rfc1242.txt

RFC 的详细文档！


RFC 1242                Benchmarking Terminology               July 1991


                an Ethernet on one side and a 56KB serial link on the
                other.  This is has also been referred to as the "fire
                hose effect".  Networks that make use of serial links
                between local high speed networks will usually have
                link speed mismatch at each end of the serial links.

        Measurement units:
                Ratio of input and output data rates.

        Issues:

        See Also:
                constant load (3.4)
                back-to-back (3.1)

3.10  MTU-mismatch behavior

        Definition:
                The network MTU (Maximum Transmission Unit) of the
                output network is smaller than the MTU of the input
                network, this results in fragmentation.

        Discussion:
                The performance of network devices can be significantly
                affected by having to fragment frames.

        Measurement units:
                Description of behavior.

        Issues:

        See Also:

3.11  Overhead behavior

        Definition:
                Processing done other than that for normal data frames.

        Discussion:
                Network devices perform many functions in addition
                to forwarding frames.  These tasks range from internal
                hardware testing to the processing of routing
                information and responding to network management
                requests.  It is useful to know what the effect of
                these sorts of tasks is on the device performance.
                An example would be if a router were to suspend
                forwarding or accepting frames during the processing
                of large routing update for a complex protocol like



Benchmarking Methodology Working Group                          [Page 7]

RFC 1242                Benchmarking Terminology               July 1991


                OSPF.  It would be good to know of this sort of
                behavior.

        Measurement units:
                Any quantitative understanding of this behavior is by
                the determination of its effect on other measurements.

        Issues:
                bridging and routing protocols
                control processing
                icmp
                ip options processing
                fragmentation
                error processing
                event logging/statistics collection
                arp

        See Also:
                policy based filtering (3.13)

3.12  Overloaded behavior

        Definition:
                When demand exceeds available system resources.

        Discussion:
                Devices in an overloaded state will lose frames.  The
                device might lose frames that contain routing or
                configuration information.  An overloaded state is
                assumed when there is any frame loss.

        Measurement units:
                Description of behavior of device in any overloaded
                states for both input and output overload conditions.

        Issues:
                How well does the device recover from overloaded state?
                How does source quench production effect device?
                What does device do when its resources are exhausted?
                What is response to system management in overloaded
                state?

        See Also:

3.13  Policy based filtering

        Definition:
                Filtering is the process of discarding received



Benchmarking Methodology Working Group                          [Page 8]

RFC 1242                Benchmarking Terminology               July 1991


                frames by administrative decision where normal
                operation would be to forward them.

        Discussion:
                Many network devices have the ability to be
                configured to discard frames based on a number
                of criteria.  These criteria can range from simple
                source or destination addresses to examining
                specific fields in the data frame itself.
                Configuring many network devices to perform
                filtering operations impacts the throughput
                of the device.

        Measurement units:
                n/a

        Issues:
                flexibility of filter options
                number of filter conditions

        See Also:

3.14  Restart behavior

        Definition:
                Reinitialization of system causing data loss.

        Discussion:
                During a period of time after a power up or
                reset, network devices do not accept and forward
                frames.  The duration of this period of unavailability
                can be useful in evaluating devices.  In addition,
                some network devices require some form of reset
                when specific setup variables are modified.  If the
                reset period were long it might discourage network
                managers from modifying these variables on production
                networks.

        Measurement units:
                Description of device behavior under various restart
                conditions.

        Issues:
                Types:
                        power on
                        reload software image
                        flush port, reset buffers
                        restart current code image, without reconfuration



Benchmarking Methodology Working Group                          [Page 9]

RFC 1242                Benchmarking Terminology               July 1991


                Under what conditions is a restart required?
                Does the device know when restart needed (i.e., hung
                        state timeout)?
                Does the device recognize condition of too frequent
                        auto-restart?
                Does the device run diagnostics on all or some resets?
                How may restart be initiated?
                        physical intervention
                        remote via terminal line or login over network

        See Also:

3.15  Router

        Definition:
                A system which forwards data frames based on
                information in the network layer.

        Discussion:
                This implies "running" the network level protocol
                routing algorithm and performing whatever actions
                that the protocol requires.  For example, decrementing
                the TTL field in the TCP/IP header.

        Measurement units:
                n/a

        Issues:

        See Also:
                bridge (3.2)
                bridge/router (3.3)

3.16  Single frame behavior

        Definition:
                One frame received on the input to a device.

        Discussion:
                A data "stream" consisting of a single frame can
                require a network device to do a lot of processing.
                Figuring routes, performing ARPs, checking
                permissions etc., in general, setting up cache entries.
                Devices will often take much more time to process a
                single frame presented in isolation than it would if
                the same frame were part of a steady stream.  There
                is a worry that some devices would even discard a single
                frame as part of the cache setup procedure under the



Benchmarking Methodology Working Group                         [Page 10]

RFC 1242                Benchmarking Terminology               July 1991


                assumption that the frame is only the first of many.

        Measurement units:
                Description of the behavior of the device.

        Issues:

        See Also:
                policy based filtering (3.13)

3.17  Throughput

        Definition:
                The maximum rate at which none of the offered frames
                are dropped by the device.

        Discussion:
                The throughput figure allows vendors to report a
                single value which has proven to have use in the
                marketplace.  Since even the loss of one frame in a
                data stream can cause significant delays while
                waiting for the higher level protocols to time out,
                it is useful to know the actual maximum data
                rate that the device can support.  Measurements should
                be taken over a assortment of frame sizes.  Separate
                measurements for routed and bridged data in those
                devices that can support both.  If there is a checksum
                in the received frame, full checksum processing must
                be done.

        Measurement units:
                N-octet input frames per second
                input bits per second

        Issues:
                single path vs. aggregate
                load
                unidirectional vs bidirectional
                checksum processing required on some protocols

        See Also:
                frame loss rate (3.6)
                constant load (3.4)
                back-to-back (3.1)







Benchmarking Methodology Working Group                         [Page 11]

RFC 1242                Benchmarking Terminology               July 1991


4.  Acknowledgements

   This memo is a product of the IETF BMWG working group:

        Chet Birger, Coral Networks
        Scott Bradner, Harvard University (chair)
        Steve Butterfield, independant consultant
        Frank Chui, TRW
        Phill Gross, CNRI
        Stev Knowles, FTP Software, Inc.
        Mat Lew, TRW
        Gary Malkin, FTP Software, Inc.
        K.K. Ramakrishnan, Digital Equipment Corp.
        Mick Scully, Ungerman Bass
        William M. Seifert, Wellfleet Communications Corp.
        John Shriver, Proteon, Inc.
        Dick Sterry, Microcom
        Geof Stone, Network Systems Corp.
        Geoff Thompson, SynOptics
        Mary Youssef, IBM

Security Considerations

   Security issues are not discussed in this memo.

Author's Address

   Scott Bradner
   Harvard University
   William James Hall 1232
   33 Kirkland Street
   Cambridge, MA 02138

   Phone: [phone]

   EMail: [e-mail]
   Or, send comments to: [e-mail].














Benchmarking Methodology Working Group                         [Page 12]