from a common distribution).</t>

          <t><figure>
              <preamble></preamble>

              <artwork><![CDATA[Emulated Delay                        Sub-Sample size
Variation     0ms
adk.combined (all)           300 values             75 values
Adj. for ties           raw         mean adj    raw        mean adj
TC observed             226.6563    67.51559    54.01359   21.56513
P-value                         0          0           0          0
Mean std dev (all),us         719                    635
Mean diff of means,us         649          0         606          0

Variation +/- 2.5ms
adk.combined (all)           300 values             75 values
Adj. for ties            raw        mean adj     raw       mean adj
TC observed              14.50436   -1.60196     3.15935   -1.72104 
P-value                         0     0.873      0.00799    0.89038 
Mean std dev (all),us        1655                   1702
Mean diff of means,us         471          0         513          0

Variation +/- 5ms
adk.combined (all)           300 values             75 values
Adj. for ties            raw        mean adj     raw       mean adj
TC observed               8.29921   -1.28927     0.37878   -1.81881
P-value                         0    0.81601     0.29984    0.90305
Mean std dev (all),us        3023                   2991
Mean diff of means,us         582          0         513          0

Variation +/- 7.5ms
adk.combined (all)           300 values             75 values
Adj. for ties            raw        mean adj     raw       mean adj
TC observed              2.53759    -0.72985     0.29241   -1.15840 
P-value                  0.01950     0.66942     0.32585    0.78686 
Mean std dev (all),us        4449                   4506
Mean diff of means,us         426          0         856          0

]]></artwork>

              <postamble></postamble>
            </figure></t>

          <t>From the table above, we conclude the following:</t>

          <t><list style="numbers">
              <t>None of the raw or mean adjusted results pass the ADK
              criterion with 0 ms emulated delay variation. Use of the 75
              value sub-sample yielded the same conclusion. (We note the same
              results when comparing same implementation samples for both
              NetProbe and Perfas+.)</t>

              <t>When the smallest emulated delay variation was inserted
              (+/-2.5ms), the mean adjusted samples pass the ADK criterion and
              the high P-value supports the result. The raw results do not
              pass.</t>

              <t>At higher values of emulated delay variation (+/-5.0ms and
              +/-7.5ms), again the mean adjusted values pass ADK. We also see
              that the 75-value sub-sample passed the ADK in both raw and mean
              adjusted cases. This indicates that sample size may have played
              a role in our results, as noted in the Appendix of <xref
              target="RFC2680"></xref> for Goodness-of-Fit testing.</t>
            </list></t>

          <t>We note that 150 value sub-samples were also evaluated, with ADK
          conclusions that followed the results for 300 values. Also,
          same-implementation analysis was conducted with results similar to
          the above, except that more of the "raw" or uncorrected samples
          passed the ADK criterion.</t>
        </section>
      </section>

      <section title="One-way Delay, Loss threshold, RFC 2679">
        <t>This test determines if implementations use the same configured
        maximum waiting time delay from one measurement to another under
        different delay conditions, and correctly declare packets arriving in
        excess of the waiting time threshold as lost.</t>

        <t>See Section 3.5 of <xref target="RFC2679"></xref>, 3rd bullet point
        and also Section 3.8.2 of <xref target="RFC2679"></xref>.</t>

        <t><list style="numbers">
            <t>configure an L2TPv3 path between test sites, and each pair of
            measurement devices to operate tests in their designated pair of
            VLANs.</t>

            <t>configure the network emulator to add 1.0 sec one-way constant
            delay in one direction of transmission.</t>

            <t>measure (average) one-way delay with 2 or more implementations,
            using identical waiting time thresholds (Thresh) for loss set at 3
            seconds.</t>

            <t>configure the network emulator to add 3 sec one-way constant
            delay in one direction of transmission equivalent to 2 seconds of
            additional one-way delay (or change the path delay while test is
            in progress, when there are sufficient packets at the first delay
            setting)</t>

            <t>repeat/continue measurements</t>

            <t>observe that the increase measured in step 5 caused all packets
            with 2 sec additional delay to be declared lost, and that all
            packets that arrive successfully in step 3 are assigned a valid
            one-way delay.</t>
          </list></t>

        <t>The common parameters used for tests in this section are:</t>

        <t><list style="symbols">
            <t>IP header + payload = 64 octets</t>

            <t>Poisson sampling at lambda = 1 packet per second</t>

            <t>Test duration = 900 seconds total (March 21, 2011)</t>
          </list>The netem emulator was set to add constant delays as
        specified in the procedure above.</t>

        <section title="NetProbe results for Loss Threshold">
          <t>In NetProbe, the Loss Threshold is implemented uniformly over all
          packets as a post-processing routine. With the Loss Threshold set at
          3 seconds, all packets with one-way delay >3 seconds are marked
          "Lost" and included in the Lost Packet list with their transmission
          time (as required in Section 3.3 of <xref target="RFC2680"></xref>).
          This resulted in 342 packets designated as lost in one of the test
          streams (with average delay = 3.091 sec).</t>
        </section>

        <section title="Perfas+ Results for Loss Threshold">
          <t>Perfas+ uses a fixed Loss Threshold which was not adjustable
          during this study. The Loss Threshold is approximately one minute,
          and emulation of a delay of this size was not attempted. However, it
          is possible to implement any delay threshold desired with a
          post-processing routine and subsequent analysis. Using this method,
          195 packets would be declared lost (with average delay = 3.091
          sec).</t>
        </section>

        <section title="Conclusions for Loss Threshold">
          <t>Both implementations assume that any constant delay value desired
          can be used as the Loss Threshold, since all delays are stored as a
          pair <Time, Delay> as required in <xref
          target="RFC2679"></xref> . This is a simple way to enforce the
          constant loss threshold envisioned in <xref target="RFC2679"></xref>
          (see specific section references above). We take the position that
          the assumption of post-processing is compliant, and that the text of
          the RFC should be revised slightly to include this point.</t>
        </section>
      </section>

      <section title="One-way Delay, First-bit to Last bit, RFC 2679">
        <t>This test determines if implementations register the same relative
        change in delay from one packet size to another, indicating that the
        first-to-last time-stamping convention has been followed. This test
        tends to cancel the sources of error which may be present in an
        implementation.</t>

        <t>See Section 3.7.2 of <xref target="RFC2679"></xref>, and Section
        10.2 of <xref target="RFC2330"></xref>.</t>

        <t><list style="numbers">
            <t>configure an L2TPv3 path between test sites, and each pair of
            measurement devices to operate tests in their designated pair of
            VLANs, and ideally including a low-speed link (it was not possible
            to change the link configuration during testing, so the lowest
            speed link present was the basis for serialization time
            comparisons).</t>

            <t>measure (average) one-way delay with 2 or more implementations,
            using identical options and equal size small packets (64 octet IP
            header and payload)</t>

            <t>maintain the same path with additional emulated 100 ms one-way
            delay</t>

            <t>measure (average) one-way delay with 2 or more implementations,
            using identical options and equal size large packets (500 octet IP
            header and payload)</t>

            <t>observe that the increase measured between steps 2 and 4 is
            equivalent to the increase in ms expected due to the larger
            serialization time for each implementation. Most of the
            measurement errors in each system should cancel, if they are
            stationary.</t>
          </list></t>

        <t>The common parameters used for tests in this section are:</t>

        <t><list style="symbols">
            <t>IP header + payload = 64 octets</t>

            <t>Periodic sampling at l packet per second</t>

            <t>Test duration = 300 seconds total (April 12)</t>
          </list>The netem emulator was set to add constant 100ms delay.</t>

        <section title="NetProbe and Perfas+ Results for Serialization">
          <t>When the IP header + payload size was increased from 64 octets to
          500 octets, there was a delay increase observed.</t>

          <t><figure>
              <preamble></preamble>

              <artwork><![CDATA[Mean Delays in us
NetProbe
Payload    s1      s2      sA      sB
500    190893  191179  190892  190971
 64    189642  189785  189747  189467
Diff     1251    1394    1145    1505

Perfas
Payload    p1      p2      p3      p4
500    190908  190911  191126  190709
 64    189706  189752  189763  190220
Diff     1202   1159    1363      489
]]></artwork>

              <postamble>Serialization tests, all values in
              microseconds</postamble>
            </figure></t>

          <t>The typical delay increase when the larger packets were used was
          1.1 to 1.5 ms (with one outlier). The typical measurements indicate
          that a link with approximately 3 Mbit/s capacity is present on the
          path.</t>

          <t>Through investigation of the facilities involved, it was
          determined that the lowest speed link was approximately 45 Mbit/s,
          and therefore the estimated difference should be about 0.077 ms. The
          observed differences are much higher.</t>

          <t>The unexpected large delay difference was also the outcome when
          testing serialization times in a lab environment, using the NIST Net
          Emulator and NetProbe <xref
          target="I-D.morton-ippm-advance-metrics"></xref>.</t>
        </section>

        <section title="Conclusions for Serialization">
          <t>Since it was not possible to confirm the estimated serialization
          time increases in field tests, we resort to examination of the
          implementations to determine compliance.</t>

          <t>NetProbe performs all time stamping above the IP-layer, accepting
          that some compromises must be made to achieve extreme portability
          and measurement scale. Therefore, the first-to-last bit convention
          is supported because the serialization time is included in the
          one-way delay measurement, enabling comparison with other
          implementations.</t>

          <t>Perfas+ is optimized for its purpose and performs all time
          stamping close to the interface hardware. The first-to-last bit
          convention is supported because the serialization time is included
          in the one-way delay measurement, enabling comparison with other
          implementations.</t>
        </section>
      </section>

      <section title="One-way Delay, Difference Sample Metric (Lab)">
        <t>This test determines if implementations register the same relative
        increase in delay from one measurement to another under different
        delay conditions. This test tends to cancel the sources of error which
        may be present in an implementation.</t>

        <t>This test is intended to evaluate measurements in sections 3 and 4
        of <xref target="RFC2679"></xref>.</t>

        <t><list style="numbers">
            <t>configure an L2TPv3 path between test sites, and each pair of
            measurement devices to operate tests in their designated pair of
            VLANs.</t>

            <t>measure (average) one-way delay with 2 or more implementations,
            using identical options</t>

            <t>configure the path with X+Y ms one-way delay</t>

            <t>repeat measurements</t>

            <t>observe that the (average) increase measured in steps 2 and 4
            is ~Y ms for each implementation. Most of the measurement errors
            in each system should cancel, if they are stationary.</t>
          </list>In this test, X=1000ms and Y=1000ms.</t>

        <t>The common parameters used for tests in this section are:</t>

        <t><list style="symbols">
            <t>IP header + payload = 64 octets</t>

            <t>Poisson sampling at lambda = 1 packet per second</t>

            <t>Test duration = 900 seconds total (March 21, 2011)</t>
          </list>The netem emulator was set to add constant delays as
        specified in the procedure above.</t>

        <section title="NetProbe results for Differential Delay">
          <t></t>

          <t><figure title="Average delays before/after 1 second increase">
              <preamble></preamble>

              <artwork align="center"><![CDATA[Average pre-increase delay, microseconds        1089868.0
Average post 1s additional, microseconds        2089686.0
Difference (should be ~= Y = 1s)                 999818.0]]></artwork>

              <postamble></postamble>
            </figure></t>

          <t>The NetProbe implementation observed a 1 second increase with a
          182 microsecond error (assuming that the netem emulated delay
          difference is exact).</t>

          <t>We note that this differential delay test has been run under lab
          conditions and published in prior work <xref
          target="I-D.morton-ippm-advance-metrics"></xref>. The error was 6
          microseconds.</t>
        </section>

        <section title="Perfas+ results for Differential Delay">
          <figure title="Average delays before/after 1 second increase">
            <preamble></preamble>

            <artwork align="center"><![CDATA[Average pre-increase delay, microseconds        1089794.0
Average post 1s additional, microseconds        2089801.0
Difference (should be ~= Y = 1s)                1000007.0]]></artwork>

            <postamble></postamble>
          </figure>

          <t></t>

          <t>The Perfas+ implementation observed a 1 second increase with a 7
          microsecond error.</t>
        </section>

        <section title="Conclusions for Differential Delay">
          <t>Again, the live network conditions appear to have influenced the
          results, but both implementations measured the same delay increase
          within their calibration accuracy.</t>
        </section>
      </section>

      <section title="Implementation of Statistics for One-way Delay">
        <t>The ADK tests the extent to which the sample distributions of
        one-way delay singletons from two implementations of <xref
        target="RFC2679"></xref> appear to be from the same overall
        distribution. By testing this way, we economize on the number of
        comparisons, because comparing a set of individual summary statistics
        (as defined in Section 5 of <xref target="RFC2679"></xref>) would
        require another set of individual evaluations of equivalence. Instead,
        we can simply check which statistics were implemented, and report on
        those facts, noting that Section 5 of <xref target="RFC2679"></xref>
        does not specify the calculations exactly, and gives only some
        illustrative examples.<figure>
            <preamble></preamble>

            <artwork><![CDATA[                                              NetProbe  Perfas+

5.1. Type-P-One-way-Delay-Percentile            yes       no

5.2. Type-P-One-way-Delay-Median                yes       no

5.3. Type-P-One-way-Delay-Minimum               yes       yes

5.4. Type-P-One-way-Delay-Inverse-Percentile    no        no


]]></artwork>

            <postamble>Implementation of Section 5 Statistics</postamble>
          </figure></t>

        <t>Only the Type-P-One-way-Delay-Inverse-Percentile has been ignored
        in both implementations, so it is a candidate for removal or
        deprecation in RFC2679bis (this small discrepancy does not affect
        candidacy for advancement).</t>
      </section>
    </section>

    <section title="Conclusions and RFC 2679 Errata">
      <t>The conclusions throughout Section 6 support the advancement of <xref
      target="RFC2679"></xref> to the next step of the standards track,
      because its requirements are deemed to be clear and unambiguous based on
      evaluation of the test results for two implementations. The results
      indicate that these implementations produced statistically equivalent
      results under network conditions that were configured to be as close to
      identical as possible.</t>

      <t>Sections 6.2.3 and 6.5 indicate areas where minor revisions are
      warranted in RFC2679bis. The IETF has reached consensus on guidance for
      reporting metrics in <xref target="RFC6703"></xref>, and this memo
      should be referenced in RFC2679bis to incorporate recent experience
      where appropriate.</t>

      <t>We note that there is currently one erratum with status "Held for
      document update" for <xref target="RFC2679"></xref>, and it appears this
      minor revision and additional text should be incorporated in
      RFC2679bis.</t>
    </section>

    <section anchor="Security" title="Security Considerations">
      <t>The security considerations that apply to any active measurement of
      live networks are relevant here as well. See <xref
      target="RFC4656"></xref> and <xref target="RFC5357"></xref>.</t>
    </section>

    <section anchor="IANA" title="IANA Considerations">
      <t>This memo makes no requests of IANA, and hopes that IANA will welcome
      our new computer overlords as willingly as the authors.</t>
    </section>

    <section anchor="Acknowledgements" title="Acknowledgements">
      <t>The authors thank Lars Eggert for his continued encouragement to
      advance the IPPM metrics during his tenure as AD Advisor.</t>

      <t>Nicole Kowalski supplied the needed CPE router for the NetProbe side
      of the test set-up, and graciously managed her testing in spite of
      issues caused by dual-use of the router. Thanks Nicole!</t>

      <t>The "NetProbe Team" also acknowledges many useful discussions with
      Ganga Maguluri.</t>
    </section>
  </middle>

  <back>
    <references title="Normative References">
      <?rfc include="reference.RFC.2119"?>

      <?rfc include='reference.RFC.2026'?>

      <?rfc include='reference.RFC.2330'?>

      <?rfc include='reference.RFC.2679'?>

      <?rfc include='reference.RFC.2680'?>

      <?rfc include='reference.RFC.3432'?>

      <?rfc include='reference.RFC.4656'?>

      <?rfc ?>

      <?rfc ?>

      <?rfc include='reference.RFC.5357'?>

      <?rfc include='reference.RFC.5657'?>

      <?rfc include='reference.RFC.6576'?>

      <?rfc include='reference.RFC.6703'?>
    </references>

    <references title="Informative References">
      <?rfc include='reference.I-D.morton-ippm-advance-metrics'?>

      <?rfc include='reference.I-D.bradner-metricstest'?>

      <?rfc include='reference.RFC.3931'?>

      <reference anchor="Perfas">
        <front>
          <title>Qualität in IP-Netzen Messverfahren</title>

          <author fullname="C. Heidemann" initials="C." surname="Heidemann">
            <!---->

            <organization>Deutsche Telekom</organization>
          </author>

          <date month="November" year="2001" />
        </front>

        <seriesInfo name="published by ITG Fachgruppe, 2nd meeting"
                    value="5.2.3 (NGN) http://www.itg523.de/oeffentlich/01nov/Heidemann_QOS_Messverfahren.pdf " />
      </reference>

      <reference anchor="ADK">
        <front>
          <title>K-sample Anderson-Darling Tests of fit, for continuous and
          discrete cases</title>

          <author fullname="Fred Scholz" initials="F.W." surname="Scholz">
            <!-- fullname="F.W. Scholz" -->

            <organization abbrev="Boeing">Boeing Computer
            Services</organization>
          </author>

          <author initials="M.A." surname="Stephens">
            <!-- fullname="M.A. Stephens" -->

            <organization>Simon Fraser University</organization>
          </author>

          <date month="May" year="1986" />
        </front>

        <seriesInfo name="University of Washington, Technical Report"
                    value="No. 81" />
      </reference>

      <reference anchor="Rtool">
        <front>
          <title>R: A language and environment for statistical computing. R
          Foundation for Statistical Computing, Vienna, Austria. ISBN
          3-900051-07-0, URL http://www.R-project.org/</title>

          <author fullname="R Development Core Team" initials=""
                  surname="R Development Core Team">
            <!-- fullname="F.W. Scholz" -->

            <organization abbrev="Boeing">Boeing Computer
            Services</organization>
          </author>

          <date month="" year="2011" />
        </front>

        <seriesInfo name="" value="" />
      </reference>

      <reference anchor="Radk">
        <front>
          <title>adk: Anderson-Darling K-Sample Test and Combinations of Such
          Tests. R package version 1.0.</title>

          <author fullname="Fritz Scholz" initials="F." surname="Scholz">
            <!-- fullname="F.W. Scholz" -->

            <organization abbrev="Boeing">Boeing Computer
            Services</organization>
          </author>

          <date month="" year="2008" />
        </front>

        <seriesInfo name="" value="" />
      </reference>

      <reference anchor="WIPM">
        <front>
          <title>AT&T Global IP Network</title>

          <author fullname="AT&T" initials="" surname="">
            <!---->
          </author>

          <date month="" year="2012" />
        </front>

        <seriesInfo name=""
                    value="http://ipnetwork.bgtmo.ip.att.net/pws/index.html" />
      </reference>

      <reference anchor="Fedora14">
        <front>
          <title>Fedora Project Home Page</title>

          <author fullname="Fedora Project" initials="" surname="">
            <!---->
          </author>

          <date month="" year="2012" />
        </front>

        <seriesInfo name="" value="http://fedoraproject.org/" />
      </reference>

      <reference anchor="netem">
        <front>
          <title>"netem" Documentation</title>

          <author fullname="The Linux Foundation" initials="" surname="">
            <!---->
          </author>

          <date month="" year="2009" />
        </front>

        <seriesInfo name=""
                    value="http://www.linuxfoundation.org/collaborate/workgroups/networking/netem" />
      </reference>
    </references>
  </back>
</rfc>

PAFTECH AB 2003-20262026-04-24 07:27:18