Network Working Group                                      R. Mandeville
Internet-Draft                             European Network Laboratories
Expiration Date: February November 1999                                 J. Keene Perser
                                                          Netcom Systems
                                                             August 1998
                                                                May 1999

           Benchmarking Methodology for LAN Switching Devices
                    <draft-ietf-bmwg-mswitch-00.txt>
                    <draft-ietf-bmwg-mswitch-01.txt>

Status of this Memo

  This document is an Internet-Draft. Internet-Draft and is in full conformance with
  all provisions of Section 10 of RFC2026.

  Internet-Drafts are working documents of the Internet Engineering
  Task Force (IETF),its (IETF), its areas, and its working groups.  Note that
  other groups may also distribute working documents as Internet-Drafts. Internet-
  Drafts.

  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."

   To view the entire

  The list of current Internet-Drafts, please check
   the "1id-abstracts.txt" listing contained in the Internet-Drafts can be accessed at
  http://www.ietf.org/ietf/1id-abstracts.txt

  The list of Internet-Draft Shadow Directories on ftp.is.co.za (Africa), ftp.nordu.net
   (Northern Europe), ftp.nis.garr.it (Southern Europe), munnari.oz.au
   (Pacific Rim), ftp.ietf.org (US East Coast), or ftp.isi.edu
   (US West Coast).

   This memo provides information for the Internet community. This memo
   does not specify an Internet standard can be accessed at
  http://www.ietf.org/shadow.html.

Table of any kind. Distribution Contents

1. Introduction  . . . . . . . . . . . . . . . . . . . . . . . . .  2
2. Requirements  . . . . . . . . . . . . . . . . . . . . . . . . .  2
3. Test setup  . . . . . . . . . . . . . . . . . . . . . . . . . .  2
4. Frame formats and sizes . . . . . . . . . . . . . . . . . . . .  3
5. Benchmarking Tests  . . . . . . . . . . . . . . . . . . . . . .  4
   5.1  Fully meshed throughput, frame loss and forwarding rates  . .  4
   5.2  Partially meshed overloading  . . . . . . . . . . . . . . . .  7
   5.3  Head of
   this memo is unlimited.

Abstract line blocking . . . . . . . . . . . . . . . . . . . . 10
   5.4  Partially meshed multiple devices . . . . . . . . . . . . . . 13
   5.5  Multiple streams of unidirectional traffic  . . . . . . . . . 15
   5.6  Filter illegal frames . . . . . . . . . . . . . . . . . . . . 18
   5.7  Broadcast frame handling and latency  . . . . . . . . . . . . 20
   5.8  Maximum forwarding rate and minimum interframe gap  . . . . . 21
   5.9  Address caching capacity  . . . . . . . . . . . . . . . . . . 23
5.10 Address learning rate . . . . . . . . . . . . . . . . . . . . 26
6. Security Considerations . . . . . . . . . . . . . . . . . . . . 28
7. Authors' Address  . . . . . . . . . . . . . . . . . . . . . . . 28
   Appendix A:  Formulas  . . . . . . . . . . . . . . . . . . . . . . 29

1. Introduction

   This document is intended to provide methodology for the benchmarking
   of local area network (LAN) switching devices.  It extends the
   methodology already defined for benchmarking network interconnecting
   devices in RFC 1944 2544 to switching devices.

   This RFC primarily deals with devices which switch frames at the
   Medium Access Control (MAC) layer. It provides a methodology for
   benchmarking switching devices, forwarding performance, congestion
   control, latency, address handling and filtering. In addition to
   defining the tests, this document also describes specific formats for
   reporting the results of the tests.

1. Introduction
   This document defines a specific set of tests to measure and report
   the performance characteristics of network switching devices.

   A previous document, "Benchmarking Terminology for LAN Switching
   Devices" (RFC 2285), defined many of the terms that are used in this
   document.  The terminology document SHOULD be consulted before
   attempting to make use of this document.

2. Requirements

   The following RFCs SHOULD be consulted before attempting to make use
   of this document:

   * RFC 1242 "Benchmarking Terminology for Network Interconnect
               Devices"

   * RFC 1944 2285 "Benchmarking Methodology Terminology for Network Interconnect LAN Switching Devices"

   * RFC 2285 2544 "Benchmarking Terminology Methodology for LAN Switching Network Interconnect
               Devices"

   For the sake of clarity and continuity, this RFC adopts the template
   for benchmarking tests set out in Section 26 of RFC 1944. 2544.

   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.

3. Test setup

   This document extends the general test setup described in section 6
   of RFC 1944 2544 to the benchmarking of LAN switching devices.  RFC 1944 2544
   primarily describes non-meshed traffic where input and output
   interfaces  are grouped in mutually exclusive sending and receiving
   pairs.  In fully meshed traffic, each interface of a DUT/SUT is set
   up to both receive and transmit frames to all the other interfaces
   under test.

   Prior to each test run, the DUT/SUT MUST learn the MAC addresses used
   in the test and the address learning MUST SHOULD be verified to avoid verified.  Addresses
   not learned will be forwarded as flooded frames being counted as and reduce the amount
   of correctly received forwarded frames.  The forwarding
   rate, namely the rate at which address learning
   frames are offered may have to be adjusted to be as low as 50 frames
   per second or even less, to guarantee successful learning.  The
   DUT/SUT address aging time SHOULD be configured to be greater than
   the period between of the learning phase of the test and plus the test run; in non-meshed and partially meshed tests,
   the aging duration
   plus any configuration time SHOULD at a minimum be set to at least required by the length of testing device.
   Addresses SHOULD NOT age out until the test period. duration is completed.
   More than one learning trial may be needed for the association of the
   address to the port to occur.

   If a DUT/SUT uses a hashing algorithm with address learning, the
   DUT/SUT may not learn the necessary addresses to perform the tests.
   The format of the MAC addresses MUST be adjustable so that the
   address mapping may be re-arranged to make a DUT/SUT learn addresses
   without confusion.

   It is recommended that SNMP and Spanning Tree be disabled when bench-
   marking switching devices unless investigating overhead behavior. If
   such protocols cannot be turned off, it is recommended that the
   levels of offered load be reduced (less than 100%) to allow for
   the additional management frames.

4.  Frame formats and sizes

   For

   The frame formats and sizes, refer to format is defined in RFC 1944, sections 2544 section 8 and 9 and MUST contain a
   unique signature field located in the UDP DATA area of the Test Frame
   (see Appendix C.

   There C of RFC 2544).  The purpose of the signature field is
   filter out frames that are three not part of the offered load.

   The signature field MUST be unique enough to identify the frames not
   originating from the DUT/SUT.  The signature field SHOULD be located
   after byte 56 (ISO/IEC 8802-3 collision window) or at the end of the
   frame.  The length, contents and method of detection is not defined
   in this memo.

   The signature field MAY have a unique identifier per port.  This
   would filter out misforwarded frames.  It is possible for a DUT/SUT
   to strip off the MAC layer, send it through its switching matrix,
   and transmit it out with the correct destination MAC address but the
   wrong payload.

   For frame sizes, refer to RFC 2544, section 9.

   There are three possible frame formats for layer 2 Ethernet switches:
   standard MAC Ethernet frames, standard MAC Ethernet frames
   with vendor-specific tags added to them, and IEEE 802.3ab 802.3ac
   frames tagged to accommodate 802.3p,q. 802.3p&q.  The two types of tagged
   frames may exceed the standard maximum length frame of 1518 bytes,
   and may not be accepted by the interface controllers of some
   DUT/SUTs. It is recommended to check the compatibility of the DUT/SUT
   with tagged frames before testing.

   Devices switching tagged frames of over 1518 bytes will have a lower
   maximum forwarding rate than standard untagged frames.

5. Benchmarking Tests

   The following tests offer objectives, procedures, and reporting
   formats for benchmarking LAN switching devices.

5.1  Fully meshed throughput, frame loss and forwarding rates
     5.2  Partially meshed overloading
     5.3  Head of line blocking
     5.4  Partially meshed multiple devices
     5.5  Multiple streams of unidirectional traffic
     5.6  Filter illegal frames
     5.7  Broadcast frame handling and latency
     5.8  Maximum forwarding rate and minimum interframe gap
     5.9  Address caching capacity
     5.10 Address learning rate

5.1  Fully meshed throughput, frame loss and forwarding rates

Objective:

5.1.1 Objective

   To determine the throughput, frame loss and forwarding rates of
   DUT/SUTs offered fully meshed traffic as defined in RFC 2285.

Procedure:

   RFC 2285 points out that when

5.1.2 Setup Parameters

   When offering bursty full meshed traffic, the
   variables which following parameters
   MUST be defined are frame size, bust size,
   interframe gap, interburst gap, and load. defined.  Each variable parameter is configured with the following
   considerations.

      Frame Size - Recommended frame sizes are 64, 128, 256, 512, 1024,
      1280 and 1518 bytes, per RFC 2544 section 9.  The four CRC bytes
      are included in the frame size specified.

      Interframe Gap (IFG)  - The IFG between frames inside a burst
      MUST be at the minimum specified by the standard (9.6 us for
      10Mbps
      Ethernet and 0.96 us Ethernet, 960 ns for 100Mbps Ethernet, and 96 ns for
      1 Gbps Ethernet).

      Interburst Gap (IBG) - This is the interval between bursts of
      traffic.  Refer to Appendix A, Calculating Interburst Gap, A Formulas, for the formula used to
      compute IBG.

      Duplex mode - Half duplex or full duplex.

      Load / Port - Load per port is expressed in a percentage of the
      medium's maximum intended load possible.  The actual transmitted
      frame per second is dependent upon half duplex or full duplex
      operation.  The test SHOULD be run multiple times with a different
      load per port in each case. The 100% load translates to
      a transmit load of 50% for half duplex. This type of test SHOULD
      also be run at higher than 100% loads.

      In half duplex mode, exactly half of the target intended load SHOULD be
      sent
      transmitted to each of the ports under test. For example, with a
      100% load of 64-byte frames, the target intended load for each port under
      test is 7440 frames received per second and 7440 frames
      transmitted per second (for 10Mbps Ethernet).

      Frame Size - Recommended frame sizes are 64, 128, 256, 512, 1024,
      1280

      In full duplex mode, the entire intended load SHOULD be
      transmitted to each of the ports under test. For example, with a
      100% load of 64-byte frames, the intended load for each port under
      test is 14880 frames received per second and 1518 bytes, 14880 frames
      transmitted per RFC 1944 section 9. second (for 10Mbps Ethernet).

      Burst Size - The burst size defines the number of packets frames sent
      back-to-back at the minimum legal IFG (96 bit times) before
      pausing transmission to receive frames.  Burst sizes
      SHOULD vary between 1 and 930 frames.

      To avoid truncating bursts, a  A burst size of 1 will
      simulate non-bursty traffic.

      Addresses per port - Represents the number of addresses which
      are being tested for each port.  Number of addresses SHOULD be an even
      multiple into 7440. 7440 is the maximum frames per second a
      binary exponential (i.e. 1, 2, 4, 8, 16, 32, 64, 128, 256, ...).
      Recommended values are 1, 16 and 256.

      Test Duration - Test duration SHOULD be between 1 and 300 seconds.
      RFC 2285 recommends a duration of at least 10 seconds for half
      duplex mode; 14880 is each
      test.

5.1.3 Procedure

   All ports MUST transmit the maximum exact number of frames.  All ports SHOULD
   start transmitting their frames per second for full
      duplex mode.  Refer to Appendix A for within 1% of the test duration.  For
   a table test duration of recommended burst
      values. 10 seconds, all ports SHOULD have started
   transmitting frames with 100 milliseconds of each other.

   Each port in the test sends MUST send frames to all other ports in a round-
   round robin type fashion.  The following table shows how each port in
   a test
   SHOULD MUST transmit frames to all other ports in the test.  In this
   example, there are six ports with 1 address per port:

   Source Port, then Port       Destination Ports (in order of transmission)

   Port #1           2       3       4       5       6       2...
   Port #2           3       4       5       6       1       3...
   Port #3           4       5       6       1       2       4...
   Port #4           5       6       1       2       3       5...
   Port #5           6       1       2       3       4       6...
   Port #6           1       2       3       4       5       1...

   As shown in the table, there is an equal distribution of destination
   addresses for each transmit opportunity. This keeps the test balanced
   so that one destination port is not overloaded by the test algorithm
   and all ports are equally and fully loaded throughout the test.  Not
   following this algorithm exactly will produce inconsistent results.

   For tests using multiple addresses per port, the actual port
   destinations are the same as described above and the actual
   source/destination address pairs are SHOULD be chosen randomly to
   exercise the DUT/SUT's ability to perform address lookups.

   For every address, the testing device sends MUST send learning packets frames to
   allow the DUT/SUT to load update its address tables properly.

   To measure the DUT/SUT's ability to switch traffic while performing
many
   different address lookups, the number of addresses per port SHOULD be
   increased in a series of tests.

Reporting format:

   In these tests, a

5.1.4 Measurements

   Each port SHOULD transmit and should receive the same amount number of
   packets. frames that it
   transmitted.  Each receiving port MUST categorize, then count the packets
   frames into one of two groups:

      1.) Received Frames: received with frames MUST have the correct
          destination MAC address and SHOULD match a valid
address. signature field.

      2.) Flood count: defined in RFC 2285 3.8.3.

   Any packet frame received which does not have a valid the correct destination
   address MUST not be counted as a received packet frame and can SHOULD be counted
   as part of a flood
   count as described in 3.8.3 in RFC 2285.

   The results for these tests count.

   Any frame originating from the DUT/SUT MUST not be counted as a
   received frame.  Frames originating from the DUT/SUT MAY be counted
   as flooded frames or not counted at all.

   Frame loss rate of the DUT/SUT SHOULD be reported as defined in
   RFC 2544 section 26.3 with the form following notes: Frame loss rate
   SHOULD be measured at the end of
numerical
   data or a graph with text to indicate the data type. test duration.  The data types term "rate",
   for this measurement only, does not imply the throughput test and for units in the frame loss rate test are described fashion of
   "per seconds."

   Throughput measurement is defined in RFC 1944. 2544.

   Forwarding rate (FR) of the DUT/SUT SHOULD be reported as the number
   of frames per second that the device is observed to successfully
   transmit to the correct destination interface in response to a
   specified offered load. The offered load MUST also be cited.

   Forwarding rate at maximum offered load (FRMOL ) SHOULD (FRMOL) MUST be reported
   as the number of frames per second that a device can successfully
   transmit to the correct destination interface in response to the
   maximum offered load as defined in RFC 2285, section 3.6. The
   maximum offered load MUST also be cited.

   Maximum forwarding rate (MFR) SHOULD MUST be reported as the highest
   forwarding rate of a DUT/SUT taken from an iterative set of
   forwarding rate measurements. The load applied to the device MUST
   also be cited.

5. 2  Partially meshed overloading

To be done.

5. 3  Head-of-line blocking

To be done.

5.4   Partially Meshed Multiple Devices

To

5.1.5 Reporting format

   The results for these tests SHOULD be done.

5.5   Multiple streams reported in the form of unidirectional traffic

To be done.

5.6   Filter illegal frames

To a
   graph.  The x coordinate SHOULD be done.

5.7   Broadcast the frame handling and latency size, the y coordinate
   SHOULD be the test

To results.  There SHOULD be done.

5.8   Maximum forwarding rate at least two lines on
   the graph, one plotting the theoretical and minimum interframe gap

To be done.

5.9   Address Caching Capacity

Objective: one plotting the test
   results.

   To determine measure the DUT/SUT's ability to switch traffic while performing
   many different address caching capacity lookups, the number of a LAN switching device
   as defined in RFC 2285, section 3.8.1.

Procedure:

   This test SHOULD at a minimum addresses per port
   MAY be performed increased in a three-port
   configuration as described below.

   The first port (port 1) series of tests.

5.2  Partially meshed overloading

5.2.1 Objective

   To determine the testing device is connected to the
DUT/SUT throughput when transmitting from/to multiple ports
   and is the port from which a testing device sends frames to/from one port. As with varying
   source addresses and a fixed destination address corresponding to the
MAC
   address fully meshed throughput test, this
   test is a measure of the receiving port. By receiving frames with varying
source
   addresses, capability of the DUT/SUT will learn these new addresses from DUT to switch frames
   without frame loss.  Results of this test can be used to determine
   the
sending port ability of the test device.

   A second DUT to utilize an Ethernet port (port 2) of when switching
   traffic from multiple Ethernet ports.

5.2.2 Setup Parameters

   When offering bursty meshed traffic, the testing device following parameters MUST
   be defined.  Each parameter is connected to configured with the
DUT/SUT following
   considerations.

      Frame Size - Recommended frame sizes are 64, 128, 256, 512, 1024,
      1280 and acts as the receiving port for the address learning frames. This
   port also sends "control" frames back to 1518 bytes, per RFC 2544 section 9.  The four CRC bytes
      are included in the addresses learned
   on frame size specified.

      Traffic Direction - Traffic can be generated in one direction, the first port.
      reverse direction, or both directions.

      Interframe Gap (IFG)  - The algorithm for this is explained below.

   --  A third port (port 3) on the testing device IFG between frames inside a burst
      MUST be connected to
a
   port on at the DUT/SUT and act as a monitoring port to listen minimum specified by the standard (9.6 us for
   flooded frames.

   The algorithm
      10Mbps Ethernet, 960 ns for the test is as follows:

   BEGIN
      Set Initial Value of N to user specified number, where N 100Mbps Ethernet, and 96 ns for
      1 Gbps Ethernet).

      Interburst Gap (IBG) - This is the
      number interval between bursts of addresses
      traffic.  Refer to be verified in each iteration
    WHILE NOT Finished DO
      PAUSE Appendix A, Calculating Interburst Gap, for
      the aging time specified
      Address learning:  Port 1 sends N frames with varying
         source addresses formula used to compute IBG.

      Duplex mode - Half duplex or full duplex.

      Load / Port 2 to attempt to fill the DUT/SUT - Load per port is expressed in a percentage of the
      medium's maximum intended load possible.  The actual transmitted
      frame per second is dependent upon half duplex or full duplex
      operation.  The test SHOULD be run multiple times with a different
      load per port in each case.

      In half duplex mode, exactly half of the intended load SHOULD be
      transmitted to each of the ports under test. For example, with a
      100% load of 64-byte frames, the intended load for each port under
      test is 7440 frames received per second and 7440 frames
      transmitted per second (for 10Mbps Ethernet).

      In full duplex mode, the entire intended load SHOULD be
      transmitted to each of the ports under test. For example, with a
      100% load of 64-byte frames, the intended load for each port under
      test is 14880 frames received per second and 14880 frames
      transmitted per second (for 10Mbps Ethernet).

      Burst Size - The burst size defines the number of frames sent
      back-to-back at the minimum legal IFG (96 bit times) before
      pausing transmission to receive frames.  Burst sizes
      SHOULD vary between 1 and 930 frames.  A burst size of 1 will
      simulate non-bursty traffic.

      Addresses per port - Represents the number of addresses which
      are being tested for each port.  Number of addresses SHOULD be a
      binary exponential (i.e. 1, 2, 4, 8, 16, 32, 64, 128, 256, ...).
      Recommended values are 1, 16 and 256.

      Test Duration - Test duration SHOULD be between 1 and 300 seconds.
      RFC 2285 recommends a duration of at least 10 seconds for each
      test.

5.2.3 Procedure

   In this test, each transmitting port MUST transmit the exact number
   of frames.  Depending upon traffic direction, some or all of the
   ports will be transmitting.

   Frames transmitted from the Many Ports MUST be destined to the One
   port.  Frames transmitted from the One Port MUST be destined to the
   Many ports in a round robin type fashion.  See section 5.1.3 for a
   description of the round robin fashion.

   For tests using multiple addresses per port, the actual port
   destinations are the same as described above and the actual
   source/destination address pairs SHOULD be chosen randomly to
   exercise the DUT/SUT's ability to perform address lookups.

        +----------+
        |          |
        |   Many   | <--------
        |          |          \
        +----------+           \
                                \
        +----------+             \               +-------------+
        |          |              ------------>  |             |
        |   Many   |  <----------------------->  |     One     |
        |          |              ------------>  |             |
        +----------+             /               +-------------+
                                /
        +----------+           /
        |          |          /
        |   Many   |  <-------
        |          |
        +----------+

   For every address, the testing device MUST send learning frames to
   allow the DUT/SUT to update its address tables properly.

5.2.4 Measurements

   Each receiving port MUST categorize, then count the frames into one
   of two groups:

      1.) Received Frames: received frames MUST have the correct
          destination MAC address and SHOULD match a signature field.

      2.) Flood count: defined in RFC 2285 3.8.3.

   Any frame received which does not have the correct destination
   address MUST not be counted as a received frame and SHOULD be counted
   as part of a flood count.

   Any frame originating from the DUT/SUT MUST not be counted as a
   received frame.  Frames originating from the DUT/SUT MAY be counted
   as flooded frames or not counted at all.

   Forwarding rate (FR) of the DUT/SUT SHOULD be reported as the number
   of frames per second that the device is observed to successfully
   transmit to the correct destination interface in response to a
   specified offered load. The offered load MUST also be cited.

   Forwarding rate at maximum offered load (FRMOL) MUST be reported
   as the number of frames per second that a device can successfully
   transmit to the correct destination interface in response to the
   maximum offered load as defined in RFC 2285, section 3.6. The
   maximum offered load MUST also be cited.

   Maximum forwarding rate (MFR) MUST be reported as the highest
   forwarding rate of a DUT/SUT taken from an iterative set of
   forwarding rate measurements. The load applied to the device MUST
   also be cited.

5.2.5 Reporting Format

   The results for these tests SHOULD be reported in the form of a
   graph.  The x coordinate SHOULD be the frame size, the y coordinate
   SHOULD be the test results.  There SHOULD be at least two lines on
   the graph, one plotting the theoretical and one plotting the test
   results.

   To measure the DUT/SUT's ability to switch traffic while performing
   many different address lookups, the number of addresses per port
   MAY be increased in a series of tests.

5.3 Head-of-line blocking

5.3.1 Objective

   To determine how a DUT handles congestion.  Namely, does the device
   implement congestion control and does congestion on one port
   affect an uncongested port?

5.3.2 Setup Parameters

   The following parameters MUST be defined.  Each variable is
   configured with the following considerations.

      Frame Size - Recommended frame sizes are 64, 128, 256, 512, 1024,
      1280 and 1518 bytes, per RFC 2544 section 9.  The four CRC bytes
      are included in the frame size specified.

      Duplex mode -  Half duplex or full duplex.

      Interframe Gap (IFG)  -  The IFG between frames MUST be at the
      minimum specified by the standard (9.6 us for 10Mbps Ethernet,
      960 ns for 100Mbps Ethernet, and 96 ns for 1 Gbps Ethernet).

      Addresses per port - Represents the number of addresses which
      are being tested for each port.  Number of addresses SHOULD be a
      binary exponential (i.e. 1, 2, 4, 8, 16, 32, 64, 128, 256, ...).
      Recommended values are 1, 16 and 256.

      Test Duration - Test duration SHOULD be between 1 and 300 seconds.
      RFC 2285 recommends a duration of at least 10 seconds for each
      test.

5.3.3 Procedure

   This test MUST consist of a multiple of four ports.  Four ports are
   REQUIRED and MAY be expanded to fully utilize the DUT/SUT in
   increments of four.  Each group of four will contain a test block
   with two of the ports as source transmitters and two of the ports as
   receivers. The diagram below depicts the flow of traffic between the
   switch ports:

        +----------+   50 % MOL                  +-------------+
        |          |  ------------------------>  |             |
        |          |   50 % MOL                  | uncongested |
        |          |  ---------                  |             |
        +----------+            \                +-------------+
                                 \
                                  \
                                   \
        +----------+                \            +-------------+
        |          |                 --------->  |             |
        |          |   100 % MOL                 | congested   |
        |          |  ------------------------>  |             |
        +----------+                             +-------------+

   Both source transmitters MUST transmit the exact number of frames.
   The first source MUST transmit frames at the MOL with the destination
   address of the two receive ports in an alternating order.  The first
   frame to the uncongested receive port, second frame to the congested
   receive port, then repeat.  The second source transmitter MUST
   transmit frames at the MOL only to the congested receive port.

   Both receive ports SHOULD distinguish between frames originating from
   the source ports and frames originating from the DUT/SUT.  Only
   frames from the source ports SHOULD be counted.

   The uncongested receive port should be receiving at a rate of half
   the MOL.  The number of frames received on the uncongested port
   SHOULD be 50% of the frames transmitted by the first source
   transmitter.  The congested receive port should be receiving at the
   MOL.  The number of frames received on the congested port should be
   between 100% and 150% of the frames transmitted by one source
   transmitter.

   Frames destined to uncongested ports in a switch device should not
   be dropped due to other ports being congested, even if the source
   is sending to both the congested and uncongested ports.

5.3.4 Measurements

   Any frame received which does not have the correct destination
   address MUST not be counted as a received frame and SHOULD be counted
   as part of a flood count.

   Any frame originating from the DUT/SUT MUST not be counted as a
   received frame.  Frames originating from the DUT/SUT MAY be counted
   as flooded frames or not counted at all.

   Frame loss rate of the DUT/SUT's congested and uncongested ports MUST
   be reported as defined in RFC 2544 section 26.3 with the following
   notes:  Frame loss rate SHOULD be measured at the end of the test
   duration.  The term "rate", for this measurement only, does not imply
   the units in the fashion of "per seconds."

   Forwarding rate (FR) of the DUT/SUT's congested and uncongested ports
   MUST be reported as the number of frames per second that the device
   is observed to successfully transmit to the correct destination
   interface in response to a specified offered load. The offered load
   MUST also be cited.

5.3.5 Reporting format

   This test MUST report the frame lost rate at the uncongested port,
   the maximum forwarding rate (at 50% offered load) at the uncongested
   port, and the frame lost rate at the congested port.  This test MAY
   report the frame counts transmitted and frame counts received by the
   ports.

   If the DUT implements a flow control mechanism, an indication of this
   is presented by observing no frame loss on the congested port.  It
   should be noted that this test expects the overall load to the
   congested port to be greater than 100%. Therefore if the load is
   greater than 100% and no frame loss is detected, then the DUT must be
   implementing a flow control mechanism.  The type of flow control
   mechanism used is beyond the scope of this memo.

   If there is frame loss at the uncongested port, "Head of Line"
   blocking exists.  The DUT cannot forward the amount of traffic to the
   congested port and as a result it is also losing frames destined to
   the uncongested port.

   It should be noted that some DUTs may not be able to handle the 100%
   load presented at the input port. In this case, there may be frame
   loss reported at the uncongested port which is due to the load at the
   input port rather than the congested port's load.

   If the uncongested frame loss is reported as zero, but the maximum
   forwarding rate is less than 7440 (for 10Mbps Ethernet), then this
   may be an indication of congestion control being enforced by the DUT.
   In this case, the congestion control is affecting the throughput of
   the uncongested port.

   If no congestion control is detected, the expected percentage frame
   loss for the congested port is 33% at 150% overload.  It is receiving
   100% load from 1 port, and 50% from another, and can only get 100%
   possible throughput, therefore having a frame loss rate of 33%
   (150%-50%/150%).

5.4 Partially Meshed Multiple Devices

5.4.1 Objective

   To determine the throughput, frame loss and forwarding rates of two
   switching devices equipped with multiple Ethernet ports and one high
   speed backbone uplink (Gigabit Ethernet, ATM, SONET).

5.4.2 Setup Parameters

   When offering bursty partially meshed traffic, the following
   parameters MUST be defined.  Each variable is configured with the
   following considerations.

      Frame Size - Recommended frame sizes are 64, 128, 256, 512, 1024,
      1280 and 1518 bytes, per RFC 2544 section 9.  The four CRC bytes
      are included in the frame size specified.

      Interframe Gap (IFG)  -  The IFG between frames inside a burst
      MUST be at the minimum specified by the standard (9.6 us for
      10Mbps Ethernet, 960 ns for 100Mbps Ethernet, and 96 ns for
      1 Gbps Ethernet).

      Interburst Gap (IBG) - This is the interval between bursts of
      traffic.  Refer to Appendix A, Calculating Interburst Gap, for
      the formula used to compute IBG.

      Duplex mode -  Half duplex or full duplex.

      Load / Port - Load per port is expressed in a percentage of the
      medium's maximum intended load possible.  The actual transmitted
      frame per second is dependent upon half duplex or full duplex
      operation.  The test SHOULD be run multiple times with a different
      load per port in each case.

      In half duplex mode, exactly half of the intended load SHOULD be
      transmitted to each of the ports under test. For example, with a
      100% load of 64-byte frames, the intended load for each port under
      test is 7440 frames received per second and 7440 frames
      transmitted per second (for 10Mbps Ethernet).

      In full duplex mode, the entire intended load SHOULD be
      transmitted to each of the ports under test. For example, with a
      100% load of 64-byte frames, the intended load for each port under
      test is 14880 frames received per second and 14880 frames
      transmitted per second (for 10Mbps Ethernet).

      Burst Size - The burst size defines the number of frames sent
      back-to-back at the minimum legal IFG (96 bit times) before
      pausing transmission to receive frames.  Burst sizes
      SHOULD vary between 1 and 930 frames.

      Addresses per port - Represents the number of addresses which
      are being tested for each port.  Number of addresses SHOULD be a
      binary exponential (i.e. 1, 2, 4, 8, 16, 32, 64, 128, 256, ...).
      Recommended values are 1, 16 and 256.

      Test Duration - Test duration SHOULD be between 1 and 300 seconds.
      RFC 2285 recommends a duration of at least 10 seconds for each
      test.

        Local Traffic - A Boolean value of ON or OFF.  The frame
sequence
      algorithm MAY be altered to remove local traffic.  With local
      traffic ON, the algorithm is exactly the same as a fully meshed
      throughput.  With local traffic OFF, the port sends frames to all
      other ports on the other side of the backbone uplink in a round
      robin type fashion.

5.4.3 Procedure

   All ports MUST transmit the exact number of frames.  All ports SHOULD
   start transmitting their frames within 1% of the test duration.  For
   a test duration of 10 seconds, all ports SHOULD have started
   transmitting frames with 100 milliseconds of each other.

   Each port in the test MUST send frames to all other ports in a
   round robin type fashion as defined in section 5.1.  Local traffic
   MAY be removed from the round robin list in order to send the entire
   load across the backbone uplink.

   For tests using multiple addresses per port, the actual port
   destinations are the same as described above and the actual
   source/destination address pairs SHOULD be chosen randomly to
   exercise the DUT/SUT's ability to perform address lookups.

   For every address, the testing device MUST send learning frames to
   allow the DUT/SUT to update its address tables properly.

   To measure the DUT/SUT's ability to switch traffic while performing
   many different address lookups, the number of addresses per port
   MAY be increased in a series of tests.

5.4.4 Measurements

   Each port should receive the same amount of frames that is
   transmitted.  Each receiving port MUST categorize, then count the
   frames into one of two groups:

      1.) Received frames MUST have the correct destination MAC address
          and SHOULD match a signature field.

      2.) Flood count (defined in RFC 2285 3.8.3).

   Any frame received which does not have the correct destination
   address MUST not be counted as a received frame and SHOULD be counted
   as part of a flood count.

   Any frame originating from the DUT/SUT MUST not be counted as a
   received frame.  Frames originating from the DUT/SUT MAY be counted
   as flooded frames or not counted at all.

   Frame loss rate of the DUT/SUT SHOULD be reported as defined in
   RFC 2544 section 26.3 with the following notes:  Frame loss rate
   SHOULD be measured at the end of the test duration.  The term "rate",
   for this measurement only, does not imply the units in the fashion of
   "per seconds."

   Forwarding rate (FR) of the DUT/SUT SHOULD be reported as the number
   of frames per second that the device is observed to successfully
   transmit to the correct destination interface in response to a
   specified offered load. The offered load MUST also be cited.

   Forwarding rate at maximum offered load (FRMOL) MUST be reported
   as the number of frames per second that a device can successfully
   transmit to the correct destination interface in response to the
   maximum offered load as defined in RFC 2285, section 3.6. The
   maximum offered load MUST also be cited.

   Maximum forwarding rate (MFR) MUST be reported as the highest
   forwarding rate of a DUT/SUT taken from an iterative set of
   forwarding rate measurements. The load applied to the device MUST
   also be cited.

5.4.5 Reporting format

   The results for these tests SHOULD be reported in the form of a
   graph.  The x coordinate SHOULD be the frame size, the y coordinate
   SHOULD be the test results.  There SHOULD be at least two lines on
   the graph, one plotting the theoretical and one plotting the test
   results.

   To measure the DUT/SUT's ability to switch traffic while performing
   many different address table lookups, the number of addresses per port
   MAY be increased in a series of tests.

5.5 Multiple streams of unidirectional traffic

5.5.1 Objective

   To determine the throughput of the DUT/SUT when presented multiple
   streams of unidirectional traffic with half of the ports on the
   DUT/SUT are receiving frames destined to the other half of the
   ports.

5.1.2 Setup Parameters

   The following parameters MUST be defined.  Each variable is
   configured with the following considerations.

      Frame Size - Recommended frame sizes are 64, 128, 256, 512, 1024,
      1280 and 1518 bytes, per RFC 2544 section 9.  The four CRC bytes
      are included in the frame size specified.

      Duplex mode - Half duplex or full duplex.

      Load / Port - Load per port is expressed in a percentage of the
      medium's maximum intended load possible.  The actual transmitted
      frame per second is dependent upon half duplex or full duplex
      operation.  The test SHOULD be run multiple times with a different
      load per port in each case.

      In half duplex mode, exactly half of the intended load SHOULD be
      transmitted to each of the ports under test. For example, with a
      100% load of 64-byte frames, the intended load for each port under
      test is 7440 frames received per second and 7440 frames
      transmitted per second (for 10Mbps Ethernet).

      In full duplex mode, the entire intended load SHOULD be
      transmitted to each of the ports under test. For example, with a
      100% load of 64-byte frames, the intended load for Port #1.
      Controlling:  Port 2 sends N each port under
      test is 14880 frames with varying
         destination addresses corresponding to Port 1.
      IF (Port 3 received per second and 14880 frames
      transmitted per second (for 10Mbps Ethernet).

      Addresses per port - Represents the number of addresses which
      are being tested for each port.  Number of addresses SHOULD be a frame during Control phase) OR
         (Port
      binary exponential (i.e. 1, 2, 4, 8, 16, 32, 64, 128, 256, ...).
      Recommended values are 1, 16 and 256.

      Test Duration - Test duration SHOULD be between 1 did and 300 seconds.
      RFC 2285 recommends a duration of at least 10 seconds for each
      test.

5.5.3 Procedure

   Ports do not send and receive frames simultaneously. As a
   consequence, there should be no collisions unless the correct # DUT is
   misforwarding frames, generating flooded or Spanning-Tree frames or
   is enabling some flow control mechanism.  Ports used for this test
   are either transmitting or receiving, but not both. Those ports which
   are transmitting send frames destined to addresses corresponding to
   each of frames)
      THEN
         Address Table the ports receiving. This creates a unidirectional mesh of DUT/SUT was full
         Set N to lower
   traffic.

   All ports MUST transmit the exact number (in binary search method)
      ELSE
         Address Table of DUT/SUT was NOT full
         Set N frames.  All ports SHOULD
   start transmitting their frames within 1% of the test duration.  For
   a test duration of 10 seconds, all ports SHOULD have started
   transmitting frames with 100 milliseconds of each other.

   Each transmitting port in the test MUST send frames to higher number (in binary search method)
      IF High all receiving
   ports in a round robin type fashion. The following table shows how
   each port in a test MUST transmit frames to all other ports in the
   test.  In this 8 port example, port 1 through 4 are transmitting and Low Values
   ports 5 through 8 are receiving; each with 1 address per port:

   Source Port, then Destination Ports (in order of N Meet
      THEN
         Test transmission)

   Port #1              5       6       7       8       5       6...
   Port #2              6       7       8       5       6       7...
   Port #3              7       8       5       6       7       8...
   Port #4              8       5       6       7       8       5...

   As shown in the table, there is Finished, Value of N equals number an equal distribution of destination
   addresses supported for each transmit opportunity. This keeps the test balanced
   so that one destination port is not overloaded by DUT/SUT
      ELSE
         Continue Test
     END WHILE
   DONE
   Using a binary search approach, the test targets algorithm
   and all receiving ports are equally and fully loaded throughout the exact number
   of
   test.  Not following this algorithm exactly will product inconsistent
   results.

   For tests using multiple addresses supported per port with minimal test iterations. Due
   to port, the aging time of DUT/SUT address tables, each iteration may take
   some time during actual port
   destinations are the waiting period for same as described above and the addresses actual
   source/destination address pairs SHOULD be chosen randomly to clear. If
   possible, configure the DUT/SUT for a low value for the aging time.

   Once the high and low values of N meet, then
   exercise the threshold of DUT/SUT's ability to perform address
   handling has been found. lookups.

   For this test, the aging time of every address, the DUT/SUT testing device MUST be known. Use a
short
   aging time if possible send learning frames to reduce
   allow the time needed DUT/SUT to run the test. load its address tables properly.  The address
   table's aging time MUST be longer than the time necessary to produce
   packets at the specified rate. If a low frame rate is used for
   the test, then it may SHOULD be possible that sending a large amount of
   frames may actually take longer than the aging time. Keep in mind
   that the test actually sends twice as many frames as the number
   of addresses being tested due to set sufficiently longer than the
   learning phase time and test duration time combined.  If the address table
   ages out during the
   controlling phase.

   Set test, the initial value results will show a lower performing
   DUT/SUT.

   To measure the DUT/SUT's ability to switch traffic while performing
   many different address lookups, the number of addresses per port to
   MAY be increased in a number
   slightly higher than series of tests.

5.5.4 Measurements

   Each port should receive the same number of addresses frames that it
   transmitted.  Each receiving port MUST categorize, then count the DUT/SUT can
handle.
   This step primes the binary search and can reduce the number
   frames into one of
   iterations required to determine two groups:

      1.) Received Frames: received frames MUST have the exact number supported.

   Set correct
          destination MAC address and SHOULD match a signature field.

      2.) Flood count: defined in RFC 2285 3.8.3.

   Any frame received which does not have the forwarding rate to correct destination
   address MUST not be counted as a number that is reasonable to received frame and SHOULD be handled
   by counted
   as part of a flood count.

   Any frame originating from the DUT/SUT and one that is high enough so that MUST not be counted as a
   received frame.  Frames originating from the test
iterations are DUT/SUT MAY be counted
   as flooded frames or not too long.

Reporting format:

   After counted at all.

   Frame loss rate of the test is run, results for each iteration DUT/SUT SHOULD be displayed reported as defined in a table to include:

   --  the number of addresses used for each test iteration.

   --
   RFC 2544 section 26.3 with the frame following notes:  Frame loss rate used for each test iteration.

   --  number
   SHOULD be measured at the end of control frames that were transmitted by the test port
   number 2. Control frames are duration.  The term "rate",
   for this measurement only, does not imply the frames sent with varying destination
   addresses to confirm that units in the DUT/SUT has learned all fashion of
   "per seconds."

   Forwarding rate (FR) of the
addresses
   for each test iteration.

   -- DUT/SUT SHOULD be reported as the number
   of frames received by test port 2 during the control
   portion of each test. If per second that the number is non-zero, this device is an
indication
   of the DUT/SUT flooding a frame in which observed to successfully
   transmit to the correct destination address is
not interface in the address table.

   -- response to a
   specified offered load. The offered load MUST also be cited.

   Forwarding rate at maximum offered load (FRMOL) MUST be reported
   as the number of frames per second that test port 1 received during a device can successfully
   transmit to the control
   portion of correct destination interface in response to the test. This number will include those frames which are
   Spanning tree frames. For
   maximum offered load as defined in RFC 2285, section 3.6. The
   maximum offered load MUST also be cited.

   Maximum forwarding rate (MFR) MUST be reported as the highest
   forwarding rate of a normal test iteration, this number DUT/SUT taken from an iterative set of
   forwarding rate measurements. The load applied to the device MUST
   also be cited.

5.1.5 Reporting format

   The results for these tests SHOULD be equal to reported in the number form of frames transmitted by port 2 during a
   graph.  The x coordinate SHOULD be the
   control phase.

   -- frame size, the number of frames that test port 1 received during y coordinate
   SHOULD be the control
   phase not including Spanning Tree or other non test generated frames.
   In all cases, this number results.  There SHOULD be equal at least two lines on
   the graph, one plotting the theoretical and one plotting the test
   results.

   To measure the DUT/SUT's ability to switch traffic while performing
   many different address lookups, the number of frames
   transmitted by addresses per port 2 during the control phase
   MAY be increased in a series of the test.

   --  the number tests.

5.6 Filter illegal frames

5.6.1 Objective

   The objective of frames the filter illegal frame test port 3 received during is to determine
   the control
phase behavior of the test. If DUT under errors or abnormal frame conditions.
   The results of the value is not zero, then this indicates that for
   that test iteration, indicate if the DUT/SUT could not determine the proper
destination
   port for that many frames. In other words, filters the DUT/SUT flooded errors,
   or simply propagates the
frame errored frames along to
   all ports since its address table was full.

5.10   Address Learning Rate

Objective:

   Once the maximum number of addresses supported destination.

5.1.2 Setup Parameters

   The following parameters MUST be defined.  Each variable is
   configured with the following considerations.

      Load / Port - Load per port by the
DUT/SUT is
   known, expressed in a percentage of the addressing learning rate (the rate
      medium's maximum intended load possible.  The actual transmitted
      frame per second is dependent upon half duplex or full duplex
      operation.  The test SHOULD be run multiple times with a different
      load per port in each case.

      Test Duration - Test duration SHOULD be between 1 and 300 seconds.
      RFC 2285 recommends a duration of at which least 10 seconds for each
      test.

5.6.3 Procedure

   Each of the DUT/SUT
learns
   these addresses) can illegal frames for Ethernet MUST be determined.

Procedure:

   An algorithm similar to checked:

   Oversize - The DUT/SUT MAY filter frames larger than 1518 bytes
   from being propagated through the one used DUT/SUT (ISO 8802-3 4.2.4.2.1).
   Oversized frames transmitted to determine address caching
   capacity can be used the DUT/SUT should not appear as
   receive frames or as error frames on any port.  DUT/SUT supporting
   tagged Frames MAY forward frames up to determine and including 1522 bytes
   long (IEEE 802.3ac 4.2.4.2.1).

   Undersize - The DUT/SUT MUST filter frames less than 64 bytes from
   being propagated through the address learning rate. This
   test iterates DUT/SUT (per ISO 8802-3 4.2.4.2.2).
   Undersized frames (or collision fragments) transmitted to the rate at which address learning DUT/SUT
   MUST not appear as receive frames are offered
   by or as error frames on another port.

   CRC Errors - The DUT/SUT MUST filter frames that fail the test device connected to Frame Check
   Sequence Validation (ISO 8802-3 4.2.4.1.2) from being propagated
   through the DUT/SUT.  It is recommended  Frames with an invalid CRC transmitted to
set the number of addresses offered
   DUT/SUT should not appear as receive frames or as error frames on
   another port.

   Dribble Bit Errors - The DUT/SUT MUST correct and forward frames
   containing dribbling bits.  Frames transmitted to the DUT/SUT that do
   not end in this test to the
   maximum caching capacity.  However, the address learning rate might
be
   determined for different numbers of addresses an octet boundary but in each test run,
   the number contain a valid frame check sequence
   MUST remain constant.

   Initializing the forwarding rate primes be accepted by the binary search algorithm DUT/SUT (ISO 8802-3 4.2.4.2.1) and can help forwarded
   to shorten the overall test duration.

   A third correct receive port on with the frame ending in an octet
   boundary (ISO 8802-3 3.4).

   Alignment Errors - The DUT/SUT MUST listen for flooded frames.

   In this test, filter frames than fail the forwarding rate SHOULD be varied until a rate is
   found that Frame
   Check Sequence Validation AND do not end in an octet boundary.  This
   is a combination of a CRC error and a Dribble Bit error.  When both
   errors are occurring in the threshold for same frame, the rate supported by DUT/SUT MUST determine
   the DUT/SUT. It
   may be useful to pick a value slightly higher than CRC error takes precedence and filters the advertised
   forwarding rate.

Reporting format:

   To be done.

Section 6. Security Considerations

   This document does not yet address Security Considerations.

Section 7. Authors' Address

   Robert Mandeville
   European Network Laboratories (ENL)
   2, rue Helene Boucher
   87286 Guyancourt Cedex
   France

   Phone: + 33 1 39 44 12 05
   EMail: bob@enl.net

   Judy Keene
   Netcom Systems
   20550 Nordhoff St.
   Chatsworth, CA 91311
   USA

   Phone: +1 818 700 5100
   Email: judy_keene@netcomsystems.com

Appendix A:  Calculating frame (ISO 8802-3
   4.2.4.1.2) from being propagated.

5.7 Broadcast frame handling and latency test

5.7.1 Objective

   The objective of the Interburst Gap

   IBG Broadcast Frame Handling and Latency Test is defined in RFC 2285 as a function to
   determine the throughput and latency of maximum media rate (also
   known as line rate), the length DUT when handling
   broadcast traffic.  The ability to forward broadcast frames will
   depend on special features built into the device for that purpose.
   It is therefore necessary to determine the ability of switches to
   handle broadcast frames, since there may be many different ways of the frames in the bursts
   implementing such a feature.

5.7.2 Setup Parameters

   The following parameters MUST be defined.  Each variable is
   configured with the
   preamble following considerations.

      Frame Size - Recommended frame sizes are 64, 128, 256, 512, 1024,
      1280 and the interframe gap (IFG), the number of frames 1518 bytes, per RFC 2544 section 9.  The four CRC bytes
      are included in the
bursts,
   and the intended load.

   Using the burst size, frame size and specified.

      Duplex mode - Half duplex or full duplex.

      Load / Port - Load per port is expressed in a percentage of the
      medium's maximum intended load possible.  The actual transmitted
      frame per port, the IBG can
be
   calculated:

     Burst size * ((preamble 64 + (frame size * 8 bits) + 96 IFG bit
times))
             * 1 (for full duplex) or .5 (for second is dependent upon half duplex)
            (10 bit duplex or full duplex
      operation.  The test SHOULD be run multiple times equal 1 microsecond)

   Example:

      Burst size = 24
      Frame size = 64

        24 * (64 + 64*8 + 96) = 24 * (672) = 16,128 bit/times =
                                                 1612.8 us IBG with a different
      load per port in each case.

      In half duplex mode, exactly half of the target intended load SHOULD be sent
      transmitted to each of the ports under test. For example, with a
      100% load of 64-byte frames, the target intended load for each port under
      test is 7440 frames received per second and 7440 frames
      transmitted per second (for 10Mbps Ethernet).

   Recommended characteristic values for burst size are:

2       15      60      240     930
3       16      62      248
4       20      80      310
5       24      93      372
6       30      120     465
8       31      124     496
10      40      155     620
12      48      186     744

Network Working Group                                      R. Mandeville
Internet-Draft                             European Network Laboratories
Expiration Date: February 1999                                  J. Keene
                                                          Netcom Systems
                                                             August 1998

           Benchmarking Methodology for LAN Switching Devices
                    <draft-ietf-bmwg-mswitch-00.txt>

Status

      In full duplex mode, the entire intended load SHOULD be
      transmitted to each of this Memo

   This document is an Internet-Draft. Internet-Drafts are working
   documents the ports under test. For example, with a
      100% load of 64-byte frames, the Internet Engineering Task Force (IETF),its areas, intended load for each port under
      test is 14880 frames received per second and 14880 frames
      transmitted per second (for 10Mbps Ethernet).

      Test Duration - Test duration SHOULD be between 1 and its working groups. Note that other groups may also distribute
   working documents as Internet-Drafts.

   Internet-Drafts are draft documents valid for 300 seconds.
      RFC 2285 recommends a maximum duration 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 least 10 seconds for each
      test.

5.7.3 Procedure

   For this test, there are two parts to cite them other than as "work in progress."

   To view the entire list be run.

   Broadcast Frame Throughput - This portion of current Internet-Drafts, please check the "1id-abstracts.txt" listing contained test uses a single
   source test port to transmit frames with a broadcast address using
   the frame specified in RFC 2544.  Selected receive ports then
   measure the Internet-Drafts
   Shadow Directories on ftp.is.co.za (Africa), ftp.nordu.net
   (Northern Europe), ftp.nis.garr.it (Southern Europe), munnari.oz.au
   (Pacific Rim), ftp.ietf.org (US East Coast), or ftp.isi.edu
   (US West Coast). forwarding rate and Frame loss rate.

   Broadcast Frame Latency - This memo provides information for test uses the Internet community. This memo
   does not specify an Internet standard same setup as the
   Broadcast Frame throughput, but instead of any kind. Distribution a large stream of
   this memo is unlimited.

Abstract

   This document frames
   being sent, only one frame is intended sent and the latency to provide methodology for each of the benchmarking
   receive ports are measured in seconds.

5.7.4 Measurements

   Frame loss rate of local area network (LAN) switching devices. It extends the
   methodology already DUT/SUT SHOULD be reported as defined for benchmarking network interconnecting
   devices in
   RFC 1944 to switching devices.

   This RFC primarily deals 2544 section 26.3 with devices which switch frames the following notes:  Frame loss rate
   SHOULD be measured at the
   Medium Access Control (MAC) layer. Itprovides a methodology end of the test duration.  The term "rate",
   for
   benchmarking switching devices, forwarding performance, congestion
   control, latency, address handling and filtering. In addition this measurement only, does not imply the units in the fashion of
   "per seconds."

   Forwarding rate (FR) of the DUT/SUT SHOULD be reported as the number
   of frames per second that the device is observed to successfully
   transmit to
   defining the tests, this document correct destination interface in response to a
   specified offered load. The offered load MUST also describes specific formats for
   reporting be cited.

5.8 Maximum forwarding rate and minimum interframe gap

5.8.1 Objective

   The objective of the results Maximum forwarding rate test is to find the
   peak value of the tests.

1. Introduction
   This document defines Forwarding Rate when the Offered Load is varied
   between the throughput (RFC 1242) and the Maximum Offered Load
   (RFC 2285).

   The Minimum Interframe gap Test overloads a specific set of tests to measure DUT/SUT port and report measure
   the performance characteristics of network switching devices.

   A previous document, "Benchmarking Terminology output for LAN Switching
   Devices" (RFC 2285), defined many of forward pressure.  If the terms that are used in this
   document. DUT/SUT transmits frames
   with an interframe gap less than 96 bits (ISO 8802-3 4.2.3.2.2), then
   forward pressure is detected.

5.8.2 Setup Parameters

   The terminology document SHOULD following parameters MUST be consulted before
   attempting to make use of this document.

2. Requirements

   The defined.  Each variable is
   configured with the following RFCs considerations.

      Frame Size - Recommended frame sizes are 64, 128, 256, 512, 1024,
      1280 and 1518 bytes, per RFC 2544 section 9.  The four CRC bytes
      are included in the frame size specified.

      Duplex mode - Half duplex or full duplex.

      Test Duration - Test duration SHOULD be consulted before attempting to make use
   of this document:

   * RFC 1242 "Benchmarking Terminology for Network Interconnect
     Devices"

   * RFC 1944 "Benchmarking Methodology for Network Interconnect
     Devices"

   * between 1 and 300 seconds.
      RFC 2285  "Benchmarking Terminology recommends a duration of at least 10 seconds for LAN Switching Devices"

   For each
      test.

        Step Size - The minimum incremental resolution that the sake of clarity Offered
      Load (OL) will be incremented in frames per second.  The smaller
      the step size, the more accurate the measurement and continuity, this RFC adopts the template
   for benchmarking tests set out in Section 26 more
      iterations required.  As the Offered Load approaches the Maximum
      Offered Load, the minimum step size will increase because of RFC 1944.

   The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT",
   "SHOULD", "SHOULD NOT", "RECOMMENDED",  "MAY", gap
      resolution on the testing device.

5.8.3 Procedure

   If the throughput and "OPTIONAL" in
   this document the Maximum Offered Load are the same, then
   Maximum Forwarding rate is equal to be interpreted as described in RFC 2119.

3. Test setup

   This document extends the general Maximum Offered Load.

   This test setup described SHOULD at a minimum be performed in section 6
   of RFC 1944 a two-port
   configuration as described below.  Learning frames MUST be sent to
   allow the benchmarking of LAN switching devices. RFC 1944
   primarily describes non-meshed traffic where input and output
   interfaces  are grouped in mutually exclusive sending and
   receiving pairs. In fully meshed traffic, each interface of a DUT/SUT is set up to both receive and transmit update its address tables properly.

   The first port (port 1) device transmits frames to all at the other interfaces under test.

   Prior Offered Load
   to each test run, the DUT/SUT MUST learn the MAC addresses used
in DUT/SUT.  A second port (port 2) receives frames from the test
   DUT/SUT and measures the address learning MUST be verified Forwarding Rate.

   The Offered Load is incremented for each Step Size to avoid flooded
   frames being counted as correctly received frames. find the
   Maximum Forwarding Rate.  The forwarding
   rate, namely algorithm for the rate at which address learning frames are offered
may
   have to be adjusted to be as low test is as 50 follows:

    CONSTANT
      MOL = ... frames/sec; {Maximum Offered Load}
    VARIABLE
      MFR   := 0 frames/sec; {Maximum Forwarding Rate}
      OLOAD := starting throughput in frames/sec; {offered load}
      STEP  := ... frames/sec; {Step Size}
    BEGIN
      OLOAD := OLOAD - STEP;
    DO
    BEGIN
      OLOAD := OLOAD + STEP
      IF (OLOAD > MOL) THEN
      BEGIN
        OLOAD := MOL
      END
        AddressLearning; {Port 2 broadcast frame with its source
address}
      Transmit(OLOAD); {Port 1 sends frames per second or even
less, to guarantee successful learning. The DUT/SUT address aging time
SHOULD be
   configured to be greater Port 2 at Offered load}
      IF (Port 2 Forwarding Rate > MFR) THEN
      BEGIN
         MFR := Port 2 Forwarding Rate; {A higher value than the period between the learning phase
of
   the test and the before}
      END
    END
    WHILE (OLOAD >= MOL); {MFR equals Maximum Forwarding Rate}
    DONE
   The Minimum Interframe gap test run; in non-meshed and partially meshed tests,
   the aging time SHOULD SHOULD, at a minimum minimum, be set to at least the length of
   the test period.  More than one trial may performed in
   a two-port configuration as described below.  Learning frames MUST be needed for the
association
   of the address to the port
   sent to occur.

   If a DUT/SUT uses a hashing algorithm with address learning, allow the DUT/SUT may not learn the necessary addresses to perform the tests. update its address tables properly.

   The format first port (port 1) device transmits frames with an interframe
   gap of 88 bits to the MAC addresses MUST be adjustable so that the
address
   mapping may be re-arranged DUT/SUT.  This will apply forward pressure to make a
   the DUT/SUT learn addresses
   without confusion.

   It is recommended that SNMP and Spanning Tree be disabled when bench-
   marking switching devices unless investigating overhead behavior. If
   such protocols cannot be turned off, overload it is recommended that the
   levels at a rate of offered load be reduced (less than 100%) to allow for
   the additional management frames.

4.  Frame formats and sizes

   For frame formats and sizes, refer to RFC 1944, sections 8 and 9 and
   Appendix C.

   There are three frame formats for layer 2 Ethernet switches:
   standard MAC Ethernet frames, standard MAC Ethernet one byte per frame.  The
   frames MUST be constructed with vendor-specific tags added to them, a source address of port 1 and IEEE 802.3ab
   frames tagged to accommodate 802.3p,q.  The two types a
   destination address of tagged port 2.

   A second port (port 2) receives frames may from the DUT/SUT and measures
   the Forwarding Rate.  The measured Forwarding Rate SHOULD not exceed
   the standard medium's maximum length frame theoretical utilization.

5.8.4 Measurements

   Port 2 MUST categorize, then count the frames into one of 1518 bytes, two groups:

      1.) Received Frames: received frames MUST have the correct
          destination MAC address and
   may SHOULD match a signature field.

      2.) Flood count: defined in RFC 2285 3.8.3.

   Any frame received which does not be accepted by have the interface controllers correct destination
   address MUST not be counted as a received frame and SHOULD be counted
   as part of some DUT/SUTs.
   It is recommended to check a flood count.

   Any frame originating from the compatibility of DUT/SUT MUST not be counted as a
   received frame.  Frames originating from the DUT/SUT
   with tagged frames before testing.

   Devices switching tagged MAY be counted
   as flooded frames or not counted at all.

5.8.5 Reporting format

   Maximum forwarding rate (MFR) MUST be reported as the highest
   forwarding rate of over 1518 bytes will have a lower
   maximum DUT/SUT taken from an iterative set of
   forwarding rate than standard untagged frames.

5. Benchmarking Tests measurements. The following tests offer objectives, procedures, and reporting
   formats for benchmarking LAN switching devices.

     5.1  Fully meshed throughput, frame loss and forwarding rates
     5.2  Partially meshed overloading
     5.3  Head load applied to the device MUST
   also be cited.

   Forwarding rate (FR) of line blocking
     5.4  Partially meshed multiple devices
     5.5  Multiple streams the DUT/SUT SHOULD be reported as the number
   of unidirectional traffic
     5.6  Filter illegal frames
     5.7  Broadcast frame handling and latency
     5.8  Maximum forwarding rate and minimum interframe gap
     5.9  Address caching capacity
     5.10 per second that the device is observed to successfully
   transmit to the correct destination interface in response to a
   specified offered load. The offered load MUST also be cited.

5.9 Address learning rate

5.1  Fully meshed throughput, frame loss and forwarding rates

Objective: Caching Capacity

5.9.1 Objective

   To determine the throughput, frame loss and forwarding rates address caching capacity of
DUT/SUTs
   offered fully meshed traffic a LAN switching device
   as defined in RFC 2285.

Procedure:

   RFC 2285 points out that when offering bursty meshed traffic, the
   variables which 2285, section 3.8.1.

5.9.2 Setup Parameters

   The following parameters MUST be defined are frame size, bust size,
   interframe gap, interburst gap, and load. defined.  Each variable is
   configured with the following considerations.

      Interframe Gap (IFG)

     Age Time - The IFG between frames inside maximum time that a burst
MUST
      be at the minimum specified by the standard (9.6 us for 10Mbps
      Ethernet and 0.96 us for 100Mbps Ethernet).

      Interburst Gap (IBG) DUT/SUT will keep a learned
     address in its forwarding table.

     Addresses Learning Rate - This is the interval between bursts of
      traffic.  Refer The rate at which new addresses are
     offered to Appendix A, Calculating Interburst Gap, for the formula used DUT/SUT to compute IBG.

      Load / Port - The test SHOULD be run multiple times with a
      different load per port in each case. learned.  The 100% load translates to
      a transmit load of 50% for half duplex. This type of test SHOULD
      also be run rate at higher than 100% loads.

      In half duplex mode, exactly half of the target load SHOULD be
      sent to each of the ports under test. For example, with a 100%
      load of 64-byte frames, the target load for each port under test
      is 7440 frames received per second and 7440 which address
     learning frames transmitted per
      second (for 10Mbps Ethernet).

      Frame Size - Recommended frame sizes are 64, 128, 256, 512, 1024,
      1280 and 1518 bytes, per RFC 1944 section 9.

      Burst Size offered may have to be adjusted to be as low as
     50 frames per second or even less, to guarantee successful
     learning.

     Initial Addresses - The burst size defines the initial number of packets sent
      back-to-back at the minimum legal IFG (96 bit times) before
      pausing transmission addresses to receive frames.  Burst sizes
      SHOULD vary start the
     test with.  The number MUST be between 1 and 930 frames.

      To avoid truncating bursts, a burst size SHOULD be an even
      multiple into 7440. 7440 is the maximum frames per second for half
      duplex mode; 14880 is number
     supported by the maximum frames per second for full
      duplex mode.  Refer to Appendix A for a table implementation.

5.9.3 Procedure

   The aging time of recommended burst
      values.

   Each port in the test sends frames to all other ports in a round-
   robin type fashion. DUT/SUT MUST be known.  The following table shows how each port in a test
   SHOULD transmit frames to all other ports in aging time MUST be
   longer than the test. In this
   example, there are six ports with 1 address per port:

   Source Port, then Destination Ports (in order of transmission)

   Port #1              2       3       4       5       6       2...
   Port #2              3       4       5       6       1       3...
   Port #3              4       5       6       1       2       4...
   Port #4              5       6       1       2       3       5...
   Port #5              6       1       2       3       4       6...
   Port #6              1       2       3       4       5       1...

   As shown in time necessary to produce frames at the table, there specified
   rate.  If a low frame rate is an equal distribution of destination
   addresses used for each transmit opportunity. This keeps the test balanced
   so test, then it may be
   possible that one destination port is not overloaded by sending a large amount of frames may actually take
   longer than the aging time.

   This test algorithm
   and all SHOULD at a minimum be performed in a three-port
   configuration as described below.

   This test MUST consist of a multiple of three ports.  Three ports
   are equally REQUIRED and MAY be expanded to fully loaded throughout the test. For
   tests using multiple addresses per port, the actual port destinations
   are utilized the same DUT/SUT in
   increments of three.  Each group of three will contain a test
   block as described above follows:

   The first port (port 1) send frames with varying source addresses and the actual source/destination
   a fixed destination address
   pairs are chosen randomly corresponding to exercise the DUT/SUT's ability to
perform MAC address lookups.

   For every address, of the testing device sends learning packets to allow
   receiving port (port 2) of the DUT/SUT to load its address tables properly.

   To measure DUT/SUT. By receiving frames with
   varying source addresses, the DUT/SUT's ability to switch traffic while performing
many
   different address lookups, DUT/SUT will learn these new addresses
   from the number sending port of the test device.  The source addresses per port SHOULD MAY
   be
   increased in a series of tests.

Reporting format:

   In these tests, a sequential order.

   A second port SHOULD transmit and receive (port 2) acts as the same amount of
   packets. Each receiving port MUST count for the packets received with a valid
address.
   Any packet received which does not have a valid address MUST not be
   counted
   learning frames.  This port also sends test frames back to the
   addresses learned on the first port.  The algorithm for this is
   explained below.

   A third port (port 3) on the DUT/SUT act as a received packet monitoring port to
   listen for flooded frames.

   It is highly recommended that SNMP, Spanning Tree, and can any other
   frames originating from the DUT/SUT be counted as part of a disabled when running this
   test.  If such protocols cannot be turned off, the flood count as described in 3.8.3 in RFC 2285.

   The results for these tests SHOULD MUST
   be reported in the form of
numerical
   data or a graph with text modified only to indicate count frame originating from port 1 and MUST
   NOT count frames originating from the data type. DUT/SUT.
   The data types algorithm for the throughput test is as follows:

    CONSTANT
      AGE = ...;  {value greater that DUT aging time}
      MAX = ...;  {maximum address support by implementation}
    VARIABLE
      LOW  := 0;    {Highest passed valve}
      HIGH := MAX;  {Lowest failed value}
      N    := ...;  {user specified initial starting point}
    BEGIN
      DO
        BEGIN
        PAUSE(AGE);   {Age out any learned addresses}
          AddressLearning(Port 2); {broadcast a frame with its source
                                  Address and for the broadcast destination}
          AddressLearning(Port 1); {N frames with varying source
addresses
                                  to Port 2}
        Transmit(Port 2); {N frames with varying destination addresses
                           corresponding to Port 1}
        IF (Port 3 receive frame loss rate test are described in
   RFC 1944.

   Forwarding rate (FR) != 0) OR
           (Port 1 receive frames < Port 2 transmit) THEN
          BEGIN  {Address Table of the DUT/SUT SHOULD be reported as the was full}
            HIGH := N;
          END
        ELSE
          BEGIN  {Address Table of DUT/SUT was NOT full}
            LOW := N;
          END
        N := LOW + (HIGH - LOW)/2;
      END WHILE (HIGH - LOW < 2);
    END {Value of N equals number of
   frames per second that the device is observed to successfully
transmit
   to the correct destination interface in response to addresses supported by DUT/SUT}

   Using a specified
offered
   load. The offered load MUST also be cited.

   Forwarding rate at maximum offered load (FRMOL ) SHOULD be reported
as binary search approach, the test targets the exact number of frames
   addresses supported per second that a device can successfully
transmit port with consistent test iterations.  Due
   to the correct destination interface in response to aging time of DUT/SUT address tables, each iteration may take
   some time during the maximum
offered
   load as defined in RFC 2285, section 3.6. The maximum offered load
MUST
   also be cited.

   Maximum forwarding rate (MFR) SHOULD be reported as waiting period for the addresses to clear.  If
   possible, configure the highest
forwarding
   rate of a DUT/SUT taken from an iterative set for a low value for the aging time.

   Once the high and low values of forwarding rate
   measurements. The load applied to N meet, then the device MUST also be cited.

5. 2  Partially meshed overloading

To be done.

5. 3  Head-of-line blocking

To be done.

5.4   Partially Meshed Multiple Devices

To be done.

5.5   Multiple streams threshold of unidirectional traffic

To be done.

5.6   Filter illegal frames

To be done.

5.7   Broadcast frame address
   handling and latency test

To be done.

5.8   Maximum forwarding rate and minimum interframe gap

To be done.

5.9   Address Caching Capacity

Objective:

   To determine has been found.

5.9.4 Measurements

   Whether the offered addresses per port was successful forwarded
   without flooding.

5.9.5 Reporting format

   After the address caching capacity of a LAN switching device
   as defined in RFC 2285, section 3.8.1.

Procedure:

   This test is run, results for each iteration SHOULD at a minimum be performed displayed
   in a three-port
   configuration as described below. table to include:

      The first port (port 1) number of addresses used for each test iteration (varied).

      The intended load used for each test iteration (fixed).

      Number of test frames that were transmitted by test port number 2.
      This SHOULD match the testing device is connected to number of addresses used for the
DUT/SUT
   and is test
      iteration.  Test frames are the port from which a testing device sends frames sent with varying
   source addresses and a fixed
      destination address corresponding addresses to the
MAC
   address of the receiving port. By receiving frames with varying
source
   addresses, confirm that the DUT/SUT will learn these new addresses from the
sending port has learned
      all of the addresses for each test device.

   A second iteration.

      The flood count on port (port 2) 2 during the test portion of each test.
      If the testing device number is connected to non-zero, this is an indication of the DUT/SUT
   and acts as
      flooding a frame in which the receiving port for destination address is not in the
      address learning frames. This
   port also sends "control" table.

      The number of frames back correctly forwarded to the addresses learned
   on the first port. The algorithm for this is explained below.

   --  A third test port (port 3) on 1 during
      the testing device test portion of the test.  Received frames MUST be connected to
a
   port on have the DUT/SUT
      correct destination MAC address and act as SHOULD match a monitoring port signature
      field.  For a passing test iteration, this number should be equal
      to listen for
   flooded frames. the number of frames transmitted by port 2.

      The algorithm for flood count on port 1 during the test is as follows:

   BEGIN
      Set Initial Value portion of N to user specified number, where N is each test.
      If the number is non-zero, this is an indication of addresses to be verified the DUT/SUT
      flooding a frame in each iteration
    WHILE NOT Finished DO
      PAUSE for which the aging time specified
      Address learning:  Port 1 sends N frames with varying
         source addresses to Port 2 to attempt to fill destination address is not in the DUT/SUT
      address table table.

      The flood count on port 3.  If the value is not zero, then this
      indicates that for Port #1.
      Controlling:  Port 2 sends N frames with varying that test iteration, the DUT/SUT could not
      determine the proper destination addresses corresponding to Port 1.
      IF (Port 3 received a port for that many frames.  In
      other words, the DUT/SUT flooded the frame during Control phase) OR
         (Port 1 did not receive to all ports since its
      address table was full.

5.10 Address Learning Rate

5.10.1 Objective

   To determine the correct # rate of frames)
      THEN
         Address Table address learning of a LAN switching device
   as defined in RFC 2285, section 3.8.2.

5.10.2 Setup Parameters

   The following parameters MUST be defined.  Each variable is
   configured with the following considerations.

     Age Time - The maximum time that a DUT/SUT was full
         Set N will keep a learned
     address in its forwarding table.

     Initial Addresses Learning Rate - The starting rate at which new
     addresses are offered to lower number (in binary search method)
      ELSE
         Address Table of the DUT/SUT was NOT full
         Set N to higher number (in binary search method)
      IF High and Low Values of N Meet
      THEN
         Test is Finished, Value be learned.

     Number of N equals Addresses - The number of addresses supported by DUT/SUT
      ELSE
         Continue Test
     END WHILE
   DONE
   Using a binary search approach, that the test targets DUT/SUT must
     learn.  The number MUST be between 1 and the exact maximum number
   of addresses
     supported per port with minimal test iterations. Due
   to the aging time of DUT/SUT address tables, each iteration may take
   some time during the waiting period for by the addresses implementation.  It is recommended no to clear. If
   possible, configure the DUT/SUT for a low value for the aging time.

   Once the high and low values of N meet, then exceed
     the threshold of address
   handling has been found.

   For this test, the caching capacity found in section 5.9

5.10.3 Procedure

   The aging time of the DUT/SUT MUST be known. Use a
short
   aging time if possible to reduce the time needed to run the test.  The aging time MUST be
   longer than the time necessary to produce
   packets frames at the specified
   rate.  If a low frame rate is used for the test, then it may be
   possible that sending a large amount of frames may actually take
   longer than the aging time. Keep

   This test SHOULD at a minimum be performed in mind
   that a three-port
   configuration as described below.

   This test MUST consist of a multiple of three ports.  Three ports
   are REQUIRED and MAY be expanded to fully utilized the DUT/SUT in
   increments of three.  Each group of three will contain a test actually sends twice as many frames
   block as described in section 5.9.

   An algorithm similar to the number
   of addresses being tested due one used to determine address caching
   capacity can be used to determine the address learning phase and rate.  This
   test iterates the rate at which address learning frames are offered
   by the
   controlling phase.

   Set test device connected to the initial value of addresses per port DUT/SUT.  It is recommended to a number
   slightly higher than
   set the number of addresses that offered to the DUT/SUT can
handle.
   This step primes the binary search and can reduce the number of
   iterations required in this test to determine the exact number supported.

   Set
   the forwarding maximum caching capacity.

   The address learning rate to a number that is reasonable to might be handled
   by determined for different numbers
   of addresses but in each test run, the DUT/SUT number MUST remain constant
   and one that is high enough so that SHOULD be equal to or less than the test
iterations are
   not too long. maximum address caching
   capacity.

5.10.4 Measurements

   Whether the offered addresses per port was successful forwarded
   without flooding at the offered learning rate.

5.10.5 Reporting format: format

   After the test is run, results for each iteration SHOULD be displayed
   in a table to include:

   --  the table:

      The number of addresses used for each test iteration.

   --  the frame rate iteration (fixed).

      The intended load used for each test iteration.

   --  number iteration (varied).

      Number of control test frames that were transmitted by test port number 2. Control
      This SHOULD match the number of addresses used for the test
      iteration.  Test frames are the frames sent with varying
      destination addresses to confirm that the DUT/SUT has learned
      all of the addresses for each test iteration.

   --  the number of frames received by test

      The flood count on port 2 during the control test portion of each test.
      If the number is non-zero, this is an indication of the DUT/SUT
      flooding a frame in which the destination address is not in the
      address table.

   --  the

      The number of frames that correctly forwarded to test port 1 received during
      the control test portion of the test. This number will include those frames which are
   Spanning tree frames. For a normal test iteration, this number SHOULD
   be equal to the number of frames transmitted by port 2 during the
   control phase.

   --  the number of  Received frames that test port 1 received during MUST have the control
   phase not including Spanning Tree or other non test generated frames.
   In all cases,
      correct destination MAC address and SHOULD match a signature
      field.  For a passing test iteration, this number SHOULD should be equal
      to the number of frames transmitted by port 2 2.

      The flood count on port 1 during the control phase test portion of the each test.

   --
      If the number is non-zero, this is an indication of frames test port 3 received during the control
phase
   of DUT/SUT
      flooding a frame in which the test. destination address is not in the
      address table.

      The flood count on port 3.  If the value is not zero, then this
      indicates that for that test iteration, the DUT/SUT could not
      determine the proper destination port for that many frames.  In
      other words, the DUT/SUT flooded the frame to all ports since its
      address table was full.

5.10   Address Learning Rate

Objective:

   Once the maximum number of addresses supported per port by the
DUT/SUT is
   known, the addressing learning rate (the rate at which the DUT/SUT
learns
   these addresses) can be determined.

Procedure:

   An algorithm similar to the one used to determine address caching
   capacity can be used to determine the address learning rate. This
   test iterates the rate at which address learning frames are offered
   by the test device connected to the DUT/SUT.  It is recommended to
set
   the number of addresses offered to the DUT/SUT in this test to the
   maximum caching capacity.  However, the address learning rate might
be
   determined for different numbers of addresses but in each test run,
   the number MUST remain constant.

   Initializing the forwarding rate primes the binary search algorithm
   and can help to shorten the overall test duration.

   A third port on the DUT/SUT MUST listen for flooded frames.

   In this test, the forwarding rate SHOULD be varied until a rate is
   found that is the threshold for the rate supported by the DUT/SUT. It
   may be useful to pick a value slightly higher than the advertised
   forwarding rate.

Reporting format:

   To be done.

Section

6. Security Considerations

   This document does not yet address Security Considerations.

Section

7. Authors' Address

   Robert Mandeville
   European Network Laboratories (ENL)
   2, rue Helene Boucher
   87286 Guyancourt Cedex
   France

   Phone: + 33 1 39 44 12 05
   EMail: bob@enl.net

   Judy Keene

   Jerry Perser
   Netcom Systems
   20550 Nordhoff St.
   Chatsworth, CA 91311
   USA

   Phone: +1 + 1 818 700 5100
   Email: judy_keene@netcomsystems.com jerry_perser@netcomsystems.com

Appendix A:  Formulas

A.1 Calculating the Interburst InterBurst Gap

   IBG is defined in RFC 2285 as the interval between two bursts.  To
   achieve a function of maximum media rate (also
   known as line rate), desired load, the length of follow Input Parameter need to be
   defined:

     LENGTH - Frame size in bytes including the frames CRC.

     LOAD   - The intended load in the bursts with the
   preamble and the interframe gap (IFG), the percent.  Range is 0 to 100.

     BURST  - The number of frames in the
bursts,
   and burst (integer value).

     SPEED  - media's speed in bits/sec
                 Ethernet is 10,000,000 bits/sec
                 Fast Ethernet is 100,000,000 bits/sec
                 Gigabit Ethernet is 1,000,000,000 bits/sec

     DUPLEX - A constant to adjust the intended load.

   Using transmit rate for full or half
              duplex mode.  In full duplex the burst size, frame size and value is 100, in half
              duplex the load per port, value is 200.

     IFG    - A constant 96 bits for the minimum interframe gap.

   The IBG (in seconds) can be calculated:

     Burst size

          (DUPLEX/LOAD - 1) * ((preamble 64 + (frame size BURST * 8 bits) (IFG + 96 IFG bit
times))
             * 1 (for full duplex) or .5 (for half duplex)
            (10 bit times equal 1 microsecond)

   Example:

      Burst size = 24
      Frame size = 64

        24 * (64 + 64*8 8*LENGTH)] + 96) = 24 * (672) = 16,128 bit/times =
                                                 1612.8 us IFG
   IBG

   In half duplex mode, exactly half of = ----------------------------------------------------------
                                  SPEED

A.2 Calculating the target load SHOULD be sent
   to each Number of Bursts for the ports under test. For example, with a 100% load Test Duration

   The number of
   64-byte frames, the target load burst for each port under the test duration is 7440 rounded up to the
nearest
   integer number.  The follow Input Parameter need to be defined:

     LENGTH - Frame size in bytes including the CRC.

     BURST  - The number of frames received in the burst (integer value).

     SPEED  - media's speed in bits/sec
                 Ethernet is 10,000,000 bits/sec
                 Fast Ethernet is 100,000,000 bits/sec
                 Gigabit Ethernet is 1,000,000,000 bits/sec

     IFG    - A constant 96 bits for the minimum interframe gap.

     IBG    - Found in the above formula
    DURATION - Test duration in seconds.

   An intermediate number of the Burst duration needs to be calculated
   first:

                 IFG*(BURST-1) + BURST*(64 + 8*LENGTH)
    TXTIME  =  -----------------------------------------
                               SPEED

   Number of Burst for the Test Duration (rounded up):

                     DURATION
    #OFBURSTS =   --------------
                  (TXTIME + IBG)

   Example:

     LENGTH   = 64  bytes per second and 7440 frame
     LOAD     = 100 % offered load
     BURST    = 24  frames transmitted per second
   (for 10Mbps Ethernet).

   Recommended characteristic values for burst size are:

2       15      60      240     930
3       16      62      248
4       20      80      310
5       24      93      372
6       30      120     465
8       31      124     496
     SPEED    = 10      40      155     620
12      48      186     744  Mbits/sec (Ethernet)
     DUPLEX   = 200 (half duplex)
     DURATION = 10  seconds test

       IBG       = 1612.8 uS
         TXTIME    = 1603.2 uS
       #OFBURSTS = 3110