Generational Windows Multicore Performance Tests

snydeq writes "Windows XP, Windows Vista, and (soon) Windows 7 all support SMP out of the box, but as InfoWorld's Randall Kennedy notes, 'experience has shown that multiprocessing across discrete CPUs is not the same thing as multiprocessing across integrated cores within the same CPU.' As such, Kennedy set out to stress the multiprocessing capabilities of Windows XP, Windows Vista, and Windows 7 in dual-core and quad-core performance tests. The comprehensive, multiprocess workload tests were undertaken to document scalability, execution efficiency, and raw performance of workloads. 'What I found may surprise you,' Kennedy writes. 'Not only does Microsoft have a firm grasp of multicore tuning, but its scalability story promises to keep getting better with time. In other words, Windows Vista and Windows 7 are poised to reap ever greater performance benefits as Intel and AMD extend the number of cores in future editions of their processors.'"

Comments

So what?

[fpophoto]

Are we supposed to be surprised that the leading OS vendor, who's had deep, intertwined relationships for decades with hardware makers is exploiting that hardware properly?

Honest question: where's the news here?

Re:So what?

[Anonymous Coward]

The news is that nobody can say anything non-critical of Microsoft without being accused of advertising or astroturfing.

Oh wait, this is Slashdot. Nevermind.

Re:So what?

[Anonymous Coward]

The news is that Solitaire is now multi-core aware and will load all your cpu cores if you win.

Re:So what?

[kno3]

Ha, I can't believe that you could be so biased against Microsoft that you would even turn an example of them doing well into an insult. And yes, I have many a Linux obsessed friend that have argued with me saying: Vista's 64 bit support is terrible and it is unable to utilise more than one core. Fact is that it does so very well, and I am very glad of this article as it is a great thing to cite when I get told bulls**t again.

Re:So what?

[jedidiah]

Yes actually.

How long did it take them to fully exploit the 80386?

Some of us have a long memory and hold grudges.

Re:So what?

[Locutus]

look up the performance of Windows 95( the 32bit OS as MS claimed ) on the then new PentiumPro( the 32bit optimized CPU Intel claimed ). hint, an old 150MHz Pentium outperformed a 150MHz PentiumPro when running Windows 95. Real 32bit OSs like *nix, OS/2, and Windows NT showed vast performance increases running on the 32bit PentiumPro. It then took Intel almost 2 years to bring back 16bit optimizations into their latest CPU hardware.

I don't think this is about Microsoft being buddies with the hardware people. I think it has more to do with Microsoft designing poor software and throwing alot of it at the distribution such that just to get the OS off the metal, it's really resource intensive and their core OS guys are tasked with getting as much out of the available hardware as they are capable of.

Remember, tests had already shown that Windows XP outperformed Vista by 100% on the same hardware. Microsofts marketing is doing a better job now and we are constantly seeing performance tests showing Vista faster than XP and even Windows 7(beta) being faster than XP. And we are seeing alot of these performance test so once again, chalk it up to Microsoft's marketing because do you really think their OS people did in less than a year what they couldn't do in over 5 years?

LoB

Re:So what?

[squallbsr]

I would believe that the 5000 layoff is the culling of the 'bad apples' that every organization has in their ranks. The economy is just a good excuse to do it.

The proof is in where the cuts are being made. Are they cutting sales staff? Are they cutting consulting services? Or are they cutting developers? -- THAT is the question.

Re:So what?

[drsmithy]

hint, an old 150MHz Pentium outperformed a 150MHz PentiumPro when running Windows 95.

A frequently-repeated and commonly exagerated urban myth, but one that isn't supported by evidence.

Yes, in a worst case scenario (16 bit applications, hardware requiring legacy DOS thunking drivers, etc) you might see the sort of numbers you refer to, but on a properly configured Windows 95 system (32 bit applications, 32 bit drivers) the Pentium Pro performed measurably better than the Pentium (albeit not as relatively better as it did on NT).

Real 32bit OSs like *nix, OS/2, and Windows NT showed vast performance increases running on the 32bit PentiumPro.

OS/2 still had 16-bit components well past the mid-90s. Most notably, the HPFS driver.

Re:So what?

[the_B0fh]

You mean:

http://www.bestcleanfunnyjokes.info/index.php/site/comments/star_trekthe_next_generation_meets_microsoft_windows/

Re:So what?

[jimfrost]

Well, given how poorly that Windows has historically handled SMP one would think that the news is that maybe it's not as bad as we all thought. But this shouldn't be news, we've known for a long time that Microsoft has been gradually improving SMP performance.

My experience with Windows is that, in general, NT really didn't scale much beyond 2 CPUs, and 2000/XP leveled off around 4, and Vista's improvements become marginal by 8 -- except in cases where you try pretty hard to avoid OS interactions.

Maybe it's just me but I think the litmus test isn't that Windows is improving in this area, but how well it does against the competition (what you might call "general state of the art"). And it's here that I think Windows' weaknesses show: Generally they haven't done very well against players like Sun (which to me is amusing since Sun had to rework a truly awful codebase to get to where they are today, and they did it in a lot less time than Microsoft) and these days they're not even doing that well against Linux. The latter is pretty surprising since they had both a lot more resources and a heck of a head start over the free software folk. It seems clear that the multiple-competing-approaches development paradigm the FOSS folk use produces excellent results over the long term. Kind of like natural evolution.

As an aside, I had to laugh at the "whopping 430 concurrent execution threads." That's not really pushing thathard, even if it's a whole lot more than most desktop users are going to push it.

Anyway what I take out of the article is that Win7 will be able to effectively utilize the core counts we expect to be in wide use over the next five years or so. Good news, if not entirely unexpected by anyone who was paying close attention to Windows performance previously.

Re:So what?

[Anonymous Coward]

Insinuation? All he said was that Vista and 7 are better at SMP/multi-core than XP.

Re:So what?

[Locutus]

ok, a pre-emptive multi-tasking os OS like the early 90s OS/2 had 16 bit drivers. so it is not considered a "real OS" and should be categorized in the same list as Windows 95? right.

and I liked the part in that link where Intel didn't allow the people putting up the article to do their own testing. I was there, I ran it, it ran OS/2 apps much faster, it ran windows apps much slower and Intel had to come out with a new design because Windows 95 was not optimized for 32bit and that was all Microsoft had.

Like I said, I was there and it was yet another example of Microsoft's marketing driving yet another poor OS experience for anyone who ran other OS's and new what an OS was supposed to be. What and OS should be.

LoB

Re:So what?

[drsmithy]

ok, a pre-emptive multi-tasking os OS like the early 90s OS/2 had 16 bit drivers. so it is not considered a "real OS" and should be categorized in the same list as Windows 95? right.

That's not what I said at all. You were complaining about 16-bit code in Windows 95, so I pointed out that there was also 16-bit code in OS/2.

and I liked the part in that link where Intel didn't allow the people putting up the article to do their own testing. I was there, I ran it, it ran OS/2 apps much faster, it ran windows apps much slower and Intel had to come out with a new design because Windows 95 was not optimized for 32bit and that was all Microsoft had.

Rubbish. Microsoft had Windows NT (which was technically superior to OS/2 in every way).

Like I said, I was there and it was yet another example of Microsoft's marketing driving yet another poor OS experience for anyone who ran other OS's and new what an OS was supposed to be. What and OS should be.

I was also there, and an ex-OS/2 user, and Windows 95 did everything it was supposed to do and did it quite well.

However, getting back to the actual argument, the point is that claims of Windows 95 'running more slowly on a PPro than a Pentium because of 16-bit code' are flat-out wrong. If you benchmark a 32-bit application on a properly configured Windows 95 system, with both a PPro and Pentium of equivalent clock speed, the PPro will be faster.

Multicore vs. Single core

[Compholio]

'What I found may surprise you,' Kennedy writes. 'Not only does Microsoft have a firm grasp of multicore tuning, but its scalability story promises to keep getting better with time. ...'

Not really, wasn't one of the major complaints about Vista that they were changing the OS architecture to tune multicore processors to the detriment of single core processors?

Re:Multicore vs. Single core

[Bill, Shooter of Bul]

Well, what might surprise you is that XP is still faster than either one, and will only be surpassed by windows 7 when you have 32 cores or so. So they made it faster for 32 core machines to the detriment of single -> 31 core machines. That is surprising. Or as the article later suggests is due to other things in vista & 7 that increases the amount of stuff it has to do per transaction.

Its a shame really, it sounded like it was going to be a really positive article. Everyone else has had mostly positive reviews of windows 7. But this one does give me pause about eventually upgrading from XP.

Re:Multicore vs. Single core

[Compholio]

Is there really a reason you need to upgrade? If updates are your concern then why don't you switch to Mac or Linux for your next PC? Call me old fashioned but I don't tend to upgrade very often, installing updates I have no problem with but "upgrading" is a giant pain.

Re:Multicore vs. Single core

[Bill, Shooter of Bul]

I'm using "upgrade" very loosely. To make what was a long rambling post shorter, I have a mac and linux computers as well. If I have to replace the windows one, will I even get a windows one to replace it? I don't know at this point. Its nice to be able to deal with the same OS ( if necessary) as everyone else for compatibility reasons.

Re:Multicore vs. Single core

[Calinous]

XP support 1-2 processors (or cores?). XP Professional might support 4 processors/cores, but I'm not sure on this

Re:Multicore vs. Single core

[nabsltd]

XP home supports a single CPU socket, while XP Pro supports up to two CPU sockets.

Either OS can support a maximum of 32 total cores.

Re:Is the moon haunted?

[Yvan256]

Elvis.

118% slower

[TheMeuge]

Roughly 118 percent slower than XP on dual-core

Some great mathematics in this review... it also appears as if Vista isn't just not solving the problems presented to it, but also adds new ones to increase its own workload.

Fascinating...

Re:118% slower

[Anonymous Coward]

No, really... where is the troll?! It's a JOKE...

Seriously. Where are the mods?

Re:118% slower

[jc42]

Roughly 118 percent slower than XP on dual-core

Some great mathematics in this review...

Yeah, I was sorta wondering about that. Anyone know what the denominator could have been in this calculation? Are they really claiming that it runs the code backwards, undoing the calculations and going from a programs outputs to what its inputs had to be? If so, that could be a major technological advance all by itself. Imagine the useful things you could do with this capability ...

Re:118% slower

[Jerry Coffin]

This was to satisfy Bill G's desire to "factor large prime numbers."

Re:118% slower

[Kjellander]

It should be 54% slower. If it takes 118% more time to do it.

x = 100 * (1 - 100 / (100 + 118))

Re:118% slower

[Anonymous Coward]

it runs the code backwards, undoing the calculations and going from a programs outputs to what its inputs had to be?

It's called reversible computation. Microsoft is gunning for that ultimate efficiency.

Re:118% slower

[Calinous]

Bringing questions for your great answers

Re:118% slower

[adisakp]

It'd be much nicer if he just gave us the Raw Benchmark times and let us calculate the correct values rather than his statistic percentages which seem to change how they are calculated depending on the case and are sometimes wrongly describe (as in the impossible scenario you mention in your post - more than "100% slowdown "is awfully hard to get without warping reality).

Re:118% slower

[Anonymous Coward]

100 * (1 - 100 / (100 + 118)) = 5400%
(1 - 100 / (100 + 118)) = .54 = 54%

I always hated that useless 100 people multiply in there. That's what the % sign is for: it means "out of 100".

Re:118% slower

[default luser]

Yeah, I absolutely loathed the article's layout, because the benchmarks were littered carelessly all through the text. If they're going to bother posting an analylitical article with benchmark numbers, the least they could do is post a summary table.

Re:118% slower

[tixxit]

Are they really claiming that it runs the code backwards, undoing the calculations and going from a programs outputs to what its inputs had to be? If so, that could be a major technological advance all by itself. Imagine the useful things you could do with this capability ...

Sir, I introduce you to Prolog.

Re:118% slower

[jc42]

Heh; I learned prolog when I was in college, several decades back. Since then, I keep running into situations where I think "This would be so much easier if I could just write it in prolog." But sadly, that's against the guidelines in most of the corporate world, which is still trying to adjust to the advent of things like C, perl, and python, and the fact that their beloved Cobol has been eclipsed. Actual powerful languages like prolog (or even lisp) would be just too much of a shock to The Way Things Are Done. One quickly learns that it doesn't help your career to suggest them.

But I don't think that even prolog programs could run backwards, or finish before they started, or whatever "118% slower" means. The obvious interpretation of this number would be that if, for example, one system ran a program at 100 mips, the other would run it at -18 mips. If we use the standard auto analogy, it's easy to understand this: One is going forward at 100 km/s, while the other is going in reverse at 18 km/s. But I'm a bit puzzled about how you could build a CPU with a "reverse gear".

Maybe my imagination just isn't up to the job.

My experience...

[Smidge207]

I run both XP and Vista on Core2Duo processors.

I'm certain with XP and less certain with Vista (I don't use it for production work) that I can get better performance by forcing everything but EXPLORER.EXE to use the second core at a low priority.

Then as I run programs, they automatically go to the first core (with EXPLORER.EXE).

This allows me to run FOLDING, an RSS reader, LogMeIn all the time but on the second core.

I especially notice a difference when I copying files at the command prompt.

The program is called PROCESS.EXE and can be found at:

http://www.beyondlogic.org/consulting/processutil/processutil.htm

It is a manual process but it is pretty simple to create a batch file to do the dirty work.

=Smidge=

Re:My experience...

[AlterRNow]

My experience is that if you set a programs ( notepad for example ) affinity to the second core and then set it to 'realtime', Windows slows to an agonising crawl with the first core usage at 0% and the second at 100%. As far as I am concerned, SMP doesn't work ( at least, not on WinXP SP2/SP3 ).

Re:My experience...

[mobby_6kl]

This is not what happes at all, at least not on XP SP2.

Setting notepad's affinity only to CPU 3 and priority to Realtime does absolutely nothing: the overall CPU usage stays at about 1-2% and Windows is perfectly responsive. But the thread is idle, I hear you say! Well doing the exact same thing to a working WinRAR process just results in 25% overall usage and ~100% core 3 utilization, leaving the system as responsive as ever.

Re:My experience...

[AlterRNow]

I'm guessing your using a quad core machine, perhaps the behaviour is different on dual cores ( maybe an important Windows process/thread was on core 2 as well as notepad ).

Re:My experience...

[Lord Crc]

My experience is that if you set a programs ( notepad for example ) affinity to the second core and then set it to 'realtime', Windows slows to an agonising crawl with the first core usage at 0% and the second at 100%.

From MSDN:

You should almost never use REALTIME_PRIORITY_CLASS, because this interrupts system threads that manage mouse input, keyboard input, and background disk flushing. This class can be appropriate for applications that "talk" directly to hardware or that perform brief tasks that should have limited interruptions.

Re:My experience...

[Wolfrider]

Mod parent up ;-)

Re:My experience...

[AlterRNow]

I don't see how that excuses the behaviour. Multi-core == doing >1 thing at the same time, right?

And Windows XP is still faster

[ameline]

And XP is still faster than vista or 7, even on 4 cores... And he speculates that it would be faster on 8 (although he didn't measure that)

Scalability doesn't matter if you're still slower in absolute terms on systems that are available commercially at a reasonable price. (going past 8 cores these days is a very large price jump per core)

Re:And Windows XP is still faster

[Anonymous Coward]

But doesn't WinXP limited to only 4 processors?

Re:And Windows XP is still faster

[rbanffy]

"(although he didn't measure that)"

Most probably because XP can't do 8 cores.

Re:And Windows XP is still faster

[SerpentMage]

Ok so who is faster XP, or Vista?

The header says Vista and Windows 7, but yet in the article:

It should come as no surprise that Windows 7 performs very much like its predecessor. In fact, during extensive multiprocess benchmark testing, Windows 7 essentially mirrored Vista in almost every scenario. Database tasks? Roughly 118 percent slower than XP on dual-core (Vista was 92 percent slower) and 19 percent slower than XP on quad-core (identical to Vista). Workflow? A respectable 38 percent slower than XP on dual-core (Vista was 98 percent slower) and 59 percent slower on quad-core (Vista was 66 percent slower).

http://www.infoworld.com/article/09/01/22/03TC-windows-multicore_4.html

So therefore Vista and Windows 7 suck in performance to XP?

Re:And Windows XP is still faster

[Anonymous Coward]

I don't see how that's really a win though. It's like saying it's the fastest OS named Vista.

Re:And Windows XP is still faster

[quo_vadis]

XP is still faster by a large margin(20% to 40% depending on load scenario). FTFA

If you take the raw transaction times for the database and workflow tasks, then factor them against the average processor utilization for these same workloads, you see that Windows XP consumes roughly 7.2 and 40.7 billion CPU cycles, respectively, to complete a single pass of the database and messaging workflow transaction loops on our quad-core test bed. By contrast, Windows Vista takes 10.4 and 51.6 billion cycles for each workload, while Windows 7 consumes 10.9 and 48.4 billion cycles. Translation: On quad-core, the newer operating systems are at least 40 percent less efficient than XP in the database tasks and roughly 20 percent less efficient in the workflow tasks.

Re:And Windows XP is still faster

[robthebloke]

Physical Processors != CPU cores.

Re:And Windows XP is still faster

[petermgreen]

IIRC it limits to two processor chips so it will use all cores in a dual quad but not in a quad dual.

at least that is the case for XP proffesional x64 edition, MS claim it is also the case for XP proffessional but I don't have first hand confirmation of that.

Re:And Windows XP is still faster

[Cormacus]

[citation needed]

Re:And Windows XP is still faster

[UnknowingFool]

I would think XP would be faster depending on the scenario. Although the OS might be better tuned in Vista and Win7 for multi-cores, the applications that run on the OS may not be yet. As time goes on and applications are better tuned for multi-cores, that may change. Most applications today assume that there is one core and they must share it with other applications in Windows. The OS has to play a larger part in determining which core runs the app. In the future, multi-core apps might work better with the OS in determining priority and core, etc.

Re:And Windows XP is still faster

[RicktheBrick]

I have 4 q6600 quad computers. One is running vista, one is running xp and two of them are running ubuntu. I do volunteer work for world community grid. The number of results for the last 14 days are as follows: vista 184, xp 127, ubuntu1 150, ubuntu2 210. They all have different motherboards but have the same amount of ram memory. The Ubuntu computers are running 64 bit version while the vista and xp are 32 bit operating systems. Here is an article http://www.computerworld.com/action/article.do?command=viewArticleBasic&articleId=9126460&source=rss_topic12 that states that going to 8 processors does not increase efficiency by much because of the memory access problem. The processors will spend too much time waiting for their turn to access ram memory.

Re:And Windows XP is still faster

[eXonyte]

XP can certainly do 8 cores. We have a dual quad Xeon machine running XP Pro that's used in our video production department and it works great.

Re:And Windows XP is still faster

[rbanffy]

Oops... My bad. It's been a long time since I offered my high-end hardware in sacrifice to the Windows gods.

Re:And Windows XP is still faster

[Anonymous Coward]

You mean over 32 or 64 depending of the edition? Vista has the same limitation, Windows 7 doesn't.

Re:And Windows XP is still faster

[erroneus]

This would seem to add credence to my assertion that Windows 7 is just "Mojave" thrust upon the world. They aren't changing anything! They are just rearranging the deck chairs... on the titanic.

Re:And Windows XP is still faster

[Anonymous Coward]

This is less of an issue on 8x and 16x Opteron. The new i7 platform should also show improvements when dual and quad socket motherboards show up.

Re:And Windows XP is still faster

[man_of_mr_e]

And I would hazzard a bet that Red Hat 3 is faster than FC10 on the same hardware.

As software evolves, it gets more complex. More complexity means more CPU cycles used. Sorry, that happesn for all software that evolves.

tma:dr

[aliquis]

Too much ads: Didn't read.

Great job linking to a five page story with on-top layered flash ads and new whole page ads for each page.

Like I'd give a shit about the page at all in that case.

Re:tma:dr

[cplusplus]

Funny you mention that - this link was the straw that broke the camel's back and drove me to install flash block.

Re:tma:dr

[aliquis]

Wtf, and I got moderated troll for mentioning that even though I DO block flash the damn block occured on top of the article until I loaded the flash anim, just to run a minimizing animation when I closed it and then pop up again if I wanted to load the very nice stuff again ...

Not to mention that I got a separate ad page when I first visited the article and then was going to switch to page 2 to see if there was anything interesting.

It was a fucking ad, which wasn't interesting, so I left.

Weird how Slashdot users LIKE ads today. We should boycot any stories from pages which does this shit, why give them tens of thousand to millions of hits when they behave like this?

Where's the beef?

[gzipped_tar]

I tried RTFA (sorry, please mod me done for this ;) but, after clicked the "print" version, I couldn't find anything that looked like a benchmark report. No numbers. No tables. No graphs. All I saw was a page of [[weasel words]] or something like that.

Sigh..

Re:Where's the beef?

[jonaskoelker]

All I saw was a page of [[weasel words]] or something like that.

[[citation needed]]

Re:Where's the beef?

[gknoy]

This is something that needs to be brought up with the publisher of the online resource. Tell them that if their "printable view" doesn't show the charts from an article whose main substance is charts, then you are uninterested in visiting their site.

You might get a "Thanks, that's nice" response -- if you're bypassing ad revenue in the first place, you're not really their ideal customer.

Re:Where's the beef?

[gzipped_tar]

But this article has no charts in the first place! There's no presentation of data in either the normal page view or the printable view.

This has nothing to do with the ad policy. I believe this is the result of the author's lack of presentation skill (applying Halon's razor). Even Phoronix's one-paragraph-per-page benchmark reports does a better job.

Re:Where's the beef?

[Anonymous Coward]

[[citation needed]]

[[that is old by now]]

Re:Where's the beef?

[Anonymous Coward]

Thats because there wasn't one in the article itself.

Re:Where's the beef?

[IorDMUX]

I tried RTFA (sorry, please mod me done for this ;) but, after clicked the "print" version, I couldn't find anything that looked like a benchmark report. No numbers. No tables. No graphs. All I saw was a page of [[weasel words]] or something like that.

I agree. I guess I've been spoiled by *real* benchmarks by spending the week on Tom's Hardware...

Though this article did give us the following gem:

Windows 7 essentially mirrored Vista in almost every scenario. Database tasks? Roughly 118 percent slower than XP on dual-core

...Would any CS grad student like to step in and inform us what 118% slower means in software terms? Does Windows 7 cause the CPU's program counter to mysteriously run backwards, now?
...*confused*...

Re:Where's the beef?

[alexo]

sorry, please mod me done for this

Stick a fork in him!

Interesting

[quo_vadis]

It is interesting that WinXP is still better in terms of performance than either. The article suggests that Win7 and Vista would be better on systems that hypothetically had 16+ cores.

But nowadays, especially in tech savvy crowds like on /., the most popular thing to do is run VMs with virtual instances of Windows, which reduces all the hassles associated with dealing with win cruft. Got a worm? restore machine. Drivers made system unstable? restore machine. The vms are typically only given 1-2 cores, the exact use case where WinXP does way better than its successors.

So even if we move to a world with 16+ core processors, if Win7 cannot do better than a 10 year old OS, in common scenarios, how can that be called progress?

Re:Interesting

[gzipped_tar]

Sorry for posting an off-topic message here, but after reading your post and sig., I'd like to say "and Darth Vader rolls out VM snapshots" :-P

Re:Interesting

[blankinthefill]

Try running Win 98 on Vista's minimum hardware. Hell, lets go whole hog here. Try running Win 3.1 on Vista's minimum hardware. (Okay, you might have to do a lot of work to get it running, but I'm just trying to make a point). I guarantee you that both 98 and 3.1 will run faster than XP on that hardware. By a lot. If it surprises you that vista and xp run slower on the same hardware than xp, then either you're not thinking things through, or you're not very bright. As stated, they are far newer. This means they have a much higher assumed baseline of technology that they can run against, which means that they have far more assumed resources to play with. So yeah, on the same system, Vista runs slower than XP. No surprise (at all, as far as I'm concerned). Honestly, all this speed stuff is pretty pointless. The question with OSes is never really about the fastest, or we would all still be using DOS. The question with OSes is are the fast ENOUGH. This is very subjective, but it basically boils down to: will they run what we want them to run in an acceptably small amount of time. On its original release, Vista did not. However, right now Vista is certainly running fast enough for me, and I expect Win 7 will to. But you're ALWAYS going to take a performance hit moving to an OS that utilizes new technology, and I don't care what OS you use.

Re:Interesting

[jonaskoelker]

if Win7 cannot [...] how can that be called progress?

It's the new thing, the one created by the progress of time. Microsoft is generating profit, I mean progress, with their new OS.

It's progress in the sense that it allows Microsoft to survive off of a market it has already saturated and progress forward towards idunno by putting a "progress" sticker on their old^Wnew product.

</snark>

Re:Interesting

[Anonymous Coward]

Apple prides themselves on each release being faster than the last. Linux has performance improvements in pretty much every (2.6.x) kernel version. Windows seems to be the odd one out here.

Re:Interesting

[Lonewolf666]

Try running Win 98 on Vista's minimum hardware. Hell, lets go whole hog here. Try running Win 3.1 on Vista's minimum hardware. (Okay, you might have to do a lot of work to get it running, but I'm just trying to make a point). I guarantee you that both 98 and 3.1 will run faster than XP on that hardware. By a lot.

That comparison falls apart as soon a you go to a dual core CPU and more than 512 MByte RAM. Most new PCs will have that and Win 98 cannot utilize it. At best Win 98 will run using only half of the computer's resources. Now run an application that does take advantage of multiple cores. I bet XP would win.

Re:Interesting

[EvilJohn]

Terrible analogy.

Windows 98 or Windows 3.1 can't run the exact same applications. The author's point is a good one. Why does running the exact same application under VISTA or W7 cost 20 to 40 more cpu cycles?

In business terms: Why do you have to buy 20 to 40% more hardware to get the same result as I have today?

Re:Interesting

[Anonymous Coward]

But Windows is more than just the kernel.
The linux kernel is getting smarter and faster in some places, but KDE 4 will, when all is said and done, be slower than KDE 3 because it does more (Unless the performance improvements of qt4 vs qt3 take up the slack). But that KDE4 indexing app slows things down if you don't disable it, compositing slows things down if you don't have a new enough video card or your drivers have problems (nvidia for a while) and kde4 is being added to on a daily basis. Don't get me wrong, the power of linux is that you can still run xfce when you want to (or just pair down kde4 to what you need).

Re:Interesting

[UnknownSoldier]

> But you're ALWAYS going to take a performance hit moving to an OS that utilizes new technology, and I don't care what OS you use.

Nonsense.

OSX and BeOS continue(d) to get faster with each new release.

Re:Interesting

[arazor]

OSX 10.5 was initially slower than OSX 10.4 unfortunately. Only after several revisions did it reach parity. I blame apple for either releasing 10.5 too early or focusing too much time on the iphone/ipod touch.

Re:Interesting

[drsmithy]

OSX and BeOS continue(d) to get faster with each new release.

OSX was so slow at release it had nowhere to go but up. Microsoft has never released a version of Windows that performed that badly. Relatively speaking, Vista was greased lightning at release compared to OSX 10.0 (10.1, 10.2, maybe even 10.3).

Re:Interesting

[Steve Baker]

If an older version can use the same resources better than a new version without a loss of functionality, then what you have is a performance regression, which, unless it's for stability, security or feature reasons, is a bug. The question here, which is not answered, is why is there a performance regression?

Re:Interesting

[man_of_mr_e]

You mean apple falsely prides themselves. Do you really think that features like Time Machine don't add mroe CPU cycles to the load? They may improve the efficiency of the kernel or some miniscule measurable piece, but overall the workload goes up, just like every other OS.

Linux is the same. I guarantee you that if you run Red Hat 3 on the same hardware you are running the latest FC10, FC10 overall will be significantly slower, even if the kernel or other individual pieces may be faster. I'd make the same bet on Ubuntu, Gentoo, Debian, Mandriva and Suse.

Obviously, that wouldn't apply to something like DSL which works hard to reduce functionality, but overall, most OS's get slower over time even while they become more efficient at doing it.

Better multicore perfom to support more bloat

[HockeyPuck]

Ok, so if the average user is still doing the same basic tasks, browser/email/word processing it kills me that I'm now requiring the CPU power of yesterdays servers to do these basic tasks. Having multicore systems enables software vendors to increase the bloat, because the increase in cpu/ram will take care of it; therefore hiding this increase in bloat from the user. It's no difference in converting all cars to lead bodies; as long as we put 1000hp engines in them. The user experience doesn't change b/c they still have the same 0-60 times.

For example, I've always wondered how much CPU time is wasted due to anti-virus software? Let's say you have a large windows on VMware environment. Each VM needs to have antivirus on it, if you've got a server with 10-20 VMs on it; you've got 10-20 instances of anti-virus running. There's gotta be some way to calculate the total amount of CPU and power (W) wasted on this single server to just running the antivirus scanning...

How about an increase in CPU, but either keeping the bloat the same?

Re:Better multicore perfom to support more bloat

[Anonymous Coward]

"Ok, so if the average user is still doing the same basic tasks, browser/email/word processing it kills me that I'm now requiring the CPU power of yesterdays servers to do these basic tasks."

Servers - hell, Vista requires the power of yesterday's supercomputers to read email. The last time I used Windows by choice was Win98 plus Office 97 on a PII 400 with 128 MB RAM, and it easily did everything an office worker would now do with a current behemoth running Vista. For that matter, my 486 with Win 3.1, WordPerfect, and Lotus 1-2-3 did the same job just fine.

Or maybe "yesterday's servers" means servers from around, say, 2005.

Re:Better multicore perfom to support more bloat

[Anonymous Coward]

We do put more powerful engines in cars now without making them faster. Most of the extra energy is spent moving the heavy safety gear, DVD players, rear view cameras and 12 way power adjustable leather seats with built in heaters.

Although you were arguing against Windows bloat, it's actually a good analogy. Users have demanded more and more built in, fancy, high graphics add ons with the OS, and MS gave it to them. Users also wanted safety they didn't have to think about, and MS has done what it could in that regard too.

Re:Better multicore perfom to support more bloat

[Samah]

Ok, so if the average user is still doing the same basic tasks, browser/email/word processing it kills me that I'm now requiring the CPU power of yesterdays servers to do these basic tasks.

If you're still doing the same basic tasks with your current PC, why are you upgrading? If your current setup of Windows 98 will do IE, Outlook Express and Word (and that's all you care about), why are you "requiring the CPU power of yesterday's servers"? It's your decision to upgrade your PC and/or OS.

Look for the Dodgy Phrasiology

[segedunum]

Not only does Microsoft have a firm grasp of multicore tuning, but its scalability story promises to keep getting better with time.

When you see bullshit buzzwords in articles that look as if they've been written by marketing people then look out. Marketing-led, buzzword-laden people always have stories. Are we really supposed to be impressed that the richest OS developer in the world can actually create a SMP capable OS that actually works reasonably given that SMP systems have been around for years? From the tone of the article it's like they're shocked that it works.

Re:Look for the Dodgy Phrasiology

[jonaskoelker]

From the tone of the article it's like they're shocked that it works.

They're obviously familiar with Windows ME.

Re:Look for the Dodgy Phrasiology

[Anonymous Coward]

That shouldn't still make me laugh, but I used windows ME, and I'll never forget the pain.

Re:Look for the Dodgy Phrasiology

[dragonjujotu]

This is the most reasonable comment I've read so far

Re:Look for the Dodgy Phrasiology

[man_of_mr_e]

"story" is no longer a marketing word. It's used in programming now, particularly in the case of Extreme and Agile programming methodologies. It's use, as appears to be the case here is in "use cases". So it's no longer a marketing buzzword, it's a programming buzzword.

The Money Quote

[d3ac0n]

Basically, this article states the obvious: Windows XP 64 is just plain faster than Vista 64 or Win7 64. By a factor of 20-40%. But to understand why, you need to read the MONEY quote. Here it is:

In the end, it all comes down to the complexity of the execution path. With its simpler legacy kernel devoid of DRM hooks and other performance-sapping baggage, Windows XP provides a cleaner code path for the workloads to navigate as they execute. This, in turn, translates into better overall performance with lower consumption of CPU cycles.

It's the DRM baby. You strip that out of the Kernel, and Vista and Win7 will EASILY outpace XP with their more advanced and flexible SMP capability. Until Microsoft understands that people DO NOT WANT DRM and removes it from their newer OSes, these new OSes will continue to suffer from performance problems, and thusly, acceptance and sales problems.

Come on Microsoft. Apple has figured it out, DRM is a sales loser. Do you really want to keep wasting time on a loser technology in the midst of a global recession? You blew it with Vista, but you still have a chance with Win7. Offer people a DRM-Free kernel and Win7 will FLY off the shelves.

 

Re:The Money Quote

[aliquis]

I've never understood why the DRM crap matters as long as you don't run anything using it but whatever. Sounds like a bad excuse.

Re:The Money Quote

[d3ac0n]

Because ALL software has to run the DRM hook gauntlet. basically, the way Microsoft has set it up is that the DRM processes are ALWAYS running and CANNOT be disabled. So every single bit of data is processed through the DRM loop, slowing everything down.

Re:The Money Quote

[wyoung76]

And yet the average Joe won't know nor care if it has DRM built-in or not...

Re:The Money Quote

[Anonymous Coward]

you need to read the MONEY quote. Here it is:

In the end, it all comes down to the complexity of the execution path. With its simpler legacy kernel devoid of DRM hooks and other performance-sapping baggage, Windows XP provides a cleaner code path for the workloads to navigate as they execute. This, in turn, translates into better overall performance with lower consumption of CPU cycles.

Does he know this for a fact, or is he just pulling a big juicy guess out from his gaping asshole?

Re:The Money Quote

[Cynonamous Anoward]

Nope. The average user has no clue what "DRM" is. They just know that when they put vista on their formerly decent machine, it suddenly runs slow and won't let them do things that used to work just fine.

Re:The Money Quote

[quo_vadis]

I have never been a "windows fanboi"( In fact this is being posted from a linux computer) and I am no defender of Microsoft's business practices. However without doing code analysis, it is impossible to say that this slowdown is because of DRM. Nowhere in the article does it suggest that they were able to do a profile analysis of the kernel codes and compare what modules on the path were causing the delays. So while it is theoretically possible(and likely) that the source of the delay was DRM related, one cannot be sure. If you possess knowledge otherwise, please feel free to cite it and correct me.

Re:The Money Quote

[Anonymous Coward]

Come on Microsoft. Apple has figured it out, DRM is a sales loser.

What is it with you people? Apple is far worse than Microsoft on the DRM front. They lock shit down that has nothing to do with media piracy. I can't install rockbox on a newer ipod because they decided to encrypt the firmware. I can't use linux to sync newer ipods because they decided to increase the itunes database.

Fuck Apple

Re:The Money Quote

[Chabil Ha']

You're right, all Joe cares about is can he get what he needs to do, done, and can he do it quickly. The GP is just stating that Joe would be happier without the sludge because his OS would be that much more responsive. I took Windows 7 *and* Vista for a tire kicking experience last weekend. I was happy until I got to games and other CPU/GPU activities. Strip out the sludge so they run as well are better than on XP and you'll have me sold, too.

Re:The Money Quote

[twowoot4u]

Wrong! The real solution is to put more stress on the hardware vendors to both improve their driver support, as well as make faster hardware to run these 'more powerful' OS's. The faster your CPU is the better it should handle the DRM hooks, right? :D

Re:The Money Quote

[kno3]

if Windows XP 64bit actually worked then this would be useful, but it doesn't it is completely useless as an OS because it is so unstable.

Re:The Money Quote

[aliquis]

No matter how Windows is coded and designed is the problem really the DRM or Microsofts implementation of it?

Re:The Money Quote

[Toreo asesino]

Oh? That's quite a claim.

"DRM" only kick in the moment you play hi-def media with copy-protection bits enabled only. Vista is in some tests ever-so-slightly slower than XP, but then XP was to 2k, 2k to 98, etc, etc. It's a phenomenon known as "more code".

I'd appreciate it if you could justify any of these claims with say some evidence? Not the Auckland guy though, his claims were debunked rather thoroughly a long time ago.

Re:The Money Quote

[David Gerard]

O rly? I think they do care.

Re:The Money Quote

[jonaskoelker]

They obviously grabbed a hack from thepiratebay.org which did nothing except disabling the DRM, and saw a performance gain of 20-40% ;)

Re:The Money Quote

[TheThiefMaster]

How do you know? Do you have the source code to Windows Vista?

Everyone I've seen that blames "DRM" for Vista being slow has no idea what they are talking about, and are just going "Vista has DRM and is slow, therefore it must be slow because of DRM".

Correlation is not causation people!

Re:The Money Quote

[mitherin]

if Windows XP 64bit actually worked then this would be useful, but it doesn't it is completely useless as an OS because it is so unstable.

I beg to differ... I've been running XP x64 for a couple years now and its just as stable, if not more so, than x86. I've only had to do a couple tricks to make things work, simply because it was never pushed hard as a mainstream version

Re:The Money Quote

[Anonymous Coward]

This a commonly quoted myth, parroted by people (like you) who don't know what the hell they are talking about!

Re:The Money Quote

[rossjudson]

This is yet another one of those times when I wish Slashdot wasn't so ridiculously hostile to Microsoft. What we need here is some informed, possibly even official commentary from someone in the know at MS. Exactly why is a workload slower on Vista? Where's that time going? Right now something like 60-70% of corporate workloads still run on Windows OS, so gaining an understanding of exactly why is important.

When the difference is on the order of 20-40% (if the article is to be believed), we're looking at some level of system-call "tax" under Vista, or we're looking at a different _capability set_. If the workload on Vista is in a secured environment, and the same workload runs faster on XP in an unsecured environment, we're talking apples and oranges.

It could be the case the even for workloads running as root equivalents in Vista execution times are worse...but we don't really know from what's quoted in this article, and there isn't any response from MS.

I think Vista is a pretty important upgrade for most users. Even if its security mechanisms are intrusive, at least they're _there_, and that's a step in the right direction.

Re:The Money Quote

[CannonballHead]

That's an itneresting point. I wonder why they didn't test 2k, 98, and 95?

I could test an old DOS game vs. [insert new game here] and see the FPS in [insert new game here] be so, so much lower. [insert new game here] must be horrible, DRM infested, and we should all use old DOS games.

Granted, Vista does seem a bit on the slow side (although on my Q6600 w/ 7GB RAM, it runs pretty quickly all in all), and Windows 7 *seems* to run slightly faster even in a VM... but I'm so tired of reading the "XP (read: an operating system that came out many years ago) is faster on current hardware than Vista/Windows 7!"

I may as well come out and say Ubuntu is so stupid, I could run [insert random distro] on my old 486 faster than Ubuntu on my modern hardware! Or whatever. The general idea is there.

Re:The Money Quote

[Jamie's Nightmare]

Wrong. About the only source you could use to back up that claim would be troll fodder pumped out by the likes of Peter Gutmann, who himself doesn't really have a firm grasp of what he's talking about. As we can see with Modern Benchmarks, Vista can match or even beat XP in terms of performance.

But wait, that can't be. You are stealing me that evil DRM hooks are stealing clock cycles. XP doesn't have those hooks, so how can it do worse in some tests?

Re:The Money Quote

[CannonballHead]

Mod up. I used XP 64 and was really happy with it... and then it randomly became EXTREMELY slow when doing any IO, it seemed. I don't know why. I went back to XP 32 bit, which works great for under 4GB RAM. Then I got more RAM and had to get a 64 bit Windows (and yeah, had to be Windows unfortunately, software constraints... available on Mac or Windows; VM/Wine not an option due to performance issues, AFAIK)

Re:The Money Quote

[kno3]

interesting. I have tried to get a friends install working before, and found it incredibly frustrating. I also tried installing it myself but I could never get it to boot after install. Tried various discs, assumed that it didn't like some of my hardware. You may be lucky and have a computer which it is fine with. I have met many people who have had similar experiences as I, but I suppose my friends and I could just be unlucky.

Re:The Money Quote

[Ed Avis]

Apple has figured it out, DRM is a sales loser.

Really? I thought Apple were busy adding more DRM to their products.

Re:The Money Quote

[0123456]

"How do you know? Do you have the source code to Windows Vista?"

Do you?

"Everyone I've seen that blames "DRM" for Vista being slow has no idea what they are talking about, and are just going "Vista has DRM and is slow, therefore it must be slow because of DRM"."

At a minimum, the changes to the driver model required to support DRM add a whole load of extra bloat that sucks performance; code that previously would have been tightly integrated into drivers now involves a lot of interaction with the OS.

Re:The Money Quote

[jgtg32a]

I've used XP64 for 2 years now, and it works great. The only problem was a printer that I've really never used and even now has drivers, and it still doesn't get used.

Re:The Money Quote

[plague3106]

Ahh, so the article makes up crap about "drm hooks and other performance sapping bagage" and you just accept that is how the kernel is built. I see. You don't even question what the "other performance sapping bagage" might be. I'd be curious to know as well. Since neither you or the article author are MS kernel developers, I don't care what you THINK might be in the execution path.

Your post also fails, because the author doesn't say if DRM or the "other baggage" is causing the greatest loss of performance, yet you jump all over the DRM aspect.

Re:The Money Quote

[Anonymous Coward]

All you MS apologists and shills have the same talking points: (1) DRM is harmless because it isn't invoked unless you're play DRMed content (in which case you *want* it), and (2) Don't quote Peter Gutmann (the "Auckland guy") because he's been debunked.

"The Auckland guy" has most definitely not been debunked. The only serious (using the term loosely) efforts I know of have come from Microsoft itself and from the Microsoft's ad agency, ZDNet. Gutmann showed the ZDNet critics for the idiots that they are (not that it wasn't already pretty obvious on the face of it), and the Inquirer exposed the Vista team's response for the spin that it was.

"The Auckland guy" is a respected academic computer scientist and security and cryptography expert who is talking in his field of expertise. Everything he says is based on Microsoft's own developer docs or device manufacturer docs. He cites his sources. He explains it all in technical detail. And unlike his opponents his fortunes aren't tied to this argument.

The truth scares you shills so much you have to try to discredit and suppress him at every turn. That's why you say thing like "Stop quoting the Auckland guy, he's been thoroughly debunked." I hate to break it to you, but this random debunked guy from Auckland has Bruce Schneier on his side. It's not hard to tell the difference between the experts and the shills in this debate, as long as the experts get the exposure they deserve. That's why people keep posting links to the "Auckland guy" despite your desperate protests. I know who I trust.

Read Peter Gutmann's excellent article here:
http://www.cs.auckland.ac.nz/~pgut001/pubs/vista_cost.html

Re:The Money Quote

[Joe U]

Because ALL software has to run the DRM hook gauntlet. basically, the way Microsoft has set it up is that the DRM processes are ALWAYS running and CANNOT be disabled. So every single bit of data is processed through the DRM loop, slowing everything down.

Citation Needed.

Re:The Money Quote

[Anonymous Coward]

Joe does care when he can't play a track or a movie. He cares when he can play it on device X and can't on his PC.

Re:The Money Quote

[Anonymous Coward]

Of course he's pulling it out of his ass; that won't stop people from perpetuating the claim, though. To be fair, there is a grain of truth to it. DRM "features" were moved into the kernel, BUT those features are only enabled when you are processing "protected" media. Perhaps he was playing a Blu-ray disc during his tests...

Re:The Money Quote

[TheThiefMaster]

As far as I know the only DRM is a check that runs before a protected video plays, that verifies that the hardware you're using for playback is all approved, and you're connected to the TV by a HDCP-encrypted connection, etc.

AFAIK, it doesn't do anything to non-protected videos, and nothing at all to non-video.

It certainly doesn't have a check in every command to the driver trying to figure out if you are watching an illegal xvid rip of something copyrighted like everyone suggests.

Now prove me wrong.

Re:The Money Quote

[Anonymous Coward]

I sincerely hope you're not one of the Microsoft employees to be laid off. It's always entertaining to read the comments from the MS shill factory.

Re:The Money Quote

[Anonymous Coward]

are you retarded? or you are just plain stupid ?

Re:The Money Quote

[drsmithy]

But to understand why, you need to read the MONEY quote. Here it is:

The "MONEY quote" just demonstrates the author doesn't know what he's talking about in that regard.

The DRM subsystems are only engaged at the request of an application that needs it for DRM-encumbered media. Otherwise they do nothing.

Re:The Money Quote

[Anonymous Coward]

Yeah, right. Executing DRM code doesn't slow down computers. No evidence of that.

Let me solve this with math for you.

DUH^10

There you have it.

Re:The Money Quote

[Anonymous Coward]

"Basically, this article states the obvious: Windows XP 64 is just plain faster than Vista 64 or Win7 64"

And Linux distributions and MacOSX previous versions arent slower also? You are a moron.

Re:The Money Quote

[msslc3]

Since the Presidential debates, everyone knows that the average Joe is named Sam.

Re:The Money Quote

[Hoi Polloi]

They were probably referring to this.

Re:The Money Quote

[D Ninja]

It's with handling DRM (not specifically Microsoft's implementation). The fact that Microsoft MUST handle DRM is the slowdown.

Take a look at it this way:

Code Execution Path w/out DRM
Run
Function
Function
Function
End

Code Execution Path w/ DRM
Run
DRM Check
Function
DRM Check
Function
DRM Check
Second DRM Check
Function
End

One is obviously taking longer than the other.

Re:The Money Quote

[Anonymous Coward]

xp x64 has a problem copying big files
http://support.microsoft.com/kb/920739

Re:The Money Quote

[drsmithy]

Because ALL software has to run the DRM hook gauntlet. basically, the way Microsoft has set it up is that the DRM processes are ALWAYS running and CANNOT be disabled. So every single bit of data is processed through the DRM loop, slowing everything down.

If this were true, then non-DRM-capable outputs (VGA, DVI, SPDIF, etc) would not work with Vista at all.

Re:The Money Quote

[Anonymous Coward]

The problem is the DRM itself. Some might be tempted to blame Microsoft's implementation, but if your goal is to make sure that all protected content is licensed (i.e., DRM), there's really no other way to do it than to funnel all content through a mechanism that can check it.

Essentially what I'm saying is that the problem is the DRM itself because, no matter how you implement it, it needs to spend resources "validating" the content. If I was in Microsoft's position and wanted to implement DRM (which I'm not, and I don't), I would probably do it the exact same way - add a hook to a very low level of the execution pipeline and do all checking there.

So the root problem is the DRM itself. The problem with Windows is not how they implement it, but the fact that they implement it at all. That's the single reason why I haven't even considered Vista, and if it's included in W7 then that will also be the reason why I won't consider W7.

Re:The Money Quote

[Anonymous Coward]

Only on slashdot can lunix trolls get modded up.

Re:The Money Quote

[techwrench]

hmmmm....

I don't have any issues syncing to the new ipods, using linux with amarok 1.4.

I haven't tried the latest version, though.

Re:The Money Quote

[Lord Apathy]

I have yet to have drm hinder me in any way. I routinely copy dvd's, recode them to whatever I want them too, or just simply burn them to another dvd. I've downloaded music from whatever had what I wanted. I've never had windows tell me it won't do something.

What I'm saying is DRM does nothing to hinder us that don't care about the rules. Those that do care follow the rules so the DRM doesn't apply to them ether. DRM is useless.

Re:The Money Quote

[sexconker]

Yesterday's decent is today's turd.

Re:The Money Quote

[nabsltd]

Unless the CPU is 100% loaded, then you won't shouldn't notice DRM affecting actual speed.

This is because a 30 frame-per-second video will play back at 30fps on any machine that is fast enough to handle it. A theoretical quad-core 10GHz processor with a GPU capable of handling 1000x the processing of current units would still only play back that video at 30fps.

The difference is that with DRM, more CPU is used. Even though it might not be enough extra CPU usage to cause an issue, it is something.

And, it's easy to see than the DRM code in Vista takes CPU cycles at times when it shouldn't, like playing back un-protected content. This is partially due to the complete paranoia of the design in that authorizing the content at start was not good enough, so the system has hooks that essentially allows DRM on only select portions of the content, which means it must constantly check to see if the particular frame playing right now is protected, and, if so, what needs to be done.

This reminds me of the Microsoft design for security in Access databases, which checks before each row is read/written to see if the operation is permitted. This means that if you have a query that updates a bunch of rows, there is not one check at the start of the query to see if the operation is permitted, but instead right before the operation is performed on each affected row, the security check is made. This also makes transactions really slow to implement. And, like the ability to enable DRM for a few frames of a video, is just as useless.

Re:The Money Quote

[Hurricane78]

You have to realize, what TCPA means. It means that *everything* is encrypted, all the time. Your HD? Encrypted. Bus transfers to the graphics card? Encrypted. And re-encrypted. For output over HDMI and DVI, to reach your display and be decrypted again. Sound card? Sure.

So I bet even inter-process-communication is.

Re:The Money Quote

[oddfox]

I like Schneier and respect him with regards to a lot of positions but on this particular topic I don't think I can. You say that Bruce is on Gutmann's side as if Schneier had some some sort of analysis on Gutmann's claims in order to verify their authenticity. He did not, he simply discussed the article in question and said that he agrees. Nobody has ever posted an actual analysis of the XP and Vista systems to see if indeed the DRM path is the culprit in anything. Maybe instead of attacking the DRM path for playing protected media (Which I might add is only invoked when one decides to playback DRMed content) people should focus their ire on the true culprit - Lazy programming that causes slowdowns in certain situations.

You may want to have a look at the entire section here on Wikipedia about this particular issue, which specifically mentions Guttman's article. The most important bit to note, in my opinion, is one of the responses from Paul Smith (There are many good ones):

# Vista does not degrade or refuse to play any existing media, CDs or DVDs. The protected data paths are only activated if protected content requires it.

Emphasis mine on the second half of that, and right before that bullet point is the pointing out that this stuff isn't even supposed to be turned on until 2010 or 2012.

Re:The Money Quote

[Anonymous Coward]

Vista SP1 has better performance than XP SP2 and that is a fact. You can make up whatever bullshit stories and believe nameless morons from tiny 3rd world countries, but that doesn't change reality.

You are jealous of Microsoft's success, you are a troll, you are a zealot and you are a fucking idiot.

gghandkthxbai

Re:The Money Quote

[samriel]

I can't install rockbox on a newer ipod because they decided to encrypt the firmware.

I can't use linux to sync newer ipods because they decided to increase the itunes database.

So... Apple won't let you install a third-party program... on their proprietary device. Big whoop. When you bought something that was locked down, and YOU KNEW IT, you lost the right to complain about Apple protecting any rights they may have tied up in the iPod OS / hardware.

The syncing on linux point is moot, because even if you can't do it right now, you WILL be able to shortly. Thank OSS.

Re:The Money Quote

[clarkn0va]

"DRM" only kick in...with copy-protection bits... Vista is in some tests...slower than XP... It's a phenomenon known as "more code".

Are you serious? "DRM doesn't make Vista slower. Extra code makes Vista slower."

News Flash: It's an operating system. Its only job is to run other programs as securely, stably, and quickly as possible. Do you think anybody cares why it's slower? The shills keep screaming, "It's not the DRM! It's not the DRM!" Who cares? Who cares?! Vista is slower. It's not better, just slower. No, I can't justify anybody's claims that DRM is the cause of the slowness. Let MS justify to me the cause of the slowness, and let there logic go just one step beyond "Hey, it's for sure not the DRM, because the DRM never runs".

I'm not saying that your argument is full of crap, I'm just saying that it's just a bunch of made up stuff.

Re:The Money Quote

[Anonymous Coward]

Not the Auckland guy though, his claims were debunked rather thoroughly a long time ago.

Where was this debunked? Linky?

Re:The Money Quote

[setagllib]

I am very confused as to why this should apply to something like e.g. a C compiler. Why would anything but a media decoder/player/encoder require media DRM? Last I checked C compilers don't require kernel DRM support to detect copyright violations in source code. Although looking at how big and slow Visual Studio has gotten over time, I wouldn't be surprised.

Re:The Money Quote

[Anonymous Coward]

I disagree. I have been using XP64 on my laptop for about a year and a half now, and it is actually still running fine (I have not reformatted once in this time!). I have had better luck with XP64 than with any other Microsoft OS since 98SE. In fact, my current XP64 install gets used more often than the Kubuntu Hardy install, simply because it seems to be more reliable....

Re:The Money Quote

[setagllib]

Unlike Windows, if you install a very lean Linux distribution, even one with up-to-date package versions, it will be absurdly fast as you'd expect from modern hardware. Just because Ubuntu is being burdened doesn't mean the FOSS landscape itself is.

The algorithms and data structures in almost all open source applications have either stayed the same over the years, or gotten better, with the notable exception of some programs like GCC which have used the increase in system resources to advance compiled code optimisation rather than compile-time performance.

This whole "of course newer is slower" thing is just Microsoft brain damage. Apple is another company which regularly improves performance and scalability in its software products, even with DRM problems similar to Vista.

Did you know that by now hundreds/thousands of Windows *system* *calls* have built-in backwards compatibility checks to support programs whose source code is not available for maintenance? You're paying a performance penalty every time you make a system call, with no option to turn it off, just because someone somewhere might want to play The Sims. Open source solves this problem by fixing the program, rather than hacking every layer of the OS to support old bugs. You can't spell "backwards compatibility" without "backward".

Re:The Money Quote

[setagllib]

Whether or not all of the claims in Guttman's article are true (and I agree that a few are obviously based on miscommunication in Microsoft's own documentation), it is clearly evident that Vista is a lot more heavyweight than XP without really offering anything. Now either a large chunk of that is DRM, or a small chunk is DRM and the rest is sheer unmitigated engineering failure. Either way it's bad. Whatever they're doing to fix Windows 7 is very welcomed and it looks like they've learned their lesson, but we can't claim Vista doesn't suck just because some of the reasons it sucks aren't completely valid, because there are plenty of other reasons it does still suck.

Re:The Money Quote

[oddfox]

None of it is DRM, did you not even bother to notice that the protected media path is not even being enabled/requested by any content yet because Hollywood hasn't decided to start the push yet? Playing the DRM card is nonsensical and completely irrelevant to the issue of Vista performance woes.

The biggest problem with Windows Vista was the changes to how things like file copy progress is indicated as compared to previous Windows releases and the complete lack of readiness on the part of hardware vendors (Which can largely be attributed to them simply being incredibly lazy, they had plenty of time to write proper drivers). Vista reached parity for XP in most if not all desktop tasks a long time ago, as well as gaming performance. Does it use more resources? Sure, there will be some additional CPU cycles being chewed up because the OS simply has more features and capabilities. Is this noticeable on recommended or better hardware? Definitely not.

Note that I specifically do not mention workloads like the ones described in this article. Environments like that are probably better left to XP unless they need to migrate, and you can (and plenty of people do) say the same thing about moving to Linux 2.6 from 2.4. Different versions have different strengths and weaknesses, but Windows 7 does seem to do a lot of fixing (primarily focusing on feeling faster, which was a big issue for Vista in the early days especially. It wasn't exactly slow, it just didn't feel as snappy. This has been, at least in my experiences, completely resolved).

P.S. -- Please stop parroting the line that there is nothing new in Vista compared to XP. The list of improvements is very long, and the list of improvements only gets longer once you look at Windows 7.

Re:The Money Quote

[Krneki]

Don't use the word security and windows in the same sentence please.

Re:The Money Quote

[beav007]

I may as well come out and say Ubuntu is so stupid, I could run [insert random distro] on my old 486 faster than Ubuntu on my modern hardware! Or whatever. The general idea is there.

Nearly, but not quite. I can easily run the current Ubuntu release on a P4 2.4, with 512MB of RAM, and a GeForce2 MX440, and have a wide selection of Compiz 3D effects. Try putting the current Windows release on a machine with that spec, let alone turn on 3D effects.

Why should "more resources required" be equated with "progress"? The short answer is that it shouldn't be.

Re:The Money Quote

[tixxit]

Well, no. If you don't complain, Apple will keep making the same crap. You think they dropped DRM on iTunes because no one complained?

Re:The Money Quote

[Anonymous Coward]

It's not *just* that /. is hostile to MS...

They'd never tell the truth if it was DRM because the customers would demand they remove it. They'd make up some excuse about driver complexity, or malware avoidance.

As long as Microsoft gets paid more to provide you to the content providers than to provide an OS to you they're going to keep serving the content providers. Their primary concern is keeping your content safe from you, not you safe from viruses. (Why would they care, they disclaim all responsibility for any failures, known or otherwise, etc.)

Re:The Money Quote

[Anonymous Coward]

Did you know that by now hundreds/thousands of Windows *system* *calls* have built-in backwards compatibility checks to support programs whose source code is not available for maintenance? You're paying a performance penalty every time you make a system call, with no option to turn it off, just because someone somewhere might want to play The Sims. Open source solves this problem by fixing the program, rather than hacking every layer of the OS to support old bugs. You can't spell "backwards compatibility" without "backward".

Except that you're wrong. The newer versions of Windows have a shimming engine which handles (almost) all the backwards compatibility. The shims are applied when a PE is loaded, so you pay a constant cost, not a cost per syscall as you seem to imply.

Re:The Money Quote

[BikeHelmet]

I'm so tired of reading the "XP (read: an operating system that came out many years ago) is faster on current hardware than Vista/Windows 7!"

XP SP3 got an updated kernel with more performance enhancements. Can't fault it for being faster, if Microsoft keeps making it faster.

Re:The Money Quote

[benwaggoner]

Read Peter Gutmann's excellent article here:
http://www.cs.auckland.ac.nz/~pgut001/pubs/vista_cost.html

Why are we still talking about this? Gutmann had never run Vista when he wrote the article, and stopped updating it once Vista was in the market and actually testing it was possible.

He makes a ton of testable hypothoses in the article. And I don't see a one that hasn't been disproven.

It's simply not an article about Vista. It's an article describing his fantasy of how bad Vista could have been.

Re:The Money Quote

[Toreo asesino]

The best thing about you "Linux shills" is that you make outrageous claims about Windows while in the same breath letting it known publicly you've never touched it with a 10-foot pole.

And I include Peter Gutmann in that bracket too; find me a single example where one of his claims has been substantiated with actual hands-on testing.

It's awesome; kinda like you build up an almost convincing argument, only to smash it down again in the next paragraph.

Re:The Money Quote

[quadrox]

That list shows a whole bunch of relatively trivial user interface changes, many of which could easily be achieved by third party add-ons for XP already e.g. launchy instead of new start menu).

Many of the changes are just arbitrary, and many are completely irrelevant to me - new media player (don't use it) etc... They complete whacked up the configuration part (LAN/IP settings), at least before SP1. Haven't tried it since.

At a quick glance I can find no major "killer" feature - just a bunch of minor changes. Out of these:
  - 25% are nice and useful
  - 25% I hate
  - 25% Are complete useless to me (new fonts, media player, language support etc...)
  - 25% are arbitrary interface changes

Wow, how awesome. Coupled with worse performance than XP, I think it is fair to say that, for me, Vista blows.

Re:The Money Quote

[oddfox]

That list shows a whole bunch of relatively trivial user interface changes, many of which could easily be achieved by third party add-ons for XP already e.g. launchy instead of new start menu).

Maybe people like having the stuff built into the OS instead of going out and collecting a bunch of third party applications to provide basic functionality. On the topic of launchy, I found it to be completely useless and no substitute for the start menu, and guess what, a lot of people feel that way too. You know, a lot of people don't even like Firefox! I'm not one of those people though, it's my favorite browser, but I digress...

Many of the changes are just arbitrary, and many are completely irrelevant to me - new media player (don't use it) etc... They complete whacked up the configuration part (LAN/IP settings), at least before SP1. Haven't tried it since.

And this is where we get to some real beef of your post, which proves that you have no clue what you're talking about. You admit that you haven't tried post-SP1, and I'm willing to bet your pre-SP1 experiences lasted about a day or two. That's how things seem to go with Vista bashers. The changes are not just arbitrary, though I will grant that not all of them are going to be relevant to you. When was the last time you saw a new Linux kernel release, or Ubuntu/Fedora/Debian release, where every single change was applicable to you and entirely beneficial? The answer, none. I find that the figure of 25% which you pulled out of your ass is about 24% higher than the amount of useful stuff for me when it comes to new Linux distro or kernel releases (Which is, by the way, a completely irrelevant metric to be using because I am not the center of the universe). Does that mean that Linux distros are just throwing on a bunch of fluff because it's not always stuff that is directly applicable to me and my usage scenarios? Not in the least.

The new media player was a welcome addition for the people who actually enjoy using it, and the people who have to use it from time to time. I know this might be hard for you to understand, but diff'rent strokes for diff'rent folks. One of my old friends would insist on WMP because of his multimedia keys, among other things. Other friends just plain like it. You can't convert everyone to software that you personally feel is superior (I always push VLC). The TCP/IP configuration, I have no idea what the hell you are talking about because undearneath all of the new stuff, behind the new Networking Center, it's got the same goddamn configuration dialogs that have been here since 2k/XP. Boo hoo you might have to dig one level deeper to get to something. Every Average Joe desktop user I come across likes the way the Networking Center presents information instead of just having Interface 1 Interface 2 Wireless 1, stuff like that. It's more accessible and it gives more information on the surface, with the same amount of depth underneath.

At a quick glance I can find no major "killer" feature - just a bunch of minor changes. Out of these: - 25% are nice and useful - 25% I hate - 25% Are complete useless to me (new fonts, media player, language support etc...) - 25% are arbitrary interface changes

Are you so dense that you can't understand that stuff like language support and an enhanced user interface are things that most users appreciate? Language support especially because uhhh hey guess what, lots of people like to use their computer in their own language/locale. Localization progress is touted by every software project including Windows because it's important. If you really think these are arbitrary user interface changes then what it really boils down to is how resistant you are to change your own computing habits, even if those changes would ultimately result in increased workflow and production. When you stop resisting these changes and start learning their advantages, the reas

Re:The Money Quote

[aliquis]

To what extent does this affect OS X?

Re:The Money Quote

[aliquis]

Ok, am I free of this in OS X?

It would be easier to understand if I understood WHY and eventually found a source telling me how.

But well, I can't understand why one would want to encrypt anything. Encrypting the DRM:ed content seems good enough. Or well, not doing that would be ok to :D

Re:The Money Quote

[Anonymous Coward]

Learn to moderate faggots.

http://en.wikipedia.org/wiki/Troll_(Internet)

Re:Is the moon haunted?

[oldspewey]

The boys celebrate their victory back home; meanwhile, on the moon, the asphyxiated whale lies dead. The end credits roll over this shot in silence.

Linux supports SMP out of the box

[Anonymous Coward]

It's not news but then nor is the article.

Re:Linux supports SMP out of the box

[Ender Wiggin 77]

Out of the box?? I use Ubuntu (Hardy) on a 3Ghz Quad-core and had big performance issues when moderate amount of IO was happening (eg. copy some files while using OpenOffice or Pidgin or FF.

I got things to work better by tweaking the thread scheduler to deadline, tweak 'swappiness' and some others I don't recall. Took days of research.

It still has occasionally Gnome UI lockups but it's usable now. I didn't treak XP at all to get concurrent processes without GUI lockups.

I'm sticking with Linux for a number of reasons, but performance on my quads is not one of them.

Not to worry ...

[jc42]

The software developers will quickly undo all the speed advances that should result from multi-core CPUs. Software has a much shorter development time than hardware, so all the advantage in this contest is with the software.

How about 32 bit XP?

[Anonymous Coward]

It's nice to have my beliefs vindicated by someone with the time (and expertise?) to perform the tests, but how does the 32 bit version of XP compare? 32 bit XP is ubiquitous. 64 bit, not so much.

Sheesh

[moniker127]

Its funny how if microsoft releases an OS like vista- people bitch about how different it is from XP, and if they release an OS like windows 7- people bitch about how its the same as vista. Personally- I care more about the great new interface in windows 7 than shaving a split second off the time it takes to compile something. Sure, for things like servers, performance is what counts, but neither windows 7 nor windows vista are operating systems intended to run as servers. They're intended to be networked business workstations, or unnetworked home computers.

Re:Sheesh

[Dog-Cow]

"...or unnetworked home computers"

And this is what I hate most about Vista. I would have thought that by now Microsoft would realize that people are no longer "unnetworked", even at home.

Why do Vista Home versions leave out basics such as telnet?! I don't use it for remote access, I use it for debugging network problems. Why can't Vista Home versions participate in a domain? Compared to XP Pro, Vista Home is completely crippled and totally useless. On Home Premium, non-admins can't even watch DVDs by default. In 2008 (now 2009)!

Performance is completely secondary when there's nothing to run anyway.

Re:Sheesh

[Anonymous Coward]

So just get vista ultimate, or better yet, download the currently free beta of windows 7 ultimate. Or, explore alternative nonspecific routes.

Re:Sheesh

[wbo]

I have never used Vista Home Basic but I know for a fact that Vista Home Premium does indeed include a telnet client. It is not installed by default but it can be installed of of the installation DVD by selecting it in the Turn Windows Features on or off panel.

Vista Home Premium certainly does not require the user to have administrative privileges to watch a DVD (or any other video for that matter.) You were probably using a player that was written with the (bad) assumption that the user would have administrative rights. Older versions of PowerDVD and WinDVD are especially bad about this. Try using something like VLC or Windows Media Player instead.

It is true that Vista Home Basic and Home Premium cannot join a domain but how many home users actually need to have their own personal systems joined to a corporate domain? Especially since systems can still access some domain resources even if they aren't joined to a domain as long as proper credentials are provided. If you really need to be able to join a system to a domain then you should consider using Vista Business or if you need to join a domain and Windows Media Center then perhaps Vista Ultimate.

Re:Sheesh

[Anonymous Coward]

Its funny how if microsoft releases an OS like vista- people bitch about how different it is from XP, and if they release an OS like windows 7- people bitch about how its the same as vista.

Um... that makes perfect sense to me. People bitch about how much worse and different Vista is to XP. Now we get Win7, which is roughly the same as Vista. So, it's logical to assume Win7 is ALSO worse than XP, and thus people have every right to bitch about it.

Or in other words...

XP == tolerable
Vista < XP
Vista == not-tolerable
bitch if not-tolerable
Win7 == Vista

Therefore...

Win7 < XP
Win7 == not-tolerable
bitch if not-tolerable

What part of that logic seems "funny" to you?

Re:Sheesh

[dragonjujotu]

On that note, why should a business be required to fork an additional $100+/copy to get such functionality. XP Pro wasn't nearly as expensive for what it provided?

Re:Sheesh

[man_of_mr_e]

All versions of Vista have a telnet client. It's just not installed by default, you have to go into programs and settings and then windows components and install the client, no disk needed.

Better than Vista, still worse than XP

[Animats]

First, go to the real story, bypassing an intermediate blog and two interstitial ads.

Second, the article says the performance of the newer OSs is worse than XP. "In fact, during extensive multiprocess benchmark testing, Windows 7 essentially mirrored Vista in almost every scenario. Database tasks? Roughly 118 percent slower than XP on dual-core (Vista was 92 percent slower) and 19 percent slower than XP on quad-core (identical to Vista). Workflow? A respectable 38 percent slower than XP on dual-core (Vista was 98 percent slower) and 59 percent slower on quad-core (Vista was 66 percent slower)."

Third, there are no tables or graphs anywhere in these articles, and very few numbers. As a benchmarking article, this is awful.

Re:Better than Vista, still worse than XP

[zuperduperman]

Completely agree. As much as I believe Vista is slower than XP for a whole range of scenarios, I'm having a heap of trouble believing the numbers in this article.

Vista and 7 are 118% slower than XP on database tasks???? WTF? What does that even mean? I strongly suspect this reviewer has something seriously screwed up with their Vista setup, like missing drivers or some other problem. I don't know how you can possibly calculate a number like '118%', but I can't think of any way Vista is that much slower unless it's running on 1GB RAM, or windows defender is running on max settings, the SATA drivers are not installed, or some other dumb-ass stoopid thing that you would never do on a server OS.

Infoworld report is fluff

[Anonymous Coward]

The Infoworld report basically says, Windows 7 is (much) slower than XP, but it will get faster when you have 24 or more cores. AND... Microsoft will make it faster, why, because they said so.

Really. Shouldn't that be in an op-ed piece. A report shouldn't speculate and frankly any speculation about Microsoft promises about better or faster... Well Microsoft's *actions* speak far louder than Infoworld's words.

I wonder ...

[lwriemen]

... if OS/2 on a single processor still outperforms Windows NT^H^HXP on multiple processors? ;-)

Where are the server OS's?

[adonoman]

I'd like to see how Server 2003 and 2008 stand up - since longer, less interactive processing is what they are tuned for. XP, Vista and 7 are tuned for quick user response.

Why not tweak the XP kernel?

[wonkavader]

It's great that MS was able to tune the Vista kernel to avoid locks which reduce performance on multiple cores, but I'd rather see the same work done for XP, giving us something MUCH faster on a high number of cores, rather than a pig we can compensate for with many cores.

More great mathematics

[Lonewolf666]

From page 2 of TFA:

In terms of raw application throughput, Windows XP clearly is still king of the hill. However, despite its current edge on dual-core and quad-core systems, Microsoft's 8-year-old OS is beginning to show its age. For example, when you contrast the dual- and quad-core transaction times for the ADO (database) and MAPI (workflow) workloads, you see that scalability -- in terms of a percentage improvement from dual-core to quad-core -- is capped at 265 percent for the database tasks and 32 percent for the messaging workflow tasks. While excellent by legacy Windows NT standards, these improvements pale next to the 571 percent boost witnessed for the same SQL-driven database workload under Windows 7, or the 58 percent improvement for the MAPI message store workflow task under Windows Vista.

(emphasis mine)
So we are supposed to believe that the database test on Windows 7 runs 571 percent faster on a quad-core compared to a dual core?
That would be a factor of 6.71, or in terms of performance per core, a factor of 3.355. In other words, the quad core would do 3.355 times more work per core than the dual core. That sounds not very believable, considering similar tests the German C't magazine has done in the past (for Linux and Windows 2000). In those tests, both OS scaled at best linear with the number of CPUs, so the "performance boost" from going from dual to quad core was at best 100% (in most tests more like 80%).

Maybe I'm misunderstanding what Randall C. Kennedy wanted to say. Here it would have helped if he posted his raw data and test configuration, as most reputable testers do. But as he only posted a few end results, I can only say that his numbers seem bogus. I rated the Infoworld article with 1 of 5 points.

Re:More great mathematics

[Calinous]

There is a possibility - that the dual core is forced to switch threads much more often than the quad core. However, while this kind of workloads definitely exist, the chances of stumbling upon it are small to say at least

NUMA

[jpmorgan]

As a HPC developer, there's a few areas where XP falls down. With the release of the new Core i7 line from Intel, the end of the FSB is in sight. Both Intel and AMD now use a ccNUMA memory architecture, which has tremendous implications on software design. In short, if your software isn't aware of the system's memory topology, you're going to end up with most of your memory traffic going over the processor interconnects and that's a substantial performance hit over going directly to memory (2-4 times slower).

XP's NUMA support is very weak. Sometimes the easiest solution is to write your own allocator (and preallocate huge chunks of ram).

And before somebody comes along and says 'no real HPC is done in Windows!' there are a lot of old, crusty engineering software packages that everybody is scared of porting.

Re:NUMA

[Anonymous Coward]

Second the parent, we have several number crunching engineering programs that could always stand to run quicker (often take several hours/run). If anyone has real inside data on these performance issues relative to different versions of Windows it would be appreciated.

Re:NUMA

[Lonewolf666]

Interesting point, but the Infoworld article really should have tested this rather than speculating about the scalability.

As the "biggest" existing system you can test on XP (Pro), an AMD Opteron workstation with two quad cores would make sense. That means eight cores and NUMA becomes a factor. With that system, XP vs. Vista vs. Windows 7 results would actually tell us something about scalability.

What about multi-function?

[CannonballHead]

Nobody is going to argue that if you run one single application (a database something), a "small" OS will work better. There are Linux versions that are specifically geared towards doing that sort of thing, right? Ubuntu is probably slower at something than [insert other dist].

The real question is, though... what about normal usage? Unfortunately, that's hard to measure... but how does Vista/Windows 7 affect normal user productivity and speed as opposed to simple benchmarks designed to test out efficiency at doing ONE thing?

If Vista and Windows 7 were designed to have a lot of background processes to help the user do this or that, then why not test that, too? XP wasn't designed that way, apparently, while Windows Vista/7 are more designed that way. So give it a level playing field and test what it was designed to do.

I don't have an answer of whether or not Vista/Win7 are slower or faster when doing other things (like, say, searching for a file because you can't remember where you put it, running multiple applications, using something DRM enabled, or whatever), but it'd be interesting to try to test it rather than a generic "XP runs a single application faster than Vista because Vista has more stuff running in the background." It'd be interesting to try to physically load the system with lots of applications and see which is better then.

Re:What about multi-function?

[b4dc0d3r]

Under normal usage with a single application, multiple threads still play a big part. When you hit WIN+R to open the Run dialog, and a number of other places, Explorer (the shell functions of Explorer anyway) starts a new thread to run the dialog, so that the shell doesn't stop responding. Threading 101 I know.

With Windows XP at least, it uses QueueUserWorkItem to start the thread, instead of a CreateThread/Ex call. QueueUserWorkItem uses thread pools, so I often get stuck with my work notebook (not my home one) where I hit WIN+R and nothing happens, hit it again 30 seconds later, and again, and finally 3 windows show up at the same time. I assume it's because the thread pool is full, otherwise my post doesn't make sense. Anyway, these are the types of user productivity things that probably will seem "snappier" due to multithreading, since it can get this type of thread out of the way quickly.

There are a lot of single-use threads created, such as the file Open/Save windows. Open Notepad and check the number of threads open - it should be 1. Do file/Save as, and Process Explorer now shows 5 threads. UltraEdit went from 3 to 6 using File/Open. that's all in the common control library, not the application. (These might be pooled, might not, I haven't looked at it).

My point is, the UI itself can seem snappier if these utility threads are scheduled on different cores, as long as they don't block of course. they are not always running at the same time, but the moment they have to you'll notice.

just test it with an avi file

[Anonymous Coward]

yes, it's very easy to test it, get an avi file, lets say 100MB play it on XP, measure CPU utilization, now get the same file and do the same test on vista, compare results !!! and now who is the whore? test has to be performed on identical hardware ;)

I completely disagree

[JamesRose]

We've got all this dual core, quad core technology and at the moment almost no software companies are actually coding their programs to use it! It's rediculous and windows is absolutely right to push ahead and optomize for multiple cores- because as the base of most machine's it is the most important part of the system that needs upgrading. We can only hope this actually pushes some other software companies to start taking advantage of all this untapped power. If windows weren't optomizing for quad core and up they would be making tehmselves seriously vulnerable and would be actively slowing the adoption of multi core software systems.

Re:I completely disagree

[jedidiah]

Oh pulleeze...

One of the "benchmarks" here was a database workload. Databases have
been exploiting multiple CPUs since before the current iteration of
Windows (NT) even existed. This is sort of stuff is old news.

NT4 (designed by the VMS lead) should be scalable for that kind of
task, nevermind XP.

Oops...there is some info on config

[Lonewolf666]

On rereading, I found a link ("How I tested") that gives at least an overview of the configuration. For the hardware:

I repeated this scenario across all three Windows operating systems installed in a triple-boot configuration on both dual-core and quad-core test beds (a Dell OptiPlex 745 with Core 2 Duo E6700, 4GB RAM, and 10K RPM SATA disk and an HP EliteBook 8730w with Core 2 Extreme Q9300, 8GB RAM, and 7200 RPM SATA disk, respectively).

So on one hand, I have to apologize for dissing Mr. Kennedy on lack of transparency.

On the other hand, he obviously used two different systems with different amounts of RAM which can introduce new errors. For instance, lets assume the working set as defined on Wikipedia (URL:http://en.wikipedia.org/wiki/Working_set>) has a size of 6 GByte. Then the Dell OptiPlex 745 with only 4GB RAM will have to keep reloading from disk, while the HP EliteBook may be able to run entirely from cache in the second and any further pass. I consider that a bad error inmethodology.

..info

[xenolion]

ok that's good XP is faster than Vista or Win7 on dual cores....why do i care... hm looking at my screen right now Im running more than one app none of them are dual core aware. Only the OS is. Does the average Joe know how to set a program to the second core or do they just leave it to the os to figure out? So here is what i want to know. Windows is able to see the second core so does it take the lower used item and send them over to it while they sleep? Like the services it loads or does it just stay on the first core? If Windows could move things over to the second core by itself for sleeping apps it may become faster for the standard apps that dont know about the second core.

Microsoft have a firm grasp of multicore tuning

[Anonymous Coward]

Sure. Can we get a honest comparison here, instead of this incestuous old bear vs. dead turkey fest? Find a couple of boxes, then let some micros~1 guys tune images for each, some linux guys tune images for each, some solaris guys tune images for each, throw in a couple BSDs (FreeBSD, DragonflyBSD, and heck, see how well NetBSD is doing too), maybe add minix and qnx for kicks, and have an independent panel run each image through a preset series of tests with automated data gathering. Systemic bias, people. It's not hard to eliminate it, just don't pull punches.

Its even more so what than that...

[Giant Electronic Bra]

Since when did you run your high throughput transaction processing system on a desktop OS? These numbers are basically meaningless in the sense that they don't reflect anything anyone would actually do with the software that was tested.

Now, a comparison between 2000 Server, 2003, and 2008 would have been more useful.

As you say, I suppose this whole thing demonstrates that MS can make progress optimizing an SMP kernel. Sure would be pretty surprising if they couldn't!

Maybe someone will make some comparisons vs some Linux kernel builds and some OpenSolaris builds. That would be just as interesting, since it is a bit less clear whether or not those teams have or are able to make equivalent or better optimizations.

DRM Check

[Gonoff]

How does the system 'know' when to start running the DRM? There must be something running at all times "just in case" the paying customer decides to excersise their right to play their own stuff.

Whether it is a service, thread or whatever, it doesn't matter. Some system resources have to be used in advance. That can only drop the performance.

Re:DRM Check

[TheThiefMaster]

How about "when the user presses the play button"?

I'd expect it to be called from the codec's initialize function myself.

Re:DRM Check

[drsmithy]

How does the system 'know' when to start running the DRM?

The application goes "Hey ! Windows ! I need a protected path before I can play this media."

There must be something running at all times "just in case" the paying customer decides to excersise their right to play their own stuff.

No, there does not.

It is not the OS's job to check whether or not a given file (more accurately, byte stream) is DRM-encumbered, nor does it make any attempt to do so. It is only the OS's job to provide DRM-capable output (and ensure it remains DRM-encumbered) when an application asks for it, which is what it does.

In short: If you aren't playing DRM-encumbered content, the DRM does NOTHING.

Re:DRM Check

[sexconker]

I don't know the details of Vista/7's implementations, but come on - just use your head.

If the file header has the broadcast flag, or otherwise indicates the file is DRM crippled, the DRM checks begin.

If no, then DRM checks aren't going to run.

It's about the same level as:

OH NO. My PC is automatically adjusting my clock for daylight saving time. MY FUCKING CLOCK CYCLES ARE BEING STOLEN!

Re:DRM Check

[daveime]

How does it know to open Excel when I double click that .xls file.
How does it know to open Word when I double click that .doc file.
How does it know to open Access when I double click that .mdb file.

So THAT'S why Vista is so slow ... every application on your system is preloaded and running all the time, just in case a user wants to DO SOMETHING.

</sarcasm>

Re:DRM Check

[Anonymous Coward]

The application goes "Hey ! Windows ! I need a protected path before I can play this media."

So network performance wasn't degraded severely when audio was played black like this, right?

"Please note that some of what we are seeing is expected behavior, and some of it is not. In certain circumstances Windows Vista will trade off network performance in order to improve multimedia playback. This is by design"

Re:DRM Check

[drsmithy]

So network performance wasn't degraded severely when audio was played black like this [zdnet.com], right?

Not by DRM, it wasn't.

Re:DRM Check

[makomk]

I'd expect it to be called from the codec's initialize function myself.

Yeah, but the trouble is that if you do that, there are all sorts of interesting ways the user can modify the state of the system beforehand, and it's basically impossible to check them all. So, for example, Vista continously runs checks to make sure that no unauthorised changes have been made to the kernel, and I assume there's an equivalent functionality making sure that nothing (not even supposedly trusted processes) can submit commands to the graphics card that'd put it in a state where protected video could be snooped.

Re:DRM Check

[Anonymous Coward]

That's not your WMP process requesting a DRM-encumbered path, it's two high-priority drivers fighting against each other and Microsoft decided to code the network driver to let the sound drivers get their time. DRM has nothing to do with it because he wasn't playing an encrypted file in a process requesting protected video path and other stupid things.

Re:DRM Check

[makomk]

If no, then DRM checks aren't going to run.

Well, the DRM checks aren't. The system integrity checks to prevent users bypassing the DRM, OTOH, still have to. For example, Windows Vista has code running to detect unauthorised changes to the kernel and reboot, even when no DRMed video is playing (officially to prevent developers from doing things that could affect system stability). I suspect there's overhead in the video card driver model too, to prevent stuff like a hacker setting up the card state so they have read access to the framebuffer via something apparently innocent. (It's much easier to put code in place to prevent hackers from changing the system state in a way that allows DRM to be bypassed, than it is to detect it reliably afterwards.)

Re:DRM Check

[sexconker]

XP has a little thing called the system file checker.

You know, checking for unauthorized changes to system files and replacing them automatically.

Re:DRM Check

[im_thatoneguy]

Kernel and Driver protection?! That sounds terrible!

Re:DRM Check

[TheThiefMaster]

Well IIRC it requires a "signed" graphics card driver to enable HDCP playback. You also cannot snoop another process's graphics surfaces without the surface having been opened in shared mode by the first process (and even that is new in DX10), so there is no possibility of a program snooping a video being played by another program.

For a single program trying to trick the DRM into playing to a readable memory surface, the DRM'd codec would be able to detect a readable surface and would refuse to play to it. I wouldn't be surprised if it refused to play to a program's in-memory surface full-stop in fact, and insist on rendering to its own surface and blitting it to the screen itself.

Trust me, there is no reason for anything to do with a DRM'd video to run while the video isn't being played (which would have to be done via the DRM system, unless it had been completely cracked). Any DRM-related services "running" would in fact be just sitting there in a wait state (code not even running) until they were called on.

The only Windows built-in "DRM" that is running all the time is the system files protection, and that is only running all the time because it protects the OS, which runs all the time.

Re:DRM Check

[makomk]

Well IIRC it requires a "signed" graphics card driver to enable HDCP playback. You also cannot snoop another process's graphics surfaces without the surface having been opened in shared mode by the first process (and even that is new in DX10), so there is no possibility of a program snooping a video being played by another program.

You're assuming that the hacker would use the DirectX API. Remember that, in Windows Vista, a large chunk of the graphics driver is in userspace, which means userspace can submit commands to the card, and this needs to be secured somehow. (Interestingly, it looks like some of the cost of this is actually borne by the graphics hardware, in terms of implementing page tables and memory protection.)

For a single program trying to trick the DRM into playing to a readable memory surface, the DRM'd codec would be able to detect a readable surface and would refuse to play to it. I wouldn't be surprised if it refused to play to a program's in-memory surface full-stop in fact, and insist on rendering to its own surface and blitting it to the screen itself.

Not convinced this is true if you bypass the API. Microsoft may have a way of detecting this at the hardware level, but it seems a bit like overkill. There are plenty of low-level ways to do it, too, even if the API doesn't expose them.

Trust me, there is no reason for anything to do with a DRM'd video to run while the video isn't being played (which would have to be done via the DRM system, unless it had been completely cracked). Any DRM-related services "running" would in fact be just sitting there in a wait state (code not even running) until they were called on.

You'd think so, but effective DRM has to be designed into the system at every level - if it's just bolted on, it's too easy to disable or bypass. Plus, it's safer to detect attacks on the security model when they occur than leaving it until playback is started - that way, you can trigger on any stage of the exploit process, not just the resident part.

The only Windows built-in "DRM" that is running all the time is the system files protection, and that is only running all the time because it protects the OS, which runs all the time.

You're forgetting PatchGuard - highly polymorphic code, running all the time, intended to stop people patching the Vista kernel. (By now, I expect they've inserted calls to PatchGuard checks all over the place - there's a bit of a cat-and-mouse game with hackers figuring out how to disable it.)

Re:DRM Check

[TheThiefMaster]

I think you'd find if you looked that the user-space parts of any driver can't communicate with hardware directly. They can be given a DMA mapping by the system-level parts of the driver, for reading/writing (normally only one at a time) to the hardware's memory directly, and can call the kernel-level part of the driver for it to do stuff. The kernel-level part would be secured against processes trying to access each-other's graphics-card data.

Wiki says that patchguard is only in the x64 versions of Windows, and actually isn't new with Vista, it's in Windows XP and Windows Server 2003 x64 versions too. Considering that MS said that quite a few "Windows" crashes were caused by kernel code "patched" by drivers (especially some antivirus and firewall programs), I'm not surprised that they discourage it.

Though I have just found out that patchguard doesn't stop drivers patching each other. However, the x64 version of Vista requires drivers to be signed by Microsoft, so you couldn't use one driver to patch the graphics driver in an attempt to intercept the rendered video on x64, because you'd never get a driver that did this signed by MS. I don't think you could patch the user-space portion of a driver from your code, unless you were in system-debugger mode, because Windows just wouldn't give you the process handle of it, so you wouldn't be able to write to its address-space. I'm assuming you know enough about "Virtual Memory" to know that processes can't just write to each-other's memory without the kernel's permission.

On the other hand Vista 32 seems to be wide open to a hack that used a dodgy driver to patch the graphics driver in order to intercept the rendering commands used to display the protected video.
But without patchguard running, there is nothing to cause the "slowdown" people attribute to DRM in Vista. Yet they still claim it.

But when it all boils down at the end, it's easier just to use a badly-made blu-ray/hddvd player which has the video flowing over an unencrypted link between two chips, than to try to hack around Vista's HDCP support.

"Vista's new DRM" is talking about support for playing HDCP-protected video streams, and nothing more. Some people lump "patchguard" under "Vista DRM" too, but that's not in 32-bit Vista, and it's not DRM, it's protection of the kernel from malicious and stupid driver code.

This seems to be a reasonably good article on the subject, if you want further reading: http://blogs.zdnet.com/Bott/?p=299&tag=rbxccnbzd1

At work...

[CompMD]

I have a Core2 Duo machine running a basic configuration of XP. Its quite fast. The only time I've seen it get bogged down is when it has to pull calendar information from Exchange, and that's not the workstation's fault.

That having been said, I'm perfectly happy with my dual P2 running NT4 you insensitive clods!

This is a submarine article

[Anonymous Coward]

CmdrTaco should not have fallen for an article written by PR shills.

NUMA is old hat, unless you're in Redmond

[Gothmolly]

Unix kernel coders have written NUMA-aware stuff for years. When MS is late to the party, why not just say so? And if they're always late, why bother with them?

Oh boy!

[PingXao]

They've got a great story, you betcha! And it's only going to get better! Rah rah! Sis boom bah!

It's disgusting. I wanna puke.

HPC and time sharing - failure

[skandalfo]

At my work, we maintain several Windows clusters for financial derivatives valuation.

We can't really move all of them to Linux (no matter how much we would like to do it), because some of the calculations have been implemented using MS only technologies, like ActiveX (yes, you read that well) and .NET (the last time we checked it the Mono runtime was ~5-6 times slower than MS implementation of .NET for our code).

When we needed to upgrade the Windows clusters recently, we had to move from 2-cpu-1-core to 2-cpu-4-core machines, since it was what was being sold. What we've observed is that Windows (Server 2003) is unable to fairly share the CPU time when there are more active threads than available cores. We get a lot of variance on the overall calculation time when the clusters are very loaded because of this.

The same tests done on SLES-9 (yes, 9) based Linux clusters with similar hardware did not suffer from this problem. CPU time was divided equally among all threads. And we are using a 4-year old kernel, that doesn't even sport the newest completely-fair-scheduler.

Re:HPC and time sharing - failure

[ericlondaits]

ActiveX is an interation of the COM technology, which provides components at the system level. In that respect it's similar to Java Beans (AFAIK), OpenOffice's internal component architecture (forgot it's name), Firefox's internal component architecture (XPCOM), and others. ... Granted, it's almost a MS-only technology (because of lack of popular ports of the architecture for other OSs), but it's a good solid serious technology that got a bad name because of a general lack of understanding of what ActiveX means in the context of the browser.

Also, you don't implement "calculations" in ActiveX... it's just an architectural wrapper on standard objects or procedures... so any calculation-intentsive app should be easy to port to an alternate component or object architecture.

Windoze sucks...

[Anonymous Coward]

Multicore optimization will just help it suck much quicker...

COme on windows 7 is beta

[majortom1981]

Come on why does anyone take this article seriously? He tested an os that is in beta. Microsoft specifically stated that the beta was not performance tested and that wont be done till later around the rc stage. Come on this article should not be taken seriously at all. I thought people on slashdot would be more tech savy and know that you cant do any sort of performance testing on a beta especially when microsoft themselves stated they havent done any performance fixing on the beta.

Codec Not Installed

[HannethCom]

What I really loved was when my sound card drivers didn't have the latest DRM crap in them for Vista. I could play PCM WAV files fine, but when I tried to play a MP3 file in WMP it would say "Codec Not Installed".

It took me 2 hours, at the time, to find out that nothing was wrong with my installation, just that MP3 files go through the DRM layer and they wouldn't play because my sound drivers did not support the latest version of Vista's DRM yet.

Server kernel wins server benchmarks, news at 11

[Zzzoom]

They tested two desktop kernels against XP x64 and its Server 2003 kernel...doh!

Bullshit

[im_thatoneguy]

Complete and utter bullshit.

We're a VFX company. We work with all manner of multi-core applications. Cloth simulation, Global Illumination, Caustics, Optical Flow tracking, compositing etc etc.

Every single one of our computers are 64 bit. We have Windows XP x64 and we have Vista x64.

I'm looking at a chart right this very second of render times for our current job. 9 million polygons, 6GB of RAM usage, 100% CPU usage across all 4 cores. NO RENDER PERFORMANCE HIT. Render software scales better than just about anything else on earth. Each core renders its little slice of the scene and returns it to the application. There is no cross talk, it scales pretty much linearlly with very very little overhead. If anything is going to expose some sort of massive performance hit, it would be rendering.

If Vista x64 is running a DRM check on every ray casting function we would see it. If Vista was running 118% slower we would see it. We have identical machines running the identical piece of software and they're returning on average statistically identical results.

I've got millions of photons bouncing around a scene and supposedly each calculation is being 'taxed' by some DRM check? I don't see it.

They're all generating pixels, what could be more "DRM related" than reading footage, processing footage and creating new footage?

Maybe this test found some piece of software that doesn't run well on Vista. I can buy that argument. But Vista and Windows 7 are not substantially slower than XP at processing. In fact they seem to be no slower from my experience with a wide variety of extremely processor and memory intensive tasks.

Re:Bullshit

[sparcnut]

If your render jobs sit in userspace cranking away, doing very few syscalls, then the OS differences should not affect the numbers significantly.

Old Asto-turf

[omb]

I am getting increasingly annoyed, and bored, by the fact that everytime we have a M$ story here, especially with the Windows-7 run up we see the same band of M$ astroturfers generating noise here.

Character assassination, eg of Gutmann and Schneier and opinion/speculation is no substitute for clear numerate analysis and benchmarking.

Let me offer two opinions based on nearly 40 years of operating systems experience, starting with the EDSAC-II:

(a) No one whoc claims that DRM is only active for part of the time has never seen/understood the inside of a scheduler or device driver, at the very least the DRM system must protect itself.

(b) The memory bandwith considerations for multi-core are much more complicated, especially for HPC, than just NUMA, which itself is an old kludge mandated by earlier system designs. In a very real sense the NU.. is now always present, since caches are ubiquitous and mandatory and almost always layered and hardware managed. The is no particular benefit or reason to make the backing DRAM Non Uniform, quite the opposite!

Finally I remark that there are two very different situations depending on chip architecture eg Intel v AMD and the workload. With Intel, and the FSB, a limited bandwidth, to the NorthBridge is shared out between all the cores, which is why Intel is rapidly migrating away from the FSB architecture. By contrast, an 8 core AMD system, with two quad cores has twice the memory bandwidth (almost) as the single quad system (due to scheduling latency and interfearence) in the Hyperchannel

If your workload is essentially infinitely parallelisable then you can make your workload scale, slightly less, eg 0.8, with increasing cores _and_ by keeping idle time on all cores, your system will feel snappy and responsive eg for gaming and transaction processing.

If, for some logical or physical reasons, your problem has inherent limit on its parallelism then you have a much harder problem. Examples are the partial-differential equations of mathematical physics (Navier-Stokes, Heat, Elasticity) and directed stochastic processes use in asset pricing and (sensible) risk management things are much more complex and mostly depend on parallel algorithms and minimising latency. For much more detail see the Berkeley paper http://view.eecs.berkeley.edu/wiki/Main_Page [The Landscape of Parallel Computing Research: A View From Berkeley].

To cut to the chase M$ made a marketing choice, plumb DRM into the resource schedulers and IO system, even if hook based, as it should be, this must impact parallelism and introduce locking latency costs which must be paid all the time, and if done less that perfectly, will reduce scalability which will harm responsiveness.

So you pay so that M$ can cosy up to Hollywood, RIAA and MPAA, all of whom have problems with their business model. No amount of astroturf can put lipstick on this pig!

Re:Old Asto-turf

[man_of_mr_e]

Character assassination, eg of Gutmann and Schneier and opinion/speculation is no substitute for clear numerate analysis and benchmarking.

Gutmann's analysis has been debunked by numerous people, not to mention the fact that he never even performed a single bit of analysis of a real vista machine to make any of his claims.

Schneier, while a great cryptographer, is blasted because he accepted Gutmann's analysis without so much as a thought as to whether or not it might be valid. Real scientists prove each others work (or disprove it, no hard feelings). Schneier didn't do either of them, he just parroted it and lended it credibility by his name.