A long time ago, an acquaintance of mine was working part-time at a tool manufacturer that was running either AIX or HP-UX (I cannot recall which) that had an uptime of something like 11 years. I do not recall what they used it for, unfortunately.
Haha :) I always extend my respect for such stuff..
It just shows how everything is bloated and ballooned today..
You barelly can browse modern web with 32bit today..
VSZ hits the sky (3GB).
** 2023-07-14 18:38 PDT The DOS machine is getting DoSed. It's still beeping and happy but it's busy. **
This website is hosted on a 39 year old PCjr running at 4.77Mhz and it has been running over 2,500 hours continuously now. No reboots or program restarts ... you can see the current runtime stats by visiting http://brutmanlabs.org/status .
The machine specs are:
- IBM PCjr w/ NEC V20 CPU (the V20 gives a small speed bump compared to the original 8088)
- jrIDE sidecar providing expansion RAM to bring the system up to 736KB and an IDE port
- Kingston SSD w/ a Startech SATA-IDE bridge
- Parallel printer sidecar, modified to be bi-directional
- Xircom PE3-10BT Ethernet adapter hanging off of the parallel port
- IBM PC DOS 5.02 and mTCP HTTPServ
- APC UPS (45 watt power draw with networking equipment)
- Dynamic DNS is being handled by my home router, which forwards port 80 to the machine.
All of the upgrade parts are there for performance or convenience; you could use period correct parts and everything would work the same. (The IDE adapter would be a homebrew MFM adapter and you'd have to use something like a 3Com 3C503 on a bus adapter, but all of that existed in the mid 1980s when the machine was new.)
The web server is my own work, part of the mTCP project. Here are some of the features:
- serves HTTP 0.9, 1.0 and 1.1 requests to be friendly to vintage browsers
- Maps "normal" looking paths and resources to DOS 8.3 file format
- HTTP 1.1 requests can be pipelined.
- can serve up to 8 concurrent connections
- logging to local disk and over UDP
- can serve pre-compressed content
- basic auth
- runs on DOS 2.1 and up
- built in SNTP client for time syncing
Besides the UPS it needs the SNTP client to achieve long run times, otherwise dropped interrupts cause the machine to lose time. Without the SNTP client it was losing up to a few minutes per day depending on the system load. The SNTP client also helped it transition through the daylight savings time change in March.
The limiting factor is going to be disk space for logging; it is generating logs and eventually that disk partition will fill up. (I need to add log rotating and compression.) This machine was running when the ChatGPT client for DOS was announced, and it was hosting the mTCP networking pages at the time, so it got quite a bit of traffic. I learned after that to leave a lot of space for logs.
A PCjr? That somehow makes this more funny than if it was a 5150 or something (but equally impressive).
I remember playing around with Xircom parallel port ethernet adapters and TCP/IP packet drivers (and corresponding applications) in the 90s on an old 286 laptop I still had. Almost exclusively used it as a client, though. Good times.
I have a love/hate relationship with the Xircom adapter. It's portable and great for machines without ISA slots, but the max throughput is about 40KB/sec. A nice, real ISA card like a WD8003 can do over 100KB/sec on the same machine.
Hmm, I now have memories of both a parallel Xircom adapter, and just a null-modem connection with SLIP and PPP (pretty sure I used both). The Xircom adapter might have come after. Though with that, you'd get at most around 10kB/s (at 115200 baud), and that's assuming the 286 has a 16550A to begin with...
One of my friends was way ahead of the rest of us in 1987, and bought a V20 to upgrade his Tandy computer. He works for a telcom now. Nice to see one still churning away.
I bought my first NEC V20 in 1986 or 1987. It was my first time touching the motherboard of a computer which made it nerve wracking, but they were very popular at the time. I bought mine mail order through the Exec PC BBS, which I think was in Chicago.
Did you need to do anything extra for cooling? One thing that impressed me about old hardware that I did not appreciate back then is that the CPUs don't even need heatsinks. I imagine this PCjr don't have one either, but it's probably got a fan somewhere to circulate air through?
There is a fan internally in the machine, but it was placed to cool the 5.25" floppy drive when it was in use.
I have more open space in this machine because I am using a 3.5" drive instead. I also replaced the original fan with a quieter Noctua. The jrIDE is running naked on the side of the machine because I think it was having heat issues.
In a later iteration of this machine it will get more direct cooling; the slots in the case are kind of restrictive.
Yeah, far too much for a little CPU like this. Never mind the horror of trying to port all of the libraries and keep them up to date.
Although there are people are using Apache in front of their vintage computers to terminate SSL for them while still having the vintage computer handle the request.
That must have been a beefy 486, as I remember I had trouble getting a Pentium 100 Mhz Toshiba laptop to play mp3's on Linux kernel ver 2.4, and it could only do so from the bash shell without XWindows running. It could manage it on Windows 98, though, but only with the windows media player, if I remember correctly. Winamp 2 was a bit of a CPU hog for some reason, even though I never used visualizations.
I played mp3s on a 486dx2... I think at 40MHz (but could be after 100MHz upgrade). The biggest issue was bitrate, I think it struggled with 128kps but was fine if they were encoded anywhere below. Certainly could not play 160kps. 96kps mp3s were common enough on the internet back then with dialup, although they sounded awful.
Now, if you did anything on the computer other than let WinAmp play without the flame graph, it would stutter. I had the machine under my desk and used VNC to connect to it and change tracks or whatever.
The machine continues to receive the hug of death .. especially with our friendly Europeans waking up. Have faith, it's still running. (And it's been surviving like this for four hours now.)
I've turned down the logging level a little bit and turned off the beeper. On this machine, a 50ms beep on the motherboard buzzer is 50ms of delay. :)
I think it's impressive how your site's managed to stay online when many sites hosted on much more powerful hardware haven't been able to handle HN frontpage levels of traffic.
Thanks ... I think people are having time-outs so it's not anywhere near close to perfect, but the machine has been running at 100% for five hours or so now and it is not crashing, so I'm happy.
I very friendly opened the link, and it is still serving pages. The images are pretty slow to load, though. While reading the page, I thought it was just text, but then suddenly a banner appeared.
Great demo of what such a machine can do, and how much we take our 3GHz, 12 core machines for granted.
There is some beauty to the fact that even if you wanted to update your software, you can't unless you patch it by yourself, so you know that in a month or a year from now it will be exactly the same way you left it the last time you configured it (apart from the chance the hardware fails or the security by obscurity is breached somehow).
Sadly the project is mostly unrelated to my day job. I started mTCP at least 6 years before joining Google and at most of my time at Google is spent on much less fun things.
On the plus side, when I finally do get around to building a cluster of these and a load balancer I'll know what to do. ;)
pfft...that is nothing. I was on a 286 running a DOS IRC client and managed to take back an IRC channel with more than 150 users that was previously taken over...
No, it's a 2009 creation. When I started mTCP I did netcat first because it was simple. My first iteration of an IRC client wasn't much better than netcat. It has improved since then though.
Ah. I remember mTCP, from trying again much later, then. You said you started it, so is that all yours? In any case, very impressive work, and still useful every once in a while next to the cool factor! And HTTP/1.1 with pipelining is seriously cool...
That keyboard there was a work of art. I can still remember typing on one as a kid. So responsive, so satisfying, it just compelled you to want to write more. I own a few mechanical keyboards now and none of them compare to the original IBM Model M (I have heard that there are companies making 'new ones' though so maybe I'll have to try one.)
* No standard ISA slots, instead a bulky and expensive ”sidecar” system
* Partially incompatible with regular IBM PC software
* Max 128K RAM
IBM likely did this stuff on purpose to avoid cannibalizing PC sales, but it ended up killing the Jr. Later on Tandy would borrow the PCjr sound and graphics hardware (superior to a normal CGA PC/XT) for a line of more successful personal computers.
I type every day on an IBM model M ps2 keyboard that I have owned for 30 years lol. Currently connected to an i9-13900K system via a ps2 to usb adapter
Could this claim the title of “oldest host on the public internet serving traffic”?
At first I thought “~100 days, so what?” - but that was before I knew this was an 8088 managing to hold up to even just the background noise of the modern net (portscans, etc). It’s surviving being slashdotted by HN. Very impressive.
I'm sure I can go for a few more years until the next patch ...
On a more serious note, the web server is the problem here. I've tried to run long periods of time before but eventually it would crash. I finally found a 10+ year old parsing bug that wasn't handling quoting correctly, and it was some sort of crypto coin mining JSON request that tripped the bug. So even what I thought was bullet proof years ago turned out to be broken by changes in the user traffic.
For the next iteration I've got to put a better Ethernet card on it. The Xircom PE3-10BT device is nice because it's convenient, but the bandwidth would be 2x higher with a real Ethernet card on the bus.
And normally this machine is idle so the speed and bandwidth are not a problem. Right now it's very popular. :)
I don't know what's on the site, maybe it's busy uploading data to various people, but usually the original 10mbps ethernet is enough to serve most ~light websites (anything that is not as heavy as youtube or an image blog basically) to the hacker news homepage, and I'm not getting synacks so this is not the web server (layer 7) being slow
The Xircom is pretty bad, as it costs a lot to do the I/O through the parallel port. Just using TCP/IP sockets (no disk access or processing) the machine can send and received about 42KB/sec. A better adapter can do nearly 3x that on the same machine.
So about 1Mbps max with a good adapter? Wow, more than I thought... yeah, a hard disk of the era, not even AT bus, most likely won't be able to keep up with that, heh.
I'm repeating myself a bit, but, dude, it's an 8088 (EDIT: ok, technically a NEC V20, pretty negligible though). It has an 8 bit wide bus. It runs at 4.77MHz and needs many cycles (at least 4? more?) per instruction. With a parallel port adapter, not even an 8 bit ISA one. I haven't done the math, not even on an envelope, but I somehow doubt the Ethernet adapter is the bottleneck here...
I'm not getting a SYNACK back from it within the default firefox-on-linux timeout of 60 seconds. Guess I'm obliged now to run Wireshark for the next hour to prove a point just in case it does respond to that (interplanetary latency style), but I'm going to call that at least fairly dead
Edit: actually, I'm not sure how long my router will keep a half-open tcp connection in its state table. It may not show up in Wireshark on my laptop. 10 minutes in, no synack showing up: I'm calling it
"Dead" for me is if it actually crashed and does not recover without interference. I'm not surprised that an 8088 (not even an 8086!) will either take a really long time to reply SYNACK, or just drop packets entirely when the queue is full, when hammered with HN levels of crowds.
* It's getting hammered. I didn't expect it to be this bad.
* If it can't process things fast enough packets might be dropped. So the TCP/IP error rates are probably pretty high right now.
* It's logging all of this crap too ...
Normally it can do the handshake in tens of milliseconds. Right now the load on it is basically "crush." But it's queuing and answering as best as it can.
There were several speeds of the V20, including the base version at 5Mhz. Using it as a drop-in replacement and keeping the system clock speed the same the NEC V20 would still give you a 15 to 20% performance bump because it used less clock cycles when executing many insgtructions.
(This machine has not been altered to speed the clock.)
100+ days of runtime on nearly 40 year old hardware not designed as a server exposed to all of the garbage coming in on port 80.
Remember, this is a home computer from the mid 1980s. This thing is way outside of it's duty cycle. And the software is holding up pretty well too, even during what is effectively a DoS attack on a DOS machine.
Well it’s about a computer from 40 years ago! That’s why I don’t see what’s so special; any computer from that era that still works today could easily run for a hundred days.
https://www.brutman.com/forums/index.php