Network Working Group R. Mandeville
Request for Comments: 2285 European Network Laboratories
Category: Informational February 1998
Benchmarking Terminology for LAN Switching Devices
Status of this Memo
This memo provides information for the Internet community. It does
not specify an Internet standard of any kind. Distribution of this
memo is unlimited.
Copyright Notice
Copyright (C) The Internet Society (1998). All Rights Reserved.
Table of Contents
1. Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . 2
2. Existing definitions . . . . . . . . . . . . . . . . . . . . . . 2
3. Term definitions . . . . . . . . . . . . . . . . . . . . . . . . 3
3.1 Devices. . . . . . . . . . . . . . . . . . . . . . . . . . . 3
3.1.1 Device under test (DUT) . . . . . . . . . . . . . . . . 3
3.1.2 System under test (SUT) . . . . . . . . . . . . . . . . 3
3.2 Traffic orientation. . . . . . . . . . . . . . . . . . . . . 4
3.2.1 Unidirectional traffic. . . . . . . . . . . . . . . . . 4
3.2.2 Bidirectional traffic . . . . . . . . . . . . . . . . . 5
3.3 Traffic distribution . . . . . . . . . . . . . . . . . . . . 6
3.3.1 Non-meshed traffic. . . . . . . . . . . . . . . . . . . 6
3.3.2 Partially meshed traffic. . . . . . . . . . . . . . . . 7
3.3.3 Fully meshed traffic. . . . . . . . . . . . . . . . . . 8
3.4 Bursts . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
3.4.1 Burst . . . . . . . . . . . . . . . . . . . . . . . . . 9
3.4.2 Burst size . . . . . . . . . . . . . . . . . . . . . . 10
3.4.3 Inter-burst gap (IBG). . . . . . . . . . . . . . . . . 10
3.5 Loads . . . . . . . . . . . . . . . . . . . . . . . . . . . 11
3.5.1 Intended load (Iload) . . . . . . . . . . . . . . . . 11
3.5.2 Offered load (Oload) . . . . . . . . . . . . . . . . . 12
3.5.3 Maximum offered load (MOL) . . . . . . . . . . . . . . 13
3.5.4 Overloading . . . . . . . . . . . . . . . . . . . . . 14
3.6 Forwarding rates . . . . . . . . . . . . . . . . . . . . . 15
3.6.1 Forwarding rate (FR) . . . . . . . . . . . . . . . . . 15
3.6.2 Forwarding rate at maximum offered load (FRMOL). . . . 16
3.6.3 Maximum forwarding rate (MFR). . . . . . . . . . . . . 16
3.7 Congestion control . . . . . . . . . . . . . . . . . . . . 17
3.7.1 Backpressure . . . . . . . . . . . . . . . . . . . . . 17
3.7.2 Forward pressure . . . . . . . . . . . . . . . . . . . 18
Mandeville Informational [Page 1]RFC 2285 Benchmarking Terminology February 1998
3.7.3 Head of line blocking . . . . . . . . . . . . . . . . 19
3.8 Address handling . . . . . . . . . . . . . . . . . . . . . 20
3.8.1 Address caching capacity . . . . . . . . . . . . . . . 20
3.8.2 Address learning rate . . . . . . . . . . . . . . . . 20
3.8.3 Flood count . . . . . . . . . . . . . . . . . . . . . 21
3.9 Errored frame filtering . . . . . . . . . . . . . . . . . . 21
3.9.1 Errored frames . . . . . . . . . . . . . . . . . . . . 22
3.10 Broadcasts . . . . . . . . . . . . . . . . . . . . . . . . 22
3.10.1 Broadcast forwarding rate at maximum load . . . . . . 22
3.10.2 Broadcast latency . . . . . . . . . . . . . . . . . . 23
4. Security Considerations . . . . . . . . . . . . . . . . . . . . 24
5. References. . . . . . . . . . . . . . . . . . . . . . . . . . . 24
6. Acknowledgements. . . . . . . . . . . . . . . . . . . . . . . . 24
7. Author's Address. . . . . . . . . . . . . . . . . . . . . . . . 24
8. Full Copyright Statement. . . . . . . . . . . . . . . . . . . . 25
1. Introduction
This document is intended to provide terminology for the benchmarking
of local area network (LAN) switching devices. It extends the
terminology already defined for benchmarking network interconnect
devices in RFCs 1242 and 1944 to switching devices.
Although it might be found useful to apply some of the terms defined
here to a broader range of network interconnect devices, this RFC
primarily deals with devices which switch frames at the Medium Access
Control (MAC) layer. It defines terms in relation to the traffic put
to use when benchmarking switching devices, forwarding performance,
congestion control, latency, address handling and filtering.
2. Existing definitions
RFC 1242 "Benchmarking Terminology for Network Interconnect Devices"
should be consulted before attempting to make use of this document.
RFC 1944 "Benchmarking Methodology for Network Interconnect Devices"
contains discussions of a number of terms relevant to the
benchmarking of switching devices and should also be consulted.
For the sake of clarity and continuity this RFC adopts the template
for definitions set out in Section 2 of RFC 1242. Definitions are
indexed and grouped together in sections for ease of reference.
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.
Mandeville Informational [Page 2]RFC 2285 Benchmarking Terminology February 1998
3. Term definitions
3.1 Devices
This group of definitions applies to all types of networking devices.
3.1.1 Device under test (DUT)
Definition:
The network forwarding device to which stimulus is offered and
response measured.
Discussion:
A single stand-alone or modular unit which receives frames on one
or more of its interfaces and then forwards them to one or more
interfaces according to the addressing information contained in
the frame.
Measurement units:
n/a
Issues:
See Also:
system under test (SUT) (3.1.2)
3.1.2 System Under Test (SUT)
Definition:
The collective set of network devices to which stimulus is offered
as a single entity and response measured.
Discussion:
A system under test may be comprised of a variety of networking
devices. Some devices may be active in the forwarding decision-
making process, such as routers or switches; other devices may be
passive such as a CSU/DSU. Regardless of constituent components,
the system is treated as a singular entity to which stimulus is
offered and response measured.
Mandeville Informational [Page 3]RFC 2285 Benchmarking Terminology February 1998
Measurement units:
n/a
Issues:
See Also:
device under test (DUT) (3.1.1)
3.2 Traffic orientation
This group of definitions applies to the traffic presented to the
interfaces of a DUT/SUT and indicates whether the interfaces are
receiving only, transmitting only, or both receiving and
transmitting.
3.2.1 Unidirectional traffic
Definition:
When all frames presented to the input interfaces of a DUT/SUT are
addressed to output interfaces which do not themselves receive any
frames.
Discussion:
This definition conforms to the discussion in section 16 of RFC
1944 which describes how unidirectional traffic can be offered to
a DUT/SUT to measure throughput. Unidirectional traffic is also
appropriate for:
-the measurement of the minimum inter-frame gap -the creation of
many-to-one or one-to-many interface overload -the detection of
head of line blocking -the measurement of forwarding rates and
throughput when congestion control mechanisms are active.
When a tester offers unidirectional traffic to a DUT/SUT reception
and transmission are handled by different interfaces or sets of
interfaces of the DUT/SUT. All frames received from the tester by
the DUT/SUT are transmitted back to the tester from interfaces
which do not themselves receive any frames.
It is useful to distinguish traffic orientation and traffic
distribution when considering traffic patterns used in device
testing. Unidirectional traffic, for example, is traffic
orientated in a single direction between mutually exclusive sets
of source and destination interfaces of a DUT/SUT. Such traffic,
Mandeville Informational [Page 4]RFC 2285 Benchmarking Terminology February 1998
however, can be distributed between interfaces in different ways.
When traffic is sent to two or more interfaces from an external
source and then forwarded by the DUT/SUT to a single output
interface the traffic orientation is unidirectional and the
traffic distribution between interfaces is many-to-one. Traffic
can also be sent to a single input interface and forwarded by the
DUT/SUT to two or more output interfaces to achieve a one-to-many
distribution of traffic.
Such traffic distributions can also be combined to test for head
of line blocking or to measure forwarding rates and throughput
when congestion control mechanisms are active.
When a DUT/SUT is equipped with interfaces running at different
media rates the number of input interfaces required to load or
overload an output interface or interfaces will vary.
It should be noted that measurement of the minimum inter-frame gap
serves to detect violations of the IEEE 802.3 standard.
Issues:
half duplex / full duplex
Measurement units:
n/a
See Also:
bidirectional traffic (3.2.2)
non-meshed traffic (3.3.1)
partially meshed traffic (3.3.2)
fully meshed traffic (3.3.3)
congestion control (3.7)
head of line blocking (3.7.3)
3.2.2 Bidirectional traffic
Definition:
Frames presented to a DUT/SUT such that every receiving interface
also transmits.
Discussion:
This definition conforms to the discussion in section 14 of RFC
1944.
Mandeville Informational [Page 5]RFC 2285 Benchmarking Terminology February 1998
When a tester offers bidirectional traffic to a DUT/SUT all the
interfaces which receive frames from the tester also transmit
frames back to the tester.
Bidirectional traffic MUST be offered when measuring the
throughput or forwarding rate of full duplex interfaces of a
switching device.
Issues:
truncated binary exponential back-off algorithm
Measurement units:
n/a
See Also:
unidirectional traffic (3.2.1)
non-meshed traffic (3.3.1)
partially meshed traffic (3.3.2)
fully meshed traffic (3.3.3)
3.3 Traffic distribution
This group of definitions applies to the distribution of frames
forwarded by a DUT/SUT.
3.3.1 Non-meshed traffic
Definition:
Frames offered to a single input interface and addressed to a
single output interface of a DUT/SUT where input and output
interfaces are grouped in mutually exclusive pairs.
Discussion:
In the simplest instance of non-meshed traffic all frames are
offered to a single input interface and addressed to a single
output interface. The one-to-one mapping of input to output
interfaces required by non-meshed traffic can be extended to
multiple mutually exclusive pairs of input and output interfaces.
Measurement units:
n/a
Mandeville Informational [Page 6]RFC 2285 Benchmarking Terminology February 1998
Issues:
half duplex / full duplex
See Also:
unidirectional traffic (3.2.1)
bidirectional traffic (3.2.2)
partially meshed traffic (3.3.2.)
fully meshed traffic (3.3.3)
burst (3.4.1)
3.3.2 Partially meshed traffic
Definition:
Frames offered to one or more input interfaces of a DUT/SUT and
addressed to one or more output interfaces where input and output
interfaces are mutually exclusive and mapped one-to-many, many-
to-one or many-to-many.
Discussion:
This definition follows from the discussion in section 16 of RFC
1944 on multi-port testing. Partially meshed traffic allows for
one-to-many, many-to-one or many-to-many mappings of input to
output interfaces and readily extends to configurations with
multiple switching devices linked together over backbone
connections.
It should be noted that partially meshed traffic can load backbone
connections linking together two switching devices or systems more
than fully meshed traffic. When offered partially meshed traffic
devices or systems can be set up to forward all of the frames they
receive to the opposite side of the backbone connection whereas
fully meshed traffic requires at least some of the offered frames
to be forwarded locally, that is to the interfaces of the DUT/SUT
receiving them. Such frames will not traverse the backbone
connection.
Measurement units:
n/a
Issues:
half duplex / full duplex
Mandeville Informational [Page 7]RFC 2285 Benchmarking Terminology February 1998
See Also:
unidirectional traffic (3.2.1)
bidirectional traffic (3.2.2)
non-meshed traffic (3.3.1)
fully meshed traffic (3.3.3)
burst (3.4.1)
3.3.3 Fully meshed traffic
Definition:
Frames offered to a designated number of interfaces of a DUT/SUT
such that each one of the interfaces under test receives frames
addressed to all of the other interfaces under test.
Discussion:
As with bidirectional partially meshed traffic, fully meshed
traffic requires each one the interfaces of a DUT/SUT to both
receive and transmit frames. But since the interfaces are not
divided into groups as with partially meshed traffic every
interface forwards frames to and receives frames from every other
interface. The total number of individual input/output interface
pairs when traffic is fully meshed over n switched interfaces
equals n x (n - 1). This compares with n x (n / 2) such interface
pairs when traffic is partially meshed.
Fully meshed traffic on half duplex interfaces is inherently
bursty since interfaces must interrupt transmission whenever they
receive frames. This kind of bursty meshed traffic is
characteristic of real network traffic and can be advantageously
used to diagnose a DUT/SUT by exercising many of its component
parts simultaneously. Additional inspection may be warranted to
correlate the frame forwarding capacity of a DUT/SUT when offered
meshed traffic and the behavior of individual elements such as
input or output buffers, buffer allocation mechanisms, aggregate
switching capacity, processing speed or medium access control.
The analysis of forwarding rate measurements presents a challenge
when offering bidirectional or fully meshed traffic since the rate
at which the tester can be observed to transmit frames to the
DUT/SUT may be smaller than the rate at which it intends to
transmit due to collisions on half duplex media or the action of
congestion control mechanisms. This makes it important to take
account of both the intended and offered loads defined in sections
3.5.1.and 3.5.2 below when reporting the results of such
forwarding rate measurements.
Mandeville Informational [Page 8]RFC 2285 Benchmarking Terminology February 1998
When offering bursty meshed traffic to a DUT/SUT a number of
variables have to be considered. These include frame size, the
number of frames within bursts, the interval between bursts as
well as the distribution of load between incoming and outgoing
traffic. Terms related to bursts are defined in section 3.4
below.
Measurement units:
n/a
Issues:
half duplex / full duplex
See Also:
unidirectional traffic (3.2.1)
bidirectional traffic (3.2.2)
non-meshed traffic (3.3.1)
partially meshed traffic (3.3.2)
burst (3.4.1)
intended load (3.5.1)
offered load (3.5.2)
3.4 Bursts
This group of definitions applies to the intervals between frames or
groups of frames offered to the DUT/SUT.
3.4.1 Burst
Definition:
A sequence of frames transmitted with the minimum legal inter-
frame gap.
Discussion:
This definition follows from discussions in section 3.16 of RFC
1242 and section 21 of RFC 1944 which describes cases where it is
useful to consider isolated frames as single frame bursts.
Measurement units:
n/a
Issues:
Mandeville Informational [Page 9]RFC 2285 Benchmarking Terminology February 1998
See Also:
burst size (3.4.2)
inter-burst gap (IBG) (3.4.3)
3.4.2 Burst size
Definition:
The number of frames in a burst.
Discussion:
Burst size can range from one to infinity. In unidirectional
traffic as well as in bidirectional or meshed traffic on full
duplex interfaces there is no theoretical limit to burst length.
When traffic is bidirectional or meshed bursts on half duplex
media are finite since interfaces interrupt transmission
intermittently to receive frames.
On real networks burst size will normally increase with window
size. This makes it desirable to test devices with small as well
as large burst sizes.
Measurement units:
number of N-octet frames
Issues:
See Also:
burst (3.4.1)
inter-burst gap (IBG) (3.4.3)
3.4.3 Inter-burst gap (IBG)
Definition:
The interval between two bursts.
Discussion:
This definition conforms to the discussion in section 20 of RFC
1944 on bursty traffic.
Mandeville Informational [Page 10]RFC 2285 Benchmarking Terminology February 1998
Bidirectional and meshed traffic are inherently bursty since
interfaces share their time between receiving and transmitting
frames. External sources offering bursty traffic for a given
frame size and burst size must adjust the inter-burst gap to
achieve a specified average rate of frame transmission.
Measurement units:
nanoseconds
microseconds
milliseconds
seconds
Issues:
See Also:
burst (3.4.1)
burst size (3.4.2)
3.5 Loads
This group of definitions applies to the rates at which traffic is
offered to any DUT/SUT.
3.5.1 Intended load (Iload)
Definition:
The number of frames per second that an external source attempts
to transmit to a DUT/SUT for forwarding to a specified output
interface or interfaces.
Discussion:
Collisions on CSMA/CD links or the action of congestion control
mechanisms can effect the rate at which an external source of
traffic transmits frames to a DUT/SUT. This makes it useful to
distinguish the load that an external source attempts to apply to
a DUT/SUT and the load it is observed or measured to apply.
In the case of Ethernet an external source of traffic MUST
implement the truncated binary exponential back-off algorithm to
ensure that it is accessing the medium legally
Mandeville Informational [Page 11]RFC 2285 Benchmarking Terminology February 1998
Measurement units:
bits per second
N-octets per second
(N-octets per second / media_maximum-octets per second) x 100
Issues:
See Also:
burst (3.4.1)
inter-burst gap (3.4.3)
offered load (3.5.2)
3.5.2 Offered load (Oload)
Definition:
The number of frames per second that an external source can be
observed or measured to transmit to a DUT/SUT for forwarding to a
specified output interface or interfaces.
Discussion:
The load which an external device can be observed to apply to a
DUT/SUT may be less than the intended load due to collisions on
half duplex media or the action of congestion control mechanisms.
This makes it important to distinguish intended and offered load
when analyzing the results of forwarding rate measurements using
bidirectional or fully meshed traffic.
Frames which are not successfully transmitted by an external
source of traffic to a DUT/SUT MUST NOT be counted as transmitted
frames when measuring forwarding rates.
The frame count on an interface of a DUT/SUT may exceed the rate
at which an external device offers frames due to the presence of
spanning tree BPDUs (Bridge Protocol Data Units) on 802.1D-
compliant switches or SNMP frames. Such frames should be treated
as modifiers as described in section 11 of RFC 1944.
Offered load MUST be indicated when reporting the results of
forwarding rate measurements.
Mandeville Informational [Page 12]RFC 2285 Benchmarking Terminology February 1998
Measurement units:
bits per second
N-octets per second
(N-octets per second / media_maximum-octets per second) x 100
Issues:
token ring
See Also:
bidirectional traffic (3.2.2)
fully meshed traffic (3.3.3)
intended load (3.5.1)
forwarding rate (3.6.1)
3.5.3 Maximum offered load (MOL)
Definition:
The highest number of frames per second that an external source
can transmit to a DUT/SUT for forwarding to a specified output
interface or interfaces.
Discussion:
The maximum load that an external device can apply to a DUT/SUT
may not equal the maximum load allowed by the medium. This
will be the case when an external source lacks the resources
to transmit frames at the minimum legal inter-frame gap or when
it has sufficient resources to transmit frames below the
minimum legal inter-frame gap. Moreover, maximum load may vary
with respect to parameters other than a medium's maximum
theoretical utilization. For example, on those media employing
tokens, maximum load may vary as a function of Token Rotation
Time, Token Holding Time, or the ability to chain multiple
frames to a single token. The maximum load that an external
device applies to a DUT/SUT MUST be specified when measuring
forwarding rates.
Measurement units:
bits per second
N-octets per second
(N-octets per second / media_maximum-octets per second) x 100
Issues:
Mandeville Informational [Page 13]RFC 2285 Benchmarking Terminology February 1998
See Also:
offered load (3.5.2)
3.5.4 Overloading
Definition:
Attempting to load a DUT/SUT in excess of the maximum rate of
transmission allowed by the medium.
Discussion:
Overloading can serve to exercise buffers and buffer allocation
algorithms as well as congestion control mechanisms. The number
of input interfaces required to overload one or more output
interfaces of a DUT/SUT will vary according to the media rates of
the interfaces involved.
An external source can also overload an interface by transmitting
frames below the minimum inter-frame gap. A DUT/SUT MUST forward
such frames at intervals equal to or above the minimum gap
specified in standards.
A DUT/SUT using congestion control techniques such as backpressure
or forward pressure may exhibit no frame loss when a tester
attempts to overload one or more of its interfaces. This should
not be exploited to suggest that the DUT/SUT supports rates of
transmission in excess of the maximum rate allowed by the medium
since both techniques reduce the rate at which the tester offers
frames to prevent overloading. Backpressure achieves this purpose
by jamming the transmission interfaces of the tester and forward
pressure by hindering the tester from gaining fair access to the
medium. Analysis of both cases should take the distinction
between intended load (3.5.1) and offered load (3.5.2) into
account.
Measurement units:
bits per second
N-octets per second
(N-octets per second / media_maximum-octets per second) x 100
Issues:
Mandeville Informational [Page 14]RFC 2285 Benchmarking Terminology February 1998
See Also:
unidirectional traffic (3.2.1)
intended load (3.5.1)
offered load (3.5.2)
forwarding rate (3.6.1)
backpressure (3.7.1)
forward pressure (3.7.2)
3.6 Forwarding rates
This group of definitions applies to the rates at which traffic is
forwarded by any DUT/SUT in response to a stimulus.
3.6.1 Forwarding rate (FR)
Definition:
The number of frames per second that a device can be observed to
successfully transmit to the correct destination interface in
response to a specified offered load.
Discussion:
Unlike throughput defined in section 3.17 of RFC 1242, forwarding
rate makes no explicit reference to frame loss. Forwarding rate
refers to the number of frames per second observed on the output
side of the interface under test and MUST be reported in relation
to the offered load. Forwarding rate can be measured with
different traffic orientations and distributions.
It should be noted that the forwarding rate of a DUT/SUT may be
sensitive to the action of congestion control mechanisms.
Measurement units:
N-octet frames per second
Issues:
See Also:
offered load (3.5.2)
forwarding rate at maximum offered load (3.6.2)
maximum forwarding rate (3.6.3)
Mandeville Informational [Page 15]RFC 2285 Benchmarking Terminology February 1998
3.6.2 Forwarding rate at maximum offered load (FRMOL)
Definition:
The number of frames per second that a device can be observed to
successfully transmit to the correct destination interface in
response to the maximum offered load.
Discussion:
Forwarding rate at maximum offered load may be less than the
maximum rate at which a device can be observed to successfully
forward traffic. This will be the case when the ability of a
device to forward frames degenerates when offered traffic at
maximum load.
Maximum offered load MUST be cited when reporting forwarding rate
at maximum offered load.
Measurement units:
N-octet frames per second
Issues:
See Also:
maximum offered load (3.5.3)
forwarding rate (3.6.1)
maximum forwarding rate (3.6.3)
3.6.3 Maximum forwarding rate (MFR)
Definition:
The highest forwarding rate of a DUT/SUT taken from an iterative
set of forwarding rate measurements.
Discussion:
The forwarding rate of a device may degenerate before maximum load
is reached. The load applied to a device must be cited when
reporting maximum forwarding rate.
Mandeville Informational [Page 16]RFC 2285 Benchmarking Terminology February 1998
The following example illustrates how the terms relative to
loading and forwarding rates are meant to be used. In particular
it shows how the distinction between forwarding rate at maximum
offered load (FRMOL) and maximum forwarding rate (MFR) can be used
to characterize a DUT/SUT.
(A) (B)
Test Device DUT/SUT
Offered Load Forwarding Rate
------------ ---------------
(1) 14,880 fps - MOL 7,400 fps - FRMOL
(2) 13,880 fps 8,472 fps
(3) 12,880 fps 12,880 fps - MFR
Measurement units:
N-octet frames per second
Issues:
See Also:
offered load (3.5.2)
forwarding rates (3.6.1)
forwarding rate at maximum load (3.6.2)
3.7 Congestion control
This group of definitions applies to the behavior of a DUT/SUT when
congestion or contention is present.
3.7.1 Backpressure
Definition:
Any technique used by a DUT/SUT to attempt to avoid frame loss by
impeding external sources of traffic from transmitting frames to
congested interfaces.
Discussion:
Some switches send jam signals, for example preamble bits, back to
traffic sources when their transmit and/or receive buffers start
to overfill. Switches implementing full duplex Ethernet links may
use IEEE 802.3x Flow Control for the same purpose. Such devices
may incur no frame loss when external sources attempt to offer
traffic to congested or overloaded interfaces.
Mandeville Informational [Page 17]RFC 2285 Benchmarking Terminology February 1998
It should be noted that jamming and other flow control methods may
slow all traffic transmitted to congested input interfaces
including traffic intended for uncongested output interfaces.
A DUT/SUT applying backpressure may exhibit no frame loss when a
tester attempts to overload one or more of its interfaces. This
should not be interpreted to suggest that the interfaces of the
DUT/SUT support forwarding rates above the maximum rate allowed by
the medium. In these cases overloading is only apparent since
through the application of backpressure the DUT/SUT avoids
overloading by reducing the rate at which the tester can offer
frames.
Measurement units:
frame loss on congested interface or interfaces N-octet frames per
second between the interface applying backpressure and an
uncongested destination interface
Issues:
jamming not explicitly described in standards
See Also:
intended load (3.5.1)
offered load (3.5.2)
overloading (3.5.4)
forwarding rate (3.6.1)
forward pressure (3.7.2)
3.7.2 Forward pressure
Definition:
Methods which depart from or otherwise violate a defined
standardized protocol in an attempt to increase the forwarding
performance of a DUT/SUT.
Discussion:
A DUT/SUT may be found to inhibit or abort back-off algorithms in
order to force access to the medium when contention occurs. It
should be noted that the back-off algorithm should be fair whether
the DUT/SUT is in a congested or an uncongested state.
Transmission below the minimum inter-frame gap or the disregard of
flow control primitives fall into this category.
Mandeville Informational [Page 18]RFC 2285 Benchmarking Terminology February 1998
A DUT/SUT applying forward pressure may eliminate all or most
frame loss when a tester attempts to overload one or more of its
interfaces. This should not be interpreted to suggest that the
interfaces of the DUT/SUT can sustain forwarding rates above the
maximum rate allowed by the medium. Overloading in such cases is
only apparent since the application of forward pressure by the
DUT/SUT enables interfaces to relieve saturated output queues by
forcing access to the medium and concomitantly inhibiting the
tester from transmitting frames.
Measurement units:
intervals between frames in microseconds
intervals in microseconds between transmission retries during
16 successive collisions.
Issues:
truncated binary exponential back-off algorithm
See Also:
intended load (3.5.1)
offered load (3.5.2)
overloading (3.5.4)
forwarding rate (3.6.1)
backpressure (3.7.1)
3.7.3 Head of line blocking
Definition:
Frame loss or added delay observed on an uncongested output
interface whenever frames are received from an input interface
which is also attempting to forward frames to a congested output
interface.
Discussion:
It is important to verify that a switch does not slow transmission
or drop frames on interfaces which are not congested whenever
overloading on one of its other interfaces occurs.
Measurement units:
forwarding rate and frame loss recorded on an uncongested
interface when receiving frames from an interface which is also
forwarding frames to a congested interface.
Mandeville Informational [Page 19]RFC 2285 Benchmarking Terminology February 1998
Issues:
input buffers
See Also:
unidirectional traffic (3.2.1)
3.8 Address handling
This group of definitions applies to the address resolution process
enabling a DUT/SUT to forward frames to their correct destinations.
3.8.1 Address caching capacity
Definition:
The number of MAC addresses per n interfaces, per module or per
device that a DUT/SUT can cache and successfully forward frames to
without flooding or dropping frames.
Discussion:
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 that can be assigned per n interfaces, per module
and per chassis before a DUT/SUT begins flooding frames.
Measurement units:
number of MAC addresses per n interfaces, modules, or chassis
Issues:
See Also:
address learning rate (3.8.2)
3.8.2 Address learning rate
Definition:
The maximum rate at which a switch can learn new MAC addresses
without flooding or dropping frames.
Mandeville Informational [Page 20]RFC 2285 Benchmarking Terminology February 1998
Discussion:
Users may want to know how long it takes a switch to build its
address tables. This information is useful to have when
considering how long it takes a network to come up when many users
log on in the morning or after a network crash.
Measurement units:
frames with different source addresses per second
Issues:
See Also:
address caching capacity (3.8.1)
3.8.3 Flood count
Definition:
Frames forwarded to interfaces which do not correspond to the
destination MAC address information when traffic is offered to a
DUT/SUT for forwarding.
Discussion:
When recording throughput statistics it is important to check that
frames have been forwarded to their proper destinations. Flooded
frames MUST NOT be counted as received frames. Both known and
unknown unicast frames can be flooded.
Measurement units:
N-octet valid frames
Issues:
spanning tree BPDUs.
See Also:
address caching capacity (3.8.1)
3.9 Errored frame filtering
This group of definitions applies to frames with errors which a
DUT/SUT may filter.
Mandeville Informational [Page 21]RFC 2285 Benchmarking Terminology February 1998
3.9.1 Errored frames
Definition:
Frames which are over-sized, under-sized, misaligned or with an
errored Frame Check Sequence.
Discussion:
Switches, unlike IEEE 802.1d compliant bridges, do not necessarily
filter all types of illegal frames. Some switches, for example,
which do not store frames before forwarding them to their
destination interfaces may not filter over-sized frames (jabbers)
or verify the validity of the Frame Check Sequence field. Other
illegal frames are under-sized frames (runts) and misaligned
frames.
Measurement units:
n/a
Issues:
See Also:
3.10 Broadcasts
This group of definitions applies to MAC layer and network layer
broadcast frames.
3.10.1 Broadcast forwarding rate
Definition:
The number of broadcast frames per second that a DUT/SUT can be
observed to deliver to all interfaces located within a broadcast
domain in response to a specified offered load of frames directed
to the broadcast MAC address.
Discussion:
There is no standard forwarding mechanism used by switches to
forward broadcast frames. It is useful to determine the broadcast
forwarding rate for frames switched between interfaces on the same
card, interfaces on different cards in the same chassis and
Mandeville Informational [Page 22]RFC 2285 Benchmarking Terminology February 1998
interfaces on different chassis linked together over backbone
connections. The terms maximum broadcast forwarding rate and
broadcast forwarding rate at maximum load follow directly from the
terms already defined for forwarding rate measurements in section
3.6 above.
Measurement units:
N-octet frames per second
Issues:
See Also:
forwarding rate at maximum load (3.6.2)
maximum forwarding rate (3.6.3)
broadcast latency (3.10.2)
3.10.2 Broadcast latency
Definition:
The time required by a DUT/SUT to forward a broadcast frame to
each interface located within a broadcast domain.
Discussion:
Since there is no standard way for switches to process
broadcast frames, broadcast latency may not be the same on all
receiving interfaces of a switching device. The latency
measurements SHOULD be bit oriented as described in section 3.8
of RFC 1242. It is useful to determine broadcast latency for
frames forwarded between interfaces on the same card, on
different cards in the same chassis and on different chassis
linked over backbone connections.
Measurement units:
nanoseconds
microseconds
milliseconds
seconds
Issues:
See Also:
broadcast forwarding rate (3.10.1)
Mandeville Informational [Page 23]RFC 2285 Benchmarking Terminology February 1998
4. Security Considerations
Documents of this type do not directly effect the security of the
Internet or of corporate networks as long as benchmarking is not
performed on devices or systems connected to operating networks.
The document points out that switching devices may violate the IEEE
802.3 standard by transmitting frames below the minimum interframe
gap or unfairly accessing the medium by inhibiting the backoff
algorithm. Although such violations do not directly engender
breaches in security, they may perturb the normal functioning of
other interworking devices by obstructing their access to the medium.
Their use on the Internet or on corporate networks should be
discouraged.
5. References
[1] Bradner, S., "Benchmarking Terminology for Network
Interconnection Devices", RFC 1242, July 1991.
[2] Bradner, S., and J. McQuaid, "Benchmarking Methodology for
Network Interconnect Devices", RFC 1944, May 1996.
6. Acknowledgments
The Benchmarking Methodology Working Group of the IETF and
particularly Kevin Dubray (Bay Networks) are to be thanked for the
many suggestions they collectively made to help complete this
document. Ajay Shah (WG), Jean-Christophe Bestaux (ENL), Henry Hamon
(Netcom Systems), Stan Kopek (Digital) and Doug Ruby (Prominet) all
provided valuable input at various stages of this project.
Special thanks go to Scott Bradner for his seminal work in the field
of benchmarking and his many encouraging remarks.
7. Author's Address
Robert Mandeville
European Network Laboratories (ENL)
2, rue Helene Boucher
78286 Guyancourt Cedex
France
Phone: + 33 1 39 44 12 05
Mobile Phone + 33 6 07 47 67 10
Fax: + 33 1 39 44 12 06
EMail: bob.mandeville@eunet.fr
Mandeville Informational [Page 24]RFC 2285 Benchmarking Terminology February 1998
8. Full Copyright Statement
Copyright (C) The Internet Society (1998). All Rights Reserved.
This document and translations of it may be copied and furnished to
others, and derivative works that comment on or otherwise explain it
or assist in its implementation may be prepared, copied, published
and distributed, in whole or in part, without restriction of any
kind, provided that the above copyright notice and this paragraph are
included on all such copies and derivative works. However, this
document itself may not be modified in any way, such as by removing
the copyright notice or references to the Internet Society or other
Internet organizations, except as needed for the purpose of
developing Internet standards in which case the procedures for
copyrights defined in the Internet Standards process must be
followed, or as required to translate it into languages other than
English.
The limited permissions granted above are perpetual and will not be
revoked by the Internet Society or its successors or assigns.
This document and the information contained herein is provided on an
"AS IS" basis and THE INTERNET SOCIETY AND THE INTERNET ENGINEERING
TASK FORCE DISCLAIMS ALL WARRANTIES, EXPRESS OR IMPLIED, INCLUDING
BUT NOT LIMITED TO ANY WARRANTY THAT THE USE OF THE INFORMATION
HEREIN WILL NOT INFRINGE ANY RIGHTS OR ANY IMPLIED WARRANTIES OF
MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE.
Mandeville Informational [Page 25]
