rfc957.txt

RFC 相关的技术文档




RFC 957                                                   September 1985
Experiments in Network Clock Synchronization


   ARPANET gateways of the WIDEBAND/EISN satellite system were also
   included in the experiments in order to determine the feasability of
   synchronizing clocks across the ARPANET.

   There were four principal issues of interest in the experiments:

      1.  What are the factors affecting accuracy of a network of clocks
          using the power grid as the basic timing source, together with
          corrections broadcast from a central point?

      2.  What are the factors affecting accuracy of a network of clocks
          synchronized via links used also to carry ordinary data.

      3.  How does the accuracy of the various radio clocks - WWVB, GOES
          and WWV compare?

      4.  What is the best way to handle disruptions, such as a leap
          second?

   These issues will be discussed in turn after presentation of the
   experiment design and execution.

4.1.  Experiment Design

   Figure 2 shows the configuration used in a series of tests conducted
   during late June and early July of 1985.  The tests involved six
   hosts, three reference clocks and several types of communication
   links.  The tests were designed to coincide with the insertion of a
   leap second in the standard time broadcast by NBS, providing an
   interesting test of system stability in the face of such disruptions.
   The test was also designed to test the feasability of using the power
   grid as a reference clock, with corrections broadcast as described
   above, but not used to adjust the local clock.
















Mills                                                          [Page 11]



RFC 957                                                   September 1985
Experiments in Network Clock Synchronization


      ARPAnet                              |                      
      - - - - - - - - - - - - - - - - - -  |  - - - - - - - - - - 
                                       56K |                      
      +---------+     +---------+     +----+----+ 1.2 +---------+ 
      |   WWV   | 1.2 |         | 4.8 |         +-----+  WWVB   | 
      |  radio  +-----+  DCN6   +-----+  DCN1   |async|  radio  | 
      |  clock  |async|         |DDCMP|         +--+  |  clock  | 
      +---------+     +---------+     +----+----+  |  +---------+ 
                       Ethernet            |       |              
      DCnet     ===o===============o=======o===    | 1822/DH      
                   |               |               |              
              +----+----+     +----+----+     +----+----+         
      power   |         |     |         |     |         |    power
      freq <--+  DCN3   |     |  DCN5   |     |  DCN7   +--> freq 
      60 Hz   |         |     |         |     |         |    60 Hz
              +---------+     +----+----+     +---------+         
                               9.6 |                              
      - - - - - - - - - - - - - -  |  - - - - - - - - - - - - - - 
                                   | DDCMP                        
                              +----+----+     +---------+         
                              |         | 1.2 |  GOES   |         
      FORDnet                 |  FORD1  +-----+satellite|         
                              |         |async|  clock  |         
                              +---------+     +---------+         

                    Figure 2. Network Configuration

   Only those hosts and links directly participating in the tests are
   shown in Figure 2.  All hosts shown operate using the DCnet protocols
   and timekeeping algorithms summarized in this document and detailed
   in [5].  The DCnet hosts operate as one self-contained net of the
   Internet systems, while the FORDnet hosts operate as another with
   distinct net numbers.  The gateway functions connecting the two nets
   are distributed in the DCN5 and FORD1 hosts and the link connecting
   them.  This means that, although the clock offsets of individual
   DCnet hosts are visible to other DCnet hosts and the clock offsets of
   individual FORDnet hosts are visible to other FORDnet hosts, only the
   clock offset of the gateway host on one net is visible to hosts on
   the other net.

   In Figure 2 the links are labelled with both the intrinsic speed, in
   kilobits per second, as well as the link protocol type.  The DDCMP
   links use microprocessor-based DMA interfaces that retransmit in case
   of message failure.  The 1822/DH link connecting DCN1 and DCN7
   operates at DMA speeds over a short cable.  The Ethernet link uses




Mills                                                          [Page 12]



RFC 957                                                   September 1985
Experiments in Network Clock Synchronization


   DMA interfaces that retransmit only in case of collisions.  The
   asynchronous links are used only to connect the reference clocks to
   the hosts over a short cable.

   While all hosts and links were carrying normal traffic throughout the
   test period, the incidence of retransmissions was very low, perhaps
   no more than a few times per day on any link.  However, the DDCMP
   link protocol includes the use of short control messages exhanged
   between the microprocessors about once per second in the absence of
   link traffic. These messages, together with retransmissions when they
   occur, cause small uncertaincies in Hello message delays that
   contribute to the total measurement error.  An additional uncertaincy
   (less than 0.5 per-cent on average) in Hello message length can be
   introduced when the link protocol makes use of character-stuffing or
   bit-stuffing techniques to achieve code transparency, such as with
   the LAPB link-level protocol of X.25.  However, the particular links
   used in the tests use a count field in the header, so that no
   stuffing is required.

   Although the timekeeping algorithms have been carefully designed to
   be insensitive to traffic levels, it sometimes happens that an
   intense burst of traffic results in a shortage of memory buffers in
   the various hosts.  In the case of the Ethernet interfaces, which
   have internal buffers, this can result in additional delays while the
   message is held in the interface pending delivery to the host.
   Conditions where these delays become significant occur perhaps once
   or twice a day in the present system and were observed occasionally
   during the tests.  As described above, the correction-sample
   processing incorporates a filtering procedure that discards the vast
   majority of glitches due to this and other causes.

4.2.  Experiment Execution

   The series of experiments conducted in late June and early July of
   1985 involved collecting data on the delays and offsets of the six
   hosts and three reference clocks shown in Figure 2.  In order to
   accomplish this, a special program was installed in a Unix 4.2bsd
   system connected to the Ethernet link but not shown in Figure 2.  The
   program collected each 128-octet Hello message broadcast from DCN1
   every 16 seconds and appended it bit-for-bit to the data base.  The
   total volume of raw data collected amounted to almost 0.7 megabyte
   per day.

   The raw Hello-message data were processed to extract only the
   timestamp and measured clock offsets for the hosts shown in Table 1
   and then reformatted as an ASCII file, one line per Hello message.



Mills                                                          [Page 13]



RFC 957                                                   September 1985
Experiments in Network Clock Synchronization


        Host    Clock   Drift   Experiment Use                 
        Name    ID      (ppm)                                  
        ------------------------------------------------------ 
        DCN1    WWVB    -2.5    WWVB reference host            
        DCN3    -       60-Hz   power-grid (unlocked)          
        DCN5    DCN1    6.8     Ethernet host                  
        DCN6    DCN1    -1.7    DDCMP host, WWV reference host 
        DCN7    DCN1    60-Hz   power-grid (locked)            
        FORD1   GOES    17.9    GOES reference host            
        WWV     -       -       WWV reference clock            
        WWVB    -       -       WWVB reference clock           

                       Table 1. Experiment Hosts

   In Table 1 the Clock ID column shows the reference host selected as
   the master clock for each host shown.  In this particular
   configuration host DCN1 was locked to host WWVB, while hosts DCN5,
   DCN6 and DCN7 were locked to DCN1.  Although the offset of GOES can
   not be directly determined from the Hello messages exchanged between
   DCnet and FORDnet hosts, the offset of FORD1 relative to GOES was
   determined by observation to be in the order of a millisecond, so for
   all practical purposes the offset of FORD1 represents the offset of
   GOES.  In addition, since the WWVB clock was considered by experience
   the most accurate and reliable and the offset of DCN1 relative to
   WWVB was negligible, DCN1 was considered the reference clock with
   offset zero relative to the NBS clocks.

   During the setup phase of the experiments the intrinsic drift rates
   of the crystal oscillators in the four hosts DCN1, DCN5, DCN6 and
   FORD1 equipped with them was measured as shown in the "Drift" column
   in Table 1.  The two hosts DCN3 and DCN7 are equipped with
   line-frequency clocks. For experimental purposes DCN3 was unlocked
   and allowed to free-run at the line-frequency rate, while DCN7
   remained locked.

   An ASCII file consisting of about 0.2 megabyte of reformatted data,
   was collected for each Universal-Time (UT) day of observation
   beginning on 28 June and continuing through 8 July.  Each file was
   processed by a program that produces an eight-color display of
   measured offsets as a function of time of observation.  Since the
   display technique uses a bit-map display and each observation
   overwrites the bit-map in an inclusive-OR fashion, the sample
   dispersion is immediately apparent. Over eight samples per pixel on
   the time axis are available in a 24-hour collection period.  On the
   other hand, the fine granularity of almost four samples per minute
   allows zooming the display to focus on interesting short-term
   fluctuations, such as in the case of the WWV clock.


Mills                                                          [Page 14]



RFC 957                                                   September 1985
Experiments in Network Clock Synchronization


4.3.  Discussion of Results

   Each of the four previously mentioned issues of interest will be
   discussed in following subsections.

4.3.1.  On Power-Grid Clocks

   Telephone interviews with operators and supervisors of the Potomac
   Electric Power Company (PEPCO), the electric utility serving the
   Washington, DC, area, indicate that there are three major operating
   regions or grids, one east of the Rockies, a second west of the
   Rockies and a third in parts of Texas.  The member electric utilities
   in each grid operate on a synchronous basis, so that clocks anywhere
   within the grid should keep identical time.  However, in the rare
   case when a utility drops off the grid, no attempt is made to
   re-establish correct time upon rejoining the grrd.  In the much more
   common case when areas within the grid are isolated due to local
   thunderstorms, for example, clock synchronization is also disrupted.

   The experiments provided an opportunity to measure with exquisite
   precision the offset between a clock connected to the eastern grid
   (DCN3) and the NBS clocks.  The results, confirmed by the telephone
   interviews, show a gradual gain in time of between four and six
   seconds during the interval from about 1700 local time to 0800 the
   next morning, followed by a more rapid loss in time between 0800 and
   1700.  If the time was slewed uniformly throughout these extremes,
   the rate would be about 100 ppm.

   The actual slewing rates depend on the demand, which itself is a
   function of weather, day of the week and season of the year.  Similar
   effects occur in the western and Texas grids, with more extreme
   variations in the Texas grid due to the smaller inertia of the
   system, and less extreme variations in the western grid, due to
   smaller extremes in temperature, less total industrial demand and a
   larger fraction of hydro-electric generation.

   The uilities consider timekeeping a non-tariffed service provided as
   a convenience to the customer.  In the eastern grid a control station
   in Ohio manually establishes the baseline system output, which
   indirectly affects the clock offset and slewing rate.  The local time
   is determined at the control station with respect to a WWVB radio
   clock. The maximum slewing rate is specified as .025 Hz (about 400
   ppm), which is consistent with the maximum rates observed.  In the
   western grid the baseline system output is adjusted automatically
   using a servomechanism driven by measured offsets from the NBS
   clocks.