Slashdot Mirror
The History of Ethernet
Z34107 tips an article at Ars about the history of ethernet, from its humble beginnings at Xerox PARC in the mid-'70s, to its standardization and broad adoption, to the never-ending quest for higher throughput. Quoting:
"It's hard to believe now, but in the early 1980s, 10Mbps Ethernet was very fast. Think about it: is there any other 30-year-old technology still present in current computers? 300 baud modems? 500 ns memory? Daisy wheel printers? But even today, 10Mbps is not an entirely unusable speed, and it's still part of the 10/100/1000Mbps Ethernet interfaces in our computers. Still, by the early 1990s, Ethernet didn't feel as fast as it did a decade earlier. Consider the VAX-11/780, a machine released in 1977 by Digital Equipment Corporation. The 780 comes with some 2MB RAM and runs at 5MHz. Its speed is almost exactly one MIPS and it executes 1757 dhrystones per second. (Dhrystone is a CPU benchmark developed in 1984; the name is a play on the even older Whetstone benchmark.) A current Intel i7 machine may run at 3GHz and have 3GB RAM, executing nearly 17 million dhrystones per second. If network speeds had increased as fast as processor speeds, the i7 would today at least have a 10Gbps network interface, and perhaps a 100Gbps one."
...does not feel much faster than my MacPlus, because operating system and software makers managed to slow everything down again using "advanced software engineering techniques."
10Mbps was huge at the time. It was much faster (proportional to need) than any of the other components in a computer system. So it's not really surprising that it hasn't quite kept pace. Many home networks are still 10Mbps, and that's plenty for two or three computers.
Q: is there any other 30-year-old technology still present in current computers?
What about SCSI? or RS-232? not as omnipresent as Ethernet but still more or less common. Happy birthday Ethernet, but you are not the only remaining dinosaur...
Yea, I agree totally, we don't need fast processing or networking.... except for those times where we do. That's why I bought a car with a top speed of 30 miles per hour. I mean, I don't need a car that can go faster, except for when I'm driving on a road with a higher speed limit. In fact, I buy everything with a maximum capacity of my average use, rather than my peak use. That's why my house has zero bedrooms and zero bathrooms. I worked out the math, and I don't use either one of those stupid things anywhere near 50% of the time.
In the 1980s, ethernet tended to be over Thinnet or Thicknet. I seem to recall speeds of 1-3Mbps over those technologies. Twisted pair came out somewhere around 1990 at 10Mbps.
Today I mostly use 1Gps, but deal with servers that are 10G.40G and 100G will be standard in datacenters in a few years.
The blurb indicates that Ethernet is the only technology that we are using from 30 years ago. Back then all the machines I used had Memory, cpus, displays, and keyboards. The particualr technology changed - just like Ethernet technology's changes.
Where law ends, tyranny begins -- William Pitt
.... was the loading of a still image.
I disagree. I definitely remember seeing an animated line drawn porn movie being rendered on an EGA display in either '87 or '88. Granted this was the late '80s, but it was still the '80s. The scary thing is how well I can remember the images, including the blue colour palette.
I am Slashdot. Are you Slashdot as well?
Heck, the (quite definitely still extant) 1/4inch TRS jack was developed in 1878 for telephone exchange patch panels...
Not only had I been born, I had written a Basic program to generate D&D character stats by 1980. Yes, my PUBLIC elementary school had some forward thinking administrators.
There's really not much wrong with DHCP. Mature networks offer contracts with durations to clients and then honor them. This is to prevent the client from having to do expensive processing to deal with having the rug pulled out from under it, as well as a recognition that good networks don't just fall away on a whim. A lot needs to happen when an IP address changes, not the least of which is severing and rebuilding any active connections, which must invoke every application owning a connection. If you need to move clients around frequently, you're probably doing something wrong, but you can always reduce your lease time.
Someone had to do it.
Of course, 9600 baud was really fast back then, and some of them today use 115200 instead. You could crank a Unibus up to 9600 or maybe even 19200 if you had the I/O processor card (KMC?).
Bill Stewart
New Fast-Compression-only CPR http://preview.tinyurl.com/dy575ks
I'm with you. I think the guy's a genius. Better than the Recipie Troll, Helen Keller and the SCO licensing guy all rolled into one. Dr. Bob is funny, on-topic (in his hilariously off-topic way) and damn smart. Plus, he's somehow got a gift for frist-psotting, as well. I hope he keeps visiting us for a long time to come.
Mods, Dr. Bob deserves an "informative"!
When you give false hope to HIV sufferers then you are very likely to lead someone down a false path of recovery that could easily lead to that persons death.
You are worse than a troll. You are dangerous.
Don't know something? Look it up. Still don't know? Then ask.
Now this really dates me. But in 1975, I got a tour of Xerox PARC when I was taking a summer course in computer architecture at UC Santa Cruz. Alan Kay showed us some of the early Alto machines. They were still having trouble getting a smooth phosphor coating on the custom-made page-sized CRTs. We saw the PARC 3mb/s Ethernet, which Kay described as "an Alohanet with a captive ether," the first networked file server, and the first networked laser printer. It was clear this was the future, if the price could come down by about a factor of 10. Kay was hoping that some day a workstation might cost as little as a grand piano.
At Ford Aerospace, I was responsible for putting in the first Ethernet, around 1981. It was mostly "thick Ethernet" at 10mb/s. Ethernet cables weren't standard items, but Ford Aerospace routinely built cables for satellite ground stations, so we had the appropriate cables made up and pulled through the telephone ducts run through the building's concrete floors. I checked out a time-domain reflectometer from the measurement equipment pool and took a look at the cable. Cables ended in PL-239 coax connectors, and sections were joined with a barrel. The Ethernet tranceivers had SO-239 connectors on both ends, so the cable went through them. We used a vampire tap once or twice, but it didn't work out as well. The TDR showed a transceiver as generating almost no reflections. But bending the cable tighter than a 1' radius caused a noticeable impedance mismatch.
We were bothered that coax Ethernet wasn't a balanced system. There's a DC component to the signal, which means you can't use decoupling capacitors between sections to get rid of hum. We spent time on grounding issues and looked at the cable signal with scopes a lot. Repeaters were very expensive then, and we were trying to avoid them.
The network interfaces were mostly 3Com boards. Our original network consisted of a PDP 11/70, a PDP 11/45, a VAX 11/780, and a PDP 11/34 used as a gateway to a 9600 baud leased line "backbone link" to Ford HQ in Dearborn MI. We later added four Sun 2 workstations and a Sun server. Everything ran TCP/IP. Ford HQ had a similar link to Ford Aerospace in Colorado Springs,which had an ARPANET IMP. So we could get to the ARPANET over a 9600 baud shared backbone. We could FTP files instead of mailing tapes! I used to Telnet into Stanford's machines over that link.
I did a lot of work on 3COM's TCP/IP implementation, which originally was totally incapable of coping with a mix of speeds in the network. That's why I have those RFCs on network congestion with my name on them. This was before telephone de-regulation, and that 9600 baud leased line was expensive.
The article mentions that "There used to be a lot of fear, uncertainty, and doubt surrounding the performance impact of collisions." There was a period around 1984-1990 when coax Ethernet performance in practice was much worse than theory predicted. The problem was finally figured out by Wes Irish at Xerox PARC. It turns out that the defective design of a SEEQ Ethernet interface chip was causing the problem. As the state machine of the chip transitioned at the end of receiving a packet, there was a period of a few nanoseconds when the chip momentarily turned on the transmitter power, jamming the coax for a few nanoseconds. This reset the "quiet time" timer on all the other stations on the cable, causing them to ignore any following packet for several microseconds, after which they dropped back to the proper "look for sync" state. Back-to-back packets thus lost the second packet, which caused retransmissions and killed performance, but didn't show up as a "collision" to the controll
"By all means let's be open-minded, but not so open-minded that our brains drop out."
- Richard Dawkins
If all else fails, immortality can always be assured by spectacular error.
agreed, Dr. Bob is doing it right.
The only enhancement I can come up with would be to branch out into homepathy. That really gets the nerds in a lather.
the preceding comment is my own and in no way reflects the opinion of the Joint Chiefs of Staff
You're failing to see that there are times when that max speed is a byproduct of another useful feature. For instance, my car can top 250km/h and I will never get it anywhere near that speed. But I am capable of accelerating to get out of a tight spot when I am traveling 120. It is possible for me to overtake vehicles on a 2 lane road where my wife's 4 cylinder crossover could not. I am capable of pulling out into traffic and accelerating to flow of traffic on busy roads where my wife's vehicle couldn't. This is all because my car has the torque and gearing that comes with a >250km/h vehicle.
There are many times when mundane tasks such as running office application, browsing the web and watching videos run up against anemic system barriers. A netbook from 3 years ago should be able to do all of these things proficiently, but try copying a large amount of data from one Office program to another while having a few other programs running and you'll quickly hit your page file. How about watching a video while this is happening? Yes, all of these things still work on the anemic system, but sometimes it's worth the extra money to not be bogged down during the outliers.
They were essentially similar to early USB:
http://en.wikipedia.org/wiki/Transputer#Links
"The basic design of the transputer included serial links that allowed it to communicate with up to four other transputers, each at 5, 10 or 20 Mbit/s -- which was very fast for the 1980s. Any number of transputers could be connected together over even longish links (tens of metres) to form a single computing "farm"."
For a time in the 1980s, with five transputers (four borrowed), using a link endpoint to drive a robot, I had the fastest (or maybe second fastest) computer (cluster) on Princeton's University's campus (in a robotics lab I managed). But it was awkward to program it in Occam. And eventually I had to return the borrowed transputers.
What the transputers could have become... Sad they ended up in the dustbin of history...
A 21st century issue: the irony of technologies of abundance in the hands of those still thinking in terms of scarcity.