RFC 415 UNKNOWN PERFORMANCE · MEASUREMENT

Tenex bandwidth

A TENEX test of network throughput and the CPU used for transfers.

On rfc-editor.org ↗
PUBLISHED
November 1972
AUTHORS
H. Murray
STREAM
Legacy
SAMPLE SIZE
1 million bits
MAX BUFFERED REAL BAUD
61.1K
MIN UNBUFFERED REAL BAUD
12K
DOI
10.17487/RFC0415

RFC text

Original text · RFC Editor View on rfc-editor.org ↗
Network Working Group                                          H. Murray
Request for Comments: 415                    Stanford Research Institute
NIC: 392                                                29 November 1972


                            TENEX BANDWIDTH

   NIC 11584 (RFC 392) BY G. HICKS AND B. WESSLER AT UTAH RECENTLY
   DISCUSSED THE COST OF USING THE NETWORK.

   I WOULD LIKE TO TAKE THESE SAME TYPES OF NUMBERS AND LOOK AT THEM
   FROM ANOTHER POINT OF VIEW.  WITHOUT CALCULATING COSTS, LET US
   CONSIDER ULTIMATE PERFORMANCE OF THE HOSTS.  I WROTE A SIMPLE TENEX
   PROGRAM THAT SENT ITSELF STRINGS OVER THE NET.  IT USED BIN/BOUT AND
   THE BUFFERED SEND MODE.   IT COUNTED THINGS, BUT DID NOT PROCESS THE
   STRING.  WITH SAMPLES OF A MILLION BITS, THE FOLLOWING RESULTS WERE
   OBTAINED.

   BYTES/SIZE      REAL BAUD       CPU BAUD      CPU NEEDED

     50/36          48.8K           291K          16%
    100/36          46.5K           309K          15%
    200/36          52.7K           322K          16%
    400/36          59.3K           267K          22%
    800/36          61.1K           279K          21%

     50/8           22.0K           70K           31%
    100/8           26.7K           76K           35%
    200/8           29.0K           79K           36%
    400/8           30.0K           81K           37%
    800/8           31.9K           78K           40%
   1600/8           38.1K           64K           59%
   3200/8           41.8K           59K           70%

   THE FOLLOWING WERE OBTAINED BY USING SIN/SOUT WITHOUT THE BUFFERED
   MODE.

   BYTES/SIZE      REAL BAUD       CPU BAUD      CPU NEEDED
     50/36          36K             95K           38%
    100/36          44K             95K           45%
    200/36          49K             92K           53%
    400/36          54K             90K           60%

     50/8           12K             22K           57%
    100/8           16K             21K           75%
    200/8           18K             20K           92%
    400/8           20K             20K           99%
   THESE TESTS WERE RUN WITH NO OTHER LOAD ON OUR SYSTEM, AN EARLY
   VERSION OF 1.29.  THE INPUT AND OUTPUT HALVES OF THE TRANSMISSION
   HAVE BEEN AVERAGED TOGETHER.  I.E. THE ABOVE BAUD RATES WERE
   CALCULATED USING 2 MILLION BITS SINCE THE STRINGS WENT OUT AND IN.

OTHER PIECES OF DATA:

   OUR TTY'S AND LPT HAVE ULTIMATE CPU BANDWIDTHS NEAR 15-20 KB.  AT
   2400 BAUD, A TTY TAKES 15% OF THE CPU.  TELNETS NESTED THREE DEEP ARE
   ALMOST COMPUTE LIMITED WHEN JUST TYPING THINGS OUT ON A 2400 BAUD
   TERMINAL.

   AS A ROUGH CALCULATION, THE BANDWIDTH OF THE TIP TAPE TRANSMISSION
   FEATURE - USING STEVE BUTTERFIELD'S (OF BBN) NETMAG PROGRAM - IS
   ABOUT 7 KILOBITS/SEC.  ONE TAPE OF ABOUT 6,000 TENEX PAGES TOOK ABOUT
   4 HOURS TO TRANSMIT.  THIS WAS A FULL TAPE FROM ETAC TO CCA LATE ONE
   NIGHT WITH NOTHING ELSE RUNNING ON OUR SYSTEM.  ABOUT 30% OF THE CPU
   IS NEEDED TO MAINTAIN THIS BANDWIDTH.  AGAIN THIS IS ONLY ABOUT 20KB
   PER CPU SEC.


        [This RFC was put into machine readable form for entry]
    [into the online RFC archives by Helene Morin, Via Genie 12/99]

ISO Plain Language

On this page
PROBLEMThe author wanted to examine TENEX host performance during network transfers, rather than calculate transfer costs.
MECHANISMA simple program sent strings to itself over the network and counted throughput and CPU use for different byte sizes and transfer modes.
WHAT WAS MEASUREDThe tables show different real and CPU baud rates for buffered and unbuffered transfers under the reported test conditions.

§1Test Setup

The author describes a simple TENEX program that sent strings over the network to itself, using BIN/BOUT and buffered send mode. It counted data but did not process the strings. Samples contained one million bits.

The tests ran with no other load on the system, using an early version of TENEX 1.29. Input and output halves were averaged together, so reported baud rates used two million bits of combined traffic.

The test program sent data out and received it back without processing the contents. The reported rates combine the outgoing and returning data.

§2Buffered Transfer Results

With buffered send mode and 36-bit sizes, the table reports real baud rates from 46.5K to 61.1K and CPU baud rates from 267K to 322K. CPU needed ranges from 15% to 22% for those entries.

With buffered send mode and 8-bit sizes, real baud rates range from 22.0K to 41.8K, while CPU needed ranges from 31% to 70%. The table lists each tested byte size separately.

The buffered tests report different speeds and CPU use for different byte sizes. The values are measurements under the stated test conditions, not a guarantee for other systems.

§3Unbuffered Transfers and Other Comparisons

The second table uses SIN/SOUT without buffered mode. For 36-bit sizes, its real baud rates range from 36K to 54K and CPU needed ranges from 38% to 60%. For 8-bit sizes, real baud rates range from 12K to 20K and CPU needed ranges from 57% to 99%.

The RFC also reports that TTYs and line printers have ultimate CPU bandwidths near 15-20 KB, and that a TIP tape transmission using NETMAG was about 7 kilobits per second and used about 30% of the CPU.

The unbuffered table reports its own speeds and CPU use for each size. The RFC also gives comparison figures for local terminals, printers and a tape transfer.

§4References