draft-ietf-bmwg-lanswitch-00.txt   draft-ietf-bmwg-lanswitch-01.txt 
Expiration Date: January 1997 Network Working Group R. Mandeville
INTERNET-DRAFT European Network Laboratories
Expiration Date: May 1997 Nov 1996
Benchmarking Terminology for Local Area Switching Devices Benchmarking Terminology for LAN Switching Devices
<draft-ietf-bmwg-lanswitch-00.txt> < draft-ietf-bmwg-lanswitch-01.txt >
Status of this Document Status of this Document
This document is an Internet-Draft. Internet-Drafts are working documents This document is an Internet-Draft. Internet-Drafts are working documents
of the Internet Engineering Task Force (IETF), its areas, and its working of the Internet Engineering Task Force (IETF), its areas, and its working
groups. Note that other groups may also distribute working documents as 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 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 may be updated, replaced, or obsoleted by other documents at any time. It
skipping to change at line 30 skipping to change at line 32
To learn the current status of any Internet-Draft, please check the To learn the current status of any Internet-Draft, please check the
``1id-abstracts.txt'' listing contained in the Internet-Drafts Shadow ``1id-abstracts.txt'' listing contained in the Internet-Drafts Shadow
Directories on ds.internic.net (US East Coast), nic.nordu.net (Europe), Directories on ds.internic.net (US East Coast), nic.nordu.net (Europe),
ftp.isi.edu (US West Coast), or munnari.oz.au (Pacific Rim). ftp.isi.edu (US West Coast), or munnari.oz.au (Pacific Rim).
Distribution of this document is unlimited. Please send comments to Distribution of this document is unlimited. Please send comments to
bmwg@harvard.edu or to the editor. bmwg@harvard.edu or to the editor.
Abstract Abstract
The purpose of this draft is to extend the benchmarking terminology and The purpose of this draft is to define and discuss benchmarking terminology
methodology already defined for network interconnect devices in RFCs 1242 for local area switching devices. It is meant to extend the terminology
and 1944 by the Benchmarking Methodology Working Group (BMWG) of the already defined for network interconnect devices in RFCs 1242 and 1944 by
Internet Engineering Task Force (IETF) to address the specific requirements the Benchmarking Methodology Working Group (BMWG) of the Internet
of local area switches. Appendix A lists the tests and conditions that we Engineering Task Force (IETF).
believe should be included for specific cases and gives additional
information about testing practices.
Although switches have clearly evolved from bridges, they have matured LAN switches are one of the principal sources of new bandwidth in the local
enough in the last few years to deserve special attention. Switches are seen area and are handling a significantly increasing proportion of network
as one of the principal sources of new bandwidth in the local area and are traffic. The multiplicity of products brought to market makes it desirable
handling a significantly increasing proportion of network traffic. The to define a set of terms to be used when evaluating the performance
multiplicity of products brought to market makes it desirable to define a characteristics of local area switching devices. Well-defined terminology
set of benchmarks designed to provide reliable and comparable data to the will help in providing the user community with complete, reliable and
user community with which to evaluate the performance characteristics of comparable data on LAN switches.
switching devices.
1. Introduction 1. Introduction
The purpose of this draft is to discuss and define a number of terms and The purpose of this draft is to discuss and define terminology for the
procedures for benchmarking switches. This draft covers local area devices benchmarking of LAN switching devices. This draft covers local area devices
which switch frames at the Media Access Control (MAC) layer. Its intention which switch frames at the Media Access Control (MAC) layer. It discusses
is to describe a benchmarking methodology which fully exercizes local area throughput, latency, address handling and filtering.
switching devices at the MAC layer. It defines tests for throughput,
latency, address handling and filtering.
2. Term definitions 2. Term definitions
A previous document, "Benchmarking Terminology for Network Interconnect A previous document, "Benchmarking Terminology for Network Interconnect
Devices" (RFC 1242), defined many of the terms that are used in this Devices" (RFC 1242), defined many of the terms that are used in this
document. The terminology document should be consulted before attempting to document. The terminology document should be consulted before attempting to
make use of this document. A more recent document, "Benchmarking Methodology make use of this document. A more recent document, "Benchmarking Methodology
for Network Interconnect Devices" (RFC 1944), defined a number of test for Network Interconnect Devices" (RFC 1944), defined a number of test
procedures which are directly applicable to switches. Since it discusses a procedures which are directly applicable to switches. Since it discusses a
number of terms relevant to benchmarking switches it should also be consulted. number of terms relevant to benchmarking switches it should also be consulted.
skipping to change at line 104 skipping to change at line 101
Unidirectional traffic is made up of a single or multiple streams of frames Unidirectional traffic is made up of a single or multiple streams of frames
forwarded in one direction only from one or more ports of a switching device forwarded in one direction only from one or more ports of a switching device
designated as input ports to one or more other ports of the device designated as input ports to one or more other ports of the device
designated as output ports. designated as output ports.
Discussion: Discussion:
This definition conforms to the discussion in section 16 of RFC 1944 on This definition conforms to the discussion in section 16 of RFC 1944 on
multi-port testing which describes how unidirectional traffic can be offered multi-port testing which describes how unidirectional traffic can be offered
to ports of a device to measure maximum rate of throughput. to ports of a device to measure maximum rate of throughput.
With regard to benchmarking switching devices some additional applications Unidirectional traffic SHOULD be offered to devices for:
of unidirectional traffic are to be considered:
- the measurement of the minimum inter-frame gap - the measurement of the minimum inter-frame gap
- the detection of head of line blocking
- the measurement of throughput on ports when congestion control is activated
- the creation of many-to-one or one-to-many port overload - the creation of many-to-one or one-to-many port overload
- the measurement of the aggressivity of the back-off algorithm in the case - the detection of head of line blocking
of CSMA/CD devices - the measurement of throughput when congestion control mechanisms are active
A couple of these applications, head of line blocking and congestion control Unidirectional streams of traffic can be used to create different patterns
testing require unidirectional streams of traffic to be set up in a of traffic. For example unidirectional streams can be offered to two input
particular way between at least four ports with two streams running from one ports so as to overload a single output port (2-to-1) or they can be offered
of the input ports to two output ports and a third stream running between to a single input port and switched by the device under test to two or more
the second input port and one of the output ports. These streams can be output ports (1-to-2). Such patterns can be combined to test for head of
pictured as an inverted " Z " with input ports on the left and output ports line blocking or to measure throughput when congestion control mechanisms
on the right. are active.
Many-to-one overload requires a minimum to two input and one output ports When devices are equipped with ports running at different media rates the
when all ports run at the same speed. When devices are equipped with ports number of input streams required to load or overload an output port or ports
running at different speeds the number of ports required to overload an will vary.
output port or ports will vary.
Issues: Issues:
half duplex / full duplex half duplex / full duplex
Measurement units: Measurement units:
n/a n/a
See Also: See Also:
bidirectional traffic (2.3) bidirectional traffic (2.3)
multidirectional traffic (2.4) multidirectional traffic (2.4)
2.3. Bidirectional traffic 2.3. Bidirectional traffic
Definition: Definition:
Bidirectional traffic is made up of a single stream or multiple streams of Bidirectional traffic is made up of two or more streams of frames forwarded
frames forwarded in both directions between ports belonging to two distinct in opposite directions between at two or more ports of a switching device.
groups of ports on a switching device.
Discussion: Discussion:
This definition conforms to the discussions in sections 14 and 16 of RFC This definition conforms to the discussions in sections 14 and 16 of RFC
1944 on bidirectional traffic and multi-port testing. 1944 on bidirectional traffic and multi-port testing.
Bidirectional traffic MUST be offered when measuring the maximum rate of Bidirectional traffic MUST be offered when measuring the maximum rate of
throughput on full duplex ports of a switching device. throughput on full duplex ports of a switching device.
It is not recommended to offer bidirectional traffic to measure maximum
rates of throughput between isolated pairs of half duplex CSMA/CD ports
since the capture effect may result in one of the ports transmitting for
extended periods to the exclusion of the other port. The capture effect is
generally considered to be an anomalous ramification of the truncated binary
exponential back-off algorithm implemented in CSMA/CD devices.
Issues: Issues:
back-off truncated binary exponential back-off algorithm
Measurement units: Measurement units:
n/a n/a
See Also: See Also:
unidirectional traffic (2.2) unidirectional traffic (2.2)
multidirectional traffic (2.4) multidirectional traffic (2.4)
2.4. Multidirectional traffic 2.4. Multidirectional traffic
Definition: Definition:
Multidirectional traffic is made up of multiple streams of frames forwarded Multidirectional traffic is made up of streams of frames that are switched
between all of the ports of a switching device. simultaneously between multiple ports of a switching device. When such
streams are fully meshed each of the ports under test will both send frames
to and receive frames from all of the other ports under test.
Discussion: Discussion:
This definition extends the discussions in sections 14 and 16 of RFC 1944 on This definition extends the discussions in sections 14 and 16 of RFC 1944 on
bidirectional traffic and multi-port testing. bidirectional traffic and multi-port testing.
As with bidirectional multi-port tests, multidirectional traffic exercizes As with bidirectional multi-port tests, multidirectional traffic exercises
both the input and output sides of the ports of a switching device. But both the transmission and reception sides of the ports of a switching
since ports are not divided into two groups every port forwards frames to device. Since ports are not divided into two groups every port forwards
and receives frames from every other port. The total number of individual frames to and receives frames from every other port. The total number of
unidirectional streams offered in a multidirectional test for n switched individual unidirectional streams offered in a multidirectional test for n
ports equals n x (n - 1). This compares with n x (n / 2) such streams in a switched ports equals n x (n - 1). This compares with n x (n / 2) such
bidirectional multi-port test. It should be noted however that bidirectional streams in a bidirectional multi-port test. It should be noted however that
multiport tests create a greater load than multidirectional tests on bidirectional multiport tests create a greater load than multidirectional
backbone connections linking together two switching devices. Since none of tests on backbone connections linking together two switching devices because
the transmitted frames are forwarded locally all of the traffic is sent over none of the transmitted frames are forwarded locally. Backbone tests SHOULD
the backbone. Backbone tests SHOULD use bidirectional multiport traffic. use bidirectional multi-port traffic.
Multidirectional traffic is inherently bursty since ports must interrupt Multidirectional traffic on half duplex ports is inherently bursty since
transmission intermittently to receive frames. When offering such bursty ports must interrupt transmission intermittently to receive frames. When
traffic to a device under test a number of variables have to be defined. offering such bursty traffic to a device under test a number of variables
They include frame size, the number of frames within bursts as well as the have to be considered. They include frame size, the number of frames within
interval between bursts. The terms burst size and inter-burst gap are bursts as well as the interval between bursts. The terms burst, burst size
defined in sections 2.6 and 2.7 below. and inter-burst gap are defined in sections 2.5, 2.6 and 2.7 below.
Bursty multidirectional traffic exercizes many of the component parts of a Bursty multidirectional traffic is characteristic of real network traffic.
switching device simultaneously as they would be on a real network. It It simultaneously exercises many of the component parts of a switching
serves to determine the maximum throughput of a switching device when many device such as input and output buffers, buffer allocation mechanisms,
of its componenet parts are working at once. Complementary tests may single aggregate switching capacity, processing speed and behavior of the media
out the performance characteristics of particular parts such as buffer size, access controller.
backplane capacity, switching speed and the behavior of the media access
controller . These tests are detailed in the methodology sections below.
Measurement units: Measurement units:
n/a n/a
Issues: Issues:
half duplex / full duplex half duplex / full duplex
See Also: See Also:
unidirectional traffic (2.2) unidirectional traffic (2.2)
bidirectional traffic (2.3) bidirectional traffic (2.3)
target rate / target load (2.6)
2.5 Burst 2.5 Burst
Definition: Definition:
A frame or a group of frames transmitted with the minimum inter-frame gap A group of frames transmitted with the minimum inter-frame gap allowed by
allowed by the media. the media. This definition allows for single frame bursts and infinite bursts.
Discussion: Discussion:
This definition follows from the discussion in section 21 of RFC 1944. It is This definition follows from the discussion in section 21 of RFC 1944. It is
useful to consider isolated frames as single frame bursts. useful to consider isolated frames as single frame bursts.
Measurement units: Measurement units:
n/a n/a
Issues: Issues:
skipping to change at line 236 skipping to change at line 220
burst size (2.6) burst size (2.6)
2.6 Burst size 2.6 Burst size
Definition: Definition:
The number of frames in a burst. The number of frames in a burst.
Discussion: Discussion:
Burst size can range from one to infinity. In unidirectional streams there Burst size can range from one to infinity. In unidirectional streams there
is no theoretical limit to the burst length. Bursts in bidirectional and is no theoretical limit to the burst length. Bursts in bidirectional and
multidirectional streams of traffic are finite since ports interrupt multidirectional streams of traffic on half duplex media are finite since
transmission intermittantly to receive frames. In multidirectional networks ports interrupt transmission intermittently to receive frames.
bursts from several sources might be transmitted between ports at any one On real networks burst size can increase with window size. This makes it
time. This makes it desirable to test devices for large burst sizes. desirable to test devices with small as well as large burst sizes.
Measurement units: Measurement units:
number of N-octet frames number of N-octet frames
Issues: Issues:
See Also: burst (2.5) See Also: burst (2.5)
2.7 Inter-burst gap (IBG) 2.7 Inter-burst gap (IBG)
Definition: Definition:
The interval between two bursts. The interval between two bursts.
Discussion: Discussion:
This definition conforms to the discussion in section 20 of RFC 1944 on This definition conforms to the discussion in section 20 of RFC 1944 on
bursty traffic. bursty traffic.
Bidirectional and multidirectional streams of traffic are inherently bursty Bidirectional and multidirectional streams of traffic are inherently bursty
since ports share their time between receiving and transmitting frames. since ports share their time between receiving and transmitting frames. The
Assuming the number of frames per burst and frame length to be fixed, the rate of transmission of an external source of traffic is a function of the
value of the inter-burst gap will determine the rate of transmission. number of frames per burst, frame length and the inter-burst gap. External
External sources offering bursty multidirectional traffic for a given frame sources offering bursty multidirectional traffic for a given frame size and
size and burst size MUST adjust the inter-burst gap to achieve a specified burst size MUST adjust the inter-burst gap to achieve a specified rate of
rate of transmission. transmission.
When a burst contains a single frame inter-burst gap and inter-frame gap are When a burst contains a single frame inter-burst gap and inter-frame gap are
equal. equal.
When a burst is infinite the interburst gap equals the minimum inter-frame gap.
Measurement units: Measurement units:
nanoseconds nanoseconds
microseconds microseconds
miliseconds milliseconds
seconds seconds
Issues: Issues:
See Also: burst size (2.6), load (2.8) See Also: burst size (2.6), load (2.8)
2.8 Load 2.8 Load, nominal and real
Definition: Definition:
The amount of traffic per second going through the transmit and receive The amount of traffic per second that a port transmits and receives.
sides of a port.
Discussion: Discussion:
Load can be expressed in a number of ways: bits per second, frames per Load can be expressed in a number of ways: bits per second, frames per
second with the frame size specified or as a percentage of the maximum frame second with the frame size specified or as a percentage of the maximum frame
rate allowed by the media for a given frame size. For example, a rate allowed by the media for a given frame size. A unidirectional stream of
port-to-port unidirectional stream of 7440 64-byte Ethernet frames per 7440 64-byte Ethernet frames per second is equivalent to a 50% load given
second offers a 50% load on the receive side of the input port and a 50% that the maximum rate of transmission on an Ethernet is 14880 64-byte frames
load on the transmit side of the output port given that the maximum line per second.
rate on an Ethernet is 14880 frames per second. In the case of bidirectional In the case of bidirectional or multidirectional traffic port load is the
or multidirectional traffic port load is the sum of the frames received and sum of the frames transmitted and received on a port per second.
transmitted on a port per second.
There is room for varying the balance between incoming and outgoing traffic There is room for varying the balance between incoming and outgoing traffic
when loading ports with bidirectional and multidirectional traffic. In the when loading ports with bidirectional and multidirectional traffic. In the
case of port-to-port bidirectional traffic a 100% load can be created by case of bidirectional traffic a 100% load can be created by offering a n%
offering a n% load on the receive side of the input port and a (100 - n)% load on one port and a (100 - n)% load on the opposite port.
load on its transmit side. The output port will be offered the inverse load.
Multidirectional traffic will be equally distributed over all ports under Multidirectional traffic will be equally distributed over all ports under
test when port receive and transmit sides are offered 50% loads. When test when all ports are offered 50% of the target load.
benchmarking with balanced multidirectional loading ports under test MUST be It has to kept in mind that an external source may not deliver frames to a
offered an equally distributed load. device under test at the desired rate due to collisions on CSMA/CD links or
Target loads and actual loads may differ widely due to collisions on CSMA/CD the action of congestion control mechanisms. Because of this it is often
links or the action of congestion control mechanisms. External sources of necessary to distinguish between the desired or target load (nominal load)
Ethernet traffic MUST implement the truncated binary exponential back-off and the actual load (real load) offered to the device under test.
algorithm when executing bidirectional and multidirectional performance External sources of Ethernet traffic MUST implement the truncated binary
tests to ensure that the external source of traffic is not accessing the exponential back-off algorithm when executing bidirectional and
medium illegally. multidirectional performance tests to ensure that the external source of
traffic is accessing the medium legally.
Frames which are not successfully transmitted by the external source of Frames which are not successfully transmitted by the external source of
traffic to the device under test should be not counted as transmitted frames traffic to the device under test MUST NOT be not counted as transmitted
in performance benchmarks. frames in performance benchmarks.
Measurement units: Measurement units:
bits per second bits per second
N-octets per second N-octets per second
(N-octets per second / media_maximum-octets per second) x 100 (N-octets per second / media_maximum-octets per second) x 100
Issues: Issues:
token ring token ring
2.9 Overload 2.9 Overload
Definition: Definition:
Loading a port or ports in excess of the maximum line rate allowed by the media. Loading a port or ports in excess of the maximum rate of transmission
allowed by the media.
Discussion: Discussion:
Overloading can serve to test a device's buffer depth or congestion control Overloading can serve to exercise input and/or output buffers, buffer
mechanism. Unidirectional overloads require a minimum of two input and one allocation algorithms and congestion control mechanisms. Unidirectional
output ports when all ports run at the same nominal speed. Balanced overloads require a minimum of two input and one output ports when all ports
bidirectional and multidirectional overloading occur when the sum of the run at the same nominal speed.
traffic offered to the input and output sides of all ports exceeds the Bidirectional and multidirectional overloading occurs when the sum of the
maximum line rate allowed by the media by the same amount. traffic transmitted and received on each port exceeds the maximum media
rate. The external source of traffic MUST transmit at the same rate situated
between more than 50% and a 100% of the maximum media rate to each of the
ports under test in order to equally distribute an overload over all ports
under test.
Measurement units: Measurement units:
N-octet frames per second N-octet frames per second
Issues: target load and mesured load Issues: nominal/real load
See Also: See Also:
2.10 Speed 2.10 Speed
Definition: Definition:
A measure of switching throughput which records the maximum number of frames The number of frames that a device is capable of delivering to the correct
that a switched port is capable of receiving and/or transmitting per second. destination port in a given time interval. The maximum speed of a switching
device is the highest number of frames it can deliver during a one second
interval to the correct destination port.
Discussion: Discussion:
In multidirectional benchmarking it is important to record the speed at Switching devices which exhibit no frame loss may be found to deliver frames
which switching devices are able to forward frames to their destination to their proper destination ports at differing rates. This may be due to the
addresses. Speed can vary for a number of reasons such as head of line action of congestion control mechanisms at high loads or the relative
blocking, excessive collisions on CSMA/CD media, the action of congestion aggressiveness of the truncated binary back-off algorithm. Speed MUST only
control mechanisms at high loads or the backplane capacity of the switching be sampled on the output side of the ports under test. This is because an
device. The rate of throughput on token rings is mostly a function of the input port may receive frames at higher rates when the device under test
media acces controllers. drops frames.
The rate of throughput can be measured on the input as well as the output
sides of a port. The rate of throughput measured on the output side of a
port measures the rate at which a device forwards frames to their
destinations. This rate MUST be reported as the rate of throughput. The
aggregate rate of throughput can be skewed when a device drops frames since
the input port may receive at a much higher rate than it transmits.
Measurement units: Measurement units:
N-octet frames per second N-octet frames per second
Issues: Issues:
See Also: See Also:
2.11 Valid frame / invalid frame 2.11 Flooded frame
Definition: Definition:
A frame which is forwarded to its proper destination port based on MAC A unicast frame which is received on ports which do not correspond to the
address information is valid. A frame which is received on ports which do frame's destination MAC address information.
not correspond to the MAC address information is invalid.
Discussion: Discussion:
When recording throughput statistics it is important to check that frames When recording throughput statistics it is important to check that frames
have been forwarded to their proper desinations. Invalid frames are have been forwarded to their proper destinations. Flooded frames MUST NOT be
generally unknown unicast frames which the device under test forwards or counted as received frames.
floods to all ports.
Measurement units: Measurement units:
N-octet valid frames per second N-octet valid frames per second
Issues: Issues:
Spanning tree BPDUs. Spanning tree BPDUs.
See Also: See Also:
2.11 Backpressure 2.11 Backpressure
Definition: Definition:
A jamming technique used by some switching devices to avoid frame loss when A jamming technique used by some switching devices to avoid frame loss when
congestion on one or more of its ports occurs. one or more of its ports are saturated.
Discussion: Discussion:
Some switches are designed to send jam signals, for example preamble bits, Some switches are designed to send jamming signals back to traffic sources
back to traffic sources when their transmit and/or receive buffers start to when ports begin to saturate. Such devices may incur no frame loss when
overfill. Such devices may incur no frame loss when ports are offered target ports are offered target loads in excess of 100% by external traffic
loads in excess of 100% by external traffic sources. Jamming however affects sources. Jamming however affects traffic destined to congested as well as
traffic destined to congested as well as uncongested ports so it is uncongested ports so it is important to measure the maximum speed at which a
important to measure the maximum speed at which a jamming port can forward device can forward frames to both congested and uncongested ports when
frames to uncongested port destinations. backpressure mechanisms are active.
Measurement units: Measurement units:
N--octet frames per second between the jamming port and an uncongested N--octet frames per second between the jamming port and an uncongested
destination port destination port
Issues: Issues:
not explicitly described in standards not explicitly described in standards
See Also: See Also:
forward pressure (2.12) forward pressure (2.12)
2.12 Forward pressure 2.12 Forward pressure
Definition: Definition:
A technique which modifies the binary exponential backoff algorithm to avoid A technique which modifies the truncated binary exponential backoff
frame loss when congestion on one or more of its ports occurs. algorithm to avoid frame loss when congestion on one or more of the ports
under test occurs.
Discussion: Discussion:
Some switches avoid buffer overload by retransmitting buffered frames Some switches avoid buffer overload by retransmitting buffered frames
without waiting for the interval calculated by the normal operation of the without waiting for the interval calculated by the normal operation of the
backoff algorithm. It is important to measure how aggressive a switch's backoff algorithm. It is useful to measure how aggressive a switch's backoff
backoff algorithm is in both congested and uncongested states. Forward algorithm is in both congested and uncongested states. Forward pressure
pressure is manifested by lower numbers of collisions when congestion on a reduces the number of collisions when congestion on a port builds up.
port builds up.
Measurement units: Measurement units:
intervals in microseconds between transmission retries during 16 successive intervals in microseconds between transmission retries during 16 successive
collisions. collisions.
Issues: Issues:
not explicitly described in standards not explicitly described in standards
See also: See also:
backpressure (2.11) backpressure (2.11)
2.13 Head of line blocking 2.13 Head of line blocking
Definition: Definition:
A pathologocal state whereby a switch drops frames forwarded to an A pathological state whereby a switch drops frames forwarded to an
uncongested port whenever frames are forwarded from the same source port to uncongested port whenever frames are forwarded from the same source port to
a congested port. a congested port.
Discussion: Discussion:
It is important to verify that a switch does not propagate frame loss to It is important to verify that a switch does not propagate frame loss to
ports which are not congested whenever overloading on one of its ports occurs. ports which are not congested whenever overloading on one of its ports occurs.
Measurement units: Measurement units:
frame loss recorded on an uncongested port when receiving frames from a port frame loss recorded on an uncongested port when receiving frames from a port
which is also forwarding frames to a congested destination port. which is also forwarding frames to a congested destination port.
Issues: Issues:
Input buffers Input buffers
See Also: See Also:
2.14 Address handling 2.14 Address handling
Definition: Definition:
The number of different destination MAC addresses which a switch can learn. The number of MAC addresses per port, per module or per device which a
switch can cache and successfully forward frames to without flooding or
dropping frames.
Discussion: Discussion:
Users building networks will want to know how many nodes they can connect to Users building networks will want to know how many nodes they can connect to
a switch. This makes it necessary to verify the number of MAC addresses a switch. This makes it necessary to verify the number of MAC addresses that
that can be assigned per port, per module and per chassis before a switch can be assigned per port, per module and per chassis before a switch begins
begins flooding frames. flooding frames.
Measurement units: Measurement units:
number of MAC addresses number of MAC addresses
Issues: Issues:
See Also: See Also:
2.15 Address learning speed 2.15 Address learning rate
Definition: Definition:
The maximum rate at which a switch can learn MAC addresses before starting The maximum rate at which a switch can learn MAC addresses before starting
to flood frames. to flood or drop frames.
Discussion: Discussion:
Users may want to know how long it takes a switch to build up its address Users may want to know how long it takes a switch to build up its address
tables. This information may be useful for a user to have when considering tables. This information is useful to have when considering how long it
how a network comes up after a crash. takes a network to come up when many users log on in the morning or after a
network crash.
Measurement units: Measurement units:
frames per second with each successive frame sent to the switch containing a frames per second with each successive frame sent to the switch containing a
different source address. different source address.
Issues: Issues:
See Also: address handling (2.14) See Also: address handling (2.14)
2.16 Filtering illegal frames 2.16 Filtering illegal frames
Definition: Definition:
Switches do not necessarily filter all types of illegal frames. Some Switches do not necessarily filter all types of illegal frames. Some
switches, for example, do not store frames before forwarding them to their switches, for example, do not store frames before forwarding them to their
destination ports. These so-called cut-through switches forward frames after destination ports. These so-called cut-through switches forward frames after
reading the destination and source address fields. They do not normally reading the destination and source address fields. They do not normally
filter over-sized frames (jabbers) or verify the validity of the Frame Check filter over-sized frames (jabbers) or verify the validity of the Frame Check
Sequence field. Other illegal frame types are under-sized frames (runts), Sequence field. Other examples of illegal frame types are under-sized frames
misaligned frames and frames followed by dribble bits. (runts), misaligned frames and frames followed by dribble bits.
Measurement units: Measurement units:
N-octet frames filtered or not filtered N-octet frames filtered or not filtered
Issues: Issues:
See Also: See Also:
2.17 Broadcast latency 2.17 Broadcast rate
Definition:
The number of broadcast frames forwarded by the device under test per
second. The maximum broadcast rate corresponds to highest number of
broadcast frames a switch can forward either locally or over a backbone
connection.
Discussion:
There is no standard forwarding mechanism used by switches to forward
broadcast frames. It is useful to determine the broadcast forwarding rate
both locally and over backbone connections.
Measurement units:
N-octet frames per second
Issues:
See Also:
broadcast latency
2.18 Broadcast latency
Definition: Definition:
The time it takes a broadcast frame to go through a switching device and be The time it takes a broadcast frame to go through a switching device and be
forwarded to each destination port. forwarded to each destination port.
Discussion: Discussion:
Since there is no standard way for switches to process broadcast frames, Since there is no standard way for switches to process broadcast frames,
broadcast latency may not be the same on all receiving ports of a switching broadcast latency may not be the same on all receiving ports of a switching
device. Broadcast latency SHOULD be determined on all receiving ports. device. Broadcast latency SHOULD be determined on all receiving ports both
locally and, if applicable, over backbone connections.
Measurement units: Measurement units:
The latency measurements SHOULD be bit oriented as described in 3.8 of RFC The latency measurements SHOULD be bit oriented as described in 3.8 of RFC
1242 and reported for all connected receive ports. 1242 and reported for all connected receive ports.
Issues: Issues:
See Also: See Also:
broadcast rate
3. Editor's Address 3. Acknowledgments
In order of appearance Ajay Shah of Wandel & Goltermann, Jean-Christophe
Bestaux of European Network Laboratories, Stan Kopek of Digital Equipment
Corporation, Henry Hamon of Netcom Systems and Kevin Dubray of Bay Networks
were all instrumental in getting this draft done.
A special thanks goes to the IETF BenchMark WorkGroup for the many
suggestions it collectively made to help shape this draft.
The editor
Bob Mandeville
4. Editor's Address
Robert Mandeville Robert Mandeville
ENL (European Network Laboratories) ENL (European Network Laboratories)
email: bob.mandeville@eunet.fr email: bob.mandeville@eunet.fr
35, rue Beaubourg 35, rue Beaubourg
75003 Paris 75003 Paris
France France
phone: +33 07 47 67 10 phone: +33 6 07 47 67 10
fax: + 33 1 42 78 36 71 fax: + 33 1 42 78 36 71
Bob Mandeville !!!PLEASE TAKE NOTE!!!
ENL ENL HAS MOVED TO A NEW SITE:
Robert Mandeville, ENL
European Network Laboratories European Network Laboratories
office phone, fax and voice mail: +33 1 42 78 36 71 6 Parc Ariane, le Mercure
mobile phone: +33 07 47 67 10 Blvd des Chenes
78284 Guyancourt
France
NEW LAB PHONE, FAX, VOICE MAIL: +33 1 39 44 12 05
mobile phone: +33 6 07 47 67 10
 End of changes. 

This html diff was produced by rfcdiff 1.23, available from http://www.levkowetz.com/ietf/tools/rfcdiff/