One document matched: draft-morton-bmwg-imix-genome-02.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-morton-bmwg-imix-genome-02"
     ipr="trust200902">
  <front>
    <title abbrev="IMIX Genome">IMIX Genome: Specification of variable packet
    sizes for additional testing</title>

    <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>

    <date day="7" month="July" year="2011" />

    <abstract>
      <t>Benchmarking Methodologies have always relied on test conditions with
      constant packet sizes, with the goal of understanding what network
      device capability has been tested. Tests with constant packet size
      reveal device capabilities but differ significantly from the conditions
      encountered in operational deployment, and so additional tests are
      sometimes conducted with a mixture of packet sizes, or "IMIX". The
      mixture of sizes a networking device will encounter is highly variable
      and depends on many factors. An IMIX suited for one networking device
      and deployment will not be appropriate for another. However, the mix of
      sizes may be known and the tester may be asked to augment the fixed size
      tests. To address this need, and the perpetual goal of specifying
      repeatable test conditions, this draft defines a way to specify the
      exact repeating sequence of packet sizes from the usual set of fixed
      sizes, and other forms of mixed size specification.</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>

      <t></t>
    </note>
  </front>

  <middle>
    <section title="Introduction">
      <t>This memo defines a method to unambiguously specify the sequence of
      packet sizes used in a load test.</t>

      <t>Benchmarking Methodologies <xref target="RFC2544"></xref> have always
      relied on test conditions with constant packet sizes, with the goal of
      understanding what network device capability has been tested. Tests with
      the smallest size stress the header processing capacity, and tests with
      the largest size stress the overall bit processing capacity. Tests with
      sizes in-between may determine the transition between these two
      capacities.</t>

      <t>Streams of constant packet size differ significantly from the
      conditions encountered in operational deployment, and so additional
      tests are sometimes conducted with a mixture of packet sizes. The set of
      sizes used is often called an Internet Mix, or "IMIX" <xref
      target="Spirent"></xref>, <xref target="IXIA"></xref>, <xref
      target="Agilent"></xref>.</t>

      <t>The mixture of sizes a networking device will encounter is highly
      variable and depends on many factors. An IMIX suited for one networking
      device and deployment will not be appropriate for another. However, the
      mix of sizes may be known and the tester may be asked to augment the
      fixed size tests. The references above cite the original studies and
      their methodologies - similar methods can be used to determine new size
      mixes.</t>

      <t>To address this need, and the perpetual goal of specifying repeatable
      test conditions, this draft proposes a way to specify the exact
      repeating sequence of packet sizes from the usual set of fixed sizes:
      the IMIX Genome. Other, less exact forms of size specification are also
      recommended for extremely complicated or customized size mixes.</t>

      <t>This memo takes the position that it cannot be proven for all
      circumstances that the sequence of packet sizes does not affect the test
      result, thus a standardized specification of sequence is valuable.</t>
    </section>

    <section title="Scope and Goals">
      <t>This memo defines a method to unambiguously specify the sequence of
      packet sizes that have been used in a load test, assuming that a
      relevant mix of sizes is known to the tester and the length of the
      repeating sequence is not very long (<100 packets).</t>

      <t>The IMIX Genome will allow an exact sequence of packet sizes to be
      communicated as a single-line name, resolving the current ambiguity with
      results that simply refer to "IMIX".</t>

      <t>While documentation of the exact sequence is ideal, the memo also
      covers the case where the sequence of sizes is very long or may be
      generated by a pseudo-random process.</t>

      <t>It is a colossal non-goal to standardize one or more versions of the
      IMIX. This topic has been discussed on many occasions on the
      bmwg-list<xref target="IMIXonList"></xref>. The goal is to enable
      customization with minimal constraints while fostering repeatable
      testing once the fixed size testing is complete.</t>
    </section>

    <section title="Specification of the IMIX Genome">
      <t>The IMIX Genome is specified in the following format:</t>

      <t>IMIX - 123456...x</t>

      <t>where each number is replaced by the letter corresponding to the size
      of the packet at that position in the sequence. The following table
      gives the letter encoding for the <xref target="RFC2544"></xref>
      standard sizes (64, 128, 256, 512, 1024, 1280, and 1518 bytes) and
      "jumbo" sizes (2112, 9000, 16000). Note that the 4 octet Ethernet frame
      check sequence may fail to detect bit errors in the larger jumbo frames,
      see <xref target="jumbo"></xref>.</t>

      <texttable>
        <preamble></preamble>

        <ttcol>Size, bytes</ttcol>

        <ttcol>Genome Code Letter</ttcol>

        <c>64</c>

        <c>a</c>

        <c>128</c>

        <c>b</c>

        <c>256</c>

        <c>c</c>

        <c>512</c>

        <c>d</c>

        <c>1024</c>

        <c>e</c>

        <c>1280</c>

        <c>f</c>

        <c>1518</c>

        <c>g</c>

        <c>2112</c>

        <c>h</c>

        <c>9000</c>

        <c>i</c>

        <c>16000</c>

        <c>j</c>

        <c>MTU</c>

        <c>z</c>

        <postamble></postamble>
      </texttable>

      <t>For example: a five packet sequence with sizes 64,64,64,1280,1518
      would be designated:</t>

      <t>IMIX - aaafg</t>

      <t>While this approach allows some flexibility, there are also
      constraints.</t>

      <t><list style="symbols">
          <t>Non-RFC2544 packet sizes would need to be approximated by those
          available in the table.</t>

          <t>The Genome for very long sequences can become undecipherable by
          humans.</t>

          <t>z=MTU is seen as valuable (so far).</t>

          <t>Whether more tabulated packet sizes would be useful is TBD, and
          "jumbo" sizes were added in this version.</t>
        </list>Some questions testers must ask and answer when using the IMIX
      Genome are:</t>

      <t><list style="numbers">
          <t>Multiple Source-Destination Address Pairs: is the IMIX sequence
          applicable to each pair, across multiple pairs in sets, or across
          all pairs?</t>

          <t>Multiple Tester Ports:is the IMIX sequence applicable to each
          port, across multiple ports in sets, or across all ports?</t>
        </list>The chosen configuration would be expressed the following
      general form:</t>

      <texttable>
        <preamble></preamble>

        <ttcol>Source Address/Port/Blade</ttcol>

        <ttcol>Destination Address/Port/Blade</ttcol>

        <ttcol>Corresponding IMIX</ttcol>

        <c>x.x.x.x Blade2</c>

        <c>y.y.y.y Blade3</c>

        <c>IMIX - aaafg</c>

        <postamble></postamble>
      </texttable>

      <t>where testers can specify the IMIX used between any two entities in
      the test architecture.</t>
    </section>

    <section title="Specification of a Custom IMIX">
      <t>The Custom IMIX is specified in the following format:</t>

      <t>CUSTOM IMIX - 123456...x</t>

      <t>where each number is replaced by the letter corresponding to the size
      of the packet at that position in the sequence. The tester MUST complete
      the following table, giving the letter encoding for each size used,
      where each set of three lower-case letters would be replaced by the
      integer size in octets.</t>

      <texttable>
        <preamble></preamble>

        <ttcol>Size, bytes</ttcol>

        <ttcol>Custom Code Letter</ttcol>

        <c>aaa</c>

        <c>A</c>

        <c>bbb</c>

        <c>B</c>

        <c>ccc</c>

        <c>C</c>

        <c>ddd</c>

        <c>D</c>

        <c>eee</c>

        <c>E</c>

        <c>fff</c>

        <c>F</c>

        <c>ggg</c>

        <c>G</c>

        <c>etc.</c>

        <c>up to Z</c>

        <postamble></postamble>
      </texttable>

      <t>For example: a five packet sequence with sizes aaa,aaa,aaa,ggg,ggg
      would be designated:</t>

      <t>CUSTOM IMIX - AAAGG</t>
    </section>

    <section title="Reporting Long or Pseudo-Random Packet Sequences">
      <t>When the IMIX-Genome cannot be used (when the sheer length of the
      sequence would make the genome unmanageable) or when the sequence is
      designed to vary within some proportional constraints, a table is
      necessary.</t>

      <texttable>
        <preamble></preamble>

        <ttcol>IP Length</ttcol>

        <ttcol>Percentage of Total</ttcol>

        <ttcol>Other Length(s)</ttcol>

        <c>64</c>

        <c>23</c>

        <c>82</c>

        <c>128</c>

        <c>67</c>

        <c>146</c>

        <c>1000</c>

        <c>10</c>

        <c>1018</c>

        <postamble></postamble>
      </texttable>

      <t>Note that this approach also allows non-standard packet sizes, but
      trades the short genome specification and ability to specify the exact
      sequence for other flexibilities.</t>
    </section>

    <section title="Security Considerations">
      <t>Benchmarking activities as described in this memo are limited to
      technology characterization using controlled stimuli in a laboratory
      environment, with dedicated address space and the other constraints
      <xref target="RFC2544"></xref>.</t>

      <t>The benchmarking network topology will be an independent test setup
      and MUST NOT be connected to devices that may forward the test traffic
      into a production network, or misroute traffic to the test management
      network.</t>

      <t>Further, benchmarking is performed on a "black-box" basis, relying
      solely on measurements observable external to the DUT/SUT.</t>

      <t>Special capabilities SHOULD NOT exist in the DUT/SUT specifically for
      benchmarking purposes. Any implications for network security arising
      from the DUT/SUT SHOULD be identical in the lab and in production
      networks.</t>
    </section>

    <section anchor="IANA" title="IANA Considerations">
      <t>This memo makes no requests of IANA, and hopes that IANA will leave
      it alone as well.</t>
    </section>

    <section title="Acknowledgements">
      <t>Thanks to Sarah Banks, Aamer Akhter, and Steve Maxwell for their
      review and comments.</t>
    </section>
  </middle>

  <back>
    <references title="Normative References">
      <?rfc include='reference.RFC.2544'?>

      <?rfc include="reference.RFC.2119"?>

      <?rfc ?>

      <?rfc ?>

      <?rfc ?>

      <?rfc ?>

      <?rfc ?>

      <?rfc ?>

      <?rfc ?>

      <?rfc ?>
    </references>

    <references title="Informative References">
      <reference anchor="Spirent">
        <front>
          <title>Test Methodology Journal: IMIX (Internet Mix) Journal</title>

          <author fullname="Spirent" surname="">
            <organization>http://gospirent.com/whitepaper/IMIX%20Test%20Methodolgy%20Journal.pdf</organization>
          </author>

          <date month=" " year="2006" />
        </front>
      </reference>

      <reference anchor="IXIA">
        <front>
          <title>Library: Test Plans</title>

          <author fullname="IXIA">
            <organization>http://www.ixiacom.com/library/test_plans/display?skey=testing_pppox</organization>
          </author>

          <date year="2010" />
        </front>
      </reference>

      <reference anchor="Agilent">
        <front>
          <title>The Journal of Internet Test Methodologies</title>

          <author fullname="Agilent">
            <organization>http://www.ixiacom.com/pdfs/test_plans/agilent_journal_of_internet_test_methodologies.pdf</organization>
          </author>

          <date year="2007" />
        </front>
      </reference>

      <reference anchor="IMIXonList">
        <front>
          <title>Discussion on IMIX</title>

          <author fullname="Several">
            <organization>http://www.ietf.org/mail-archive/web/bmwg/current/msg00691.html</organization>
          </author>

          <date year="2003" />
        </front>
      </reference>

      <reference anchor="jumbo">
        <front>
          <title>Discussion of Jumbo Packets and FCS Failure, see
          http://sd.wareonearth.com/~phil/jumbo.html and
          http://staff.psc.edu/mathis/MTU/arguments.html#crc</title>

          <author fullname="">
            <organization>http://www.ietf.org/mail-archive/web/bmwg/current/msg00691.html</organization>
          </author>

          <date year="" />
        </front>
      </reference>
    </references>
  </back>
</rfc>

PAFTECH AB 2003-20262026-04-24 06:01:58