Slashdot Mirror
NetBSD Sets Internet2 Land Speed World Record
Daniel de Kok writes "Researchers of the Swedish University Network
(SUNET) have beaten the Internet2 Land Speed Record using two Dell 2650 machines with single 2GHz CPUs running NetBSD 2.0 Beta. SUNET has transferred around
840 GigaBytes of data in less than 30 minutes, using a single IPv4 TCP stream, between a host at the Luleå
University of Technology and a host connected to a Sprint PoP in San Jose, CA, USA. The
achieved speed was 69.073 Petabit-meters/second. According to the research team, NetBSD was chosen 'due to the scalability of the TCP code.'"
"More information about this record including the NetBSD configuration can be found at:
http://proj.sunet.se/LSR2/
The website of the Internet2 Land Speed Record (I2-LSR) competition is located at:
http://lsr.internet2.edu/"
...but don't the three main BSD projects use pretty much the same TCP/IP stack?
Javascript + Nintendo DSi = DSiCade
Fools, BSD is dea . . . oh, wait, what?
trustedworlds.net - gaming, security, and the gunk that lives in between
They will still get slashdotted.
how about we get 1MBS real downloadspeed in everyones home before we go shooting porn to reach ISP owners at the speed of light.
How does that work?
Does this mean we've broken the "station wagon loaded with DVD's" barrier yet?
We can now DoS sites at even faster speed !
This signature was left intentionally blank.
cleaning their pants out? I'm also dusting off the old BSDemon shirt.
-- the only good thing the French ever did was two chicks at one time
What is a petabit-meter? How is it a significant measure of transmission speed?
"They redundantly repeated themselves over and over again incessantly without end ad infinitum" -- ibid.
when UDP has so much less overhead?
Did they check for any inband compression? They data they're sending isn't randomised.
840GB/30 minutes = 466 MB/s, or 3,728 Mbps
SUNET Internet2 Land Speed Record: 69.073 Pbmps
Now give me my carma..
What was the slogan of the recent pro-piracy demo in Sweden? "Vi vil har sex, vi vil har sex, vi vil har 600MBit!"?
Somebody should show Valentini this, I wonder what he'd say...
Val: "You students transfered how much?"
Sunnet: "About 30 movies a minute"
Val: "Un-fucking beli-Oh wait, I already said that..."
..transferring 840 gb of swedish porn across the pond. ;)
Use Minidisc? Join the Minidisc.org forums.
When is this supposed to be available for the average joe to use?
Also, what measures (if any) have they taken to combat the current internet's limitations and vulnerabilities?
We have secretly replaced these Slashdot mods' sense of humor with a rusty nail. Let's see if they notice!!
My guess is that it's petabits times meters (as in physical distance between the machines). Which seems kind of stupid -- if the distance makes any real difference, something is wrong. How about communicating with Voyager II -- then you could get some real numbers, even at modem speeds!
Plus, I'm betting it's not a "land" speed record, seeing as how the data probably jumps through the air (satillite/microwave transmissions) at one or more points. (Not to mention the fact that being on, over, or under the surface of land or water means nothing to a data cable.)
"A great democracy must be progressive or it will soon cease to be a great democracy." --Theodore Roosevelt
"According to the Internet2 LSR contest rule #5A, IPv4 TCP single stream"
vodka, straight up, thank you!
(((840*1024)/30)/60) = 477.86 MB/s or 3,823 Mbps
Sorry, but I've seen much higher rates of it than this.
If other reasons we do lack, we swear no one will die when we attack
I've heard that joke, "never under estimate the bandwidth of a 78 chevy and a box of hard drives," but now I don't know about that one anymore.
Just wait till you see the bandwidth of my minivan loaded with backup tapes!
So, is this just using a secure connection on our internet, or did they go ahead and string up an all new internet for no one but theirselves to be on? I don't really see the point of the latter - why not dump the money into vastly improving the current internet and stomping out spammers and things that make the place bad?
SecondPageMedia - Wha
Perhaps because they wanted the data to arrive reliably?
UDP just sends off the data without caring whether it actually arrives intact at the other end, you know. TCP, on the other hand, actually gives delivery guarantees...
We need to get to the point where the only limiting factor is the human in front of the computer. I hate waiting for my computer, whether its downloading a file or waiting 2 seconds for a web browser to start. Everything should be instant - I am excited for the day that nothing happens on a computer slower than I can think about it. A 2 hour HDTV movie is about 20 gigabytes - download it to me in less than a second and prompt me what to do next.
Re: your sig...
;)
To provide more relevacne for the band you might want to use something like the following:
Googling up my brother's Acid Metal band, Ahymsa
Google places more weight on the text that's actually inside the link
Actually, they data transfered across Sweden, part of Europe and then the United States which (according to them) took up 10,157 miles total.
"Between a host at the Luleå University of Technology and a host connected to a Sprint PoP in San Jose, CA, USA."
Thats a big distance.
I suppose this may be a troll, but you just have to RTFBlurb to see that the transfer was between a university in northern Sweden, and one in San Jose, CA, USA.
Read the Fucking Summary ;)
if you take a look at map, you'll notice that san jose is kinda far away from sweden.
That depends on whether the DVDs are in cases or not I think.
At 9.4 GB per DVD (Assume single-layer double-sided DVD-R), and a travel time of 3 weeks from Sweeden to California (2 weeks on the boat, one week of driving), you'd need to get about 90,000 DVDs in your station wagon to get an effective 1680 GB/hr. That wouldn't be possible if they were in cases, but if it was just the DVDs, it's probably a close call. Might have to upgrade to dual-layer DVD's, or change the saying to "an SUV full of DVD's".
On the other hand, if you count the time to actually read the data off of the DVDs (even worse if you count the time to put the data on the DVDs too), the station wagon of DVD's barrier was broken long ago - you probably couldn't spin a DVD fast enough to get 9.4 GB of data off it in 20 seconds.
paintball
Everything should be instant
I bet you were a little shithead when you were a kid.
I mean, correct me if I'm wrong, but isn't this a somewhat useless measure? I mean, I suppose that the longer a link is, the more interference, but really, seems like a rather pointless mesure to me.
autopr0n is like, down and stuff.
Not only did you not RTFA, you didn't read the *slashdot* article:
"between a host at the Luleå University of Technology and a host connected to a Sprint PoP in San Jose, CA, USA."
This wasn't across Sweden, it was across the Atlantic Ocean and North America.
hen Swedish scientists transmit that much data across a country the size of the US, send me an email.
You don't read very well, do you? And who is the idiot who modded this insightful?
between a host at the Luleå University of Technology and a host connected to a Sprint PoP in San Jose, CA, USA
So, it went from Sweden, across the Atlantic Ocean, across the continental USA all the way to San Jose.
Hint: San Jose is on the West Coast of the USA. The Atlantic Ocean is on the East Coast of the USA.
This was just node to node.. when they build a network that 1 billion users can simultaneously transfer data TO EACH OTHER at 100 Mbps (yes I'll be happy with Mbps) .. wake me up.
S.
if internet2 is so fast, then why do you want to replace internet4 by internet6 instead of internet2?
;)
It took me a few seconds to realize he was confusing IP with Internet. After that I said it was impossible to send email over internet2 and he seemed quite satisfied with the answer
sig(h)
I've been to Sweden. I've been to San Jose, CA.
I wouldn't say that they're in walking distance from each other.
Notice that you accidentally dotted an "a", you cursive-writing moron! If you would just print like a regular person, that would never happen.
True story.
still held by Norway
sulli
RTFJ.
Now I can get my Swedish Bikini team pictures faster than ever!
I2 isn't going to replace the Internet some day, it's more of an acedemic playground not a construction project.
Theres no way you're gonna get 840gigs of Necrophilia porn on the internet. Must have been home made....
Can I get an eye poke?
Dog House Forum
Now we can download pirate proof movies and songs at even greater speed!
Of course we cant watch or listen to them, but man... hell of a download rate.
---- Booth was a patriot ----
Man I hate to be on the recieving end of a Denial of Service attack on Internet 2. 900 gigabytes of data /30 min from multiple sourses would be crushing.
Veramocor
Actually google doesn't index a lot of /. because there aren't enough inter article links to find all the articles and because google just gets the default page setup a lot of comments are hidden, not to mention Google only indexes a certain amount of dynamic data from a particular site to avoid causing what was once called "the google effect" when a poorly designed web app on a slow server would be hammered as google crawled the catalog.
Theres no way you're gonna get 840gigs of Necrophilia porn on the internet.
Don't forget, we're talking sunet.se. I used to archie tons of porn off there more than 10 years ago. If anyone's got it, sunet does.
How does that work?
Microsoft CPU sharing! It's the latest bug^h^h^hfeature
I remember the same thing being said about the actual Internet back in the mid-late 1980s. Academic playground, won't amount to much.
Don't blame Durga. I voted for Centauri.
well depends on how many tapes but a rough guess is... 10000 tapes * 20 GB / tape = 200000 GB 200000 GB * 8 bits/byte = 1.6 petabytes 1.6 petabytes * 30 m/s = 48 petabyte-meters/second
More precisely, it went from
San Jose CA to
Stockton CA to
Kansas City MO to
Fort Worth TX to
Pennsauken NJ to
Relay MD to
Chicago IL to
New York NY to
Manasquan NJ to
Tuckerton NJ to
London UK to
Brussels BE to
Amsterdam NL to
Hamburg DE to
Copenhagen DK to
Oslo NO to
Stockholm SE (where it changed carriers) to
Vasteras SE to
Gavle SE to
Luleå SE.
Or maybe it was the other direction; the site doesn't say clearly which way the transfer was.
http://alternatives.rzero.com/
cool i dint realise that San Jose, CA, USA. was a part of sweden then i migth just drop by :)
Cool, I live in Luleå, I actually have my internet connection supplied by the university. I wonder how long before I can get Internet that fast.
They Stole Sprint's DS-3 cards!
Even those who arrange and design shrubberies are under considerable economic stress at this period in history.
How different is the Linux stack that the *BSD stacks? Is there that large a performance difference?
And a better question, if NetBSD has a better stack, why doesn't Linux just adopt it? After all, it *is* BSD license..
Or is it just good old pride getting in the way again?
One of the biggest problems in networking is handling a large bandwidth-delay product (that's the amount of data in flight at once). Since distance increases the delay it is relevant.
If anyone cares, a connection with a large bandwidth delay product is sometimes called a long fat pipe. A good networking book should discuss this. I think Steven's TCP/IP Illustrated, Volume 1 has a section on it(my copy is at work.)
(S(SKK)(SKK))(S(SKK)(SKK))
Any thoughts on why they chose to use Dell 2650s?
So I have 100 peta-bytes of 0's I can compress into a few bytes (a number) then send over my 56k modem to Voyager and break all records in exsistance. What I'm getting at is I hope there is some kind of spec for the data they are transmitting, as compression can invalidate all results.
They might claim that NetBSD scales best, but it took some code changes to get it to do so (which have since been picked up and are included in the base).
:-)
The REAL reason for why they picked NetBSD is that Ragge (Anders Magnusson), the person doing a fair chunk of the testing, is heavily involved in the project and knows the code base. It was simply easiest to work with for him.
Yes, but what would the throughput have been like if it had been to MARS? We really need to be preparing our protocols for interplanetary distances after all.
Didn't M$ at one time just rampantly copy the BSD stack for Windows? Eh, too tired to care. :-)
Hurricane Ivan: A 17th century prison collapsed. All of the inmates escaped.
Why use DVDs in a station wagon when you can use the Creative Nomad Jukebox Zen Xtra (60 GB, arguably smaller size:storage ration) in a greyhound bus? hell, strap some rockets onto the bus and you can make it even faster.
Very impressive. I have few questions, though: how does it compare to quantum units? Could NetBSD be used as a basis for cheap routers in New York?
Sincerely,
Pan Tarhei Hosé, PhD.
"Homo sum et cogito ergo odi profanum vulgus et libido."
Even if they did, what's the problem? The BSD stack uses a BSD license, unsurprisingly, not the GPL. Using it in Windows would be as legitimate as using it in IRIX or Solaris or AIX.
hahaha!
Frickin' hilarious. The mods that hammer you with a "Troll" hit need to get an enema and lighten up. I'm a big BSD fan and loved it.
Trolling is a art,
I wasn't complaining. It's just funny, how M$ complains and complains about OSS, and then just copies what it wants. That's what I really meant. Anyway, they copied it into Win 3.1 or NT 3 right?
Hurricane Ivan: A 17th century prison collapsed. All of the inmates escaped.
Haven't the swiss already beating this?? CNET
Pff. They only have a tcpdump of the first 32 megs.
I wont believe it till i can see the whole thing.
All the cool scientists are using Gibibytes ;)
" How about some evidence of that? Where is this 512 way smp machine running linux?"
Thought I was bluffing, did you? :-)
It's the SGI Altix. In a linux-kernel post just today, an Altix user says that "Overall, linux scales to 512p much better than I would have predicted." This system runs with Itanium-II processors BTW.
So there you go, Linux handling a 512-way box tolerably well. Linux screams on an IBM 64-way box, with Xeon or Power 4 processors.
This has got to be one of the worst arguments ever created by man. we would probably be a few hundrded years ahead in terms of technology if people didn't ever use this argument. Here is one: If Linux is so good why isn't everyone using it?
Creative Demolition
Take a look at readable tcp dump and you'll notice that it is just the ascii character set shifted continuously. Now if you NEVER need disk access then this could be usable (aka isp and router junction points) but once you hit disk you are bottlenecked. Even with U320 SCSI you can only hit 320 MB/s (~2.5Gbit/s) assuming linear reads at full cacity of your full array of disks.
Disk is limiting pretty much anything, such as playing raw 2K video (2048x1556) in real time (seconds is relatively easy but minutes is difficult). I could care less how fast your network speed as when 1 non-solid state device (ie. disk) is entered into the mix the network performance is notional compared to real performance.
"Survival of the fittest Max, and we've got the fucking gun!" - Pi
Where could this geographic genius get such a myopic view of the world from?
Slashdot: Where nerds gather to pool their ignorance
Hi, Anyone out here have any experience with TCP performance over CDMA1xEVDO link (1.2Mbps limit). I've been hearing a lot about W-TCP which improves the performance of TCP over wireless links like this...but never saw any implementation..anyone have any idea?
Do you really mean GigaBytes or are they really Gibibytes?
Phillip
I didn't realize Priceline had expanded into the data transfer business.
Rank Presidents by th
I think the 850GB was cheating.because the pc's harddrive and bus don't have such power,and maybe the cpu can't have such power and bandwidth.
,but the difference may be omitting
I think even a windows or linux may achive a high record,though yet even lower than it
Funny that you write Vasteras and Gavle (which in swedish are Västerås and Gävle) but Luleå.
Living in the US? I mean, it's not like I would be able to pinpoint every major city in the EU. And then again - the EU has 25 member countries and the US 50 states.
And by the way, it would be nice to know if all data actually went directly between Luleå and Gävle, or if some of it took the other way through the northern ring of GigaSunet (that is, through Umeå (you remember those pirates demonstrating?)).
Geek rants since like... 2000 or something.
i have to clear all the false lies this guy is saying:
.005% of internet servers.
1. NetBSD, which claims to focus on portability (whatever that is supposed to mean), is slow, and cannot take advantage of multiple CPUs.
REAL FACT:
freebsd supports smp and the upcoming netbsd has smp support. openbsd has also started smp (see CVS tag SMP)
2. There are almost no FreeBSD developers left, and its use, according to Netcraft, is down to a sadly crippled
REAL FACT:
And also according to netcraft. freebsd is always included in the most reliable hosting site every month. and also netcraft said that freebsd is the one that is gaining rather than losing.
3. the *BSDs have balkanized yet again. There are now no less than twelve separate, competing *BSD projects, each of which has introduced fundamental incompatibilities with the other *BSDs
REAL FACT:
and there are hundreds of linux distros, w/c are also impompatible in some or any other way w/ each other.
4. Many user-level applications will no longer work under *BSD,. blah blah
REAL FACT:
gimp can be compiled on all bsds, openoffice has a freebsd port.
5. Fact: servers running OpenBSD, which claims to focus on security, are frequently compromised.
heh! and what about the percentage of compromised linux servers compared to bsd?
*BSD is only dead for the uninformed.
anyway you are a real example of a yet another linux zealot man, hah you will also face the fate what amiga users have faced before.
Dumb terminal. See previous poster for detailed explanation.
Let's assume each DVD weighs 10 grams, then 90 000 of them weighs in at 900 kg, which is more than what a station wagon and even most SUV's can handle.
What did they transfer? random stuff? movies? porn? DV footage? Did they use any compression?
Did anyone else notice the latency of 276.138 ms? Sure, you could pump 1.5 Terabytes per hour, but can you plant the bomb in de_dust?
i have to clear all the false lies this guy is saying:
:-)
- imho i think you mean 'false lies' = false statements
bsd is dead? yes it is dead, if you are pointing to the original 4.4bsd of the ucb (since the university stop developing it).
bsd is dying for the trolls who does not know what he really is talking about.
an excerpt from netcraft:
FreeBSD secured a strong foothold with the hosting and internet services communities at the genesis of the web and has anything but gone away. Indeed it is the only other operating system that is gaining, rather than losing share of the active sites found by the Web Server Survey.
still insisting bsd is dead?
uhurm ok BSD died! but now rose from the dead with great power. now it's harder to kill the undead ones! so beware! >:)
What a brilliant fucking article! You nailed it, linux sux.
Go read RFC 1323 (or the post mortem on last weeks deployement fiasco here at work) on why distance matters.
we already have it
Inter Planetarium / Transmarcian Communication Protocol
No the routing did not go through Umeå (as you can see in the trace route on the project page). Umeå is a secondary route to Luleå, cause instead of going directly through Gävle, it would have to go through Umeå, Sundsvall and Borlänge before reaching the same distance.
As you can see in this pdf on page 7:
http://proj.sunet.se/gs/GigaSunet-rapport.pdf
Luleå was the only one I saw referred to in its native alphabet; I inferred the other two from ASCII-only node names, and merely checked that they were (sometimes) spelled that way on the web.
http://alternatives.rzero.com/
anyone know what the byte-meters/second is of a station wagon doing 80mph full of hard drives?
The same goes for doing a copy on transmission. BSD has generally hidden a software checksum and/or copy in the driver, because older hardware didn't support scatter-gather and checksum. Linux didn't hide it. Note that checksum comes free (seriously!) when doing a copy, since you need to access the memory anyway. Now that cards with scatter-gather and checksum are common enough to care about, Linux can take advantage of this feature for "zero-copy transmit". (obviously, the network transmit is itself a copy and the whole point of doing a transmit)
Zero-copy receive, in the BSD style, is a way to kill SMP scalability. It involves remapping pages, which leads to cross-CPU interrupts to invalidate the old mapping. It's cheaper to copy the data.
For a fast 64-way Xeon, of course you don't use Intel's lame interconnect. That won't go past 4 CPUs at any speed. You build your own crossbar interconnect. You do 4 CPUs per node using Intel's bus, then 16 nodes per box via your custom crossbar. The RCU code was originally tuned for boxes like this, with 23 to 64 processors. As you can see it needs some tuning for the 512-way boxes. That's no surprise, and no big deal.
You have been trolled. You have lost. Have a nice day.
Quantum Virtualization, aka QV (c)(tm) by me.
Now where did that cat go..?
What a brilliant article!... eh, from 2001. :-)
/* Steinar */
(This comment is of course GPLed.)
Relay MD
I don't know about you, but for some reason I have this image of Relay MD being nothing more than a Cisco router out in the middle of a field somewhere.
On the other hand, it can't possibly be any worse than the original...CAN IT?! ;)
... at an OSS conference in Canada.
Yet another crippling bombshell hit the beleaguered *BSD community when recently IDC confirmed that *BSD accounts for less than a fraction of 1 percent of all servers. Coming on the heels of the latest Netcraft survey which plainly states that *BSD has lost more market share, this news serves to reinforce what we've known all along. *BSD is collapsing in complete disarray, as fittingly exemplified by failing dead last in the recent Sys Admin comprehensive networking test.
You don't need to be a Kreskin to predict *BSD's future. The hand writing is on the wall: *BSD faces a bleak future. In fact there won't be any future at all for *BSD because *BSD is dying. Things are looking very bad for *BSD. As many of us are already aware, *BSD continues to lose market share. Red ink flows like a river of blood. FreeBSD is the most endangered of them all, having lost 93% of its core developers.
Let's keep to the facts and look at the numbers.
OpenBSD leader Theo states that there are 7000 users of OpenBSD. How many users of NetBSD are there? Let's see. The number of OpenBSD versus NetBSD posts on Usenet is roughly in ratio of 5 to 1. Therefore there are about 7000/5 = 1400 NetBSD users. BSD/OS posts on Usenet are about half of the volume of NetBSD posts. Therefore there are about 700 users of BSD/OS. A recent article put FreeBSD at about 80 percent of the *BSD market. Therefore there are (7000+1400+700)*4 = 36400 FreeBSD users. This is consistent with the number of FreeBSD Usenet posts.
Due to the troubles of Walnut Creek, abysmal sales and so on, FreeBSD went out of business and was taken over by BSDI who sell another troubled OS. Now BSDI is also dead, its corpse turned over to yet another charnel house.
All major surveys show that *BSD has steadily declined in market share. *BSD is very sick and its long term survival prospects are very dim. If *BSD is to survive at all it will be among OS hobbyist dabblers. *BSD continues to decay. Nothing short of a miracle could save it at this point in time. For all practical purposes, *BSD is dead.
Fact: *BSD is dead