Shared Bottleneck Detection for Coupled Congestion Control for RTP Media.
draft-hayes-rmcat-sbd-00

RTP Media Congestion Avoidance                             D. Hayes, Ed.
Techniques                                            University of Oslo
Internet-Draft                                                 S. Ferlin
Intended status: Experimental                 Simula Research Laboratory
Expires: April 13, 2015                                         M. Welzl
                                                      University of Oslo
                                                        October 10, 2014

   Shared Bottleneck Detection for Coupled Congestion Control for RTP
                                 Media.
                        draft-hayes-rmcat-sbd-00

Abstract

   This document describes a mechanism to detect whether end-to-end data
   flows share a common bottleneck.  It relies on summary statistics
   that are calculated by a data receiver based on continuous
   measurements and regularly fed to a grouping algorithm that runs
   wherever the knowledge is needed.  This mechanism complements the
   coupled congestion control mechanism in draft-welzl-rmcat-coupled-cc.

Status of this Memo

   This Internet-Draft is submitted in full conformance with the
   provisions of BCP 78 and BCP 79.

   Internet-Drafts are working documents of the Internet Engineering
   Task Force (IETF).  Note that other groups may also distribute
   working documents as Internet-Drafts.  The list of current Internet-
   Drafts is at http://datatracker.ietf.org/drafts/current/.

   Internet-Drafts are draft documents valid for a maximum of six months
   and may be updated, replaced, or obsoleted by other documents at any
   time.  It is inappropriate to use Internet-Drafts as reference
   material or to cite them other than as "work in progress."

   This Internet-Draft will expire on April 13, 2015.

Copyright Notice

   Copyright (c) 2014 IETF Trust and the persons identified as the
   document authors.  All rights reserved.

   This document is subject to BCP 78 and the IETF Trust's Legal
   Provisions Relating to IETF Documents
   (http://trustee.ietf.org/license-info) in effect on the date of
   publication of this document.  Please review these documents

Hayes, et al.            Expires April 13, 2015                 [Page 1]
Internet-Draft         SBD for CCC with RTP Media           October 2014

   carefully, as they describe your rights and restrictions with respect
   to this document.  Code Components extracted from this document must
   include Simplified BSD License text as described in Section 4.e of
   the Trust Legal Provisions and are provided without warranty as
   described in the Simplified BSD License.

Table of Contents

   1.  Introduction . . . . . . . . . . . . . . . . . . . . . . . . .  3
     1.1.  The signals  . . . . . . . . . . . . . . . . . . . . . . .  3
       1.1.1.  Packet Loss  . . . . . . . . . . . . . . . . . . . . .  3
       1.1.2.  Packet Delay . . . . . . . . . . . . . . . . . . . . .  3
       1.1.3.  Path Lag . . . . . . . . . . . . . . . . . . . . . . .  4
   2.  Definitions  . . . . . . . . . . . . . . . . . . . . . . . . .  4
     2.1.  Parameter Values . . . . . . . . . . . . . . . . . . . . .  5
   3.  Mechanism  . . . . . . . . . . . . . . . . . . . . . . . . . .  5
     3.1.  Key metrics and their calculation  . . . . . . . . . . . .  6
       3.1.1.  Mean delay . . . . . . . . . . . . . . . . . . . . . .  6
       3.1.2.  Skewness Estimate  . . . . . . . . . . . . . . . . . .  7
       3.1.3.  Variance Estimate  . . . . . . . . . . . . . . . . . .  7
       3.1.4.  Oscilation Estimate  . . . . . . . . . . . . . . . . .  8
       3.1.5.  Packet loss  . . . . . . . . . . . . . . . . . . . . .  8
     3.2.  Flow Grouping  . . . . . . . . . . . . . . . . . . . . . .  8
       3.2.1.  Flow Grouping Algorithm  . . . . . . . . . . . . . . .  8
       3.2.2.  Using the flow group signal  . . . . . . . . . . . . .  9
   4.  Measuring OWD  . . . . . . . . . . . . . . . . . . . . . . . . 10
     4.1.  Time stamp resolution  . . . . . . . . . . . . . . . . . . 10
   5.  Acknowledgements . . . . . . . . . . . . . . . . . . . . . . . 10
   6.  IANA Considerations  . . . . . . . . . . . . . . . . . . . . . 10
   7.  Security Considerations  . . . . . . . . . . . . . . . . . . . 10
   8.  References . . . . . . . . . . . . . . . . . . . . . . . . . . 11
     8.1.  Normative References . . . . . . . . . . . . . . . . . . . 11
     8.2.  Informative References . . . . . . . . . . . . . . . . . . 11
   Authors' Addresses . . . . . . . . . . . . . . . . . . . . . . . . 12

Hayes, et al.            Expires April 13, 2015                 [Page 2]
Internet-Draft         SBD for CCC with RTP Media           October 2014

1.  Introduction

   In the Internet, it is not normally known if flows (e.g., TCP
   connections or UDP data streams) traverse the same bottlenecks.  Even
   flows that have the same sender and receiver may take different paths
   and share a bottleneck or not.  Flows that share a bottleneck link
   usually compete with one another for their share of the capacity.
   This competition has the potential to increase packet loss and
   delays.  This is especially relevant for interactive applications
   that communicate simultaneously with multiple peers (such as multi-
   party video).  For RTP media applications such as RTCWEB,
   [I-D.welzl-rmcat-coupled-cc] describes a scheme that combines the
   congestion controllers of flows in order to honor their priorities
   and avoid unnecessary packet loss as well as delay.  This mechanism
   relies on some form of Shared Bottleneck Detection (SBD); here, a
   measurement-based SBD approach is described.

1.1.  The signals

   The current Internet is unable to explicitly inform endpoints as to
   which flows share bottlenecks, so endpoints need to infer this from
   packet loss and packet delay.

1.1.1.  Packet Loss

   Packet loss is often a relatively rare signal.  Therefore, on its own
   it is of limited use for SBD, however, it is a valuable supplementary
   measure when it is more prevalent.

1.1.2.  Packet Delay

   End-to-end delay measurements include noise from every device along
   the path in addition to the delay perturbation at the bottleneck
   device.  The noise is often significantly increased if the round-trip
   time is used.  The cleanest signal is obtained by using One-Way-Delay
   (OWD).

   Measuring absolute OWD is difficult since it requires both the sender
   and receiver clocks to be synchronised.  However, since the
   statistics being collected are relative to the mean OWD, a relative
   OWD measurement is sufficient.  Clock drift is not usually
   significant over the time intervals used by this SBD mechanism (see
   [RFC6817] A.2 for a discussion on clock drift and OWD measurements).

   Each packet arriving at the bottleneck buffer may experience very
   different queue lengths, and therefore waiting times.  A single OWD
   sample does therefore not characterize the actual OWD of a path well.
   However, multiple OWD measurements do reflect the distribution of

Hayes, et al.            Expires April 13, 2015                 [Page 3]
Internet-Draft         SBD for CCC with RTP Media           October 2014

   delays experienced at the bottleneck.

1.1.3.  Path Lag

   Flows that share a common bottleneck may traverse different paths,
   and these paths will often have different base delays.  This makes it
   difficult to correlate changes in delay or loss.  This technique uses
   the long term shape of the delay distribution as a base for
   comparison to counter this.

2.  Definitions

   The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT",
   "SHOULD", "SHOULD NOT", "RECOMMENDED", "MAY", and "OPTIONAL" in this
   document are to be interpreted as described in RFC 2119 [RFC2119].

   Acronyms used in this document:

      OWD -- One Way Delay

      RTT -- Round Trip Time

      SBD -- Shared Bottleneck Detection

   Conventions used in this document:

      T     --     the base time interval over which measurements are
                   made.

      N     --     the number of base time, T, intervals used in some
                   calculations.

      sum_T(...) --  summation of all the measurements of the variable
                   in parentheses taken over the interval T

      sum_N(...) --  summation of N terms of the variable in parentheses

      sum_NT(...) --  summation of all measurements taken over the
                   interval N*T

      E_T(...) --  the expectation or mean of the measurements of the
                   variable in parentheses over T

      E_N(...) --  The expectation or mean of the last N values of the
                   variable in parentheses

Hayes, et al.            Expires April 13, 2015                 [Page 4]
Internet-Draft         SBD for CCC with RTP Media           October 2014

      max_T(...) --  the maximum recorded measurement of the variable in
                   parentheses taken over the interval T

      p_l, p_f, p_pdf, p_s, p_d, p_v --  various thresholds used in the
                   mechanism.

2.1.  Parameter Values

   Reference [Hayes-LCN14] uses T=350ms, N=50, p_l = 0.1, p_f = 0.2,
   p_pdf = 0.3, p_s = p_d = p_v = 0.2.  These are values that seem to
   work well over a wide range of practical Internet conditions.

3.  Mechanism

   The mechanism described in this document is based on the observation
   that the delay measurements of flows that share a common bottleneck
   have similar shape characteristics.  The shape of these
   characteristics are described using 3 key summary statistics:

      variance (estimate PDV, see Section 3.1.3)

      skewness (estimate skewest, see Section 3.1.2)

      oscillation (estimate freqest, see Section 3.1.4)

   Summary statistics help to address both the noise and the path lag
   problems by describing the general shape over a relatively long
   period of time.  This is sufficient for their application in coupled
   congestion control for RTP Media.  They can be signalled from a
   receiver, which measures the OWD and calculates the summary
   statistics, to a sender, which is the entity that is transmitting the
   media stream.  An RTP Media device may be both a sender and a
   receiver.  SBD can be performed at both the Sender and the Receiver.

                                  +----+
                                  | H2 |
                                  +----+
                                     |
                                     | L2
                                     |
                         +----+  L1  |  L3  +----+
                         | H1 |------|------| H3 |
                         +----+             +----+

       A network with 3 hosts (H1, H2, H3) and 3 links (L1, L2, L3).

                                 Figure 1

Hayes, et al.            Expires April 13, 2015                 [Page 5]
Internet-Draft         SBD for CCC with RTP Media           October 2014

   In Figure 1, there are two possible cases for shared bottleneck
   detection: a sender-based and a receiver-based case.

   1.  Sender-based: consider a situation where host H1 sends media
       streams to hosts H2 and H3, and L1 is a shared bottleneck.  H2
       and H3 measure the OWD and calculate summary statistics, which
       they send to H1 every T. H1, having this knowledge, can determine
       the shared bottleneck and accordingly control the send rates.

   2.  Receiver-based: consider that H2 is also sending media to H3, and
       L3 is a shared bottleneck.  If H3 sends summary statistics to H1
       and H2, neither H1 nor H2 alone obtain enough knowledge to detect
       this shared bottleneck; H3 can however determine it by combining
       the summary statistics related to H1 and H2, respectively.  This
       case is applicable when send rates are controlled by the
       receiver; then, the signal from H3 to the senders contains the
       sending rate.

   A discussion of the required signaling for the receiver-based case is
   beyond the scope of this document.  For the sender-based case, the
   messages and their data format will be defined here in future
   versions of this document.  We envision that an initialization
   message from the sender to the receiver could specify which key
   metrics are requested out of a possibly extensible set (losscnt, PDV,
   skewest, freqest).  The grouping algorithm described in this document
   requires all four of these metrics, and receivers MUST be able to
   provide them, but future algorithms may be able to exploit other
   metrics (e.g. metrics based on explicit network signals).  Moreover,
   the initialization message could specify T, N, and the necessary
   resolution and precision (number of bits per field).

3.1.  Key metrics and their calculation

   Measurements are calculated over a base interval, T. T should be long
   enough to provide enough samples for a good estimate of skewness, but
   short enough so that a measure of the oscillation can be made from N
   of these estimates.  Reference [Hayes-LCN14] uses T = 350ms and N =
   50, which are values that seem to work well over a wide range of
   practical Internet conditions.

3.1.1.  Mean delay

   The mean delay is not a useful signal for comparisons, however, it is
   a base measure for the 3 summary statistics.  The mean delay,
   E_T(OWD), is the average one way delay measured over T.

Hayes, et al.            Expires April 13, 2015                 [Page 6]
Internet-Draft         SBD for CCC with RTP Media           October 2014

   To facilitate the other calculations, the last N E_T(OWD) values will
   need to be stored in a cyclic buffer along with the moving average of
   E_T(OWD):

      E_N(E_T(OWD)) = sum_N(E_T(OWD)) / N

3.1.2.  Skewness Estimate

   Skewness is difficult to calculate efficiently and accurately.
   Ideally it should be calculated over the entire measurement for the
   entire period (N * T), however this would require storing every delay
   measurement over the period.  Instead, an estimate is made over T
   using the previous calculation of E_T(OWD).  Comparisons are made
   using the mean of N skew estimates.

   The skewness is estimated using two counters, counting the number of
   one way delay samples above and below the mean:

      skewest = (sum_T(OWD < E_T(OWD)) - sum_T(OWD > E_T(OWD)))/num(OWD)

         where

            if (OWD < E_T(OWD)) 1 else 0

            if (OWD > E_T(OWD)) 1 else 0

         skewest is a number between -1 and 1

      E_N(skewest) = sum_N(skewest) /N

   For implementation ease, E_T(OWD) is the mean delay of the previous T
   interval.  Care must be taken when implementing the comparisons to
   ensure that rounding does not bias skewest.

3.1.3.  Variance Estimate

   Packet Delay Variation (PDV) ([RFC5481] and [ITU-Y1540] is used as an
   estimator of the variance of the delay signal.  We define PDV as
   follows:

      PDV = (max(OWD) - E_T(OWD))

      E_N(PDV) = sum_N(PDV) /N

   This modifies PDV as outlined in [RFC5481] to provide a summary
   statistic version that best aids the grouping decisions of the
   algorithm (see [Hayes-LCN14] section IVB).

Hayes, et al.            Expires April 13, 2015                 [Page 7]
Internet-Draft         SBD for CCC with RTP Media           October 2014

3.1.4.  Oscilation Estimate

   An estimate of the low frequency oscillation of the delay signal is
   calculated by counting and normalising the significant mean,
   E_T(OWD), crossings of E_N(E_T(OWD)):

      freqest = number_of_crossings / N

      Where

         we define a significant mean crossing as a crossing that
         extends p_v * E_N(PDV) from E_N(E_T(OWD)).  In our experiments
         we have found that p_v = 0.2 is a good value.

   Freqest is a number between 0 and 1.  Freqest and can be approximated
   incrementally as follows:

      With each new calculation of E_T(OWD) a decision is made as to
      whether this value of E_T(OWD) significantly crosses the current
      long term mean, E_N(E_T(OWD), with respect to the previous
      significant mean crossing.

      A cyclic buffer, last_N_crossings, records a 1 if there is a
      significant mean crossing, otherwise a 0.

      The counter, number_of_crossings, is incremented when there is a
      significant mean crossing and subtracted from when a non zero
      value is removed from the last_N_crossings.

   This approximation of freqest was not used in [Hayes-LCN14], which
   calculated freqest every T using the current E_N(E_T(OWD)).  Our
   tests show that this approximation of freqest yields results that are
   almost identical to when the full calculation is performed every T.

3.1.5.  Packet loss

   The proportion of packets lost is used as a supplementary measure:

      PL_NT = sum_NT(lost packets) / sum_NT(total packets)

3.2.  Flow Grouping

3.2.1.  Flow Grouping Algorithm

   The following grouping algorithm is RECOMMENDED for SBD in this
   context and is sufficient and efficient for small to moderate numbers
   of flows.  For very large numbers of flows, hundreds, a more complex
   clustering algorithm may be substituted.

Hayes, et al.            Expires April 13, 2015                 [Page 8]
Internet-Draft         SBD for CCC with RTP Media           October 2014

   Flows determined to be experiencing congestion are successively
   divided into groups based on freqest, PDV, and skewest.

   The first step is to determine which flows are experiencing
   congestion.  This is important, since if a flow is not experiencing
   congestion its delay based metrics will not describe the bottleneck,
   but the "noise" from the rest of the path.  Skewness, with proportion
   of packets loss as a supplementary measure, is used to do this:

   1.  Grouping will be performed on flows where:

          E_N(skewest) < 0 || PL_NT > p_l.

   These flows, flows experiencing congestion, are then progressively
   divided into groups based on the freqest, PDV, and skewest summary
   statistics.  The process proceeds according to the following steps:

   2.  Group flows whose difference in sorted freqest is less than a
       threshold:

          diff(freqest) < p_f

   3.  Group flows whose difference in sorted E_N(PDV) is less than a
       threshold:

          diff(E_N(PDV)) < (p_pdv * E_N(PDV))

   4.  Group flows whose difference in sorted E_N(skewest) or PL_NT is
       less than a threshold:

          if PL_NT < p_l

             diff(E_N(skewness)) < p_s

          otherwise

             diff(PL_NT) < p_d

   This procedure involves sorting the groups, according to the measure
   being used to divide them.  It is simple to implement, and efficient
   for small numbers of flows, such as are expected in RTCWEB.

3.2.2.  Using the flow group signal

   A grouping decisions is made every T. Network conditions can cause
   bottlenecks to fluctuate.  A coupled congestion controller MAY decide
   only to couple groups that remain stable, say grouped together 90% of
   the time, depending on its objectives.  Recommendations concerning

Hayes, et al.            Expires April 13, 2015                 [Page 9]
Internet-Draft         SBD for CCC with RTP Media           October 2014

   this are beyond the scope of this draft and will be specific to the
   coupled congestion controllers objectives.

4.  Measuring OWD

   This section discusses the OWD measurements required for this
   algorithm to detect shared bottlenecks.

   The SBD mechanism described in this draft relies on differences
   between OWD measurements to avoid the practical problems with
   measuring absolute OWD (see [Hayes-LCN14] section IIIC).  Since all
   summary statistics are relative to the mean OWD and sender/receiver
   clock offsets are approximately constant over the measurement
   periods, the offset is subtracted out in the calculation.

4.1.  Time stamp resolution

   The SBD mechanism requires timing information precise enough to be
   able to make comparisons.  As a rule of thumb, the time resolution
   should be less than one hundredth of a typical paths range of delays.
   In general, the lower the time resolution, the more care that needs
   to be taken to ensure rounding errors don't bias the skewness
   calculation.

   Typical RTP media flows use sub-millisecond timers, which should be
   adequate in most situations.

5.  Acknowledgements

   This work was part-funded by the European Community under its Seventh
   Framework Programme through the Reducing Internet Transport Latency
   (RITE) project (ICT-317700).  The views expressed are solely those of
   the authors.

6.  IANA Considerations

   This memo includes no request to IANA.

7.  Security Considerations

   The security considerations of RFC 3550 [RFC3550], RFC 4585
   [RFC4585], and RFC 5124 [RFC5124] are expected to apply.

   Non-authenticated RTCP packets carrying shared bottleneck indications

Hayes, et al.            Expires April 13, 2015                [Page 10]
Internet-Draft         SBD for CCC with RTP Media           October 2014

   and summary statistics could attackers to alter the bottleneck
   sharing characteristics for private gain or disruption of other
   parties communication.

8.  References

8.1.  Normative References

   [RFC2119]  Bradner, S., "Key words for use in RFCs to Indicate
              Requirement Levels", BCP 14, RFC 2119, March 1997.

8.2.  Informative References

   [Hayes-LCN14]
              Hayes, D., Ferlin, S., and M. Welzl, "Practical Passive
              Shared Bottleneck Detection using Shape Summary
              Statistics", Proc. the IEEE Local Computer Networks
              (LCN) p150-158, September 2014, <http://heim.ifi.uio.no/
              davihay/
              hayes14__pract_passiv_shared_bottl_detec-abstract.html>.

   [I-D.welzl-rmcat-coupled-cc]
              Welzl, M., Islam, S., and S. Gjessing, "Coupled congestion
              control for RTP media", draft-welzl-rmcat-coupled-cc-03
              (work in progress), May 2014.

   [ITU-Y1540]
              ITU-T, "Internet protocol data communication service - IP
              packet transfer and availability performance parameters",
              Series Y: Global Information Infrastructure, Internet
              Protocol Aspects and Next-Generation Networks ,
              March 2011,
              <http://www.itu.int/rec/T-REC-Y.1540-201103-I/en>.

   [RFC3550]  Schulzrinne, H., Casner, S., Frederick, R., and V.
              Jacobson, "RTP: A Transport Protocol for Real-Time
              Applications", STD 64, RFC 3550, July 2003.

   [RFC4585]  Ott, J., Wenger, S., Sato, N., Burmeister, C., and J. Rey,
              "Extended RTP Profile for Real-time Transport Control
              Protocol (RTCP)-Based Feedback (RTP/AVPF)", RFC 4585,
              July 2006.

   [RFC5124]  Ott, J. and E. Carrara, "Extended Secure RTP Profile for
              Real-time Transport Control Protocol (RTCP)-Based Feedback
              (RTP/SAVPF)", RFC 5124, February 2008.

Hayes, et al.            Expires April 13, 2015                [Page 11]
Internet-Draft         SBD for CCC with RTP Media           October 2014

   [RFC5481]  Morton, A. and B. Claise, "Packet Delay Variation
              Applicability Statement", RFC 5481, March 2009.

   [RFC6817]  Shalunov, S., Hazel, G., Iyengar, J., and M. Kuehlewind,
              "Low Extra Delay Background Transport (LEDBAT)", RFC 6817,
              December 2012.

Authors' Addresses

   David Hayes (editor)
   University of Oslo
   PO Box 1080 Blindern
   Oslo,   N-0316
   Norway

   Phone: +47 2284 5566
   Email: davihay@ifi.uio.no

   Simone Ferlin
   Simula Research Laboratory
   P.O.Box 134
   Lysaker,   1325
   Norway

   Phone: +47 4072 0702
   Email: ferlin@simula.no

   Michael Welzl
   University of Oslo
   PO Box 1080 Blindern
   Oslo,   N-0316
   Norway

   Phone: +47 2285 2420
   Email: michawe@ifi.uio.no

Hayes, et al.            Expires April 13, 2015                [Page 12]