Slashdot Mirror
The Linux Kernel Archives
Jeremy Andrews writes "KernelTrap offers an interesting look at the history behind the Linux Kernel Archives, home of the Linux kernel. They start from the beginning in 1997, when kernel.org ran on a generic "white box PC" using a shared T1, to the present where it runs on multiple quad Opterons each with 24 gigabytes of RAM, 10 terabytes of disk space, and a gigabit link to the internet. Much of the article is based on an interview with Peter Anvin, also including quotes from Linus Torvalds, Paul Vixie of Internet Systems Consortium, Inc who donates the bandwidth, and Matt Taggart of Hewlett-Packard who donated the hardware."
The normal bandwidth used by kernel.org is between 150 to 200 megabits per second, at times when "nothing major is happening," Peter said. "Quite honestly, the test releases aren't even a blip on our radar," he added, referring to the -pre and -rc kernels, explaining that they don't noticeably increase the amount of bandwidth that is consumed. Only when an official stable release is announced does kernel.org see a spike in traffic. For example, with the upcoming 2.6.12 release Peter predicted, "I expect it go to the high 200's, for about a day." He noted that even with a direct link from a busy website such as Slashdot, that was about as much bandwidth consumption as they see from a kernel release. "What really drives up the load average is when one of the distributions that we mirror makes a release," he explained, "such as one of the Fedora cores. The kernel is only a few tens of megabytes, whereas a fedora core is a couple of gigabytes." With the upcoming release of Fedora Core 4, Peter predicts that both gigabit links will probably be saturated for 3 or 4 days. "This is largely speculation, because never before have we had the capability of serving that much traffic."
Hulk SMASH Celiac Disease
Boy what I could do with that and BitTorrent... *rubs palms together*
Very interesting...will have to check this out.
2006: generic "white box PC" using a shared T1 -- AGAIN
!!!HA!!!
...especially having dealt with something like this (on a much smaller scale) recently.
We were having bandwidth limitations on RubyForge; it was getting up to 80 GB per month at the end of 2004. Mirroring out releases helped get usage back down to 15 GB per month. Many thanks to our mirror providers!
The Army reading list
Good Grief that's a lot of pipe! Saturating a PAIR of gig links? Certainly tends to make one stop and consider how many people are actually USING linux nowadays. Good to see!
Thinking outside my Head
Way to slow.
Mod +5 funny -5 irreverant
This was a great article! I can attest the there is quite a difference with the new hardware, I got a 500KBps download last night while downloading rc3-mm2.
Can we please have the same kind of article about slashdot hardware?
"think of it as evolution in action"
The 'kernel.org' domain name was picked because by that time in 1997 the more logical seeming Linux dot names were already taken. The Transmeta domain was intentionally not used to avoid creating the false perception that Transmeta owned Linux.
I wonder what would have happened with Transmeta and Linux if they had used the Transmeta domain to host the kernel archives. Would IBM have gotten involved with Linux? Would SCO have sued Transmeta instead of IBM? Would Linus have left Transmeta?
When Linus Torvalds purchased his first computer on which he began writing the Linux kernel, the state-of-the art PC with 4 megabytes of RAM and running at 33 megahertz was too expensive for him to buy outright.
Oh my god, it's a diesel!
-1, Disagree is not a valid option. Troll, Flamebait and Offtopic are not a substitute.
At least this is a better story and more technical (aka nerdy) than oh say....what Google's homepage looked like in 1997.
...it runs on multiple quad Opterons each with 24 gigabytes of RAM, 10 terabytes of disk space, and a gigabit link to the internet...
Do I smell a challenge?
I'm in awe of that box. It just pushes so much data, all the time. And 1000Mb/s of bandwidth?! That's more bandwidth than Google!*
* I strongly suspect this not to be true.
Get your own free personal location tracker
Mods, check the timestamps before using wasting a "Redundant"....
Referring to 32-bit systems, Peter noted, "we learned that the Linux load average rolls over at 1024. And we actually found this out empirically."
Can you even get the server to TELL you what the load is when it's that high?? That's INSANE!
teeker
It's already nearly slashdotted. mirror
this post contain no useful information, no need to mod it down
As we have some figures for the numbers of machines in the early days and surely we have the traffic figures for then as well...
We should be able to make a reasonable guess at the number of machines out there with Linux on them...
Donald 'Duck' Dunn: We had a band powerful enough to turn goat piss into gasoline.
i gotta tell you, usually goat.cx grosses me out, but this one is fucking funny....
I'm really happy to see HP giving so much support. I'll definitely remember this the next time someone asks my opinion about what server hardware to buy.
It doesn't surprise me that being linked from slashdot is just a minor effect. A kernel package is tens of megabytes, while a single visit will likely consume less than 100KB.
see a Text Widget
...is get themselves mentioned on Slashdot on the same day that there's a simultaneous release of a major distribution and a Linux kernel.
It's a small world and it smells funny; I'd buy another if it wasn't for the money; Take back what I paid (SoM)
So, you are going to recommend HP for the simple fact that they are supporting kernel.org? Shouldn't you recommend them based on their actual product? How is this any different than Bush putting his cronies in high-ranking jobs? It is easier to make an informed decision when you don't involve personal politics.
However, in this post from hpa, it looks like the tools are not ready.
Love salty crackers? catchy electronica? Try !
I wonder what operating system they are running. :)
wayner@pobox.com -- Wayne A Arthurton -- www.pobox.com/~wayner
DONT USE APACHE.
This was suggested. The kernel.org people didn't seem to have interest in it. Those light http servers are probably good for lots of small static html files. kernel.org is not like that - it needs to serve + 20 MB files and CD ISOs. Your benchmarks don't measure that. I can bet the kernel.org people knows what they're using and they'd have switched if it'd be really useful.
I guess H.Peter Anvin petrified Natalie Portman with his Beowulf cluster! Watch for Soviet Russia to pour hot grits down his pants!
C|N>K
it DOES run linux, and they've got several so you can't ask us to imagine a beowulf cluster either...
Does it run MSDOS?
FGD 135
I worked at Globix when we offered free bandwidth to kernel.org. In the beginning, when things were going well and we had hundreds of millions of dollars to spend, we used this to leverage our poision in the open source community. Of course, when the bubbled bursted Globix tried to get rid of all the free riders first. It was done very selectively, though. While some were cut loose as fast as possible (like kernel.org), others were kept because they had better connections to some of the executives. I don't want to name names, just that much: it is one of the better known nudie magazines. It was quite a qide to work at Globix. They are still around, barely.
If it's an announcement of a new kernel, it is likely that at least some percent of the /. crowd will download the new kernel.
It takes a man to suffer ignorance and smile
Be yourself no matter what they say
Why mention ISC or HP at all in this article except as 'free advertising' for those firms.
"...who donates the bandwidth...Hewlett-Packard who donated the hardware."
That's a funny way to say "free".
"where it runs on multiple quad Opterons each with 24 gigabytes of RAM, 10 terabytes of disk space, and a gigabit link to the internet"
Can you image a cluster of these...no wait...
I don't have occasion to use rsync, and I'm not too familiar with its design, but I think it synchs directories by checksumming the files in them to see if they differ. So Peter is saying above that the server's bottleneck is checksumming. I would think that on a server like this, checksums could be cached - why checksum a stable file more than once? Once you have a checksum for linux-2.6.0.tar.bz2, why calculate it again?
This would require a bit of bookkeeping when files change, but wouldn't it be worth it on such a busy system? (Or am I confused?)
...I guess that:
a) kernel.org doesn't think the 'enterprise readiness' of RH Enterprise Linux is that great, (vs what Fedora offers) even in what should be considered one of the most mission-critical sites in the Linux ecosystem (or that the difference with Fedora is worth paying for)
b) No one at RH is bright enough to be embarassed by this and offer kernel.org some free licenses...
Yes, the torrent would sure be a releaf.
I'm really happy to see HP giving so much support. I'll definitely remember this the next time someone asks my opinion about what server hardware to buy.
I believe that was the reaction HP's marketing department also expected. Admittedly, providing the hardware was a very nice gesture, but in reality, it's a brilliant marketing move.
Furthermore, I hope you will take other factors and datapoints into consideration when someone asks you for your advice, though. The servers donated were relatively high-end -- they might or might not be reflective of all HP hardware.
I'm Trappped at Berkeley.
We have, indeed, considered that, but it'd not really buy us anything. Earlier Apaches would sit on a lot of memory while serving large files, but current versions just have a thread sitting in sendfile(), which is just about as lightweight as you get.
Sure, the startup cost of the transaction is higher than for a lightweight HTTP server, but the startup cost of the transaction isn't a big deal for us, and we appreciate the flexibility that Apache offers.
Where is the swap size = phys. size x2 rule?
Linux doesn't support the swapping of 48 GiB, max. is 2 GiB, :P
I read the email Linus sent out introducing his creation where it says it won't support anything other that AT Hard Disks. Cracks me up. The history of the Linux kernel would make an interesting read, moreso than other OS's because of recent events, and the fact that it wasn't created by IBM, but a lone Grad Student. I think it would make a fascinating read.
I'm not a troll, but I play one on Slashdot.
thats where we need somekind of link between cvs and a peer to peer system.
Did the interviewer forget to ask what the longest uptime is for kernel.org?? That would have been interesting to know.
the torrent would sure be a releaf.
... resist ... urge ... to ... ask ... why ... bit ... torrent ... would ... put ... leaves ... back ... on trees.
Must
"I don't know, therefore Aliens" Wafflebox1
At least on Linux, the load average includes
processes waiting for in uninterruptable sleep.
That would be disk IO, mostly.
Without having ever looked at the apache code I'd like to ask anyways:
Doesn't apache do some additional stuff per request that others don't?
Things like check whether authentication should be requested and the like?
I might be mistaken but if not - don't these things amount to a significant overhead, esp. when talking.. uh.. "lots" of requests per second?
What's different about rsync is that it does not ordinarily use a single file checksum (and therefore copy whole files if changed). Instead, to save bandwidth, it uses a more sophisticated system to ensure that only changed parts of a file are transmitted - and it detects changed parts by comparing (many) checksums, I believe. The report sums it up like this:
(Disclaimer, I have only skimmed the rsync report and that was some time ago, but I am a longtime and happy rsync user.)
you had me at #!