Beta
×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Ubuntu Download Speeds Beat Windows XP's

timothy posted more than 5 years ago | from the aggregated-circumstances dept.

Networking 515

narramissic writes "Doing a download speed test of his Time Warner cable connection, James Gaskin discovered something odd, something that he is quick to note isn't a rigorous benchmarked lab test. The discovery: His Ubuntu machine 'returned a rating from the Bandwidth.com test of 22-25mbps over several tests' while the same test done from a Windows XP PC returned a rating of 12-14mbps. The two computers used in the test are 'almost identical: both off-lease Compaq small form factor D515s, part of the very popular corporate desktop D500 family. Both have Pentium 4 processors running at 2GHz. The Ubuntu machine has 768MB of RAM, while the XP box has only 512MB of RAM. Both run Firefox 3 as their browser.' Gaskin's question: Can a little extra RAM make that much difference in Internet download speeds or does Ubuntu handles networking that much faster than Windows XP?"

cancel ×

515 comments

Sorry! There are no comments related to the filter you selected.

Linux on the desktop (5, Funny)

Yvan256 (722131) | more than 5 years ago | (#26474407)

If you can prove to people that you can download pr0n faster using Linux, they WILL switch!

I'm kidding! I'm kidding!

(or, am I?)

Re:Linux on the desktop (5, Funny)

Anonymous Coward | more than 5 years ago | (#26474533)

all i saw was "download pr0n faster" and i'm compiling a stage1 right now!!!!!

Re:Linux on the desktop (5, Insightful)

Hottie Parms (1364385) | more than 5 years ago | (#26474733)

Along the same reasoning, a good reason to switch to Linux is to avoid the malware that you get from browsing those questionable pr0n torrent sites.

I'm not kidding.

(Or, am I?)

Re:Linux on the desktop (5, Funny)

wsanders (114993) | more than 5 years ago | (#26474769)

Especially if you have had to drop out of college because an evil computer company sold you a Linux PC instead of a Windows one, you are at least not stuck with slow pr0n downloads.

Even if the answer is no... (4, Insightful)

thedonger (1317951) | more than 5 years ago | (#26474409)

The test was done on machines with differing configurations, so therefore is not valid. But interesting nonetheless.

No, haven't RTFA, thank you very much (0)

Anonymous Coward | more than 5 years ago | (#26474495)

If they were done with default configurations, it is valid. I know I have both Ubuntu and two Windows installs (Vista Home and XP Pro 64bit) and have never switched their configuration from defaults. I would assume that most other home users wouldn't either.

Though I truly and highly doubt that Ubuntu could deliver twice as fast download speeds as Windows. But I would be interested to hear why the results were what they were.

Re:No, haven't RTFA, thank you very much (5, Informative)

jackharrer (972403) | more than 5 years ago | (#26474611)

Actually I can see it all the time. My Ubuntu laptop's (IBM T42) WiFi is about 50% faster that the same configured Windows machine of my wife. We're talking about SAME hardware. I don't really know if it's drivers, or something else.

Performance on LAN is more similar, difference is about 10-20% max, but with this kind of hardware it heavily depends on HDD to write data and Windows is crap at this - it's swapping - god knows why!!!

Re:Even if the answer is no... (4, Funny)

Fred_A (10934) | more than 5 years ago | (#26474503)

The test was done on machines with differing configurations, so therefore is not valid. But interesting nonetheless.

Yeah, I wasn't even the same *operating system* !

I mean, apple and oranges !

Re:Even if the answer is no... (4, Funny)

Ethanol-fueled (1125189) | more than 5 years ago | (#26474799)

Already been said, but the article is terrible(WTF is wrong with you, Timothy) because the comparisons were done on two separate configurations. Would it have been that difficult to try fresh-out-the-box installs of each OS on the same box and/or maybe tried fresh-out-the box installs on the other box as well?

TFA might as well have been titled, "My left nut is larger than my right nut but does it produce more sperm than my right nut? Discuss." The sad thing is that people are discussing things other that what a stupid fucking article this is.

Re:Even if the answer is no... (2, Funny)

Hairy Heron (1296923) | more than 5 years ago | (#26474877)

Yes, because the only major difference, the 256 megs of more RAM, really is what gave them double internet speeds on the test. Hahahahaha, yeah right. I guess I'm going to have to go stick another gig of RAM in my box so I can get 4x the internet bandwidth of what I have now!

Re:Even if the answer is no... (1)

MobileTatsu-NJG (946591) | more than 5 years ago | (#26475097)

Yes, because the only major difference, the 256 megs of more RAM, really is what gave them double internet speeds on the test. Hahahahaha, yeah right. I guess I'm going to have to go stick another gig of RAM in my box so I can get 4x the internet bandwidth of what I have now!

Set up an XP box with 256 megs of RAM then go to Hulu.com and watch a full-res video. Tell me you're getting the data down just as fast as you were at 512 or 2 gigs.

Re:Even if the answer is no... (4, Funny)

Foofoobar (318279) | more than 5 years ago | (#26474983)

"My left nut is larger than my right nut but does it produce more sperm than my right nut? Discuss."

That's not your left nut. That's your head. Disgust.

Re:Even if the answer is no... (1)

ZarathustraDK (1291688) | more than 5 years ago | (#26475065)

"My left nut is larger than my right nut but does it produce more sperm than my right nut? Discuss."

Depends on how fast you can stream pr0n, and so we'll need to know how much ram you've got, evidently.

Re:Even if the answer is no... (5, Informative)

corsec67 (627446) | more than 5 years ago | (#26474555)

True, but considering both computers should easily be able to saturate a 100baseT connection, shouldn't both configurations be able to saturate a 22Mbps link?

This is different than the guy complaining that the computers can't fill a gigabit ethernet connection with a scp transfer while music is playing.
The http that the speed test should be using doesn't have any encryption, shouldn't be using gzip, and it shouldn't be saved to hard drive.

Re:Even if the answer is no... (1)

MobileTatsu-NJG (946591) | more than 5 years ago | (#26474559)

The test was done on machines with differing configurations, so therefore is not valid. But interesting nonetheless.

Well, sure it's interesting. I mean, Star Trek vs. Star Wars is interesting, too.

Re:Even if the answer is no... (5, Insightful)

hansamurai (907719) | more than 5 years ago | (#26474619)

Not to mention the ultra reliable online speed tests.

Mod parent up! (3, Insightful)

khasim (1285) | more than 5 years ago | (#26474757)

Who cares about the boxes themselves at this point?

The test FAILS because they're using the Internet instead of a network where they can control the other factors.

Re:Mod parent up! (4, Interesting)

ArsonSmith (13997) | more than 5 years ago | (#26475083)

Product A in lab tests always performs over 100% better/faster than product B.
Product B in normal use always performs over 100% better/faster than product A.

Which are you going to want to use? Perhaps product A is designed to max the test, while product B is designed to handle varying conditions.

Re:Even if the answer is no... (0, Troll)

Hairy Heron (1296923) | more than 5 years ago | (#26474623)

Because we all know that more RAM == more internet bandwidth right? Oh wait...

Re:Even if the answer is no... (4, Insightful)

MobileTatsu-NJG (946591) | more than 5 years ago | (#26474815)

Because we all know that more RAM == more internet bandwidth right? Oh wait...

If the machine's swapping it's not going to have a lot of room to cache that data until it's written to disk. XP is not spectacular at 512 megs.

Re:Even if the answer is no... (2, Interesting)

compro01 (777531) | more than 5 years ago | (#26474915)

Unless you're running on an old 4200rpm laptop drive, write speed shouldn't be a problem compared to internet speeds. 22mbps is only 2.75MBps, which pretty much any relatively modern drive can do, even near-full and fragmented to hell.

Re:Even if the answer is no... (2, Interesting)

MobileTatsu-NJG (946591) | more than 5 years ago | (#26474979)

Unless you're running on an old 4200rpm laptop drive, write speed shouldn't be a problem compared to internet speeds. 22mbps is only 2.75MBps, which pretty much any relatively modern drive can do, even near-full and fragmented to hell.

It is not an issue of write speed. The CPU AND the drive are busy at the same time. If swapping weren't such a nuisance demand for RAM would drop dramatically.

units (1)

bugi (8479) | more than 5 years ago | (#26475123)

22mbps is .00275MBps

I can do better than that by hand.

Re:Even if the answer is no... (4, Insightful)

no-body (127863) | more than 5 years ago | (#26474683)

Right - different OS _is_ a different configuration, with that logic all OS benchmarks are invalid.

That Windoze's TCP/IP stack is inefficient compared to Linux has come up before, so - yawn!

Re:Even if the answer is no... (5, Insightful)

gad_zuki! (70830) | more than 5 years ago | (#26474723)

Who gets 22mbps from a cable modem? Regardless, Im guessing either the ubuntu machine wasnt configured to use the ISPs web proxy but the windows one was or that the windows machine's antivirus was crippling the download.

This is a really lazy test. Didnt swap out hardware, didnt try different networks, didnt try clean installs, didnt tell us what network drivers he was using, didnt try anything really.

Also, there's no unique thing as "downloading." Its just TCP/IP. Why not try a share on the local lan? That simplifies things quite a bit. Or at the very least get off your ass and try a different ISP.

I want to say I'm surprised something so shoddy got on the slashdot, but I really am not that surprised. Between the lazy posts and idle stuff somehow getting loose into other sections, slashdot has gotten pretty crappy lately.

Re:Even if the answer is no... (2, Interesting)

Hairy Heron (1296923) | more than 5 years ago | (#26474729)

Who gets 22mbps from a cable modem?

People who have cable service that gives them 22mbps? Such a thing isn't that extraordinary.

Re:Even if the answer is no... (1)

QuantumPion (805098) | more than 5 years ago | (#26474811)

Who gets 22mbps from a cable modem?

My record speed with comcast on my motorolla surfboard was ~40 mbps. I usually get 15-20 mbps at peak times and ~30 mbps at off times.

I think I get such good speeds because I live in a poor urban area--close to the comcast NOC but not to many neighbors have cable modems.

Re:Even if the answer is no... (0)

Anonymous Coward | more than 5 years ago | (#26474985)

The test would be much more meaningful if it was done with just one computer. Test with one OS, record results, load up other OS, test again, and so on.

Re:Even if the answer is no... (1)

ArsonSmith (13997) | more than 5 years ago | (#26475009)

In the end, the only hardware configuration hat would make that much of a difference is if the windows box hat 10basetx or half-duplex. a 100basetx or 1000basetx would should saturate the 25mbs line that he seems to have. He also did say he tested it a few times so it wasn't just a one off chance of congestion.

Re:Even if the answer is no... (0)

Anonymous Coward | more than 5 years ago | (#26475139)

Instead of asking the question of whether RAM could make a difference, why didn't he just switch the farking RAM between the machines?

It's the bot net (5, Funny)

thetoadwarrior (1268702) | more than 5 years ago | (#26474421)

His window machine's contribution to a bot net is probably hogging some bandwidth.

Re:It's the bot net (4, Funny)

hendrix2k (1099161) | more than 5 years ago | (#26474481)

I believe WinAntiVirus Pro 2009 can clear that up. And probably increase d/l speeds too!

amazing (4, Insightful)

dirtyhippie (259852) | more than 5 years ago | (#26474431)

Clearly, there is no more reliable test of network performance than a flash application running inside of a web browser. On machines that are "oh, more or less" identical (I'd really like to know what network card is in them, for example?). Sheesh.

Re:amazing (0)

Anonymous Coward | more than 5 years ago | (#26474507)

Identical off lease units - only difference RAM...

and NO, increasing ram does NOT necessarily increase network throughput...

Unless of course, your box with less ram is paging heavily...

Re:amazing (2, Insightful)

CDOS_CDOS run (669823) | more than 5 years ago | (#26474573)

Which with 512Mb of ram on XP it would be. I mean this article is interesting and I don't doubt that it's a true speed difference, but this isn't a great way to test it.

Re:amazing (3, Informative)

Fallingcow (213461) | more than 5 years ago | (#26474731)

BS. XP runs fine on 0.5GB ram. Hell, when it came out, what was the norm for a new machine? 128MB? 256?

You're thinking of Vista.

Re:amazing (2, Informative)

mr_mischief (456295) | more than 5 years ago | (#26475163)

The minimum spec for the original XP and for SP3 both is a 233Mhz processor and 64MB of RAM. A 300Mhz processor and 128MB of RAM was recommended. These were extremely low-balled numbers, but a system configured such would boot and run.

Many of the applications require much more than that, though. IE7 requires 64MB minimum for just itself. Here's that requirements page [microsoft.com] .

If you take 64 MB for the OS and 64 MB for the browser, a 128MB system will probably swap from a single browser window loading a complex page, let alone doing a large download.

Now, add in Windows Firewall, some anti-virus software, and a couple of other resident programs. For testing, most of this should be turned off. The Windows Firewall I'd leave on because my Linux box would have iptables and possibly Shorewall or some other management wrapper around iptables running.

Firefox 3 isn't exactly stingy on memory use, if that's what he's using on both platforms. Neither is Flash, as it seems most download speed test web sites use.

So, yeah, he might be swapping pretty heavily at 512 MB although you're right that the base system would run okay with even less than that.

That's not the only explanation for such a difference, though. He might be running on-demand virus scanning against the download. He might not be telling us that he's saving the download to disk and one has a faster, after-market hard drive in it. An uncontrolled test is only of anecdotal value.

Re:amazing (4, Interesting)

Hairy Heron (1296923) | more than 5 years ago | (#26474963)

Yeah people keep claiming this with no real data to prove it up so it's about as worthless as the shit that the article claims. My parents have an XP box with only 512 megs of RAM and it easily maxes out at the 22mbps that they have. And that's with a half dozen apps open and at least 8 things running in the background on the systray. Seriously, the extra 256 megs of RAM isn't going to give you magically 2x the bandwidth.

Re:amazing (1)

localman57 (1340533) | more than 5 years ago | (#26474697)

Agreed. Perhaps we've merely proven that the port of Flash for Ubuntu is more efficient at using sockets than the port of Flash for Windows. Plus, we are dealing with a cable modem and the internet. Maybe your neighbor was downloading a lot of porn. Or maybe he's hacked your Windows machine, and is downloading _your_ porn... Set up a web server on a local network. Let the Windows machine download a 300 Meg file from firefox and time it. Then let the Ubuntu setup do the same thing. That's something I might care about.

Re:amazing (1)

Mashiki (184564) | more than 5 years ago | (#26474809)

Agreed bad tests are bad, along with bad articles. There are java tests that can do this much more accurately as well, and written especially for throughput and network performance. And then we can always get down to raw old file dumps.

Lets not forget network smoke, burps, dropped packets, and one of about 50 other things including the machines and network cards.

Re:amazing (1)

nategoose (1004564) | more than 5 years ago | (#26474867)

I've experienced enough differences between the same release of Firefox between Windows and Linux to more than account for this.

Re:amazing (1)

vipz (1179205) | more than 5 years ago | (#26474961)

How hard would it be to boot an Ubuntu live CD on the windows machine and repeat the test?

Obvious Explanation (-1, Redundant)

Bill Dimm (463823) | more than 5 years ago | (#26474433)

The Windows computer was busy downloading malware or sending spam in the background, so it didn't have much bandwidth available.

swap the ram and find out (5, Insightful)

bugs2squash (1132591) | more than 5 years ago | (#26474443)

surely that is quicker than writing a /. article.

Re:swap the ram and find out (1, Funny)

Anonymous Coward | more than 5 years ago | (#26474521)

Better yet, swap the hard drives.

Re:swap the ram and find out (4, Insightful)

Sockatume (732728) | more than 5 years ago | (#26474621)

Let's not jump on the guy. He didn't write the /. article. He wrote a single-page blog post about something interesting he spotted. Maybe he's out swapping the RAM right now. Blame the Slashdot submitter and editors.

Re:swap the ram and find out (0, Troll)

scuba964 (711459) | more than 5 years ago | (#26474975)

No, blame Bush.

TCP/IP Optimization (5, Informative)

MBCook (132727) | more than 5 years ago | (#26474449)

I'd guess it's some kind of TCP/IP optimization (the default size of packets, etc). It's set to one thing on Ubuntu, and another on Windows (probably for some historical reason or due to some old buggy driver).

If that's not it, I'd bet pretty high it's a bad driver in Windows.

It's quite likely that either Windows or Ubuntu is intrinsically faster for some reason, but I doubt the difference based on the way the networking stack is designed is anywhere near 10%, let alone 50% for a link this fast. On 10 gigE maybe, but not on a simple cable modem.

Re:TCP/IP Optimization (1)

duguk (589689) | more than 5 years ago | (#26474591)

I'd probably say it's way more likely its a bad network driver in Windows. Network support in Linux does seem to be a lot better. It's doubtful MTU or anything similar is going to make this much of a difference, but drivers can cause major trouble.

Re:TCP/IP Optimization (1)

bill_mcgonigle (4333) | more than 5 years ago | (#26474765)

I'd guess it's some kind of TCP/IP optimization

Yeah, I forget what's tweaked, but XP and earlier did it poorly. He should have tried Vista too.

A bogus test (5, Insightful)

dark grep (766587) | more than 5 years ago | (#26474465)

Great, very scientific. Swap the OS on both machines and see if the results hold. Otherwise 'almost exactly the same' doesn't cut it. Do a real test - the way it is described here is bogus. It may excite the Linux fan boi's but no one else is going to take it seriously.

Here's an idea... (1)

MoOsEb0y (2177) | more than 5 years ago | (#26474473)

Swap the hard drives and run the benchmarks again. If they're identical save for the amount of ram, then the Windows XP installation shouldn't freak out about new hardware.

Re:Here's an idea... (1)

Mishotaki (957104) | more than 5 years ago | (#26474805)

i would rather attack his conclusion, the memory... I would simply swap a stick of memory so that the XP machine has more than the Ubuntu machine... Since they are both P4s it's all DDR memory anyway...

this made it on slashdot? (4, Informative)

whtmarker (1060730) | more than 5 years ago | (#26474527)

The poster said 'i think ubuntu downloads stuff faster than xp but I'm not sure... the RAM is different.'

So how did this make it to slashdot. Its not like anyone but the poster has the identical hardware to run the tests properly.

@poster: If the machines are so 'identical' then swap the memory and run the tests again.

Re:this made it on slashdot? (1)

Timberwolf0122 (872207) | more than 5 years ago | (#26474849)

Or perhaps configure a dual boot on both machines.....

Scientifically Bollocks (4, Informative)

rsmith-mac (639075) | more than 5 years ago | (#26474543)

You can't test two different machines with different cases and compare the results, that's not how the scientific process works. Both machines need to be tested against the same cases - then and only then will you be able to appropriately tell if the software made a difference.

Anyhow, back on the subject, some of WinXP's default networking parameters are a bit conservative when it comes to high-bandwidth links that don't have LAN-like latency (particularly the TCP Receive Window/RWIN); a good but short description of this can be found at DSL Reports [dslreports.com] . So I wouldn't be absolutely shocked if once he corrects his methodology, he still gets similar results, although in general I find RWIN tweaking to be bollocks compared to the few people that swear it works. Vista and later OSs include self-adjusting network stacks that compensate for this and then some (Microsoft is rather proud of their sustained bandwidth over very high latency links), so I wouldn't lose any sleep over it.

Re:Scientifically Bollocks (0)

Anonymous Coward | more than 5 years ago | (#26474839)

Vista networking SUCKS. How can they be proud of it?!

Grats! (2, Insightful)

dnaumov (453672) | more than 5 years ago | (#26474565)

You finally beat a 8 year old OS!

Re:Grats! (1, Insightful)

Anonymous Coward | more than 5 years ago | (#26474673)

Uh, you think Vista would have faired better on less than a gig of memory? Or really any amount of memory?

Dated OS? (1)

CannonballHead (842625) | more than 5 years ago | (#26474567)

Internet download speeds or does Ubuntu handles networking that much faster than Windows XP?

Just going out on a limb initially to say Ubuntu is much newer than Windows XP. The Ubuntu people's release ideology is completely different from Microsoft's.

The article yields a little more information. Ubuntu 8.04

There's another question to be asked, too... I do'nt know how Bandwidth.com works. Could it also be different caching mechanisms? If bandwidth.com sends a bunch of the same information, maybe Ubuntu is caching it somehow or something. I don't know.

The cable connection the guy had also is the speed that XP is getting, and not the speed that Ubuntu is getting:

Time Warner's latest promises are for download speeds, but I think it's 10 mega bits per second to 12 mbps. Upload speeds are throttled down to 1mbps. My Ubuntu machine returned a rating from the Bandwidth.com test of 22-25mbps over several tests. That's darn fast today, faster than normal. Then I did the same test from a Windows XP PC and got results from Still fast, but not nearly as fast as the Ubuntu machine.

Anyone know how bandwidth.com in particular analyzes results?

Re:Dated OS? (5, Insightful)

vux984 (928602) | more than 5 years ago | (#26474875)

Yeah, if its a 12mbps link, and ubuntu is getting 22mbps, there is more likely something else going on than "ubuntu > xp" here.

A lot of cable providers provide 'speed boosts' to the first bit of bandwidth you request from a given source. It makes the internet as a whole a lot snappier, while large downloads etc take about as long as usual.

Perhaps they speed boosted his ubuntu test for some reason.

Another possibility, is that their bandwidth analyzer isn't working properly on ubuntu and is reporting double what it should be.

I mean, if XP was getting significantly less than his link speed and ubuntu was getting the full link speed I'd suggest bad drivers, bad cable, bad something... but XP is delivering what it should be, while ubuntu is delivering apparently more than is possible -- so my first approach would be to ensure ubuntu is REALLY getting 22mbps here, and determine how that's even possible.

e.g. ... When you measure the speed of light and find it to be twice c, your first assumption would be that you've done something seriously wrong in calculating the result, not that you've just figured out a technique for FTL communications.

Ubuntu a zealous web hog? (4, Interesting)

Un pobre guey (593801) | more than 5 years ago | (#26474571)

Anecdotally, I have also noticed that Ubuntu boxes tend to hog bandwidth, as compared to an XP box at home. When someone on the home LAN starts downloading or streaming something from a linux box, everyone else notices it immediately. The XP box is (inadvertently?) more polite about it. Still, if you're the only one pulling in the big byte loads, faster is definitely better.

Re:Ubuntu a zealous web hog? (2, Interesting)

moosesocks (264553) | more than 5 years ago | (#26474681)

Correct me if I'm wrong, but as long as you're behind a switch or a router, any one box shouldn't be able to "hog" bandwidth, unless it's threading transfers through multiple TCP streams or somesuch....

Swap the RAM. (1)

cbiltcliffe (186293) | more than 5 years ago | (#26474579)

I'd be tempted to say the memory wouldn't make that much difference. It might make a little, but not that much.
The only way to know for sure, though, is to swap the RAM between machines, then rerun the tests.

If the Windows machine is still slower, then it's definitely something to do with Windows. Although it could be that the Windows machine has Limewire running, it could be that the TCP stack has been tweaked to some very suboptimal settings, or it could be that it's running antivirus software that scans all network traffic.

Do a clean install of XP, and a clean install of Ubuntu.
Test.
Swap the RAM between machines.
Test.
Swap the hard drives between machines - reinstall XP/Ubuntu on the new drives.
Test.
Reset to BIOS defaults on both machines.
Test.
Update BIOS to latest version on both machines.
Test.
Swap hard drives back.
Reinstall.
Test.

After this, if XP still always shows as slower, then you can pretty safely say that it's the OS.
Until then, there are too many other potential variables to tell for sure, even on supposedly identical hardware.

Re:Swap the RAM. (2, Insightful)

moosesocks (264553) | more than 5 years ago | (#26474745)

I'd actually throw 1GB in both machines, and test both with that.

Given that we're testing network performance, and not swap performance, I'd want to rule out swap file usage as a factor in this test. Ubuntu 8.04 and Firefox 3 will begin swapping in a machine with only 512Mb of RAM.

TCP Window Size is the likely culpret. (5, Informative)

Above (100351) | more than 5 years ago | (#26474583)

It's the TCP implementations, and probably the TCP window size limits. Windows could turn in the same numbers if properly tuned.

You want to read this article for all the in-depth details: http://www.psc.edu/networking/projects/tcptune/ [psc.edu]

Windows has a default set many years ago, and never updated. Most of the Free Unix variants update every release, and some new variants even have fancy auto-scaling code. Any time you want to get over 10Mbps/second across any real latency with a SINGLE TCP stream you probably need to do some tuning, for some OS's the limit is much lower.

ISP's run into this all the time. An uninformed admin buys a GigE in LA and NY, pops up an FTP server and wonders why he can only get a few megabits a second across the "crappy network". A few settings later and behold, the same hardware can saturate a full gigabit.

Note, don't just go set your values really high, there are performance (memory used) tradeoffs....

Ehm wrong site? (1, Insightful)

Anonymous Coward | more than 5 years ago | (#26474601)

Shouldn't this be on fark.com or digg or some other crapcollector site? Oh wait...

Possibly not network stack but JVM instead (1, Interesting)

laing (303349) | more than 5 years ago | (#26474613)

I've read reports stating that Ubuntu's Java machine is faster than Windows'. Some of those speed test sites use Java to implement the test. This is probably the best explanation.

Could be the NIC (2, Insightful)

Hottie Parms (1364385) | more than 5 years ago | (#26474629)

It could be the NICs on the computers. Or it could be the drivers for the NICs. Or it could be any number of different possibilities.

This is not exactly front page material. I think people are being just a bit too eager to promote Linux as being a superior OS that this stuff gets pushed to the top. Of course, Linux is a superior OS, but still...

what i want to know... (1)

buddyglass (925859) | more than 5 years ago | (#26474631)

When I had Time Warner cable, the speeds topped out at 10 Mbit/s. The author of the article echoes this when he states "I think it's 10 mega bits per second to 12 mbps".

Assuming that's right, the problem isn't that Windows is slow, it's that bandwidth.com's benchmarking application is either broken on that particular version of Ubuntu or on the particular browser he's using. "Broken" in the sense that it's reporting speeds twice as high as what he's actually achieving.

TCP/IP is native to UNIX/Linux/BSD (-1, Flamebait)

fishyfool (854019) | more than 5 years ago | (#26474639)

TCP/IP is not native to Windows. Windows has the translation overhead that Linux doesn't.

Re:TCP/IP is native to UNIX/Linux/BSD (1)

abigor (540274) | more than 5 years ago | (#26475045)

Say what? Please explain, with technical examples.

Re:TCP/IP is native to UNIX/Linux/BSD (1)

KasperMeerts (1305097) | more than 5 years ago | (#26475127)

Nonsense, Windows implemented a good TCP/IP stack long ago. In fact, some think it could have been the BSD stack.

IPv4 vs IPv6? (1)

VincentSuse (1453819) | more than 5 years ago | (#26474647)

IPv4 vs IPv6?

Uh.. (5, Insightful)

mikkelm (1000451) | more than 5 years ago | (#26474677)

Only on slashdot can you have front page articles featuring original "research" done with no controls, no baselines, dissimilar base conditions, and sample bases of one single result, and have the headline speak conclusively in favour of the observed results.

If it makes FOSS looks good, that is. This is worse than digg.

Right on. (2, Insightful)

Anonymous Coward | more than 5 years ago | (#26474789)

This is Kool-Aid at its finest, and all the clueless morons feel the need to speculate on things they know nothing about with regard to an extremely flawed test. I really cannot wait until a coworker or two brings this up as if it actually had any merit, because it was on Slashdot. Given that Slashdot is owned by a FOSS company, it is in their (indirect) best interest to propagate misinformation such as this.

The Internet would be a far superior place if people were banned from discussing what they didn't know. Of course, not many people would talk much, now would they?

Re:Right on. (0)

spun (1352) | more than 5 years ago | (#26475103)

The Internet would be a far superior place if people were banned from discussing what they didn't know. Of course, not many people would talk much, now would they?

Of course, you would have been banned from posting, as you don't know what 'clueless morons' will feel the need to speculate on. You don't know that your coworkers will bring this up. You also don't know that it is in SourceForge's indirect best interest to 'propagate misinformation such as this.' In other words, here's a steaming hot cup of STFU, served with a heaping tablespoon of your own medicine.

Re:Uh.. (0)

Anonymous Coward | more than 5 years ago | (#26474977)

And yet you still bothered to:

1)create an account
2)read the summary
3)read the article
4)???
5)comment on it

CAPTCHA deterred

downloading ubuntu itself... (1)

fumanchu182 (1428447) | more than 5 years ago | (#26474679)

The most gratifying aspect out of this is if this will allow Ubuntu to download its own install iso faster. I am creeping along at 200kb/s. :(

Forget RTFA... (3, Insightful)

Darundal (891860) | more than 5 years ago | (#26474691)

...lets start with RTFS. Everyone here who keeps bitching about how this isn't a decent test obviously missed the bit of the summary where he admits it isn't, and he isn't asking if Uubntu is faster than Windows. He is specifically asking whether the difference is in the machines themselves or the OS.

More differences.. (4, Funny)

mugnyte (203225) | more than 5 years ago | (#26474703)

  One machine has a Hello Kitty sticker on it and faces West. Irrelevant? WE REPORT, YOU DECIDE!

  Maybe the tester is too close to a mental energy vortex...

Outbound connection limitation (1)

DirkBalognapantz (609779) | more than 5 years ago | (#26474713)

Could this be the result of the outbound TCP connection limit imposed after XP SP2?

Lots of variables and no constants (0)

Anonymous Coward | more than 5 years ago | (#26474717)

Why did this even make the front page??????

Is he using the same network connection? (1)

WarwickRyan (780794) | more than 5 years ago | (#26474759)

Physical network connection, I mean.

Because if the XP machine's connecting via an 10mb/s hub and linux via an gigabit switch, it'd invalidate anything at OS level.... ...it's most likely to be an buggy Flash app or buggy Javascript.

Has he tried to download a large file from his internet provide (something which'll max the connection out) on both machines, and tested the difference in load times?

re linux d/l (0)

Anonymous Coward | more than 5 years ago | (#26474767)

I found this out a long time ago. If I use a hardware router (Netgear, etc) vs linux router. The linux router more that doubles the d/l speed in speed test.

It's a dead heat (1)

networkzombie (921324) | more than 5 years ago | (#26474781)

I frequently use Linux and XP for downloading over cable (cox) and my results are always similar. I'm suspicious that anything could get 22Mbps on a 12Mbps line.

SWITCH THE RAM, DAMN IT (0, Redundant)

scorp1us (235526) | more than 5 years ago | (#26474803)

There's no reason why you can't just move the ram and re-run the tests. Time loss to you: 10 minutes.

vs being lazy an asking getting subjective answers by asking slashdot: 406735 minutes.

TCP packet size. tcp window scaling. (4, Interesting)

RichMan (8097) | more than 5 years ago | (#26474807)

possibly due to tcp window scaling

http://en.wikipedia.org/wiki/TCP_window_scale_option

ubuntu does it. Windows XP does not.

The TCP window scale option is an option to increase the TCP receive window size above its maximum value of 65,536 bytes. This TCP option, along with several others, is defined in IETF RFC 1323 which deals with Long-Fat networks, or LFN.

-rant mode, how I found out about it.
The secure side of the Presidents Choice banking web site is royally hosed by a machine that tries to use tcp window scaling. Why can't a web service provider, one that should be extra careful about security understand a standard concept.

Is this.... (1)

comm2k (961394) | more than 5 years ago | (#26474897)

Is this because WinXP defaults to adding QoS and reserves 20% bandwidth for every network device? Just uninstall/deactivate QoS for each individual network adapter.

Re:Is this.... (5, Informative)

Dude McDude (938516) | more than 5 years ago | (#26475121)

That's a myth.

Clarification about the use of QoS in end computers that are running Windows XP

As in Windows 2000, programs can take advantage of QoS through the QoS APIs in Windows XP. One hundred percent of the network bandwidth is available to be shared by all programs unless a program specifically requests priority bandwidth. This "reserved" bandwidth is still available to other programs unless the requesting program is sending data. By default, programs can reserve up to an aggregate bandwidth of 20 percent of the underlying link speed on each interface on an end computer. If the program that reserved the bandwidth is not sending sufficient data to use it, the unused part of the reserved bandwidth is available for other data flows on the same host.

http://support.microsoft.com/kb/316666 [microsoft.com]

TCP RWIN (1)

RzUpAnmsCwrds (262647) | more than 5 years ago | (#26474953)

Your TCP RWIN is too small. XP has a low default, which is too small for high-latency, high-bandwidth networks. It wasn't really a problem when XP shipped for most people, but it's getting to be a problem now.

Vista tunes this automatically. So do newer Linux distributions.

And, point of order, why are we comparing a 2001 version (2004 if you count SP2) of Windows to a 2008 version of Ubuntu?

If the result had been the other way around... (0)

Anonymous Coward | more than 5 years ago | (#26474965)

...this story wouldn't have got onto Slashdot.

unscientific (0, Redundant)

Bizzeh (851225) | more than 5 years ago | (#26474993)

this test is pretty much all bollocks... unless the SAME machine was used, and not similar machines (2 machines with the same parts isnt even good enough), then the results are not valid.

you would also need to enroll a non-bias 3rd party to conduct the test, using a non-biased software.

come back when you have done your tests properly

Driver, OS, Hardware - In That Order (1, Informative)

Anonymous Coward | more than 5 years ago | (#26475007)

Having done research about this for years in financial services labs, this isn't "odd" to me, nor has it been "odd" to me for about a decade. A lot of good hardware is hampered by rather lousy hardware driving writing and integration with the OS. Further, the Windows TCP/IP stack hasn't been known to be a hugely big performer on the desktop side.

A TCP/IP stack at its core is really about the queuing mathematics in the code itself. When you get a good match of that math between two systems, things go smoothly. When you don't, performance suffers.

Microsoft would do well to see the strides that Linux, but more so the FreeBSD folks have done in making TCP/IP stacks more efficient - hats off to the folks that have done TCP/IP stack research for better efficiency in the data center.

I'd also proffer the opinion that the threading / process code base in most UNIX OS's is vastly superior to the Windows model for efficiency - this isn't so much a comment about Microsoft as it is trade-offs made over time / different ideas.

To be fair, I've had good success in tweaking Windows TCP/IP stack parameters, but this is frowned upon in large enterprises because no one likes rolling out registry changes. Even with the tweaks, the raw network performance has always fallen short of a sample of Microsoft OS offerings. Microsoft might want to loosen things up a bit.

That's because (0)

Anonymous Coward | more than 5 years ago | (#26475075)

The Windows 7 torrents just came out! And Ubuntu has a bunch of HTTP mirrors. This isn't a fair comparison.

(For the record, I did not RTFA/S)

TCP Algorithms are "Funny" (3, Interesting)

trippd6 (20793) | more than 5 years ago | (#26475087)

I've spend a lot of time looking at this type of problem. I had a customer that wanted to transfer data at greater then 10 mbps across the internet, across the country. Lets just say with windows this is impossible.

The problem has to do with TCP algorithms. I found the ones in windows are optimized for common cases. Linux has multiple TCP/IP algorithms you can choose from. Most are significantly better the one used in windows.

The "problem" with TCP is it has to assume that packet loss equals network congestion. This is a good thing for an over-loaded network link. As the link fills up, it starts dropping packets. As the computers on each end of a TCP connection see this packet loss, they start "Backing off". They slow down their transmission rates until the packet loss is gone. In most cases they back way off, and then slowly increase the speed until they start seeing a little packet loss. The methods they use to determine what is congestion, how much they slow down, and how they recover from it greatly effects total usable bandwidth.

The bottom line: TCP Algorithms greatly effect transfer speed, and no algorithm is good for every situation. Linux gives you flexibility in this area (And by default uses a better one), and windows gives you zero.

To test raw bandwidth, you have to saturate a link with UDP data, and count how much data is received. This is pretty pointless as its not the useable bandwidth, but it does tell you the "raw" potential. The problem is the "raw" potential can be subverted by a small amount of packet loss.

Ubuntu IS faster... (-1, Offtopic)

Anonymous Coward | more than 5 years ago | (#26475093)

my monitor only runs at 60Hz on windows xp, but ubuntu has it at 120Hz!!! TWICE AS FAST!!!!!

Invalid Result (1)

gobbligook (465653) | more than 5 years ago | (#26475101)

Increasing memory in a machine can have a huge impact, but there is a point where you start to see diminishing returns.

My issue with this test is that you are running a comparison on a 2002 legacy operating system, and a fairly modern one. Driver support in XP may be better, but memory management and the TCP/IP stack may not be.

Secondly hardware differences are abundant here. "Almost the same" does not cut it, the hardware has to be identical otherwise the results are inconclusive. You need to control all variables except the one you are testing for. If you want to test hardware, then keep the OS's the same and only change that hardware component you are testing. If you want to test an OS, keep the hardware the same and only test the OS. That being said the real killer here is even if you were to test both these machines with windows XP loaded, I'll bet you'll get a different results because the OS is not the only variable that can have an impact on download speed.

A better test would have been to test the impact of RAM on the performance of Ubuntu (or XP) on your hardware with respect to download speed. This would be a simple test. But even the network connection is a variable in this test. I doubt very much that even this test can be reproduced reliably with the same results.

One more thing, test your download speed across the LAN, not across the internet. If you were really interested in finding out if Ubuntu performs better than XP, your endpoint has to be in your control. Who knows you may have been downloading from a Windows XP machine all along!

Use something on both computers (1)

TenBrothers (995309) | more than 5 years ago | (#26475147)

This could be made more scientific, in my mind, if he loaded, say, DSL or Puppy Linux on both computers and checking the download speeds for both computers. If both computers get the same D/L speed, then we know the hardware configuration (likely) is not a factor.
Load More Comments
Slashdot Login

Need an Account?

Forgot your password?