Chapter 24½ The Interface Message Processor for the ARPA Computer Network 403
and implementation of protocols and techniques for the sensible utilization of the network by the Hosts.
Implementation of the subnet involves two major technical activities: providing 50-kilobit common-carrier circuits and the associated modems; and providing IMPs, along with software and interfaces to modems and Host computers. For reasons of economic and political convenience, ARPA obtained common- carrier circuits directly through government purchasing channels; AT&T (Long Lines) is the central coordinator, although the General Telephone Company is participating at some sites and other common carriers may eventually become involved. In January 1969, Bolt Beranek and Newman Inc. (BBN) began work on the design and implementation of IMPs; a four-node test network was scheduled for completion by the end of 1969 and plans were formulated to include a total often sites by mid-1970. This paper discusses the design of the subnet and describes the hardware, the software, and the predicted performance of the IMP. The issues of Host-to-Host protocol and network utilization are barely touched upon; these problems are currently being considered by the participating Hosts and may be expected to be a subject of technical interest for many years to come.
At this time, in late 1969, the test network has become an operating reality. IMPs have already been installed at four sites, and implementation of IMPs for six additional sites is proceeding. The common carriers have installed 50-kilobit leased service connecting the first four sites and are preparing to install circuits at six additional sites.
The design of the network allows for the connection of additional Host sites. A map of a projected eleven-node network is shown in Fig. 2. The connections between the first four sites are indicated by solid lines. Dotted lines indicate planned connections.
The design of the network is discussed in two parts. The first part concerns the relations between the Hosts and the subnet, and the second part concerns the design of the subnet itself.
The basic notion of a subnet leads directly to a series of questions
about the relationship between the Hosts and the subnet: What tasks shall
be performed by each? What constraints shall each place on the other? What
dependence shall the subnet have on the Hosts? In considering these questions,
we were guided by the following principles: (1) The subnet should function
as a communications system whose essential task is to transfer bits
reliably from a source location to a specified destination. Bit transmission
should be sufficiently reliable and error free to obviate the need for
special precautions (such as storage for retransmission) on the part of
the Hosts; (2) The average transit time through the subnet should be under
a half second to provide for convenient interactive use of remote computers;
(3) The subnet operation should be completely autonomous. Since the subnet
must function as a store and forward system, an IMP must not be dependent
upon its local Host. The IMP must continue to operate whether the Host
is functioning properly or not and must not depend upon a Host for buffer
storage or other logical assistance such as program reloading. The Host
computer must not in any way be able to change the logical characteristics
of the subnet; this restriction avoids the mischievous or inadvertent modification
of the communication system by an individual Host user; (4) Establishment
of Host-to-Host protocol and the enormous problem of planning to communicate
between different computers should be an issue separated from the subnet
Messages, Links, and RFNMs In principle, a single transmission from one Host to another may range from a few bits, as with a single teletype character, up to arbitrarily many bits, as in a very long file. Because of buffering limitations in the subnet, an upper limit was placed on the size of an individual Host transmission; 8095 bits was chosen for the maximum transmission size. This Host unit of transmission is called a message. The subnet does not impose any pattern restrictions on messages; binary text may be transmitted. Messages may be of variable length; thus, a source Host must indicate the end of a message to the subnet.
A major hazard in a message switched network is congestion, which
can arise either due to system failures or to peal traffic flow. Congestion
typically occurs when a destination IMP becomes flooded with incoming messages
for its Host. If the flow of messages to this destination is not regulated,
the congestion will back up into the network, affecting other IMPs and
previous | contents | next