Other articles in the series:
- History of the relay
- History of electronic computers
- History of the transistor
- Internet history
By the mid-1960s, the first time-sharing computing systems had broadly repeated the early history of the early telephone exchanges. Entrepreneurs created these switches to allow subscribers to use the services of a taxi, a doctor or a fire brigade. However, subscribers soon discovered that local switches were just as suitable for communicating and socializing with each other. Similarly, time-sharing systems, originally designed to let users "call" computing power for themselves, soon evolved into utility switches with built-in messaging. In the next decade, computers will go through another stage in the history of the telephone - the emergence of the interconnection of switches, forming regional and long-distance networks.
Protonet
The first attempt to combine several computers into a larger unit was the project of a network of interactive computers. , American air defense system. Since each of the 23 SAGE control centers covered a specific geographic area, a mechanism was needed to transfer radar traces from one center to another when foreign aircraft crossed the border between these areas. The SAGE developers called this problem "cross-telling", and they solved it by creating data lines based on dedicated AT&T telephone lines stretched between all neighboring control centers. Ronald Entiknap, who was part of a small delegation of the Royal Forces sent to SAGE, led the development and implementation of this subsystem. Unfortunately, I did not find a detailed description of the "inter-talk" system, but, apparently, the computer in each of the control centers determined the moment when the track on the radar moved to another sector, and sent its records over the telephone line to the computer of that sector, where it could be received operator monitoring the local terminal.
The SAGE system needed to translate digital data into an analog telephone line signal (and then back at the receiving station), which gave AT&T the opportunity to develop a "Bell 101" modem (or dataset, as it was first called) capable of transmitting a modest 110 bits per second. This device was later named , for its ability to modulate an analog telephone signal with a set of outgoing digital data, and demodulate bits from the incoming waveform.
Bell 101 data set
In doing so, SAGE laid an important technical foundation for later computer networks. However, the first computer network whose legacy was quite long and influential was the network with the name known today: ARPANET. Unlike SAGE, it brought together a motley set of computers, both time-sharing and batch processing, each with its own distinct set of programs. The network was conceived as universal in scale and operation, and had to satisfy any needs of users. The project was funded by the Information Processing Techniques Office (IPTO), headed by Director , which was the department of computer research at ARPA. But the very idea of ββsuch a network came up with the first director of this department, Joseph Carl Robnett Licklider.
Idea
How did we know , Licklider, or "Lick" to his colleagues, was a psychologist by training. However, when he was working on radar systems at Lincoln Lab in the late 1950s, he became fascinated with interactive computers. This passion led him to fund some of the early experiments in time-shared computers when, in 1962, he became director of the newly formed IPTO.
By then, he dreamed of being able to link isolated interactive computers into a larger superstructure. In his 1960 paper on "human-computer symbiosis", he wrote:
It seems reasonable to envision a "thinking center" that could incorporate the functions of modern libraries and the supposed breakthroughs in information storage and retrieval, as well as the symbiotic functions described above in this paper. This picture is easily scalable into a network of such centers, connected by broadband communication lines, and available to individual users through leased telephone lines.
Just as the TX-2 ignited Leek's passion for interactive computing, SAGE may have inspired him to imagine how different interactive computing centers could be interconnected and provide a kind of telephone network for intelligent services. Wherever the idea originated, Leek began spreading it around the community of researchers he created at IPTO, and the most famous of these messages was a memo dated April 23, 1963, addressed to "Members and Branches of the Intergalactic Computer Network", that is, various researchers who received IPTO funding for time-sharing computer access and other computing projects.
The note looks jumbled and chaotic, clearly dictated on the fly and has not been edited. Therefore, in order to understand what exactly Lik wanted to say about computer networks, one has to speculate a little. However, some points immediately stand out. First, Leek revealed that the "different projects" funded by IPTO actually belong to "the same area." After that, he discusses the need to allocate money and projects to maximize the benefits of this enterprise, since among the network of researchers, "in order to make progress, every active researcher requires a software base and equipment more complex and comprehensive than he himself can create in a reasonable time." Leek concludes that some personal concessions and sacrifices are required to achieve this global effectiveness.
He then proceeds to discuss computer (rather than social) networks in detail. He writes about the need for some kind of network management language (what would later be called a protocol) and his desire to someday see an IPTO computer network consisting of "at least four large computers, perhaps six to eight small computers, and a large assortment of disk and tape drives - not to mention remote consoles and teletype stations. Finally, he describes for several pages a specific example of how interaction with such a computer network may develop in the future. Lick imagines a situation in which he is analyzing some experimental data. βThe problem is,β he writes, βI donβt have a decent charting program. Is there a suitable program somewhere in the system? Using the doctrine of network dominance, I poll the local computer first, and then the other centers. Let's say I'm working at SDC and that I find a program that looks like it's on disk at Berkeley." He asks the network to execute this program, assuming that "with a sophisticated network management system, I won't have to decide whether to transfer data to programs to process it somewhere else, or download programs to myself and run them to work on my data."
Together, these fragments of ideas open up a larger scheme conceived by Licklider: first, to divide certain specialties and areas of expertise among researchers who receive funding from IPTO, and then build a physical network of IPTO computers based on this social community. This physical manifestation of the IPTO "common cause" will allow researchers to share knowledge and benefit from specialized hardware and software at each workplace. In this way, IPTO can avoid wasteful duplication while leveraging every dollar of funding by giving every researcher from all IPTO projects access to the full range of computing capabilities.
This idea of ββsharing resources among members of the research community through a communications network planted the seeds in IPTO that would sprout a few years later in the form of the ARPANET.
Despite its military origins, the ARPANET that appeared at the Pentagon had no military justification. It is sometimes said that this network was designed as a military-style communications network capable of surviving a nuclear attack. As we will see later, there is an indirect relationship between ARPANET and an earlier project with such a purpose, and ARPA leaders periodically talked about "fortified systems" to justify the existence of their network before Congress or the Secretary of Defense. But in fact, IPTO created ARPANET purely for its own internal needs, to support the research community - most of which could not justify their activity by working for defense purposes.
Meanwhile, at the time of the release of his famous memo, Licklider had already begun planning the embryo of his intergalactic network, of which from the University of California, Los Angeles (UCLA).
Console for SAGE model OA-1008, complete with light gun (at the end of the wire, under a transparent plastic cover), lighter and ashtray.
BACKGROUND
Kleinrock was the son of working-class Eastern European immigrants, and grew up in Manhattan in the shadows. [connects northern Manhattan Island in New York City and Fort Lee in Bergen County, New Jersey.]. While at school, he took extra classes in electrical engineering at the City College of New York in the evenings. Hearing of an opportunity to study at MIT followed by a full-time semester at Lincoln Lab, he jumped at it.
The laboratory was established to serve the needs of SAGE, but has since expanded into many other research projects, often only indirectly related to air defense, if at all related to defense. Among them was the Barnstable Research project, a concept proposed by the Air Force to create an orbital belt of metal strips (like ) that could be used as a global communications system. Kleinrock conquered authority from MIT, so he decided to concentrate on communication network theory. Barnstable's research gave Kleinrock the first opportunity to apply information theory and queuing theory to a data network, and he expanded this analysis into a full dissertation on messaging networks, combining mathematical analysis with experimental data collected from simulations running on TX-2 computers in laboratories. Lincoln. Among Kleinrock's close colleagues in the lab who shared time-sharing computers with him were ΠΈ which we will get to know a little later.
By 1963, Kleinrock had accepted a job offer at UCLA, and Licklider saw it as an opportunity. Before him was a data networking expert who worked near three local computer centers: the main computer center, the health computer center, and the Western Data Center (a cooperative of thirty institutes that shared an IBM computer). What's more, six institutes from the Western Data Center had a remote modem connection to the computer, and the computer of the IPTO-sponsored System Development Corporation (SDC) was only a few miles from Santa Monica. IPTO commissioned UCLA to combine these four centers as a first computer networking experiment. Later, according to the plan, the connection with Berkeley could study the problems inherent in data transmission over long distances.
Despite a promising situation, the project failed and the network was never built. The directors of the various UCLA centers did not trust each other and did not believe in this project, which is why they refused to cede control of computing resources to each other's users. IPTO had little to no leverage in this situation, since none of the data centers received money from ARPA. This political issue points to one of the major issues in the history of the Internet. If it is very difficult to convince different participants that the organization of communication between them and cooperation plays into the hands of all parties, it is very difficult, how did the Internet appear in the first place? In future articles, we will return to these questions more than once.
The second attempt by IPTO to build the network was more successful, perhaps because it was much smaller - it was a simple experimental test. And in 1965, a psychologist and student of Licklider named Tom Merrill left Lincoln Lab to try to capitalize on the hype about interactive computers by starting his own sharing business. However, after not getting enough paying clients, he began to look for other sources of income, and eventually invited IPTO to hire him to conduct research on computer networks. The new director of IPTO, Ivan Sutherland, decided to partner with a large and respected firm as ballast, and subcontracted the work to Merrill's company through the Lincoln Lab. From the laboratory side, another old colleague of Kleinrock, Lawrence (Larry) Roberts, was assigned to lead the project.
Roberts, as an MIT student, became proficient with the Lincoln Lab's TX-0 computer. He sat spellbound for hours in front of a glowing console screen, and ended up writing a program that (badly) recognized handwritten characters using neural networks. Like Kleinrock, he ended up working for the lab for post-graduate merit, solving computer graphics and vision problems such as edge recognition and 2D imaging on the larger, more powerful TX-XNUMX.
For most of 1964, Roberts mainly concentrated on image work. And then he met with Lik. In November of that year, he attended an Air Force-sponsored conference on the future of computers at a hot springs resort in Homestead, West Virginia. There, he talked until late at night with other conference participants, and for the first time he heard Lik expound his idea of ββ\u2b\uXNUMXban intergalactic network. Something stirred in Roberts' head - he was great at processing computer graphics, but, in fact, he was limited to one unique TX-XNUMX computer. Even if he could share his software, no one else would be able to use it because no one had the equivalent hardware to run it. The only way for him to expand the impact of his works was to talk about them in scientific papers, in the hope that someone could reproduce them somewhere else. He decided that Lick was rightβthe network was the next step needed to accelerate computer research.
And Roberts ended up working with Merrill, trying to link a TX-2 from Lincoln's lab across the country to an SDC computer in Santa Monica, California. In an experimental project that appears to have been copied from Lick's "intergalactic network" memo, they planned to have the TX-2 pause in the middle of a calculation, use the automatic dialer to call the SDC Q-32, run a matrix multiplication program on that computer, and then continue the original calculations using his answer.
In addition to the meaningfulness of using expensive and advanced technology to transmit the results of a simple mathematical operation across the entire continent, it is also worth noting the terribly slow speed of this process due to the use of the telephone network. To make a call, it was necessary to set up a dedicated connection between the caller and the called, which usually went through several different telephone exchanges. In 1965, almost all of them were electromechanical (it was in this year that AT&T launched the first all-electric station in Sakasuna, New Jersey). Magnets moved metal bars from one place to another to make contact at each node. The whole process took a few seconds, during which the TX-2 had to just sit and wait. In addition, the lines, which were excellent for conversations, were too noisy to transmit individual bits, and provided very little bandwidth (a couple of hundred bits per second). A truly effective intergalactic interactive network required a different approach.
The Merrill-Roberts experiment did not demonstrate the practicality or usefulness of the long-distance network, only its theoretical performance. But even that was enough.
Solution
In mid-1966 Robert Taylor became the new IPTO director, succeeding Ivan Sutherland. He was a student of Licklider, also a psychologist, and came to IPTO through his previous administration of computer science research at NASA. Apparently, almost immediately upon arrival, Taylor decided that the time had come to realize the dream of an intergalactic network; it was he who launched the project that gave birth to ARPANET.
Money from ARPA was still flowing in, so Taylor had no problem getting additional funding from his boss, Charles Hertzfeld. However, this decision had a significant risk of failure. In addition to the fact that in 1965 there were quite a few lines connecting the opposite ends of the country, no one had previously tried to do anything similar to the ARPANET. One may recall other early experiments in computer networking. For example, Princeton and Carnegie Mallon raised the grid of shared computers in the late 1960s with IBM. The main difference of this project was its homogeneity - it used absolutely the same hardware and software computers.
On the other hand, ARPANET would have to deal with diversity. By the mid-1960s, IPTO was funding more than ten organizations, each with a computer, all running different hardware and software. The ability to share software was rare even for different models of the same manufacturer - they decided to do this only with the latest IBM System / 360 line.
System diversity was a risk that added both significant technical complexity to network design and the possibility of Licklider-style resource sharing. For example, at the University of Illinois at that time, a massive supercomputer was being built with ARPA money. . It seemed unlikely to Taylor that the local users at Urbana-Campaign could fully utilize the resources of this huge machine. Even systems of a much more modest scale - TX-2 at Lincoln Lab and Sigma-7 at UCLA - usually could not share software with each other due to fundamental incompatibility. The ability to overcome these limitations by accessing one node's software directly from another was attractive.
In a paper describing this network experiment, Merrill and Roberts suggested that such an exchange of resources would lead to something like a Ricardian for computing nodes:
The arrangement of the network may lead to a certain specialization of cooperating nodes. If a certain node X, due to the presence of special software or hardware, for example, is especially good at matrix inversion, users of other nodes in the network can be expected to use this ability by inverting their matrices at node X, instead of doing it on their own. home computers.
Taylor had another motivation for implementing a shared network. Purchasing for each new IPTO node a new computer that had all the capabilities the researchers at that node could ever need was expensive, and as more nodes were added to the IPTO portfolio, the budget grew dangerously. By linking all IPTO-funded systems into one network, it will be possible to provide new grant recipients with more modest computers, or even not buy them at all. They could use the computing power they need at remote sites with surplus resources, and the entire network would operate as a public reservoir of software and hardware.
After launching the project and securing its funding, Taylor's last significant contribution to ARPANET was the selection of a person who would directly develop the system and see to it that it was implemented. Roberts was the obvious choice. His engineering skills were undeniable, he was already a respected member of the IPTO research community, and he was one of the few people with real experience in designing and building computer networks that operated over long distances. So in the fall of 1966, Taylor called Roberts and asked him to come over from Massachusetts to work on ARPA in Washington.
But it was difficult to seduce him. Many of IPTO's academic leaders were skeptical of Robert Taylor's rule, considering it to be lightweight. Yes, Licklider was also a psychologist, had no engineering background, but at least he had a Ph.D. and some credit as one of the founding fathers of interactive computers. Taylor was an unknown man with a master's degree. How will he be able to lead the complex technical work in the IPTO community? Roberts was also among these skeptics.
But the combination of the stick and the gingerbread did the trick (most sources point to the predominance of the sticks with little to no gingerbread). On the one hand, Taylor put some pressure on Roberts' boss at Lincoln's lab, reminding him that most of the lab's funding now came from ARPA, and that he should therefore convince Roberts of the benefits of this proposal. On the other hand, Taylor offered Roberts the newly created title of "Senior Scientist" who would report directly over Taylor's head to ARPA Deputy Director and also become Taylor's heir as Director. On these terms, Roberts agreed to take on the ARPANET project. It's time to turn the idea of ββsharing resources into reality.
What else to read
- Janet Abbate, Inventing the Internet (1999)
- Katie Hafner and Matthew Lyon, Where Wizards Stay Up Late (1996)
- Arthur Norberg and Julie O'Neill, Transforming Computer Technology: Information Processing for the Pentagon, 1962-1986 (1996)
- M. Mitchell Waldrop, The Dream Machine: JCR Licklider and the Revolution That Made Computing Personal (2001)
Source: habr.com