Benchmarked: Ubuntu vs Vista vs Windows 7

Posted at 12:50pm on Tuesday February 3rd 2009

In depth: A lot of people have been chattering about the improvements Windows 7 brings for Windows users, but how does it compare to Ubuntu in real-world tests? We put Ubuntu 8.10, Windows Vista and Windows 7 through their paces in both 32-bit and 64-bit tests to see just how well Ubuntu faces the new contender. And, just for luck, we threw in a few tests using Jaunty Jackalope with ext4.

When Windows users say that Windows 7 is easier to install than ever, what do they really mean? When they say it's faster, is it just in their heads, or is Microsoft really making big strides forward? And, perhaps most importantly, when Linux benchmarkers show us how screamingly fast ext4 is compared to ext3, how well do those figures actually transfer to end users?

These are the questions we wanted to answer, so we asked Dell to provide us with a high-spec machine to give all the operating systems room to perform to their max. Our test machine packed an Intel Core i7 920, which in layman's terms has four cores running at 2.67GHz with hyperthreading and 8MB of L3 cache. It also had 6GB of RAM, plus two 500GB of hard drives with 16MB of cache.

The tests we wanted to perform for each operating system were:

How long does each operating system take to install?
How much disk space was used in the standard install?
How long does boot up and shutdown take?
How long does it take to copy files from USB to HD, and from HD to HD?
How fast can it execute the Richards benchmark?

We also, just for the heck of it, kept track of how many mouse clicks it took to install each OS.

Before we jump into the results, there are a few things we should make clear:

To ensure absolute fairness, install time was measured from the moment the computer was turned on until we reached a working desktop.
The same computer hardware was used for all tests, and all operating systems were installed fresh for this article.
We used the Ultimate versions of Windows Vista and Windows 7, simply because Windows 7 was provided only in this flavour.
We used the Windows Vista SP1 disk to accurately reflect what users are likely to experience todaay.
Our Windows 7 version is the open beta that Microsoft issued recently. It is probable Windows 7 will be at least this fast in the final build, if not faster.
For Ubuntu 9.04 we used the daily build from January 22nd.
All operating systems were installed using standard options; nothing was changed.
After checking how much space was used during the initial install, each operating system was updated with all available patches before any other tests were performed.
Our journalistic friends have informed us that Windows Vista (and, presumably, Windows 7 too) has technology to increase the speed of the system over time as it learns to cache programs intelligently. It also allows users to use flash drives to act as temporary storage to boost speed further. None of our tests are likely to show this technology in action, so please take that into account when reading the results.
The filesystem, boot, shutdown and Richards benchmarks were performed three times each then averaged.

And, of course, there's the most important proviso of all: it is very, very likely that a few tweaks to any of these operating systems could have made a big difference to these results, but we're not too interested in that - these results reflect what you get you install a plain vanilla OS, like most users do.

Install time

Amount of time taken to install, from machine being turned on to working desktop. Measured in seconds; less is better.

At first glance, you might think that Ubuntu clearly installs far faster than either version of Windows, and while that's true there is one important mitigation: both Windows Vista and Windows 7 run system benchmarks part-way through the installation to determine the computer's capabilities.

A bit of a flippant one - just how many mouse clicks does it take to install an OS with the default options?

Surprisingly, Ubuntu 8.10 gets it done with half the clicks of Windows 7. NB: hopefully it's clear this doesn't make Ubuntu 8.04 twice as easy to install. Measured in, er, mouse clicks; fewer is better.

Disk space used immediately after a fresh install. Measured in gigabytes; less is better.

While some people might complain that we used the Ultimate editions of both Vista and Windows 7, they probably forget that the standard Ubuntu includes software such as an office suite as standard. NB: Vista failed to detect the network card during install, leaving us without an internet connection until a driver was downloaded on another computer.

Bootup and shutdown

Boot up time was also measured from the moment the machine was turned on, and the timer was stopped as soon as the desktop was reached. The Dell box does take about 20 seconds to get past POST, but to avoid questions about when to start the timer we just started it as soon as the power button was pressed.

Amount of time taken to boot, from machine being turned on to working desktop. Measured in seconds; less is better.

The 32-bit version of Windows 7 is the only one to beat the one-minute mark, but that advantage is quickly lost in the switch to 64-bit. Linux has always been rather slow to boot, but as we understand it reducing boot time is one of the goals of the Ubuntu 9.04 release.

Amount of time taken to shutdown, from button being clicked to machine powering off. Measured in seconds; less is better.

Windows lags a little behind the Linuxes, with 64-bit again proving a sticking point - this time for Windows Vista.

IO testing

To test filesystem performance, we ran four tests: copying large files from USB to HD, copying large files from HD to HD, copying small files from USB to HD, and copying small files from HD to HD. The HD to HD tests copied data from one part of the disk to another as opposed to copying to a different disk. For reference, the large file test comprised 39 files in 1 folder, making 399MB in total; the small file test comprised 2,154 files in 127 folders, making 603MB in total. Each of these tests were done with write caching disabled to ensure the full write had taken place.

Amount of time taken to copy the small files from a USB flash drive to hard disk. Measured in seconds; less is better.

Amount of time taken to copy the small files from one place to another on a single hard disk. Measured in seconds; less is better.

Let us take this opportunity to remind readers that Windows 7 is still at least nine months from release.

Amount of time taken to copy the large files from a USB flash drive to hard disk. Measured in seconds; less is better.

Amount of time taken to copy the large files from one place to another on a single hard disk. Measured in seconds; less is better.

With the exception of Windows 7 while copying larges files around a hard drive, Windows generally suffered compared to Linux in all of these tests. Obviously Windows does have to worry about some things that Linux doesn't, namely DRM checks, but these figures show a drastic performance difference between the two.

Notes: Vista and Windows 7 really seemed to struggle with copying lots of small files, but clearly it's something more than a dodgy driver because some of the large-file speeds are incredible in Windows 7.

Both Vista and Windows 7 seemed to introduce random delays when deleting files. For example, about one in three times when deleting the files from our filesystem benchmark, this screen below would appear and do nothing for 25-30 seconds before suddenly springing into action and deleting the files. However, this wasn't part of our benchmark, so isn't included in the numbers above.

This was very annoying.

Richards benchmark

Notes: This was done using the cross-platform Python port of Richards. For reference, Ubuntu 8.10 uses Python 2.5.2, Ubuntu 9.04 uses Python 2.5.4, and we used Python 2.5.4 on the Windows tests. Even though the 64-bit results for Linux and Windows don't look that far apart, we have to admit to being very impressed with the Windows tests - the deviation between tests was just 3ms on Vista, and 5ms on Windows 7, compared to 20ms on Linux.

Amount of time taken to execute the Python Richards benchmark. Measured in milliseconds; less is better.

It's clear from that graph that having a 64-bit OS can make a real difference in compute-intensive tasks, but it's not too pleasing to see Windows pip Linux to the post in nearly all results.

Switching to ext4

All the Linux benchmarks above were done using ext3, so what happens when we switch to ext4? Well, not a lot:

Boot, shutdown and filesystem tests for Ubuntu 9.04/x86-64 using ext3 (blue) and ext4 (red). Measured in seconds; less is better.

Although there's no difference in shutdown speed, the boot time using ext4 dropped by 8 seconds, which is a fair improvement. We can probably discount the the USB to HD tests simply out of error margin, which leaves the HD to HD tests, and there we find a very healthy boost: 3.7 seconds were shaved off the small files test, making ext4 about 25% faster. Our tests also showed an improvement in the large file test, but it's not as marked.

Conclusions

Benchmarks are always plagued with questions, uncertainties, error margins and other complexities, which is why we're not going to try to look too deeply into these figures. Obviously we're Linux users ourselves, but our tests have shown that there are some places where Windows 7 really is making some improvement and that's good for competition in the long term. However, Linux isn't sitting still: with ext4 now stable we expect it to be adopted into distros fairly quickly. Sadly it looks like Ubuntu 9.04 won't be among the first distros to make the switch, so users looking to get the best performance from their Linux boxes will either have to fiddle with the default options, have patience, or jump ship to Fedora - which will be switching to ext4 in the next release..

You should follow us on Identi.ca or Twitter

Your comments

Use of the word "astroturf"

Anonymous Penguin (not verified) - February 5, 2009 @ 10:11pm

I can't help but feel that there's a Slashdot zealot in this thread.

You do know that you need to

Anonymous Penguin (not verified) - February 5, 2009 @ 10:36pm

You do know that you need to "shift + del" to delete a file in Windows. Simply "del" moves it to the recycle bin, which I believe takes more time. Your screenshot showing the recycle dialog tells me you were recycling, not deleting.

Who paid this guy?

Xtoff (not verified) - February 5, 2009 @ 10:45pm

Seriously, a lot of you are complaining like you paid this person to do a benchmark and you didn't get your money's worth. Sure, the results aren't all that accurate, and if you would read the damn thing you would see that the author is aware of this. This benchmark was done for the hell of it, and I for one applaud people who do things just for the hell of it.

One comment on gaming though; I've ran a dual-boot system for years (Windows XP and some linux distro) and have noticed that I generally see about 30-40FPS more in linux than Windows when I play the same game (UT2004, Q3A, etc.). The argument that "Windows is better for gaming" holds no ground. I have even seen some games run better in Wine. Are there more games compiled for Windows? Heck yes. Do games "run better" or is Windows "a gamer's OS"? You might want to hold your comments until you learn how to use linux first and try it out for yourself.

Boot time

Anonymous Penguin (not verified) - February 5, 2009 @ 10:50pm

Something has to be off with the shutdown/bootup,
I'm getting avg of 5 seconds on shutdown, boot to working desktop 58. on windows 7 x64 while vista x64 takes hours to boot or shutdown. And thats with office, avast, ventrilo, and about 15 other programs installed. I'm running a 6600 2.4 780i 8GB @ 1066 2X 8800GT SSC's (I pulled my raptor's which still have my vista installed and windows 7 is installed on a 80gb WB Sata 1.5 cache is 8mb maybe)

Another Microsoft Ripp off.

Anonymous Penguin (not verified) - February 5, 2009 @ 11:13pm

We were all led into buying Vista for the wow factor, now they are saying windows 7 is the way to go in the future. I wonder if windows 7 will be just like Vista with all the bloated software needed to run printers, and firewall, anti virus software,updates and fixes that don't work so they bring out fixes and updates to fix the fixes.They should fix Vista and forget about bringing out another OS. I think this is wrong of Microsoft to keep bringing out another OS that we will have to fix with updates to run the software we all use. Then they will try and get the people to buy Windows 8 in 2011. I will stick with LINUX from now on, it does everything Vista does without the bloat.

Great

Anonymous Penguin (not verified) - February 5, 2009 @ 11:16pm

Thanks for all the work you put into this!!!

??

Anonymous Penguin (not verified) - February 5, 2009 @ 11:23pm

It tes for idiots :)

win

kallisti5 (not verified) - February 5, 2009 @ 11:27pm

Good article, I do feel you tried your best to make it fair. (comparing two completely different operating system platforms is hard!)

And yes.. there are quite a few Windows fan boys in here... but if you paid hundreds of dollars for an OS you would have to defend it also ;)

ext4 test possibly skewed

Laurens Van Houtven <lvh@laurensvh.be> (not verified) - February 5, 2009 @ 11:35pm

I'm not entirely sure how you switched to ext4. If you just remounted the partition as ext3 -- obviously you'll see similar performance for stuff already on the disk, since that is effectively stored in ext3, NOT ext4. The only decent way to measure would be to reinstall.

Poor *old Linux

Anonymous Penguin (not verified) - February 5, 2009 @ 11:47pm

Those windows statistics are way off; even on my 4 year old DELL 8400 / 4600 machines Vista / Windows 7 starts / boots / installs / shuts down faster.

No matter how much 'faster' linux is, it still has the look and feel of a 1990's visual basic application with the little GNOME green ticks and red X's alongside the OK and CANCEL buttons.

Re: On what planet

Tuqui (not verified) - February 5, 2009 @ 11:48pm

> On what planet does windows vista boot faster than ubuntu?

On my experience after install windows boots fast, but after using it few months the boot time gets so long, at least until Vista.

Bleeding edge hardware

Anonymous Penguin (not verified) - February 6, 2009 @ 12:04am

I wonder how long it took to find a Linux distribution that would install ... I've just bought an i7 system with 12GB memory (P6T motherboard) and I'm still "fighting" with it trying to get a 64-bit Linux with Xen that supports it.
(XP installs OK, but XP X64 is giving problems with recognizing the video card).

Test Matlab

Test Matlab (not verified) - February 6, 2009 @ 12:06am

Linux is the fastest Matlab OS 50% faster than vista

Antivirus missing.

Anonymous Penguin (not verified) - February 6, 2009 @ 12:16am

I'd love to see these benchmarks with MS OneCare or some other AV installed since that is a more realistic default build

Boot Time is dependant on BIOS + OS

max_in_wa (not verified) - February 6, 2009 @ 12:40am

To all the people complaining about how their system boots so much faster, consider the point made in the article that it takes 20 seconds for the BIOS to get done with its thing.

I replaced an aging motherboard with an Asus last year, and was appalled to find that it takes 30 seconds or so to get out of the BIOS.

Anyway, with the boottime graph, the importance in the difference between OSes. The time spent in BIOS will cancel out.

Not reflected by my experience

Anonymous Penguin (not verified) - February 6, 2009 @ 12:53am

Benchmarks presented here do not reflect my experience with Windows 7, Vista and Ubuntu. Large dose of NaCl required.

Also, I'd like to see some kind of "experience consistency" metric. With linux its terrible:

Sometimes:
- You wait an hour for a fsck before you get to your desktop
- The system hangs on shutdown
- It actually suspends to disk! but its always messed up on resume (Yes I have modern, mainstream hardware - a dell).

Windows on the other hand, is consistent for me. I'll take the consistenty and functionality over a little bit more speed 10/10.

XFS?

Alan Jones (not verified) - February 6, 2009 @ 1:12am

I'd be very interested to see how the comparison would go using XFS instead. I'd imagine you'd see an improvement on the large files end of things HD to HD. No idea what else it could impact.

Cheers,

Alan.

Lets get the benchmarks on the top 10 PC games

Anonymous Penguin (not verified) - February 6, 2009 @ 1:37am

Yeah..

i'm going to say this, i'm a

Darren Kopp (not verified) - February 6, 2009 @ 1:51am

i'm going to say this, i'm a big MS fan, but i agree, that file deleting dialog when it happens drives me up the wall too!

What a load of BS...

Victor Szulc (not verified) - February 6, 2009 @ 2:38am

I just installed Windows 7, and no, I did not click 14 times to install it. 2-3 is more like it, which (once again) puts it way ahead of Linux.

Also. I got no idea where you got your stats concerning how big Vista is following installation. I just removed two Vista folders, one of them was 2 GB, the other one was 5 GB.
Again... What a load of BS...

The reason why Vista takes up more space than a Linux installation, is probably because of a phenomenon that Linuxusers aren't used to: Drivers for hardware and legacy hardware support!

That ties directly into another thing thats unknown to Linux users: Marketshare... Whahahah!

For those saying that Vista

Xaria (not verified) - February 6, 2009 @ 3:09am

For those saying that Vista doesn't come with apps, are you using Vista Ultimate? A default installation of Ubuntu (which I run at work, so yes I know what I'm talking about) includes dreadful multimedia support. Vista Ultimate comes with Windows Media Center. It supported our TV tuner card out of the box, with excellent functionality. Yes, MythTV is the Linux solution but it doesn't come with a default Ubuntu installation.

I recently tried to play a DVD under a recent Ubuntu install. It took me over an hour to get the codecs working. I tried several applications, I searched the Ubuntu forums, and EVENTUALLY got it working. Vista plays them out of the box. Most people don't know what a codec IS, let alone where to search for one.

It's not about boot times or clicks to install (most people get their machines OEM these days anyway or have a techie friend do it). It's about haven't-got-a-clue users. Apple is doing so well because their products Just Work and look great. Ubuntu has a way to go if it's going to win on the desktop against Windows 7.

Misconceptions and misteaks

Maurice Hilarius (not verified) - February 6, 2009 @ 3:18am

1) Ubuntu !=linux
It is irrelevant what distribution one compares.
What IS important is the kernel.
Here the only relevant factor in a distro is how old the relase may be.
For example RH5.x with a 2.6.18.xx kernel versus Fedora10 which has a current kernel

2) ext4 is already an install option of Fedora10, just not the default.
If, at the installer prompt, one simply appends "ext4" it will build your filesystems as ext4.
Typical Ubuntu user who knows precious little about Linux or other distros.

3) Install times: Windows comes with few or little applications.
A typical modern Linux distro,by default, installs a complete set of basically 90% of the apps that people use.

4) Cost: There is still no comparison here.

"Working Desktop"

Mike (not verified) - February 6, 2009 @ 3:40am

I'd like to know what "working desktop" really means as far as the boot time. For instance, on my mac, when the desktop is shown, it is actually "usable", meaning I can click things and do stuff.

On my Windows XP machine, once the desktop is shown, there is probably another 30 seconds of dead time before anything works as other things are still going on.

Pathetic.

Victor (not verified) - February 6, 2009 @ 3:58am

Not the article, no. The article was fine. It's everybody's comments that are pathetic. From sysadmins to desktop users. When will you learn (in life, really) that there are different perspectives on everything? "MEEEEEEEEH THAT'S NOT WHAT 'PERFORMANCE' IS!!" Performance is defined by what you use your computer for. If you use it as a paper weight, desktops are better than netbooks, but only if you don't move them a lot. Desktops are better door stops than netbooks but not if you want a more sleek door stop.

Do you see that there are different aspects on usability, ease-of-use, performance, etc? How about another example.

"MEEEEEEEEH NTFS vs. EXT3? 'NICE.'" -_- Duh? Why would you compare NTFS on Ubuntu to NTFS on Windows unless the article was on NTFS performance? And how would you even conduct a test on EXT3 under Windows that has any relevance to general, real-life situations? Windows pretty much only comes with NTFS, and does not support EXT3 out-of-the-box. Okay? If everything has to be the same EVERYWHERE, there wouldn't be any point of any benchmarks WOULD THERE..?

Good grief, people of the Internet! Think before posting! Learn to analyze your own thoughts and think about everything from every angle that you can imagine before uttering anything! (Not to say I'm perfect but my gosh.)

"MEEEEEH NICE 'BENCHMARK', DOOFUS!"
Benchmark - noun: "A standard by which something can be measured or judged." We all have identical, similar and/or differing standards on what should be conducted in a "benchmark". Accept that, or suck it.

If you don't like any benchmarks that are out, then conduct your own, or arrange in some way to have one conducted. If that is impossible for you for some reason, too bad. No need to harrass the good people who made this one. For them, maybe few mouse clicks are important for the installation process. Maybe they work as OS-installers? Huh? Shut up! The benchmark was a fair mix of tests, and even if it could also be interesting to know about performance down-the-line (time wise when a lot of sh** might've accumulated on the HD or many apps installed), this was a benching of newly-installed OS's. Alright?

Disclaimer: Not EVERYBODY's comments were pathetic. All appreciative comments for instance were quite nice to read. :-)

uummmmmm.... Who the hell

Anonymous Penguin (not verified) - February 6, 2009 @ 4:01am

uummmmmm....

Who the hell cares? Fact of the matter is just look at the price for what you get. Every day I deal with people who have no idea how to use a computer. I install software for them, anitvirus protection, spyware protection. I do this and charge them for it.

They pay me to get rid of infections, do back ups for them. They pay me to save data and they pay me well. A guy down the road who had bought a computer last week and already he has come by to see if I can remove the virus. $500.00 laptop, Windows Vista, Norton anti virus, Winav2009, $150.00 to me to fix it. Priceless

Ubuntu != Linux

Anonymous Penguin (not verified) - February 6, 2009 @ 4:29am

I would agree with that statement, but IMO Ubuntu is the #1 threat to the future of M$ Windows. It's an out-of-the-box solution that -- like said before -- supports vast majority of hardware, and will install easily on a variety of boxes while still functioning as it should.

Windows Suffers from its default enabled services

salemboot (not verified) - February 6, 2009 @ 4:29am

Disable Microsoft Shadow Volume Backup, Fast Indexing, and Ready Boost in Vista. You'll gain a marginal increase in speed where marginal is approximately a 30% increase.

I believe this is where your performance hit resides.

8.10 Intrepid Ibex seems to be the cats meow for Ubuntu and Linux Distributions in general. Rather the goats beller'.

There is not much to tweak here. You could compile the kernel for the processor (Core 2). Reiser3 will give you a huge edge over ext3. But as you said the point was the default install.

Great article.

Disabling write caching on

Anonymous Penguin (not verified) - February 6, 2009 @ 4:30am

Disabling write caching on windows will cripple NTFS write speeds for small files and delete operations since metadata updating will result in a lot of small writes.

Yeah, but...

Anonymous Penguin (not verified) - February 6, 2009 @ 4:55am

Can Ubuntu run flash full screen?

I love all the Windows

Anonymous Penguin (not verified) - February 6, 2009 @ 5:18am

I love all the Windows zealots getting all high and mighty over this. Go crusade somewhere where people care.

hmm

Brittany D (not verified) - February 6, 2009 @ 5:23am

I have to agree with a lot of people who commented on this. Most of the 'benchmarks' are quite useless for the average user. Personally, I'd like to see thigns like "firefox start time" and "speed of processing 4gb file from hdd to usb" not 'small file' and large file. Small and large are rather personal I think. To me a small file could mean 1K where for someone else a small file could mean 400MB.. Just a thought.

Windows requires antivirus

Anonymous Penguin (not verified) - February 6, 2009 @ 5:33am

Since ya can't run Windows without an antivirus product, if you are the average user mentioned in this benchmark suite, the installation, footprint, and performance times of Windows have to include that, IMHO.

Linux? What is linux? Sounds

Anonymous Penguin (not verified) - February 6, 2009 @ 5:36am

Linux? What is linux? Sounds like a cartoon.

you are stupid... you try

Anonymous Penguin (not verified) - February 6, 2009 @ 7:07am

you are stupid... you try compare system with 6 yo history and system which born trought 1 year... cool...

Me theory!

Awesome Penguin (not verified) - February 6, 2009 @ 7:07am

Ubuntu definitely supports the customization freaks better than nLiting ofcourse. But the valid points made about the "general user" comfort are important. Last 20 years or so of MSing have made us dependent.

Ya, about the benchmarks, I think the netbook revolution has definitely taken its toll on MS and i hope to see more intiatives from buntu like NBR to get the real performance+aesthetic OS on my machines.

EEEbuntu look and feel

Cute Penguin (not verified) - February 6, 2009 @ 7:16am

I second awesome penguin. I am one of the NBR users, EEEbuntu.. the customized ubuntu version for Asus EEEpc.. I customized it for my system and its amaaaaaaaaaaaaaazing!! :D

Opensource Photoshop?

Anonymous Penguin (not verified) - February 6, 2009 @ 7:22am

Gimp's UI sucks? that is like saying a stickshift sucks because you only know how to drive an automatic.
And if you are so addicted to the crack that is Photoshop try gimpshop, maybe you will like it, I don't use it because I find photoshop's Ui to be rather worthless myself, but hey, I started with the gimp.

Did I hear somebody say windows has more drivers incl legacy?

Anonymous Penguin (not verified) - February 6, 2009 @ 7:25am

Victor Szulc, you have no idea in the slightest. Have you ever compared a windows driver in size to a Linux driver for the same piece of hardware?

Light, tight and fully functional is what Linux uses verses hugely over bloated, excessively memory hungry and too often released in a state that Linux users would still call beta software and sometimes even alpha, i.e buggy.

Windows devs code to a time schedule, release it now or else, Linux devs code to their own satisfaction with extensive peer review. There is simply no comparison. It's not Linux's fault that many hardware manufacturers do not give a flying fart, but the Linux coders show beyond a shadow of a doubt they can operate without their help if required, but drivers would come faster if the manufacturers would co-operate, and that day is coming fast. The day will come when the windows die-hards will eat humble pie as Linux outperforms and outpaces everything they thought they knew about computing.

What's a bet most of the die-hards use Google. Do some research on that. How many of the worlds supercomputers run windows? Less than 3% and they can hardly be called a supercomputer, more like a try-hard, what type of systems hold the highest awards and numbers? no need to answer, windows is simpy too b****y worthless and weak to even come close to making the grade.

Now let's see how the benchmarks stack up, Roughly estimated, Linux could easily be 500-600 times faster and there is no doubting that Linux is infinitely more scaleable.

Can you get these results on a non-Linux site?

Charles Norrie (not verified) - February 6, 2009 @ 7:47am

These tests are very important and one of the ways the Linux community can tell the world that that it's aproper competitive OS.

So could I suggest the authors take the time and trouble to send the article to all those commentators and journalists who think they're talking about computers, but in essence are only mouthpieces for Redmond.

RE: Ubuntu != Linux

ddaf (not verified) - February 6, 2009 @ 8:20am

Correct, Ubuntu != Linux. But also, let's be honest here: Debian != Linux either. In fact, the only thing == Linux is the kernel. But this is a good comparison report considering that most people (like the original poster) don't seem to know the difference between GNU and Linux. And Ubuntu is the most popular distro in the world -- most likely to be the distro a newbie would try.

Ubuntu is built in Debian and can perform at least as quickly -- if not quicker. If you know your Debian so well, you would be able to sort that out. And I have to throw a cruve ball: my Debian VM boots slower than my old Ubuntu VM. It's just not set up the same.

Ubuntu is far from "bloated". Yes, you can get lighter with a minimal Debian net-install -- but then what do you have? A machine capable of 6 terminal sessions, effectively. Perhaps you want to add the things that EVERYONE else wants: a desktop, office suite, interwebs browser, etc.

I say: GO UBUNTU. Keep it up. There are some nigglies at the moment with really "out-there" hardware, but Ubuntu still has better hardware support than any version of Windows out of the box. The proof is in how it took me 3 days to track down all the drivers necessary to make my laptop run Windows XP (it's an HP Pavillion 9000 range; nothing super-fancy). It took approximately 20 minutes to install Ubuntu on the same machine and everything actually worked, out of the box. Not only that, but wireless networking using WPA2 was WAY easier to set up than in Winblows.

Good OS is useles without killer application

budirj (not verified) - February 6, 2009 @ 8:26am

mainstream users do not care about things like these. You have a breakneck speed OS, so what. OpenOffice is crappy (if you are a serious user), GIMP is OK, but far inferior to Photoshop, etc

Missing an OS?

Anonymous Penguin (not verified) - February 6, 2009 @ 8:49am

It's too bad WinXP is not in the lineup. It would for sure lag behind all the rest when it comes to patching, but I can't be sure about the rest of the benchmarks. It would be interesting to see it up against both the Linuxes and the new Windowses. For that matter, an older and widely used distro of Linux wouldn't be bad either just to see the improvements.

Fun article. Take it with a grain of salt.

djwisdom (not verified) - February 6, 2009 @ 9:12am

The article was a nice read.
The comments were even nicer to read.

As for me, the fact that this article caught my attention indicated that there's something here that captured my interest.

And I have to thank the writer for that. Now, time to move on with life.

Oh dear....

:: Xiphon :: (not verified) - February 6, 2009 @ 9:14am

..... I can't believe that you actually published this!

Surely it would make sense to get technical peer review, as to not emabrass yourself.

Mouse clicks? WTF?
Install size? Irrelivant by todays hardware standards.
DRM? C'mon, do some reading.

nice test

danizmax (not verified) - February 6, 2009 @ 9:16am

Thanks for this nice test!

The Boot/Shutdown is Bull

cantormath (not verified) - February 6, 2009 @ 9:45am

Im running:
64bit ubuntu,
On a 2.5ghz, 6mbL2-cache, 7200rpm drive, 4 gb of ram, t-61p laptop AC-powered. Standard install with Compiz-Fusion full blast,

Boot:
Just under 30secs
shutdown:
about 16 secs

I have done No modification to improve start up time and there are plenty that could cut these numbers in half.
Im running a ton of services, wireless, nm-applet, hdaps, ssh, standard apps on install, bluetooth, etc...to many to list.

No way its 68 secs on that hardware for bootup and/or shutdown for Ubuntu 32/64bit.

Business Vs Pleasure

Anonymous Penguin (not verified) - February 6, 2009 @ 10:24am

When you get a PC for your kids, do you really think it's for their homework and Instant Messaging ?
There are several things needed for Linux to grab a big slice of market:-
1. Get major software companies to port their games to it, or get a real windows emulator that supports games.
REASON: If I don't want to shell out for windows / office 2007 / photoshop etc, I sure don't want to buy an Xbox. High profile games on the PC is a must for 80% of the home PC market.
2. In order for games software houses to port their games to Linux, they need a standard platform to code to, so this community needs to pick one rather than bickering about the different Linux flavours.
3. Make future realeases of the selected platform backwards compatible for at least 3 years, longer if possible.

Failure to carry out these things will mean that Linux is only good for work, playing games that belong on a card table, and specialist uses such as music.

If the requirement for Linux users to buy a games consol to play games which run on windows continues then we (I'm a linux user) should not expect to win a large share of the home user market.

So that leaves the business market, what's needed for a large share of that?
Large companies value standardisation a great deal, windows is by default the standard to beat. Boot times and open office are not going to cut it with big business if the standard keeps changing at least every six months (like it does with ubuntu). Now I know that windows keeps getting updated and there are always several service packs, but these updates are installed quietly in the background, or through active directory so rolling out an update is very easy on windows. Updates on Ubuntu and other versions of Linux are much more difficult and if something goes wrong, recovering from it is a major hassle involving command line programming. Again Linux needs to be an operating system rather than the current franchise system if it is going to win the market.
Small companies value simplicity of support (they may only have one computer tech, or even outsource their requirements) so they can't afford to have a system that's too specialised. Windows is standard, Linux has countless variants and tweaks to make it work properly, and again we are back to updating simplicity, windows wins every time.

In short Linux doesn't really exist, you have to get a variant, debian, ubuntu, mandrake, suse, red hat, fedora (I use ubuntu and fedora myself).

Put yourself in the position of someone buying 20 PCs and a server to operate a warehouse, no IT tech.
A/ You can get windows, office 2007, sophos security on bog standard PCs, it's what your customers use, it's what your suppliers use, and HP / Dell / Whomever provide you with support for 5 years.
B/ You can get a version of Linux, it get's updated every six months, it's cheaper to install but you have to buy your own support package from a Linux Tech because it's much more technical to fix and their's no centralised support like you get with microsoft products.

Now microsoft is a company, that means there is a contact point, that means there is customer support.
Linux is a nebulous mish mash of thousands of people working in small groups to their own ends.

If it were me I would choose windows every time. Maybe Mac again because there is acompany structure their and I would be their customer. Only if both of those options would not meet my needs would I consider Linux.

I don't love windows, it's full of bugs and annoyances and it costs a fortune, but from a commercial and home user point of view, unless you are, or are willing to become, tech savvy Linux just isn't a choice.

Gaming speed XP vs Linux

Lutikka (not verified) - February 6, 2009 @ 10:51am

The reason Linux would "trumps XP in gaming tests would be you X11 card specific 3D drivers don't support some feature requested by the game. In other words, sure it may be a lot faster because it is not doing the same work :)

Those laptops

Surinderjeet Singh (not verified) - February 6, 2009 @ 11:28am

I dont worry about benchmark results but if I could get one of those beasts that you ran the benchmarks, that would make me day.

Statistical dishonesty

Anonymous Coward (not verified) - February 6, 2009 @ 11:48am

Why bother doing benchmarks in triplicate if you only give us the arithmetic average of the obtained values, but not some form of dispersion measurement.

Dishonesty..? You decide.

BETA

Fuck you (not verified) - February 6, 2009 @ 12:27pm

BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA BETA

nn

Anonymous Penguin (not verified) - February 6, 2009 @ 12:53pm

та гамно ваша убунта причем недоделаная mandriva лутше

Nice test

Anonymous Penguin (not verified) - February 6, 2009 @ 1:11pm

Thank you for nice test.
I don't agree those boot times for Ubuntu. It is faster BUT that test was made with your hardware. So it's ok.

You should put price, stability, security...

Those are reasons, that i think when i'm choosing OS.

I've using 15 years Windows, 3 years Linux.
I'm pissed off about one thing: why didn't i change earlier to Linux? Wasted so many years with sh*t..

Microshaft Employees

Anonymous Penguin (not verified) - February 6, 2009 @ 1:34pm

Wow, all the Microshaft employees and fanbois in here!

I admit, I still use Windows for some tasks, but that is quickly changing. Windows 7 will fial just as bad as Vista did.

RE: What a load of BS...

Anonymous Penguin (not verified) - February 6, 2009 @ 1:35pm

Victor are you trolling or do you actually believe what you say ?

> Also. I got no idea where you got your stats concerning
> how big Vista is following installation. I just removed
> two Vista folders, one of them was 2 GB, the other one
> was 5 GB.
> Again... What a load of BS...
Where are comparing STOCK installs here right ?
Let's start removing all that documentation in /usr/share/doc that few people read, precached install packages and sparsely used applications from our Ubuntu install. You might have a point claiming that comparing stock installs is mute by the way Microsoft packages and install's Vista but don't start talking pointless crap.

> The reason why Vista takes up more space than a Linux
> installation, is probably because of a phenomenon that
> Linuxusers aren't used to: Drivers for hardware and
> legacy hardware support!
Now this is such a load of crap, it's unbelievable.

You apparently really don't know anything about Linux. Linux support so much hardware both in terms of type of platforms (intel/amd/sparc/mips/cell/etc/etc/etc) as well as devices out of the box it's almost unbelievable that the complete directory of linux modules (of which a good part is drivers) is only 85Mb! (ubuntu with Linux kernel 2.6.27)

Specially in the last couple of years Linux driver support is gone through the roof as far as completeness goes. And legacy support has in my opinion been better in Linux for years now than it was on Windows.

I would love to see you install Vista on an old box with some old obscure network card or other old obscure hardware and have it work out of the box.

So Vista is a bit faster than Ubuntu

Joe King (not verified) - February 6, 2009 @ 2:08pm

Forget about installation times. The ordenairy user don't want to play disk jockey so would probably buy a pre-installed machine. Besides being it a one time process: who cares if it takes two days.
Redmond can definitely improve on the erratic timing of file copy that *is* annoying and a major put-off. But start-time (and for the mobile users) stop time is where Vista is great. And if one would calculate the time spend on fora to get Ubuntu working properly to tweak Vista it probably is the big winner.

installsize

Bob (not verified) - February 6, 2009 @ 2:14pm

Well the bigger install size for windows is caused by the huge amount of preinstalled drivers that are available for all kinds of devices that Ubuntu does not support by default.

DRM checks?

Anonymous Penguin (not verified) - February 6, 2009 @ 2:24pm

"Obviously Windows does have to worry about some things that Linux doesn't, namely DRM checks, but these figures show a drastic performance difference between the two."

There are no DRM checks involved in file copying. Please, get a clue.

Re: Graphics

Anonymous Penguin (not verified) - February 6, 2009 @ 3:32pm

Actually, a lot has been invested in making graphics support under Linux work as efficiently; if not more efficiently than under Windows. With graphics, CAD and visualisation apps running primarily on UNIX workstations in the 1990s; porting to Linux / PC when the hardware reached maturity seemed the next logical step. Combined with the faster filesystems and scaling solutions offered nearly exclusively to Linux based systems (think for instance VirtualGL), the claim that Ubuntu doesn't hold its' own with graphics is truly unfounded.

About Your article

Some.one (not verified) - February 6, 2009 @ 3:50pm

Dear writer of this article

I hope your having a good day when you read my comment.

Thank you for the effort you have made to make this right.

I think it's my duty to tell you that I have translated your
article for non-profitable benefits.

It made a great success and the people loved it very much, I have made totally sure not publish the translated article without clearly say "This is a Translated Article and it's Original script is located here...."

Just thought you would be pleased to know of such a success, Job well done.

Please keep the good work, good day to you

Some.One

Who Cares?

Algoz (not verified) - February 6, 2009 @ 4:18pm

No really, I am a bit of a geek and found the article interesting, but who cares. As poined out, certainly NOT the gazillions of everyday users who if properly educated would turn to Linux (whatever flavour) in a flash. To be clear, I use XP, Win7, OSX, Ubuntu 8, and Xandros.

So what users care about is...

1 - Cost
2 - Ease of fixing when in inevitable goes wrong
3 - What can I do with the computer?
4 - What else do I have to buy?

Your average user wants to surf the web, do emails, manage media (music, video, photos) and stay in touch with family and friends (skype, facebook, etc).

And here's my point, we in the Linux community will never convert users by proving that its better, we need to show them how to do the things they want to do, for less money, less hassle, and less geekiness! This is how I got my wife using Ubuntu and as she puts it... "when I turn the light on, I just want to see, I don't care about electricity, fillaments, gas, watts, etc, I just want to see!".

Anyway, 'tis Friday afternoon and thats enough ranting for one day!

I love how Ubuntu is mocked

Anonymous Penguin (not verified) - February 6, 2009 @ 4:27pm

I love how Ubuntu is mocked by not only Windows zealots, but Linux zealots as well who think you if you can't recompile your kernel you're a moron that should just use Windows.

Important Differences Missed?

Anonymous Penguin (not verified) - February 6, 2009 @ 4:28pm

I would like to second the other user who asked when the "clock stops" when measuring the Windows desktop coming up. In my experience I have to wait about 1 minute AFTER the Windows desktop "comes up" before it is ready to respond to the user. My Ubuntu (and other Linux distros) appear to be ready as soon as the desktop appears.

I would also like to see how these numbers change once virus checking software is installed in the Windows systems. (Apparently nobody in their right mind runs a Windows box without it - and leaving it out makes Windows look faster than it really is in the "real world.")

As for the EULA of software preventing you from publishing benchmarks I hope that the "freedom of speech" guaranteed by the U.S. Constitution still trumps a one-sided "agreement" that has no signature on it. (Hint: Like muscles, rights that are not exercised deteriorate)

DRM?

DoDo (not verified) - February 6, 2009 @ 5:22pm

Gotta love those DRM-Vista-bashing rumors. The author is clueless. FAIL.

Does It Matter

ToeKneeC (not verified) - February 6, 2009 @ 5:33pm

Really -
Lets see you compare FallOut 3 scores, MS Project 2007, my daughters Barbie games. Lets compare times loading iPod and Zune songs on linux or even streaming HD videos to my Xbox 360.

The OSes are completely different on what they are and what they are used for.

No show me beenchmarks on all the greeat opensource software that runs on both system (include OS X too). Such as OpenOffice. Then again, if the software runs on both system, just fork out the 100 bucks for an OS and have it all.

The 100$ benchmark

Rambling Johnny (not verified) - February 6, 2009 @ 9:37pm

I rather see what you can do if you buy a used computer for say a 100$. Something like a first generation Pentium 4 or even better a Pentium 3 933mhz 512 MB Ram like my backup rig that I am using to write these comments. Does anybody else think that we don't need more powerful hardware that what we already own to fulfill our average user need. This is where Gnu/Linux really take the lead! Windows 7 beta has light system requirement let just hope Microsoft does not bloat it up too much before the final release!

I also have to mention that any comparative benchmarking of any Linux Distro with Windows should include long term usage test. Linux might be falsely considered to be a pain to install because of drivers and codec issue but once Linux is running it going to run and run and run...

cp /media/flash /harddisk

dark_shvein (not verified) - February 6, 2009 @ 9:41pm

BTW, what FS on the usb drive? It will amazing, if winOS lose in test, founded on home fat FS)

New OS

Moon (not verified) - February 6, 2009 @ 11:05pm

did you hear the new OS: MOON
it's really good

Can't you folks read?

Anonymous Penguin (not verified) - February 7, 2009 @ 3:48am

The Title says: Ubuntu vs Vista vs Windows 7

NOT "Linux vs Vista vs Windows 7"!!
What is Linux? Linux is an OS Core, not a graphical user interface or any other fancy stuff! Just a core! It's a test between Ubuntu and Windows!

Windows 7 Installation is really faster :)

Jagadish (not verified) - February 7, 2009 @ 9:12am

After reading this benchmark and all these user reviews, i thought of giving it a try. So I downloaded Windows 7 Beta released recently by Microsoft.

I already have Windows Xp Professional SP2 in my PC. And I don't want to disturb it. So i installed Windows 7 Beta in VMWare. I had the Windows 7 Beta ISO image in my USB Pen Drive.

VMware read ISO image from USB pen drive and installed Windows 7 in just 15 mins. I mean, within 15 mins, i was able to open IE8 Beta in Windows 7 Beta :) I am surprised to see this result.

My PC Configuration is,

Microsoft Windows XP Professional Version 2002 Service Pack 2
Inter(R) Core(TM)2 Duo CPU E4500 @2.20GHz
4GB RAM
250 GB SATA Hard drive

My own experience: Dual

Anonymous Penguin (not verified) - February 7, 2009 @ 10:25am

My own experience:

Dual booting Win7 beta and ubuntu 8.10, default install in both cases.

Ubuntu takes nearly twice as Win7 long before the desktop becomes live.

Ubuntu is using less ram thank Win7.

Firefox takes same time to load on both, until after a reboot or two its faster on Win7 (too quick to stopwatch) probably because of superfetch.

Anyway personally I'm enjoying Win7.

I can see some old less memory computers or people who don't want to pay will use ubuntu but Win7 suits me better.

Boot time is not correct

Anonymous Penguin (not verified) - February 7, 2009 @ 11:16am

You have to consider not until you have the desktop is ready, but until you are able to start working.

Windows Vista shows the desktop in 15 seconds, but it takes 5 minutes until it is fully working.

You could for instance measure how much time it takes to show firefox and you would see that it is much bigger than ubuntu!!!

More benches and distros

named Penguin (not verified) - February 7, 2009 @ 3:25pm

More benches like Blender should have been there. Some more distros like Arch or most definately an optimized built Gentoo or scratch build should have been there. Though Ubuntu is the mainstream linux distro, it is also the slowest and including say Gentoo would have shown users how much they can improve in their works by switching to linux. Such distros are actually raw linux. Not all peeps have the hardware and software for doing such benches and if done they should be covered extensively...

Ubuntu superior to WinXP in boot + Firefox up running.

bbauto (not verified) - February 7, 2009 @ 4:09pm

I compared my one year old WinXP installation on a Dell Latitude D520 on HDD (clicked off all unnessesary under msconfig-Startup, only left ClamWin antivirus) and compared with my full Ubuntu8.10 installation (including avclam antivirus) on the same computor but on a Kingston Datatraveller 16GB USB-stick (which ought to be a disadvantage for Ubuntu). I measured from pressing the button until i had Firefox up running (cause i know that XP isn't ready, just because the desktop is up). Ubuntu with firefox up running took 0,57*WinXP.The only tweak ubuntu had was "noatime" in fstab, wich is recommended for USB-stick, on the other hand i have a lot of effects like compiz, awn, screenlets, bluetooth which i don't have in my minimalistic XP, and at boot ubuntu also update virus signatures and mounts the NTFS partition. Ubuntu is still superior WinXP by less than 2/3.

Not a Totally Fair Comparison

Anonymous Penguin (not verified) - February 7, 2009 @ 8:49pm

You tested on the same hardware, so it's not really a fair comparison.

From what I have heard, it is estimated that Windows 7 will cost conservatively around $200. So if you are building a computer from scratch, you will be able to buy $200 more worth of hardware if you use linux. Or said another way, if your budget is $1000, you will be able to buy $1000 worth of hardware for a linux computer, and only $800 worth for the windows computer. That represents a significant difference in speed and performance.

Therefore, to reflect more of real-world comparison using the same budget, you shouldn't cheat linux like that by giving windows a $200 advantage that wouldn't exist in the real world. Dollar for dollar, a linux computer will run circles around a windows computer.

The comments are ridiculous, i mean...

I Drive a Geo Metro (not verified) - February 7, 2009 @ 10:52pm

I appreciate the benchmarks the author made.

The generic user is probably someone who will not know how to run scripts, or modify things so they run faster/better, or know all the special tricks to speed it up.

Boot up and shut down are especially important on a laptop - when I want to do something, I want to do it NOW, and when I want to leave, I want to leave NOW. Not 12345 seconds later.

Installation time is reasonably important, although more of a "that's interesting" piece, because I seem to reinstall operating systems twice a year for friends. It is a real annoyance to have to spend two hours installing an operating system.

Time to Desktop is important, although I would probably say that Time to Using Application is more important. As noted, some operating systems display a desktop before they are running at 100%. If you are just turning on the computer to open some document, what matters more is how long it takes to get the application running.

Operating system disk use *IS* important, no matter how cheap hard-drive space is. Especially with the introduction of Netbooks, but even with many laptops, hard-drive space is a commodity to be wisely used.

What is funny is this: Of all the tests shown, the one that I really care least about is the Richards test. I don't know what the Richards test *actually tests*! I mean, start-up time I know, but "Richards"? I know a Google search could find it, I am just saying...

Overall I thought it was a useful benchmark.

For The Longest Time

Anonymous Penguin (not verified) - February 8, 2009 @ 1:57am

I have been wanting to migrate to Linux. I've made my own MythTV box and I've played with DSL and PuppyOS. I bought SuSE 8.0 and I've installed various versions of Slax, Red Hat and Ubuntu.

These all were great things, maddening at first, but ultimately a learning experience.

I like that a Linux-based makes your tired PC run really fast. I like that you get a fully functional desktop ready to do everything you want at once. I like that it's free.

But it needs stable gaming. Linux-based computers weakness it entertaining. It's somewhat more difficult to have a multimedia center than in Windows. And certainly gaming is a big loss. That's the one thing holing me back.

Apart from the io benchmarks, who cares?

Anonymous Penguin (not verified) - February 8, 2009 @ 10:26am

Wich user used to any OS cares about startup and shutdown times?
I mean, sure, if the next ubuntu (wich i use) version boots up in two seconds, yeah, changed the game.
But in my current every day use, i think, im just like everybody else and start up the damn thing, make a phone call, visit the bathroom, think about the general theory of the universe or whatever while it starts up.
Whats the the big win if it starts up in 62 seconds compared to 54 or so?

Ubuntu Godd For The Poor Folk

Anonymous Penguin (not verified) - February 8, 2009 @ 3:03pm

Please donate your old boxes to a church-group or some needy student in these hard times! To comply with the law, and with Microsoft's leasing policy, you can now replace Microsoft OS with the free (download from the net) Ubuntu OS, which can be set to erase the hard drive of all traces of the “illegal to give away ” Microsoft system and your private information, before donation! Now, explain to your lucky recipient that all the manuals they will ever need are available for free on the internet! Just ask for them in Google! OpenOffice, which is installed already is plenty adequate for homework assignments and with a little exploring, everything else can work well too! Happy computing!

The boot up benchmark is clearly invalid

Daniel Souza (not verified) - February 8, 2009 @ 4:22pm

Linux start the graphical interface after the whole system, and Windows start the graphical interface before all the other things. This benchmarked compared the time Ubuntu needs to boot up all the system versus time needed by Windows do start graphical interface.

Python benchmark

Daniel Souza (not verified) - February 8, 2009 @ 4:27pm

My OpenSUSE 11.1 x86_64 with a Pentium D 915 and 2x512MB DDR400 of memory does the richards benchmark with 684.93 ms of average time per iteration, and on the moment of the benchamrk im with firefox, pidgin, last.fm player, and other things opened.

Honestly

Anonymous Microsoftie (not verified) - February 8, 2009 @ 7:05pm

Honestly, Linux sucks. While you may construe better graphs from careful constructed benchmark 'tests', everyone knows that once up and running Windows is a cinch to use while Linux is a quagmire of configuration file madness that only a UNIX guru can make heads or tails of [and that with much effort and much time].

Thank you for the fairly

KSiimson (not verified) - February 8, 2009 @ 7:12pm

Thank you for the fairly just benchmark. Of course there are things that could be done different, but your choices are well argumented. Not only does it help the users to have an overview of what is going on, it will also be helpful to development of software.

Idiots

Anonymous Penguin (not verified) - February 8, 2009 @ 10:46pm

The majority of 'expert' comments here make me ashamed to be associated with anything called "the Linux community"

1. Why does a distro have to be cryptic/difficult/require "skill" to configure to be considered valid? Ubuntu runs a Linux kernel and open source apps a la Debian. Of course is isn't going to be optimized to your *specific* need. The beauty of it is that it works for *most* people out of the box with little effort or tweaking required. A statement like "my distro is superior to Ubuntu" is utterly meaningless and just dumb.

2. Are you brining anything to the table? If you don't have any data of your own, shut the heck up.

3. No, this isn't a "scientific" test - but the results *ARE* interesting. Yes, I do care how long the install takes. That is interesting. How much faster EXT performs is interesting. Sure I'd like a little more info - but in terms of a *practical* "this is how they compare out of the box" test, this is useful. It doesn't say "Ubuntu is better than Windows" or "distro X is superior to distro y" or anything else. It is a *subjective* comparison that an ordinary person who likes to try different OS's might experience. Again, unless you have something better to bring to the table, shut up.

On a broader note, the sheer idiocy and fake intellectual/technical bullshit of 90% of folks claiming to be "experts" because they downloaded a Slackware, Fedora, Suse or name your distro is astounding.

I'm going to echo the above

Anonymous Penguin (not verified) - February 9, 2009 @ 8:03am

I'm going to echo the above poster a bit. I've supported 24/7 IT NOC's for over a decade running a multitude of operating systems, and have conducted many, many performance tests pitting SQL v/s Oracle, UNIX v/s Linux, Linux v/s Windows. UNIX v/s windows, 32-bit platforms v/x 64-bit and so on and so forth with many different generations and architectures of hardware. The last 3-4 years has proven time and time again for Linux to be the top I/O performer over MIPS and SPARC based UNIX distributions as well as x86 and x64 windows distributions. Even SMB I/O on a typical linux client is faster than a typical Windows client (SMBv2 not yet tested) Memory management on Linux and UNIX is FAR superior to Windows. In fact, I think its quite embarrassing for windows to even release a 64-bit offering without revisiting how it reads from and writes to RAM. I use Linux at home because its what I prefer, but at work, I am OS agnostic, and I will use what works best for what is needed. In 100% of every configuration I've setup where both a Linux and Windows version existed, the Linux version was faster, less problematic, and much more secure in most cases than the windows counterpart.

You can love windows desktop or server for a multitude of reasons, and you have every right to your opinion, but from this IT persons perspective, windows has not been a superior performing OS in quite some time. I won't argue ease of use and familiarity because of course Windows is the clear winner there. That is really the last thing it has going for it though.

-T.

All those criticizing

Otus (not verified) - February 9, 2009 @ 12:04pm

All those criticizing choice of OS: This benchmark is Ubuntu vs. Vista vs. 7, feel free to make your own! :)

All those criticizing choice of tests: The objectives were clearly laid in the beginning of the article. If you don't like them, why read or post? Again, I'd love to read about your benchmark.

"It's not the OS that matters. It's the applications. The GIMP still sucks. Photoimpact 5 (from 1999) is still better than GIMP UI wise. Make an opensource version of <b>PHOTOSHOP</b>, with a Photoshop like GUI, and decent performance."

I'm not sure about the UI, but GIMP has way better features than Photoimpact 5. UI is quite subjective, though. I like the UI of PSP better than Photoshop, for instance. Have you tried Gimpshop? It's a Photoshop-like GUI for GIMP, basically. That said, GIMP beats Paint, which is the only one that comes with Vista (and 7 afaik).

9.04 alpha 4 has ext4 on

bigdavesr (not verified) - February 9, 2009 @ 7:40pm

9.04 alpha 4 has ext4 on live cd. Have not noticed a big difference from ext3,but 9.04 is still alpha and has some problems Good artical, I enjoyed reading it

Here be fanboy land, Me thinks.

Anonymous Penguin (not verified) - February 9, 2009 @ 11:09pm

I really don't care that much about any of these tests. Both OSes have their own advantages. I use windows to play games as the general public uses windows and the gaming support isn't there for linux, at present. At work it's stability, or on other machines coding libraries, that are all important so it's linux all the way. And I'll use a mac if I ever feel that I really really need to use some overstylized crap.

Tsk tsk

Victor S (not verified) - February 10, 2009 @ 1:47am

Actually, the kind of benchmarks chosen really reflect on Linux users, and what a sorry, pennypinching lot they are.

Installsize in GB?!? Who the hell cares if it's 1GB or 5GB, in a world where a 120gb HD is considered low end in a laptop?!?

Personally I feel sorry for them... Notice how they always emphasize that it's "FREE!"
Imagine being so poor, or such a scrooge, that 50$ extra on a computersystem is a big ****ing deal.
I assume it's the same lot, who goes apeshit everytime they see a supermarket-coupon that'll save them 30 cents, or who consider it an epic win, when they save 20 bucks by buying the kids carseat used.

Sad really...