One document matched: draft-zimmermann-tcpm-cubic-01.xml


<?xml version="1.0" encoding="US-ASCII"?>
<!DOCTYPE rfc SYSTEM "rfc2629.dtd" [
  <!ENTITY RFC2018 PUBLIC '' 'http://xml2rfc.ietf.org/public/rfc/bibxml/reference.RFC.2018.xml'>
  <!ENTITY RFC2119 PUBLIC '' 'http://xml2rfc.ietf.org/public/rfc/bibxml/reference.RFC.2119.xml'>
  <!ENTITY RFC5681 PUBLIC '' 'http://xml2rfc.ietf.org/public/rfc/bibxml/reference.RFC.5681.xml'>
  <!ENTITY RFC5348 PUBLIC '' 'http://xml2rfc.ietf.org/public/rfc/bibxml/reference.RFC.5348.xml'>
  <!ENTITY RFC3649 PUBLIC '' 'http://xml2rfc.ietf.org/public/rfc/bibxml/reference.RFC.3649.xml'>
  <!ENTITY RFC6582 PUBLIC '' 'http://xml2rfc.ietf.org/public/rfc/bibxml/reference.RFC.6582.xml'>
  <!ENTITY RFC4960 PUBLIC '' 'http://xml2rfc.ietf.org/public/rfc/bibxml/reference.RFC.4960.xml'>
  <!ENTITY RFC5033 PUBLIC '' 'http://xml2rfc.ietf.org/public/rfc/bibxml/reference.RFC.5033.xml'>
]>

<?xml-stylesheet type='text/xsl' href='rfc2629.xslt' ?>
<!-- For a complete list and description of processing instructions (PIs),
   please see http://xml2rfc.ietf.org/authoring/README.html. -->
<!-- Below are generally applicable Processing Instructions (PIs) that most I-Ds
   might want to use. (Here they are set differently than their defaults in
   xml2rfc v1.32) -->
<?rfc strict="yes" ?>
<!-- give errors regarding ID-nits and DTD validation -->
<!-- control the table of contents (ToC) -->
<?rfc toc="yes"?>
<!-- generate a ToC -->
<?rfc tocdepth="3"?>
<!-- the number of levels of subsections in ToC. default: 3 -->
<!-- control references -->
<?rfc symrefs="yes"?>
<!-- use symbolic references tags, i.e, [RFC2119] instead of [1] -->
<?rfc sortrefs="yes" ?>
<!-- sort the reference entries alphabetically -->
<!-- control vertical white space
   (using these PIs as follows is recommended by the RFC Editor) -->
<?rfc compact="yes" ?>
<!-- do not start each main section on a new page -->
<?rfc subcompact="no" ?>
<!-- keep one blank line between list items -->
<!-- end of list of popular I-D processing instructions -->


<rfc category="exp" ipr="trust200902" docName="draft-zimmermann-tcpm-cubic-01">

  <!-- FRONT MATTER -->
  <front>
    <title abbrev='CUBIC'>CUBIC for Fast Long-Distance Networks</title>

    <author initials='I.' surname="Rhee" fullname='Injong Rhee'>
      <organization abbrev='NCSU'>North Carolina State University</organization>
      <address>
        <postal>
          <street>Department of Computer Science</street>
          <city>Raleigh</city>
          <region>NC</region>
          <code>27695-7534</code>
          <country>US</country>
        </postal>
        <email>rhee@ncsu.edu</email>
      </address>
    </author>

    <author initials='L.' surname="Xu" fullname='Lisong Xu'>
      <organization abbrev='UNL'>University of Nebraska-Lincoln</organization>
      <address>
        <postal>
          <street>Department of Computer Science and Engineering</street>
          <city>Lincoln</city>
          <region>NE</region>
          <code>68588-01150</code>
          <country>US</country>
        </postal>
        <email>xu@unl.edu</email>
      </address>
    </author>

    <author initials='S.' surname="Ha" fullname='Sangtae Ha'>
      <organization abbrev='NCSU'>University of Colorado at Boulder</organization>
      <address>
        <postal>
          <street>Department of Computer Science</street>
          <city>Boulder</city>
          <region>CO</region>
          <code>80309-0430</code>
          <country>US</country>
        </postal>
        <email>sangtae.ha@colorado.edu</email>
      </address>
    </author>

    <author initials="A" surname="Zimmermann" fullname="Alexander Zimmermann">
      <organization>NetApp</organization>
      <address>
        <postal>
          <street>Sonnenallee 1</street>
          <city>Kirchheim</city>
          <code>85551</code>
          <country>Germany</country>
        </postal>
        <phone>+49 89 900594712</phone>
        <email>alexander.zimmermann@netapp.com</email>
      </address>
    </author>

    <author initials="L" surname="Eggert" fullname="Lars Eggert">
      <organization>NetApp</organization>
      <address>
        <postal>
          <street>Sonnenallee 1</street>
          <city>Kirchheim</city>
          <code>85551</code>
          <country>Germany</country>
        </postal>
        <phone>+49 151 12055791</phone>
        <email>lars@netapp.com</email>
      </address>
    </author>

    <author fullname="Richard Scheffenegger" initials="R."
           surname="Scheffenegger">
     <organization>NetApp</organization>
     <address>
       <postal>
         <street>Am Euro Platz 2</street>
         <code>1120</code>
         <city>Vienna</city>
         <region></region>
         <country>Austria</country>
       </postal>
       <phone>+43 1 3676811 3146</phone>
       <email>rs@netapp.com</email>
     </address>
    </author>


    <date />

    <!-- Meta-data Declarations -->
    <area>Transport</area>

    <workgroup>TCP Maintenance and Minor Extensions (TCPM) WG</workgroup>

    <keyword>TCP Congestion Control</keyword>

    <abstract>

      <t>CUBIC is an extension to the current TCP standards. The protocol
      differs from the current TCP standards only in the congestion window
      adjustment function in the sender side. In particular, it uses a
      cubic function instead of a linear window increase of the current
      TCP standards to improve scalability and stability under fast and
      long distance networks. BIC-TCP, a predecessor of CUBIC, has been a
      default TCP adopted by Linux since year 2005 and has already been
      deployed globally and in use for several years by the Internet
      community at large. CUBIC is using a similar window growth function
      as BIC-TCP and is designed to be less aggressive and fairer to TCP
      in bandwidth usage than BIC-TCP while maintaining the strengths of
      BIC-TCP such as stability, window scalability and RTT fairness.
      Through extensive testing in various Internet scenarios, we believe
      that CUBIC is safe for deployment and testing in the global
      Internet. The intent of this document is to provide the protocol
      specification of CUBIC for a third party implementation and solicit
      the community feedback through experimentation on the performance of
      CUBIC. We expect this document to be eventually published as an
      experimental RFC.</t>

    </abstract>

  </front>

  <!--  MAIN MATTER -->
  <middle>
    <!-- Section: Introduction -->
    <section title='Introduction'>

      <t>The low utilization problem of TCP in fast long-distance networks
      is well documented in <xref target="K03"/><xref target="RFC3649"/>.
      This problem arises from a slow increase of congestion window
      following a congestion event in a network with a large bandwidth
      delay product (BDP). Our experience <xref target="HKLRX06"/>
      indicates that this problem is frequently observed even in the range
      of congestion window sizes over several hundreds of packets (each
      packet is sized around 1000 bytes) especially under a network path
      with over 100ms round-trip times (RTTs). This problem is equally
      applicable to all Reno style TCP standards and their variants,
      including TCP-RENO <xref target="RFC5681"/>, TCP-NewReno <xref
      target="RFC6582"/>, TCP-SACK <xref target="RFC2018"/>, SCTP <xref
      target="RFC4960"/>, TFRC <xref target="RFC5348"/> that use the same
      linear increase function for window growth, which we refer to
      collectively as Standard TCP below.</t>

      <t>CUBIC <xref target="HRX08"/> is a modification to the congestion
      control mechanism of Standard TCP, in particular, to the window
      increase function of Standard TCP senders, to remedy this problem.
      It uses a cubic increase function in terms of the elapsed time from
      the last congestion event. While most alternative algorithms to
      Standard TCP uses a convex increase function where after a loss
      event, the window increment is always increasing, CUBIC uses both
      the concave and convex profiles of a cubic function for window
      increase. After a window reduction following a loss event, it
      registers the window size where it got the loss event as W_max and
      performs a multiplicative decrease of congestion window and the
      regular fast recovery and retransmit of Standard TCP. After it
      enters into congestion avoidance from fast recovery, it starts to
      increase the window using the concave profile of the cubic function.
      The cubic function is set to have its plateau at W_max so the
      concave growth continues until the window size becomes W_max. After
      that, the cubic function turns into a convex profile and the convex
      window growth begins. This style of window adjustment (concave and
      then convex) improves protocol and network stability while
      maintaining high network utilization <xref target="CEHRX07"/>. This
      is because the window size remains almost constant, forming a
      plateau around W_max where network utilization is deemed highest and
      under steady state, most window size samples of CUBIC are close to
      W_max, thus promoting high network utilization and protocol
      stability. Note that protocols with convex increase functions have
      the maximum increments around W_max and introduces a large number of
      packet bursts around the saturation point of the network, likely
      causing frequent global loss synchronizations.</t>

      <t>Another notable feature of CUBIC is that its window increase rate
      is mostly independent of RTT, and follows a (cubic) function of the
      elapsed time since the last loss event. This feature promotes
      per-flow fairness to Standard TCP as well as RTT-fairness. Note that
      Standard TCP performs well under short RTT and small bandwidth (or
      small BDP) networks. Only in a large long RTT and large bandwidth
      (or large BDP) networks, it has the scalability problem. An
      alternative protocol to Standard TCP designed to be friendly to
      Standard TCP at a per-flow basis must operate must increase its
      window much less aggressively in small BDP networks than in large
      BDP networks. In CUBIC, its window growth rate is slowest around the
      inflection point of the cubic function and this function does not
      depend on RTT. In a smaller BDP network where Standard TCP flows are
      working well, the absolute amount of the window decrease at a loss
      event is always smaller because of the multiplicative decrease.
      Therefore, in CUBIC, the starting window size after a loss event
      from which the window starts to increase, is smaller in a smaller
      BDP network, thus falling nearer to the plateau of the cubic
      function where the growth rate is slowest. By setting appropriate
      values of the cubic function parameters, CUBIC sets its growth rate
      always no faster than Standard TCP around its inflection point. When
      the cubic function grows slower than the window of Standard TCP,
      CUBIC simply follows the window size of Standard TCP to ensure
      fairness to Standard TCP in a small BDP network. We call this region
      where CUBIC behaves like Standard TCP, the TCP-friendly region.</t>

      <t>CUBIC maintains the same window growth rate independent of RTTs
      outside of the TCP-friendly region, and flows with different RTTs
      have the similar window sizes under steady state when they operate
      outside the TCP-friendly region. This ensures CUBIC flows with
      different RTTs to have their bandwidth shares linearly proportional
      to the inverse of their RTT ratio (the longer RTT, the smaller the
      share). This behavior is the same as that of Standard TCP under high
      statistical multiplexing environments where packet losses are
      independent of individual flow rates. However, under low statistical
      multiplexing environments, the bandwidth share ratio of Standard TCP
      flows with different RTTs is squarely proportional to the inverse of
      their RTT ratio <xref target="XHR04"/>. CUBIC always ensures the
      linear ratio independent of the levels of statistical multiplexing.
      This is an improvement over Standard TCP. While there is no
      consensus on a particular bandwidth share ratios of different RTT
      flows, we believe that under wired Internet, use of the linear share
      notion seems more reasonable than equal share or a higher order
      shares. HTCP <xref target="LS08"/> currently uses the equal
      share.</t>

      <t>CUBIC sets the multiplicative window decrease factor to 0.2 while
      Standard TCP uses 0.5. While this improves the scalability of the
      protocol, a side effect of this decision is slower convergence
      especially under low statistical multiplexing environments. This
      design choice is following the observation that the author of HSTCP
      <xref target="RFC3649"/> has made along with other researchers
      (e.g., <xref target="GV02"/>): the current Internet becomes more
      asynchronous with less frequent loss synchronizations with high
      statistical multiplexing. Under this environment, even strict MIMD
      can converge. CUBIC flows with the same RTT always converge to the
      same share of bandwidth independent of statistical multiplexing,
      thus achieving intra-protocol fairness. We also find that under the
      environments with sufficient statistical multiplexing, the
      convergence speed of CUBIC flows is reasonable.</t>

      <t>In the ensuing sections, we provide the exact specification of
      CUBIC and discuss the safety features of CUBIC following the
      guidelines specified in <xref target="RFC5033"/>.</t>

    </section>

    <!-- Section: Conventions -->
    <section title='Conventions'>
      <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"/>.</t>
    </section>

    <!-- Section: CUBIC Congestion Control -->
    <section title="CUBIC Congestion Control">

      <!-- Subsection: Window growth function -->
      <section title="Window growth function">

        <t>CUBIC maintains the acknowledgment (ACK) clocking of Standard
        TCP by increasing congestion window only at the reception of ACK.
        The protocol does not make any change to the fast recovery and
        retransmit of TCP-NewReno <xref target="RFC6582"/> and TCP-SACK
        <xref target="RFC2018"/>. During congestion avoidance after fast
        recovery, CUBIC changes the window update algorithm of Standard
        TCP. Suppose that W_max is the window size before the window is
        reduced in the last fast retransmit and recovery.</t>

        <t>The window growth function of CUBIC uses the following
        function:

          <list>
            <t>W(t) = C*(t-K)^3 + W_max (Eq. 1)</t>
          </list>
        </t>

        <t>where C is a constant fixed to determine the aggressiveness of
        window growth in high BDP networks, t is the elapsed time from the
        last window reduction,and K is the time period that the above
        function takes to increase W to W_max when there is no further
        loss event and is calculated by using the following equation:

          <list>
            <t>K = cubic_root(W_max*beta/C) (Eq. 2)</t>
          </list>
        </t>

        <t>where beta is the multiplication decrease factor. We discuss
        how we set C in the next Section in more details.</t>

        <t>Upon receiving an ACK during congestion avoidance, CUBIC
        computes the window growth rate during the next RTT period using
        Eq. 1. It sets W(t+RTT) as the candidate target value of
        congestion window. Suppose that the current window size is cwnd.
        Depending on the value of cwnd, CUBIC runs in three different
        modes. First, if cwnd is less than the window size that Standard
        TCP would reach at time t after the last loss event, then CUBIC is
        in the TCP friendly region (we describe below how to determine
        this window size of Standard TCP in term of time t). Otherwise, if
        cwnd is less than W_max, then CUBIC is the concave region, and if
        cwnd is larger than W_max, CUBIC is in the convex region. Below,
        we describe the exact actions taken by CUBIC in each region.</t>

      </section>

      <!-- Subsection: TCP-friendly region -->
      <section title="TCP-friendly region">

        <t>When receiving an ACK in congestion avoidance, we first check
        whether the protocol is in the TCP region or not. This is done as
        follows. We can analyze the window size of Standard TCP in terms
        of the elapsed time t. Using a simple analysis in <xref
        target="FHP00"/>, we can analyze the average window size of
        additive increase and multiplicative decrease (AIMD) with an
        additive factor alpha and a multiplicative factor beta to be the
        following function:

          <list>
            <t>(alpha/2 * (2-beta)/beta * 1/p)^0.5 (Eq. 3)</t>
          </list>
        </t>

        <t>By the same analysis, the average window size of Standard TCP
        with alpha 1 and beta 0.5 is (3/2 *1/p)^0.5. Thus, for Eq. 3 to be
        the same as that of Standard TCP, alpha must be equal to
        3*beta/(2-beta). As Standard TCP increases its window by alpha per
        RTT, we can get the window size of Standard TCP in terms of the
        elapsed time t as follows:

          <list>
            <t>W_tcp(t) = W_max*(1-beta) + 3*beta/(2-beta)* t/RTT (Eq. 4)</t>
          </list>
        </t>

        <t>If cwnd is less than W_tcp(t), then the protocol is in the TCP
        friendly region and cwnd SHOULD be set to W_tcp(t) at each
        reception of ACK.</t>

      </section>

      <!-- Subsection: Concave region -->
      <section title="Concave region">

        <t>When receiving an ACK in congestion avoidance, if the protocol
        is not in the TCP-friendly region and cwnd is less than W_max,
        then the protocol is in the concave region. In this region, cwnd
        MUST be incremented by (W(t+RTT) - cwnd)/cwnd.</t>

      </section>

      <!-- Subsection: Convex region -->
      <section title="Convex region">

        <t>When the window size of CUBIC is larger than W_max, it passes
        the plateau of the cubic function after which CUBIC follows the
        convex profile of the cubic function. Since cwnd is larger than
        the previous saturation point W_max, this indicates that the
        network conditions might have been perturbed since the last loss
        event, possibly implying more available bandwidth after some flow
        departures. Since the Internet is highly asynchronous, some amount
        of perturbation is always possible without causing a major change
        in available bandwidth. In this phase, CUBIC is being very careful
        by very slowly increasing its window size. The convex profile
        ensures that the window increases very slowly at the beginning and
        gradually increases its growth rate. We also call this phase as
        the maximum probing phase since CUBIC is searching for a new
        W_max. In this region, cwnd MUST be incremented by (W(t+RTT) -
        cwnd)/cwnd for each received ACK.</t>

      </section>

      <!-- Subsection: Multiplicative decrease -->
      <section title="Multiplicative decrease">

        <t>When a packet loss occurs, CUBIC reduces its window size by a
        factor of beta. Parameter beta SHOULD be set to 0.2<!--{{FIX}}-->.

          <figure>
            <artwork>
    W_max = cwnd;             // save window size before reduction
    cwnd = cwnd * (1-beta);   // window reduction
            </artwork>
          </figure>

        A side effect of setting beta to a smaller value than 0.5 is
        slower convergence. We believe that while a more adaptive setting
        of beta could result in faster convergence, it will make the
        analysis of the protocol much harder. This adaptive adjustment of
        beta is an item for the next version of CUBIC.</t>

      </section>

      <!-- Subsection: Fast convergence -->
      <section title="Fast convergence">

        <t>To improve the convergence speed of CUBIC, we add a heuristic
        in the protocol. When a new flow joins the network, existing flows
        in the network need to give up their bandwidth shares to allow the
        flow some room for growth if the existing flows have been using
        all the bandwidth of the network. To increase this release of
        bandwidth by existing flows, the following mechanism called fast
        convergence SHOULD be implemented.</t>

        <t>With fast convergence, when a loss event occurs, before a
        window reduction of congestion window, a flow remembers the last
        value of W_max before it updates W_max for the current loss event.
        Let us call the last value of W_max to be W_last_max.

          <figure >
            <artwork>
   if (W_max < W_last_max){        // check downward trend
       W_last_max = W_max;         // remember the last W_max
       W_max = W_max*(2-beta)/2;   // further reduce W_max
   } else {                        // check upward trend
       W_last_max = W_max          // remember the last W_max
   }
            </artwork>
          </figure>

        This allows W_max to be slightly less than the original W_max.
        Since flows spend most of time around their W_max, flows with
        larger bandwidth shares tend to spend more time around the
        plateau allowing more time for flows with smaller shares to
        increase their windows.</t>

      </section>

    </section>

    <!-- Section: Discussion -->
    <section title="Discussion">

      <t>With a deterministic loss model where the number of packets
      between two successive lost events is always 1/p, CUBIC always
      operates with the concave window profile which greatly simplifies
      the performance analysis of CUBIC.  The average window size of CUBIC
      can be obtained by the following function:

        <list>
          <t>(C*(4-beta)/4/beta)^0.25 * RTT^0.75 / p^0.75 (Eq. 5)</t>
        </list>

      With beta set to 0.2, the above formula is reduced to:

        <list>
          <t>(C*3.8/0.8)^0.25 * RTT^0.75 / p^0.75 (Eq. 6)</t>
        </list>

      We will determine the value of C in the following subsection
      using Eq. 6.</t>

      <!-- Subsection: Fairness to standard TCP -->
      <section title="Fairness to standard TCP">

        <t>In environments where standard TCP is able to make reasonable
        use of the available bandwidth, CUBIC does not significantly
        change this state.</t>

        <t>Standard TCP performs well in the following two types of
        networks:
          <list style='hanging'>
            <t>1. networks with a small bandwidth-delay product
            (BDP)</t>
            <t>2. networks with a short RTT, but not necessarily a
            small BDP</t>
          </list>
        </t>

        <t>CUBIC is designed to behave very similarly to standard TCP
        in the above two types of networks. The following two tables
        show the average window size of standard TCP, HSTCP, and CUBIC.
        The average window size of standard TCP and HSTCP is from
        <xref target="RFC3649"/>. The average window size of CUBIC is
        calculated by using Eq. 6 and CUBIC TCP friendly mode for three
        different values of C.</t>

        <texttable anchor='table1'>
          <ttcol align='right'>Loss Rate P</ttcol>
          <ttcol align='right'>TCP</ttcol>
          <ttcol align='right'>HSTCP</ttcol>
          <ttcol align='right'>CUBIC (C=0.04)</ttcol>
          <ttcol align='right'>CUBIC (C=0.4)</ttcol>
          <ttcol align='right'>CUBIC (C=4)</ttcol>

          <c>10^-2</c><c>12</c><c>12</c><c>12</c><c>12</c><c>12</c>
          <c>10^-3</c><c>38</c><c>38</c><c>38</c><c>38</c><c>66</c>
          <c>10^-4</c><c>120</c><c>263</c><c>120</c><c>209</c><c>371</c>
          <c>10^-5</c><c>379</c><c>1795</c><c>660</c><c>1174</c><c>2087</c>
          <c>10^-6</c><c>1200</c><c>12279</c><c>3713</c><c>6602</c><c>11740</c>
          <c>10^-7</c><c>3795</c><c>83981</c><c>20878</c><c>37126</c><c>66022</c>
          <c>10^-8</c><c>12000</c><c>574356</c><c>117405</c><c>208780</c><c>371269</c>

          <postamble>Response function of standard TCP, HSTCP, and CUBIC
          in networks with RTT = 100ms. The average window size W is
          in MSS-sized segments.</postamble>
        </texttable>

        <texttable anchor='table2'>
          <ttcol align='right'>Loss Rate P</ttcol>
          <ttcol align='right'>Average TCP W</ttcol>
          <ttcol align='right'>Average HSTCP W</ttcol>
          <ttcol align='right'>CUBIC (C=0.04)</ttcol>
          <ttcol align='right'>CUBIC (C=0.4)</ttcol>
          <ttcol align='right'>CUBIC (C=4)</ttcol>

          <c>10^-2</c><c>12</c><c>12</c><c>12</c><c>12</c><c>12</c>
          <c>10^-3</c><c>38</c><c>38</c><c>38</c><c>38</c><c>38</c>
          <c>10^-4</c><c>120</c><c>263</c><c>120</c><c>120</c><c>120</c>
          <c>10^-5</c><c>379</c><c>1795</c><c>379</c><c>379</c><c>379</c>
          <c>10^-6</c><c>1200</c><c>12279</c><c>1200</c><c>1200</c><c>2087</c>
          <c>10^-7</c><c>3795</c><c>83981</c><c>3795</c><c>6603</c><c>11740</c>
          <c>10^-8</c><c>12000</c><c>574356</c><c>20878</c><c>37126</c><c>66022</c>

          <postamble>Response function of standard TCP, HSTCP, and CUBIC
          in networks with RTT = 10ms. The average window size W is in
          MSS-sized segments.</postamble>
        </texttable>

        <t>Both tables show that CUBIC with any of these three C values
        is more friendly to TCP than HSTCP, especially in networks with
        a short RTT where TCP performs reasonably well. For example,
        in a network with RTT = 10ms and p=10^-6, TCP has an average
        window of 1200 packets. If the packet size is 1500 bytes, then
        TCP can achieve an average rate of 1.44 Gbps. In this case,
        CUBIC with C=0.04 or C=0.4 achieves exactly the same rate as
        Standard TCP, whereas HSTCP is about ten times more aggressive
        than Standard TCP.</t>

        <t>We can see that C determines the aggressiveness of CUBIC in
        competing with other protocols for the bandwidth. CUBIC is
        more friendly to the Standard TCP, if the value of C is lower.
        However, we do not recommend to set C to a very low value like
        0.04, since CUBIC with a low C cannot efficiently use the
        bandwidth in long RTT and high bandwidth networks. Based on
        these observations, we find C=0.4 gives a good balance between
        TCP-friendliness and aggressiveness of window growth.
        Therefore, C SHOULD be set to 0.4. With C set to 0.4, Eq. 6 is
        reduced to:

        <list>
          <t>1.17 * RTT^0.75 / p^0.75 (Eq. 7)</t>
        </list>

        Eq. 7 is then used in the next subsection to show the
        scalability of CUBIC.</t>
      </section>

      <!-- Subsection: Using Spare Capacity -->
      <section title="Using Spare Capacity">

        <t>CUBIC uses a more aggressive window growth function than
        Standard TCP under long RTT and high bandwidth networks.</t>

        <t>The following table shows that to achieve 10Gbps rate, standard
        TCP requires a packet loss rate of 2.0e-10, while CUBIC requires a
        packet loss rate of 3.4e-8.</t>

        <texttable anchor='table3'>
          <ttcol align='right'>Throughput(Mbps)</ttcol>
          <ttcol align='right'>Average W</ttcol>
          <ttcol align='left'>TCP P</ttcol>
          <ttcol align='left'>HSTCP P</ttcol>
          <ttcol align='left'>CUBIC P</ttcol>

          <c>1</c><c>8.3</c><c>2.0e-2</c><c>2.0e-2</c><c>2.0e-2</c>
          <c>10</c><c>83.3</c><c>2.0e-4</c><c>3.9e-4</c><c>3.3e-4</c>
          <c>100</c><c>833.3</c><c>2.0e-6</c><c>2.5e-5</c><c>1.6e-5</c>
          <c>1000</c><c>8333.3</c><c>2.0e-8</c><c>1.5e-6</c><c>7.3e-7</c>
          <c>10000</c><c>83333.3</c><c>2.0e-10</c><c>1.0e-7</c><c>3.4e-8</c>

          <postamble>Required packet loss rate for Standard TCP, HSTCP,
          and CUBIC to achieve a certain throughput. We use 1500-byte
          packets and an RTT of 0.1 seconds.</postamble>

        </texttable>

        <t>Our test results in <xref target="HKLRX06"/> indicate that
        CUBIC uses the spare bandwidth left unused by existing Standard
        TCP flows in the same bottleneck link without taking away much
        bandwidth from the existing flows.</t>

      </section>

      <!-- Subsection: Difficult Environments -->
      <section title="Difficult Environments">

        <t>CUBIC is designed to remedy the poor performance of TCP in fast
        long-distance networks. It is not designed for wireless
        networks.</t>

      </section>

      <!-- Subsection: Investigating a Range of Environment -->
      <section title="Investigating a Range of Environments">

        <t>CUBIC has been extensively studied by using both NS-2
        simulation and test-bed experiments covering a wide range of
        network environments. More information can be found in <xref
        target="HKLRX06"/>.</t>

      </section>

      <!-- Subsection: Protection against Congestion Collapse -->
      <section title="Protection against Congestion Collapse">

        <t>In case that there is congestion collapse, CUBIC behaves likely
        standard TCP since CUBIC modifies only the window adjustment
        algorithm of TCP. Thus, it does not modify the ACK clocking and
        Timeout behaviors of Standard TCP.</t>

      </section>

      <!-- Subsection: Fairness within the Alternative Congestion Control Algorithm -->
      <section title="Fairness within the Alternative Congestion Control Algorithm.">

        <t>CUBIC ensures convergence of competing CUBIC flows with the
        same RTT in the same bottleneck links to an equal bandwidth share.
        When competing flows have different RTTs, their bandwidth shares
        are linearly proportional to the inverse of their RTT ratios. This
        is true independent of the level of statistical multiplexing in
        the link.</t>

      </section>

      <!-- Subsection: Performance with Misbehaving Nodes and Outside Attackers -->
      <section title="Performance with Misbehaving Nodes and Outside Attackers">

        <t>This is not considered in the current CUBIC.</t>

      </section>

      <!-- Subsection: Responses to Sudden or Transient Events -->
      <section title="Responses to Sudden or Transient Events">

        <t>In case that there is a sudden congestion, a routing change, or
        a mobility event, CUBIC behaves the same as Standard TCP.</t>

      </section>

      <!-- Subsection: Incremental Deployment -->
      <section title="Incremental Deployment">

        <t>CUBIC requires only the change of TCP senders, and does not
        require any assistant of routers.</t>

      </section>

    </section>

    <!-- Section: Security Considerations -->
    <section title="Security Considerations">

      <t>This proposal makes no changes to the underlying security of TCP.</t>

    </section>

    <!-- Section: IANA Considerations -->
    <section title="IANA Considerations">

      <t>There are no IANA considerations regarding this document.</t>

    </section>

    <section title='Acknowledgements'>
      <t>
                 Alexander Zimmermann and Lars Eggert have received funding from
 the European Union's Horizon 2020 research and innovation program 2014-2018
 under grant agreement No. 644866 (SSICLOPS). This document reflects only the
 authors' views and the European Commission is not responsible for any use that
 may be made of the information it contains.
      </t>
    </section>

  </middle>

  <!-- BACK MATTER -->
  <back>

    <!-- Normative References -->
    <references title='Normative References'>
      &RFC2018;
      &RFC2119;
      &RFC5681;
      &RFC5348;
      &RFC3649;
      &RFC6582;
      &RFC4960;
      &RFC5033;
    </references>

    <!-- Informative References -->
    <references title='Informative References'>
      <reference anchor='FHP00'>
        <front>
          <title>A Comparison of Equation-Based and AIMD Congestion Control</title>
          <author initials='S.' surname='Floyd' fullname=''></author>
          <author initials='M.' surname='Handley' fullname=''></author>
          <author initials='J.' surname='Padhye' fullname=''></author>
          <date month='May' year='2000' />
        </front>
        <format type="URL" octets="" target="http://www.icir.org/tfrc/"/>
      </reference>

      <reference anchor='GV02'>
        <front>
          <title>Extended Analysis of Binary Adjustment Algorithms</title>
          <author initials='S.' surname='Gorinsky' fullname=''></author>
          <author initials='H.' surname='Vin' fullname=''></author>
          <date month='August' year='2002' />
        </front>
        <seriesInfo name="Technical Report" value="TR2002-29"/>
        <seriesInfo name="Department of Computer Sciences" value=""/>
        <seriesInfo name="The University of Texas at Austin" value=""/>
        <format type="HTML" octets="" target="http://www.cs.utexas.edu/users/gorinsky/pubs.html"/>
      </reference>

      <reference anchor='K03'>
        <front>
          <title>Scalable TCP: Improving Performance in HighSpeed Wide
          Area Networks</title>
          <author initials='T.' surname='Kelly' fullname=''></author>
          <date month='April' year='2003' />
        </front>
        <seriesInfo name="ACM SIGCOMM Computer Communication Review" value=""/>
      </reference>

      <reference anchor='XHR04'>
        <front>
          <title>Binary Increase Congestion Control for Fast, Long
          Distance Networks</title>
          <author initials='L.' surname='Xu' fullname=''></author>
          <author initials='K.' surname='Harfoush' fullname=''></author>
          <author initials='I.' surname='Rhee' fullname=''></author>
          <date month='March' year='2004' />
        </front>
        <seriesInfo name="In Proceedings of IEEE INFOCOM" value=""/>
      </reference>

      <reference anchor='LS08'>
        <front>
          <title>H-TCP: TCP Congestion Control for High
          Bandwidth-Delay Product Paths</title>
          <author initials='D.' surname='Leith' fullname=''></author>
          <author initials='R.' surname='Shorten' fullname=''></author>
          <date month='April' year='2008' />
        </front>
        <seriesInfo name="Internet-draft draft-leith-tcp-htcp-06" value=""/>
      </reference>

      <reference anchor='HKLRX06'>
        <front>
          <title>A Step toward Realistic Performance Evaluation of
          High-Speed TCP Variants</title>
          <author initials='S.' surname='Ha' fullname=''></author>
          <author initials='Y.' surname='Kim' fullname=''></author>
          <author initials='L.' surname='Le' fullname=''></author>
          <author initials='I.' surname='Rhee' fullname=''></author>
          <author initials='L.' surname='Xu' fullname=''></author>
          <date month='February' year='2006' />
        </front>
        <seriesInfo name="International Workshop on Protocols for Fast
        Long-Distance Networks" value=""/>
      </reference>

      <reference anchor='HRX08'>
        <front>
          <title>CUBIC: A New TCP-Friendly High-Speed TCP Variant</title>
          <author initials='S.' surname='Ha' fullname=''></author>
          <author initials='I.' surname='Rhee' fullname=''></author>
          <author initials='L.' surname='Xu' fullname=''></author>
          <date month='' year='2008' />
        </front>
        <seriesInfo name="ACM SIGOPS Operating System Review" value=""/>
      </reference>

      <reference anchor='CEHRX07'>
        <front>
          <title>Stochastic Ordering for Internet Congestion Control
          and its Applications</title>
          <author initials='H.' surname='Cai' fullname=''></author>
          <author initials='D.' surname='Eun' fullname=''></author>
          <author initials='S.' surname='Ha' fullname=''></author>
          <author initials='I.' surname='Rhee' fullname=''></author>
          <author initials='L.' surname='Xu' fullname=''></author>
          <date month='May' year='2007' />
        </front>
        <seriesInfo name="In Proceedings of IEEE INFOCOM" value=""/>
      </reference>
    </references>
<!--
  <section title="Integer cubic root function">
  from https://gist.github.com/anonymous/729557

    <t><figure anchor="cubic_root" title="Integer cubit_root implementation example" align="left">
      <artwork align="left"><![CDATA[
cubic_root(x) {
  y = 0;
  for (s = 63; s >= 0; s -= 3) {
    y += y;
    b = 3 * y * (y + 1) + 1;
    if ((x >> s) >= b) {
      x -= b << s;
      y += 1;
    }
  }
  return y;
}
]]></artwork></figure>
    </t>
  </section>
-->
  </back>
</rfc>

PAFTECH AB 2003-20262026-04-23 04:49:52