Slashdot Mirror
Ubuntu Download Speeds Beat Windows XP's
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?"
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?)
The test was done on machines with differing configurations, so therefore is not valid. But interesting nonetheless.
Help fight poverty: Punch a poor person.
His window machine's contribution to a bot net is probably hogging some bandwidth.
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.
surely that is quicker than writing a /. article.
Nullius in verba
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.
Comment forecast: Bits of genius surrounded by a sea of mediocrity.
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.
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.
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.
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.
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. 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.
You finally beat a 8 year old OS!
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?
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.
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.
"City hall" in German is "Rathaus" Kinda explains a few things......
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/
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....
Shouldn't this be on fark.com or digg or some other crapcollector site? Oh wait...
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.
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...
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.
IPv4 vs IPv6?
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.
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. :(
http://www.anthonyw.net
...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.
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...
Could this be the result of the outbound TCP connection limit imposed after XP SP2?
Why did this even make the front page??????
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.
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?
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.
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.
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?
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.
Slashdot's rate-of-post filter: Preventing you from posting too many great ideas at once.
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 because WinXP defaults to adding QoS and reserves 20% bandwidth for every network device? Just uninstall/deactivate QoS for each individual network adapter.
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?
...this story wouldn't have got onto Slashdot.
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
portfolio
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.
Say what? Please explain, with technical examples.
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)
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.
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!
Look at this http://www.firefox-now.info/
22mbps is .00275MBps
I can do better than that by hand.
Nonsense, Windows implemented a good TCP/IP stack long ago. In fact, some think it could have been the BSD stack.
As long as there are slaughterhouses, there will be battlefields.
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.
The Linux TCP/IP stack is more effecient than the XP stack.
Dell XPS M1530 Intel Core 2 Duo (2.16ghz) 3 gigs RAM Dual Booting Windows Vista Home Premium AND Ubuntu 8.10 http://www.bandwidth.com/tools/speedTest/ Six tests per OS. Vista: Download/Upload 7616/2795 7865/2724 6407/2755 10050/2800 12320/3925 15854/2905 Ubuntu: Download/Upload 12939/5897 8849/12122 15373/18646 20040/17093 8461/14969 17885/13807
Why would the author think it odd that the network stack performs so well? New to linux perhaps?
how the HELL did this garbage become a slashdot article? there was a time when slashdot actually screened out the crap and provided real tech news... if we wanted Digg we would go to Digg, we want "News for nerds, stuff that matters"
-- Sex is the antonym of pringles. Once you pop it's time to stop.
Boot the Windows box using a Ubuntu live CD and run the test again.
Repton.
They say that only an experienced wizard can do the tengu shuffle.
We used to regularly benchmark Oracle on the same hardware running Linux and then Windows Server. Linux always won. Not by a huge margin, more like 15%, but saving money and getting better performance is win-win!
I don't know, but it works for me.
I had a grilled cheese at Applebee's and tacos at Chili's. I like tacos so Chili's is better.
The Ubuntu machine has 768MB of RAM, while the XP box has only 512MB of RAM ... Can a little extra RAM make that much difference in Internet download speeds or does Ubuntu handles networking that much faster than Windows XP?
So, swap the memory sticks, run the test again and then you tell us.
My favorite quote doesn't fit into 120 characters. Now no one will like me.
I don't have TW cable, but I do have Comcast. Comcast will allow you to do what's called "PowerBoost" - which I'm sure most of you have heard of.
Essentially what it does is allow you to burst up to twice your bandwidth for a certain amount of seconds (really nice for smallish files).
PowerBoost, at least for me, seems pretty intelligent to network congestion. If it's prime time, I notice it doesn't do it as much. I believe that's what's happening here.
Besides that, no one but Time Warner has control over the network. You have no idea what's going on with it. For all anyone knows, there was fiber cut at the exact same moment...
Try this with a local server and a switch and then let us know how it is.
PS. What's a kilo bit? Is that 1000 grams worth of bits?
Discounting the machine config differences and os changes, I have never trusted these little 'bandwidth' meters over the years. Honestly the only way to really determine for yourself how much bandwith you're capable of achieving under real world conditions is to fire off a bunch of large transfers against people you know have fatter pipes than you (if you cant take a guess and figure out a couple, then your bandwidth flash app will meet your needs just fine).
Case in point, I recently switched carriers at my home office. My internal backbone is gig E, and I had been using an older juniper/netscreen firewall that would only do 10meg throughput because I had not been on a pipe that would exceed it (no reason to swap it out).
After switching carriers I noticed that I was pretty much running 90%+ utilization on that firewall's interfaces, and started poking into advertised throughput rates for my current connection, then dropped in a Juniper SSG5 which will do 140Mbit stateful/deep packet inspection (40Mbit AES/3des vpn), fired off a bunch of transfers, watched throughput and saw this pipe is capable of sustaining ~25Mbit ingress.
That awesome little bandwidth.com thing pegged my connection as a 1Mbit pipe...
I'm pretty sure (being a mac/ubuntu bod mostly but having to support windows at my office) that XP has a Quality of Service service running by default, which limits the amount of network access the computer has "for the greater good of the network". The limit can be quite annoying, and I just tend to remove it. Maybe he should see if it's active (in the network settings, if I remember correct), disable it, and run the test again.
Before anyone repartitions their drive, it's worth reading about cargo cults:
http://wwwcdf.pd.infn.it/~loreti/science.html
There are no karma whores, only moderation johns
I just went to Bandwidth.com and used their bandwidth speed test. It game me no option to select a server just started a test. Results: 5683kbps down 1679kbps up So then I went to Speedtest.net which game me a choice of servers Going from Redmond here to the Seattle servers I got 77418kbps down 9069kbps up So Bandwidth.com is not really showing a true measurement of your bandwidth. I really doubt that unless there is something wrong with his machine that it would choke at 12mbit when his network can clearly achieve 22mbit.
[HKEY_LOCAL_MACHINE\SYSTEM\CurrentControlSet\Services\Tcpip\Parameters] "Tcp1323Opts"=dword:00000001 "SackOpts"=dword:00000001 "TcpWindowSize"=dword:0003ebc0
If he was serious about finding the difference in download speeds, he would run both operating systems as virtual machines on the same piece of hardware.
Do not mock my vision of impractical footwear
yes. there is a tcp-ip configuration beyond turnind on dhcp. Different OS may have different default parameters for this configuration. If you don't know where to find it, don't meddle with it. But is NOT surprising that at this connection speeds subte change in the parameters influence the performance of the connection significantly. Especially because when the defaults for XP where set, probably the person in charge did not assume connections with more than 100Mbit for the "normal" user, while this assumption have been stupid for a system acting as a server quite often.
And this topic was discussed quite often....
I believe XP has tcp window scaling turned off by default, whereas modern Linux kernels and Vista have it turned on.
See http://en.wikipedia.org/wiki/TCP_window_scale_option
This can make a massive difference if there is more than a tiny amount of latency on the line...
http://spamdecoy.net - free throwaway anonymous email - avoid spam!
For every month I use Ubuntu, my penis grows three inches longer, so every couple of months I switch back to Windows and after a few weeks, it's back to normal. I would try OS X, but a friend had it, and he turned gay.
More than 60,000 Windows programs won't run on Linux.
http://www.extremetech.com/article2/0,2845,1153609,00.asp
That should account for some of the difference, though not all.
If windows really did half the speed of your connection, I think it might have been picked up and commented on.
I think the post should have read "My windows box is broken and my linux one isn't"
If anybody here is worried, I've got a 20M cable connection. It runs at precisely 20M and does so on all my PCs (Linux and Windows) - can I have a story posted about me?
There's loads of things you can fiddle with and it may make a difference on fast connections (Jumbo frames, MTU, Not using an onboard NIC - but none of this would have a 50% hit on the download rate at 20M).
Why even write about this if you haven't attempted to add the extra memory to the Windows XP machine to see if that makes a difference?
about the rigorless "research" done by the op, just pretend that the article was posted in "ask slashdot", get off your high horses and try to contribute to the discussion.
maybe even doing some of that rigorous research yourself.
If the benchmark he's using sends a set of data, which is stored on disk and then sent back, at least in my experience, there could be a WORLD of difference between windows and Linux on similar hardware, even with twice as much RAM for windows as for Linux. Every windows desktop I use becomes almost unusable during any continuous disk access - rsync, cp, etc., while much lesser-equipped Linux systems don't act any different doing the same tasks.
I'm talking desktops here - 1G or less RAM, single IDE hard drive, single-core post-pentium somethingorother. The server-class windows systems seem to be every bit as capable as the desktop-class Linux systems.
You are offering a hypothetical situation to a real world example.
Instead, how about just making a reliable test? Multiple servers with multiple OS's and multiple apps (all controlled) over a controlled connection.
The ONLY change should be the client OS's.
It's just basic science.
He forgot to mention that the Ubuntu box has a Type-R sticker. Mystery solved.
I can recall a 20% or better speed difference transferring files on LAN depending on whether I initiated the connection from the Linux or the Windows box.
I know Comcast has a thing (Powerboost) where it gives you double download speeds for the first x minutes of a download. Could that be at work here?
I'm doin' pretty good imo.
Also: We just made wheels.
I have a 15Mb/s FiOS connection.
When I run a flash-based speed test with Internet Explorer, I get pretty close to 15Mb/s on both downloads and uploads. With Firefox, I get 15Mb/s downloading, but only about 5Mb/s uploading.
I got these results on the exact same system with the same versions of Flash.
Window scaling is disabled by default on windows, which limits TCP sessions to 64 kB, hence the per-session bandwidth on high-latency links such as DSL.
10-12 Mbps is typical of a DSL link with a 50 ms RTT (=ping time). 64 kB is 512 kbit. 512 kbit / 0.050 s = 10240 kbps = 10 Mbps.
I've already seen tuning guides on the net explaining how to enable window scaling on windows, though I'm not that much interested ;-)
Willy
What protocols are bound to the Ubuntu and XP NICs? I'd start with equalizing the RAM as suggested earlier, disable all the extraneous Windows protocols on the XP box, and check that the receive buffers, etc are set up identically. Still, I wouldn't be surprised if the Ubuntu machine shows a modest bump.
Nothing to see here but us trolls...move along...
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?"
I don't know! But if the author wanted to know, all he had to do was to spend another $5-$10 to drop 256MB of RAM in the XP machine, making this test provide some actual information. As is, this test (and accompanying article) is completely useless.
I'll wait to install Ubuntu until it beats XP all of the time.
Fine, what is this then:
Windows (Cygwin):
$ ping -n 20 www.google.com
Pinging www.l.google.com [74.125.39.147] with 32 bytes of data:
Reply from 74.125.39.147: bytes=32 time=12ms TTL=245
[...]
Ping statistics for 74.125.39.147:
Packets: Sent = 20, Received = 20, Lost = 0 (0% loss),
Approximate round trip times in milli-seconds: Minimum = 11ms, Maximum = 41ms, Average = 16ms
Ubuntu:
lukas@9a:~$ ping www.google.com
PING www.l.google.com (74.125.39.147) 56(84) bytes of data.
64 bytes from fx-in-f147.google.com (74.125.39.147): icmp_seq=1 ttl=245 time=15.3 ms
--- www.l.google.com ping statistics ---
22 packets transmitted, 1 received, 95% packet loss, time 21003ms
rtt min/avg/max/mdev = 15.321/15.321/15.321/0.000 ms
Happens on my network no matter what I change - cables or notebooks, Vista runs ok, Ubuntu sucks big time. The only non-standard thing is that I have wired connection with manual IP address (connected by Linux based Asus router).
lukas@9a:~$ lspci | grep Eth
00:19.0 Ethernet controller: Intel Corporation 82567LM Gigabit Network Connection (rev 03)
Memory can make a difference. Ubuntu Linux handles network traffic differently than Windows. Now we have that settled. What question would you like answered next.
This article is idiotic.
How much latency did the network have? If latency was anything more than minimal, window scaling (disabled by default in XP) would allow the Ubuntu machine to better fill the connection.
How much packet loss, if any? Selective ACKs and Timestamps can affect recovery time after lost packets and transmission timeouts. XP does not use either option by default.
A quick look at /proc/sys/net/ipv4/tcp_congestion_control indicates that the default on the ubuntu machine where I'm typing this is the "cubic" flavor of TCP congestion control. I believe that XP uses the "New Reno" variety.
All of these can have an impact, and obviously TCP can be tuned on either OS. The discrepancy is probably due to TCP options that are relevant to his connection (and configurable in XP), but disabled by default.
Try using a zero-knowledge proof to show you don't know anything!
I wish apple would sell a powerbook with a real right-click. External mice work okay for desktops, but it doesn't make much sense to haul around a mouse to use on your laptop just so you can right click
(to me, it's a memory thing. I dont' like using apple keyboards either because the machine would be my personal machine and I see troubles switching back and forth to using linux at work and mac at home because my brain's confused what keyboard layout i'm using)
-Bucky
"Who knows, you didn't test it right?" With a test like that all you did was find a difference. Since there are no controls, there is no way to tell what factor(s) were in play. If he really wants to know, he can spend the time to do a proper test. However none of us can help him with his answer currently, since the data does not support any conclusion.
I think people are equally mad at the Slashdot editors for publishing crap like this. After all, if this is the kind of stuff you have to scrape up to try and support OSS, it's in bad shape.
This is too easy to test by swapping the memory between the two machines to actually pose as a question on Slashdot. How lazy can you be about this?
"It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
I'm pretty sure it's the cable company's speed boost doing it, not some incorrect measurement. I had the exact same thing happen to me a couple years ago, but with Vista, not Ubuntu.
:)
:)
I have Comcast cable internet, and at the time paid for a 8 Mbit/sec connection. I was using XP, and could reliably get 8 Mbit/sec sustained speeds when downloading from newsgroups using NewsBin Pro and Giganews. I installed the Vista RTM in January 2007, and suddenly I could get 24 Mbit/sec sustained downloads. It wasn't just a speed test reporting wacky numbers, I could tell that my downloads were coming in 3 times faster than normal.
At the urging of fellow slashdotters, I downloaded and tried a Knoppix live cd, and ran a speed test: I got almost 20 Mbit/sec.
My conclusion was that Comcast at the time must have set up their speed boost feature in a way that worked on Windows computers only. Something in the Vista networking stack (Microsoft completely re-wrote the network stack for Vista), and also something in the Linux networking stack, caused the speed boost to stay turned on and not drop back after a few seconds.
A couple weeks later, my download speeds dropped back to a maximum of 8 Mbit/sec, so Comcast must have figured it out. Time Warner apparently hasn't figured it out yet. Enjoy your free extra speed while it lasts.
Here's my post from back then (my first slashdot post ever.
http://slashdot.org/comments.pl?sid=217980&cid=17700566
This story doesn't surprise me at all. I am a developer for next generation cable equipment, and we have also seen problems with Windows XP mysteriously and severely limiting our downspeed tests (to about half of our expected speed). We spent a lot of time banging our heads against our own cable modem firmware and the network config on the laptop before we finally figured out that Windows XP was the root cause of the limited bandwidth. Not much more we could do to figure out exactly why since Windows isn't open source. Maybe we should have installed Ubuntu on the laptop. Why would MS need to make their products work well? The majority of Windows users don't know enough to measure how much it sucks anyway.
There are subtle variations in speed from different computers, even if the hardware is identical.
To have a truly conclusive test, I would recommend running an internal web server, with a direct NIC to NIC connection using a xover cable to the PC you want to test. ;P ) then download the same resource 10 times on each OS and average out the speed.
Dual boot both OSs (at different times obviously... though if you can pull off a dual dual boot, please tell me!
To be perfectly honest, there is probably no study out there performed by a reputable research company that can show the network stack in Linux is THIS MUCH faster than the Windows network stack. In fact, I would be willing to be the driver on the Compaq running windows for the network card is the compaq-provider driver and is rather stale, or even better the NIC may be a different revision than the one in the other compaq running Linux. Also, if the download speed test was performed in Windows first, chances are that Comcast had the files cached for a quicker download if the tests were performed back to back. There are too many variables to warrant this post even being displayed, and there are no whitepapers out there that will back this performance difference.
And then there was E
Logitech S 530 Mac. Three mouse buttons (plus the extra configurable ones) as the godz intended.
The no-button mouse from Apple is a close second.
i heard somewhere the windows tcp/ip stack (or part of the networking software configurations) is at fault for windows slow connection, in comparison to unix type systems.
i also heard new updates to windows dumb down the connection even more... can't recall if it was for vista or xp. but you can search for, and use, a windows bandwidth optimizer to pretty much fix the issue.
though i'm sure the ram does have some effect, in certain situations. the browser will too!
DON'T CAPITALIZE! CO-OPERATE! AND FREE EVERYTHING!
Well all I can say is that when I upgraded my home box from XP to Ubuntu 6 point something or other, my highest download speeds - real cargo, not speed test packets coming from well known test IP blocks and manipulated by the service provider - the highest sustained download speeds went from around 270 kbps to over 1 mbps. Exact same hardware, cable modem, etc. Initially I dual booted and so I was able to duplicate downloads within an hour or so of each other to see whether it was the OS or the network that made this happen. Initially I did not believe the speeds reported by Firefox and iptraf, but I did the math and they were correct.
My best guess: The Internet is a UNIX network. Microsoft products talk to it through an adapter, which creates a bottleneck. Nor can Microsoft products take full advantage of bandwidth optimization hacks that are built into UNIX-like network stacks.
>I wish apple would sell a powerbook with a real right-click.
And I wish other laptops had the "two finger" right click and the two-finger scroll.
-fb Everything not expressly forbidden is now mandatory.
Um . . . "SO WHAT?"
Hey, I like f-ing around with Linux as much as the next quasigeek, but if I need to do something important, I gotta go to Windows to do it. And ya know what? I DESPISE that fact. The fact that this gentleman got better U/L speeds with a newer OS than an older one really seems to miss a colossal point.
For example, perhaps I should write an article about how much time I saved using Office 97/2000/2003/even 2007 to scribble an exquisitely-written document than I could with OpenOffice with their whole development team behind me to help me meander through the(shall we say) offbeat menus of their, um, application.
Heck, I would hope Linux would do SOMETHING better (and easier) than Windows by now. It's been nearly TWO decades of development, guys! Flame me all you like, I can't stop you, but I have been pulling for Linux in various incarnations since 1997, so I've been there and BACK, fella.
I've wanted to run Linux on my two notebooks because it's sooooo much simpler--no antivirus, no defragging, no spyware/malware scans, none of that BS associated with Windows. But I also need to EASILY backup my entire partitions, document folders, have my external hard drives identified and a slew of other things; I need to edit audio and video easily and quickly; I need WLAN access easily and quickly; I need my video and/or audio subsystems to work easily and quickly so I can get some work done--or alternately, just enjoy myself, fer crissakes--is that too much to ask? Linux still just isn't up to the task, and as I said, I really hate that.
Don't bother asking me to stop complaining and start coding if I don't like it, either--besides having enough on my plate already, I don't have any need to start coding for MS or Windows inadequacies.
Some may enjoy 1970s-'80s-style command-line rubbish, but puh-leeze already! Anyone who wants to tell me the command line is or should be a superior experience to nearly any GUI should take their televisions, video players, and game consoles and replace them with AM radios, telegraph rigs, and wax-cylinder "audio players."
I am dual booting XP and Ubuntu on my system. I've seen Ubuntu download at 21k but the best XP has done is 16k.
I'm all for Windows bashing, but this is kind of ridiculous! I mean, wouldn't someone already have discovered if Windows would eat 50% of the network capacity in terms of transfer? This is probably an aging NIC or something, maybe a broken cable or the update was downloading SP4 the nineteenth time. Would be cool to use sensible configurations for this kind of test, like make the machine dual boot and test it on the same hardware before making wild assumptions. And now, please excuse me, I have to look for articles that bash Windows and have some valid points..
PowerBook? Right click? 2003 wants its complaint back.
Jonathanjk.com
XP's TCP/IP stack is much the same as NT has been using for quite a while. It takes ages to ramp up the TCP window size. It makes for terrible results on "speed tests" unless the test is quite a long download.
Vista is much more aggressive in increasing the receive window.
Run a throughput monitor of some sort while performing the test - preferably one that graphs throughput against time.
-- All your bass are below two Hz
There is a now issue with this kind of test and windows. ItÂs about how windows use the TCP buffers and "windows scaling".
The NDT projet (a opensource bandwidth testing package) recomend these sites to users:
http://www.psc.edu/networking/projects/tcptune/#WindowsXP
http://www.dslreports.com/drtcp
If anyone RTFA you can see 1 thing : Vista is on a DSL line, Ubuntu is connected to a cable modem. He is testing is connection speed with a different connection on each computer...
The result only mean that the cable modem is faster than the DSL.
that linux has a better network stack than windows xp....
More ram literally makes EVERYTHING faster. EVERY TIME. Without exception. Even Winamp 2.81 will open faster with more ram.
I suggest more ram as the #1 upgrade for almost every client. They almost always have an adequate CPU and inadequate RAM. Stupid Dell/Gateway/etc! Put more RAM in you butt plugs!
I hold very few opinions. I hold information based on observation and fact. If you wish to disagree, please use facts.
I can write a /. article in less than 20 seconds. It might even be better than the parent!
I hold very few opinions. I hold information based on observation and fact. If you wish to disagree, please use facts.
First some elitist sciencey guy says stuff that makes me and Jesus angry. Then I edit it all down to make me happy so it matches the bible. Then I build a museum with dinosaurs and humans coexisting. THAT is how science works in 2009. Get with the program.
I hold very few opinions. I hold information based on observation and fact. If you wish to disagree, please use facts.
I happen to be dual booting Windows 7 with my usual ubuntu at the moment for testing purposes, so I thought I'd check and see what kind of results I got with download speeds. My conclusion was this: it makes very little difference. Windows 7, and Ubuntu were pretty much the same, and I ran the test on each several times. While I'd love to see hard evidence that'd make speed freaks switch to Ubuntu, it's kinda sad to see some piece of crap like this come out.
"Real" news sites like CNN and Fox do this all the time. My guess is /. is trying to compete!
I hold very few opinions. I hold information based on observation and fact. If you wish to disagree, please use facts.
It was originally implemented in Windows 98, and it was the BSOD stack.
Glonoinha the MebiByte Slayer
.
For all I know, XP's firewall is a bit on the heavy (processing) side and who knows if Windows Update was running...
>And I wish other laptops had the "two finger" right click and the two-finger scroll.
Why, so one could have more accidental right clicks and scrolls?
I had similar results, using the same computer but dual booting between Kubuntu and XP. I was using XP to deal with Comcast tech people and did a few speed tests to confirm my upgraded bandwidth status and when I was finished with Comcast support I booted back into Kubuntu and ran the speed tests again. In kubuntu I was using Firefox, whereas in Windows XP I was using the Microsoft browser.
I'm sorry but how do I use my mod points to mark troll to any of the following /. OP post or TF ?
winXP x64 sp2:
ubuntu 8.10 x64:
huh, weird.
what's funny is this is actually a problem with firefox & flash. If you run the same speedtest in IE7/XP it will beat the crap out of ubuntu :)
This shouldn't be news!
Modern Linux kernel 2.6.17 and later has TCP auto tuning, so it can better adapt to the network and saturate it. http://www.psc.edu/networking/projects/tcptune/#Linux Windows XP default TCP window size is too small and needs registry tuning for it to be optimized high speed broadband connections. Just google for WinXP TCP tuning. Or try comparing with Vista as it has better TCP/IP stack.
A long time ago, the same laptop (a Toshiba with a 500MHz AMD K6-2) downloaded the same files (a 10 MB Mozilla installation file) about twice as fast when running Slackware (with 2.2.6 kernel if I recall) than when running Windows 2000, with 384M of RAM. This was done several times in succession and the difference was very consistent. This was done on the same hardware, with a dual boot configuration.
And mcafee speedometer is still around now. Try it yourself. Dual boot the same machine and speedometer it. It's pretty amazing.
And this is the exact reason why my tvpc now is running ubuntu for pure bit torrent goodness while the gaming pc still boots xp.
...the time of day was the factor here. The FA said he tested his XP system, then his Ubuntu system. My guess is that the Ubuntu test happened at a time where either fewer people were on his segment (at the telco, since he has DSL) or the vendor loosened the bandwidth during an off-peak time.
It must have been something you assimilated. . . .
Please stop submitting stories, each one is uniquely similar to shit.
Trackball users will be first against the wall.
How is this even news? Of course Ubuntu is faster.
For another difference, I calculated a million digits of pi in both windows XP and Ubuntu on the same machine (dual boot).
In Ubuntu, my time was 5.7s
In Windows XP, my time was more than 14s
I can confirm this, though, that in windows I get slower speeds. I get roughly the same as the OP, even.
:(){
The asus eeepc i have (1000ha model) has 1,2,3 finger click and two finger scroll in windows xp and linux.
I've witnessed speedtest.net giving higher bandwidth rates than a customer had in available bandwidth. I wouldn't trust it; I use Speakeasy's test instead.
I'd rather not have 2-button right click. My dell laptop has it so that if you touch on the "scrolling" part of the touchpad, it counts as a mouse3 event. It's the most obnoxious thing ever.
-Bucky
If they are only getting mbps on both machines then I'd say there is something else wrong. This story would be more relevant if it was Mbps.
Conservation of angular momentum makes the world go round.
Some of it's probably just window size or possibly even drivers, but I suspect Linux may also do a better job of handling Delayed Ack. It's pretty smart about only using it where there's something to be gained, whereas by default I think XP always uses it. A high-bandwidth internet connection means high BDP, which means the Nagle's Algorithm and Delayed Ack interaction gets particularly bad.
Except that to right-click on OS X, you need ctrl+mousebutton, which means you need two hands instead of one.
or I can just, you know, right click as with any mouse and lo and behold! it right clicks :P
It might *look* like there is only one button, but it actually does register right and left clicks, just like it does when I boot into XP.
I get sick of Mac stereotypes perpetuated by people who really ought to know better.
Oh I use my mac because its a superior environment to work and play in, not because I am some kind of OS/Hardware snob (stereotype #2) :P
"The first time I got drunk, I got married. The second time I bought a chimpanzee, after that I stayed sober" Arian Seid
Regedit this, reboot, done, no need to complain to the entire world. Any sysadmin should be able to give you the solution.
Windows Registry Editor Version 5.00
[HKEY_LOCAL_MACHINE\SYSTEM\CurrentControlSet\Services\Tcpip\Parameters]
"TcpWindowSize"=dword:0000faf0
"SackOpts"=dword:00000001
"Tcp1323Opts"=dword:00000003
[HKEY_LOCAL_MACHINE\SYSTEM\CurrentControlSet\Services\AFD\Parameters]
"DefaultReceiveWindow"=dword:0000faf0
"DefaultSendWindow"=dword:0000faf0
There's a setting in Windows XP that, by default, is set to allow bandwidth reservation for QoS packets. In the Group Policy Editor, it's:
Local Computer Policy / Computer Configuration / Administrative Templates / Network / QOS Packet Scheduler / Limit Reservable Bandwidth
Could that be the cause of this differential?
There seems to be conflicting information about this setting if you read information on the Internet - some say that unsetting this gets back up to 20% of your bandwidth while others say leave it alone as it's only used when QoS packets are sent, mainly when using VoIP.
It would be interesting to get a definitive answer on this.
Gentoo Linux - another day, another USE flag.
Once I had to transfer a few gigabytes from one machine to the other, and I was doing this by piping the data through netcat. When running XP on the sending box and Ubuntu on the receiving box, the speed was much slower than I expected, so I rebooted the sending box from a Ubuntu livecd and tried again, and the speed was approximately what it should have been.
When windows writes to a fragmented file system, the download rate can slow significantly.
Repeat the test after a disk defrag and the download rates will improve significantly.
ymmv this might mess up some sound during heavy downloads.. so far I havent had a problem.
Storm
People please: taking 2 data points is not a test, especially if you change more than one variable. Gesh, this should have been taught in junior high science.
There are a lot of things I really like about my Macbook Pro and the touchpad (quality and behavior) is one of them. I take it you disagree, so whatever.
-fb Everything not expressly forbidden is now mandatory.
Assuming all other conditions are equal (and I'll probably never believe that having not seen the test setup personally) the next step would be to take packet traces with Ethereal, tcpdump or similar in both OSs under the same conditions. If it's an actual difference, this could just be an issue of TCP settings and the way the download test is being performed.
One thing that could be it is the TCP delayed acknowledgment timer setting. I've seen this thing introduce huge delays for the IMAP protocol when Windows is the client vs Linux. I would expect the download test to not have so many round trips for this to be a problem, however the only way to tell for sure is to take those packet dumps in both OSs and submit them to a technical audience for analysis. Without that, the rest of the info posted about this is just noise.
Can you also do things like middle-drag?
The Tao of math: The numbers you can count are not the real numbers.
= random number generator?
for(b=(a=0)+1;;b+=(a+=b))print(a+"\n"+b+"\n");
XP TCP/IP stack is obsolete. Vista TCP/IP stack is much better. Yet another reason to use Vista
I have a fairly normal HP laptop, an nx7300, and that supports multi touch, such as 2 fingers for middle click, 3 for right, 2 finger scrolling and so forth. At least, it does under Ubuntu! I've not tried it in Windows 'cos ... Well, I don't use Windows.
So, there are other laptops which support it, as long as you have the right software.
Tap with two fingers instead of one on the touchpad. I think there's a system preferences setting for this, but I forget.
Network performance between different NICs and using the same NICs with different drivers, different settings, different switches, and different cabling can make a HUGE difference. One of my jobs is working on the design and build out of ticker plants for market data. We tend to hammer on networks REALLY hard!
There are several simple basic things that can easily vary which will make at least a 200% performance difference on either 100baseT or 1000baseT LANs.
For example a lot of card/switch combinations will fail to negotiate full duplex operation, that's a 50% performance hit right there.
Beyond that different cards have different amounts of intelligence and different amounts of buffering and DMA capabilities. Most drivers are generic chip set drivers, so they usually don't optimally set up the hardware. Different implementation bugs in either the card or the driver can also interact in various ways which can seriously degrade performance.
Overall I'd say that if you have a sufficient level of expertise with the drivers and the NIC you can pretty much always get SOME improvement in any given setup, and for the truly bad cases I've seen 3x better performance after tweaking on Linux.
"Malo periculosam, libertatem quam quietam servitutem." -- Jefferson
22-25 and 12-14 is a BIG difference in speeds. Has the Windows computer been checked for malware and suspicious services?
Aside from that, I know from personal experience that a lot of Windows software will install a service that will automatically check for software updates. (HP and Google both do this) If any software update, antivirus update, or even a MS update was being downloaded that would account for the speed difference.
I like and use Linux, but I doubt that this is a case of "linux is teh aw3s0me omgz0r!" Most likely there is something on the Windows computer, either malicious or legitimate, using the extra bandwidth.
Until 2 months ago, I was a Win2k user only. Until someone got me on Linux. Now I regularly get 35 kbps downloads - yes I have a slow cable (all I can afford for now) but before on Win2k, 30 was *tops*. While I constently had to re-set the connection with 'ipconfig /renew' - to the point I wrote a 1 click button script to do that job. Linux NEVER has that problem.
I'm looking foward to a much faster connection now.
- Kc
-- Kevin C. Redden kcredden@ gmail 392992
The trick to getting XP to download at a faster rate is looking to see how many seeders there are. How often do you need to download a new operative system anyway? Oh, you mean...
Artificial Intelligence stands no chance against Natural Stupidity
Speedtests produce different numbers because of the different TCP settings.
I bet you if you download an .iso from your ISP's ftp server and you measure the time it gets to finish, the results would be exactly the same irrespective of the OS.
While the "article" is an utter failure since it's not even a dual-boot system, or far better, many dual-boot systems - if somebody were to do this properly, Linux *should* be the faster of the 2 aside from driver any driver issues.
For the people that aren't aware, Windows does limit the number of simultaneous network connections depending on what version (Home, Pro, Server) that you are running - however, I've just gotten home from work, and am not going to my car to get my old MSCE book...
The default TCP window sizes on XP for a sub-Gigabit LAN are 8 Kb. While that value is a sensible, conservative default for a LAN, this value can be easily changed OS-wide in the registry, Group policy, or a PowerToy utility. Smartly coded programs can also of course change it for their own connections using SOCKOPTS.
Using a gigabit LAN, which uses 16 KB window sizes by defualt, you get much better speeds on XP, even without registy tweaks:
The problem is not XP's TCP/IP stack in general, which easily does Gigabit-class throughput as shown above. Since the OP didn't say anything about his LAN hardware, I am going to assume he's seeing the lmitations of an 8 KB TCP window size when talking to an internet server with non-trivial latency.
Set the XP box up dual boot and answer the question yourself.
Ubuntu download:
Go to ubuntu.com, follow the download link.
Time: ~10 Seconds.
Windows XP download:
Go to the torrent site of your choice, find still active tracker with some seeds or at least one distributed copy. Wait.... Wait...
Time: >>10 Seconds.
quod est demonstrandum.
oh... wait...
This is probably just a fluke.
I experienced the exact opposite when I upgraded to Ubuntu 8.10 from 8.04.
In my case it was that Ubuntu 8.10 used a automatic MTU (maximum transfer unit) setting that resulted in a 50% decrease in bandwidth compared to Windows and previous Ubuntu releases. I set in manually (to 1500) and now have the same speed as before.
No, it is not the Ubuntu. It is the Linux operating system what is used on the Ubuntu.
Any REAL Linux user knows that Linux is _faster_ on networking than Windows.
You do not need to think about browsers or any applications (what ain't part of OS or Ubuntu!) when thinking what makes the network speed so great. It is the one of main purposes to OS to exist, to give a networkin capabilities for applications, so they do not need to include it itself.
Ubuntu is NOT anyway special system to other... so stop these Ubuntu marketing on slashdot.
It seems that people does not even understand what Ubuntu is and how it is marketed now for people by terms what does not relay anykind facts. Just like on other news, Ubuntu users are mostly a newbies on Linux, and it can be noticed easily by their skills.
It's been a while since I've noticed this specifically (as it's been a while since I've touched Windows in any serious way), but I do distinctly recall the increased download speed under linux being a non-insignificant factor in my preferred Linux use back around 1998-1999.
I had an external 56k modem which got about 4.5kbps max in Windows (98) and IIRC almost 7kbps in Linux (Mandrake 6 at the time, IIRC). I shortly thereafter moved the modem to a dedicated 486 debian machine which did dial-on-demand for the home network (which was composed of my brother and me). We later tried it out with the cable modem and we got maybe 15% better performance with Linux, again.
~/ssh slashdot.org ssh: connect to host slashdot.org port 22: too many beers
I'm assuming that the O.P. is using the onboard NIC to perform these speed tests. If they are, then yes the extra system memory makes the difference. Simply put, an onboard NIC has to use system memory to handle it's off loading, which is why a dedicated NIC is going to be even faster - not only does it include dedicated memory but it does its own processing, thus completely off-loading the tcp/ip stack from the cpu/system resources. As a final note, the Linux system is still using the original BSD TCP/IP stack that Win2k and earlier versions used. As of XP, MS changed the entire stack (reinveting the damn wheel) trying to break Samba and increase vendor lock-in but instead they increased network overhead for XP/Vista and all later versions of windows (requiring network upgrades to be factored in for Vista Adoption that killed it for businesses).
Mod me up/Mod me down: I wont frown as I've no crown
People are JUSTrecognizing this? I have Comcast, and I havea dual boot machine, so the hardware is exactly the same for both. Ubuntu kills Windows XP at download speed test sites. Frequently Ubuntu will pin the meter. However this does not translate into superior download speeds all the time. All too frequently it seems to be very slow. Occasionally though, iy gets interesting. Early in the morning sometimes Comcast takes off the restrictions on the line (probably because there are so ferw people using), and I can hit incredible (for the US) download speeds. Not wure what it is about Ubuntu that shows such incredible speed during these tests, but I wish it were true!
Open Source: Eroding the Digital Divide
My Compaq R4000 Synaptic pad has two finger scroll.
Look, my very first question is:
1) Are you running Anti-Virus software? Most Windows Anti-virus suites will analyze downloads which puts a cost and thus slowdown on downloads.
Follow up question
2) If not, why the hell not? You could very well have a viral infection that is wasting resources.
This is not news. This is ancedotal evidence at best. However, since it portrays Microsoft in a negative light, it makes it way on to Slashdot which sometimes poses as a source of technical news.
Well, sure, but the problem is when I switch from my machine to someone's who has an actual physical 2nd mouse button, will my brain be able to keep it straight, or will it be like when I switch cars and stall it out because it takes a while to remember how much I need to feather the clutch.
-Bucky
Does he have the card in full duplex in windows? If he is running half in windows and full in linux, that might do it :)
And netbsd is faster than linux. Tell us something we don't know. The network stack used by the linux kernel is more efficient than windows. And the netbsd stack is more efficient than both. Anyone have a top ten network stack efficiency ranking list?
This is a comment to those who have replied to say "this article is crappy" and "it should not be on slashdot".
The purpose of slashdot is to spur comment. By commenting, be it positive or negative, you are indirectly stating that the article SHOULD BE on slashdot and the posting decision was correct.
The only way to show that you do not appreciate the current slashdot menu selection of articles is to not interact with it at all. Specifically: don't reply to the article.
If you are worried because people are still replying to an article that you deem has no merit. Then you can console yourself in the knowledge that it really is an appropriate slashdot article and that you are not the target market slashdot is attempting to address.
Just stay silent or move on and maybe... just maybe if your lucky, the moderators will allow a more appropriate article through for you to provide your insightful opinion on tomorrow.
BTW: I downloaded the source code for the windows drivers in question and I will confirm: it is tight, yo.
It's most likely because Ubuntu doesn't return accurate results.
There used to be server problems in http://www.wesnoth.org/ MP server. Problem was that windows clients were dropping out of server randomly because of network problems.
Problem was in server side but only windows clients were affected. Problem seemed to be that windows limits maximum packet size (default kernel buffer size for sockets) to 8kb as default which cause windows clients getting a lot larger latency than linux clients. It was about 4 times longer login time for windows vista client than linux client from same lan. (8-10 seconds for linux and 30-40 seconds for windows) So somehow server/router was preferring transmission of large packets to linux clients which cause windows clients losing connection when they didn't receive data fast enough.
Of course bfw is bad example because problem might be in multiple locations like SDL. But at least one thing is sure that 8kb is way too small for high bandwidth connections. (http://www.psc.edu/networking/projects/tcptune/)
I've had a 300 mghtz Compaq with an 'advanced' 56.6k modem and 256 megs ram loading and running faster then a 1.6 ghtz celeron with the same XP OS and software other then small bits of Open Source running on the Compaq. Also had the XP install down to it's minimum required and minimum virtual memory. How many XP users realize that the largest aspect of the XP 'install' is actually virtual memory that can be altered by the user with some help from the OS. Currently have a Gateway E 3600 'out of box' running Ubuntu 8.04 and loading/running faster then my mother's which has three times the ram and is running the best/trimmest standard XP possible.