Researchers Sour on Vista Service Pack 1 Performance

Stony Stevenson passed us a link indicating that a group of researchers has described Microsoft's upcoming Windows Vista Service Pack 1 as basically a performance dud. Researchers from the Devil Mountain Software group is claiming that a series of in-house benchmark tests showed that users hoping to receive a speed boost from the update will be disappointed. "Devil Mountain ran its DMS Clarity Studio framework on a laptop Barth described as a "barn burner" -- dual-core processor, dedicated graphics, and either 1GB or 2GB of memory -- to compare performance of the SP1 release candidate that Microsoft released last week with the RTM version that hit general distribution last January. The Vista RTM was not updated with any of the bug fixes, patches or performance packs that Microsoft has pushed through Windows Update since the operating system's debut. 'One gigabyte, 2GB [of memory], it didn't make a difference,' said [CTO Craig] Barth. 'SP1 was never more than 1% or 2% faster.'"

Optimization

[ktappe]

50 million lines of code and they couldn't find anything that needed optimization?? Or were their priorities elsewhere? These days, optimization always seems to be relegated to "low man on the totem pole."

Re:Optimization

[arth1]

Most worthwhile optimisation is done by rethinking the design, and to a lesser degree hand-coding parts where you know the realities better than the compiler can guess, and just how to exploit that.
Neither is something Microsoft is likely to do -- the first costs too much (including accepting incompatibilities and devising workarounds for them), and the second requires ace programmers, not run-off-the-mill visual-anything. Changing a few compiler flags here and there, or re-compiling with a new compiler version is cheap, but usually won't have much noticeable effect. However, it's what you're most likely to see from huge corporations.

The sad thing is...

[pwnies]

...that a large amount of their userbase doesn't even know that there are alternatives. It's a shame really. Because I guarantee if Microsoft had less of a market share they would focus more on these details like optimization and straight up good code because if they didn't they wouldn't survive. Now it just seems they do only the amount of work required to keep the train rolling and their riders complacent. I'm in a workplace where 99% of the computers run Windows XP, and the sad thing is that it's a technology company that deals with security and networking. You'd expect that a large majority of them would have heard of linux or even unix for God's sake, but hardly any have. It's a Windows world and Microsoft knows it. They'll do the bare minimum amount of work possible.

Re:Optimization

[UncleTogie]

Does average joe care about optimizations? Probably not. Are they important? To people like you and I, sure, but not to average joe.

Yes, it DOES matter to Joe. Joe, however, won't call it "code optimization". Joe will simply say that "Vista runs slower than my XP did!" He doesn't care WHY it's so, but even Joe can tell the difference in speed.

We have a lot of Joes come through our shop. They notice.

Re:Are we shocked?

[Haeleth]

Windows Me was a pile of crap that crashed every five minutes. Vista is merely slightly slower than XP. I use it for games, since Wine/Cedega aren't quite there yet for the latest titles. It runs just fine, everything works just fine, everything is perfectly fast enough -- do I really care whether things are theoretically a few percent slower if I can't tell the difference without actually benchmarking? (Hint: I don't.)

I really don't see where all the Vista hate is coming from. I wouldn't want to use it day-to-day, but that's the same as any version of Windows.

Re:That's a release candidate

[mkraft]

A release candidate should be identical to the actual release; that's why it's called a "release candidate" and not a beta version. The only things that would be changed between the RC and the release are any major bugs such as crashes, exploits, etc. Any performance tweaks would have already been done by the time it hit release candidate status. Similarly any debugging code that would slow things down would have also been removed.

Re:Optimization

[sumdumass]

Well, seeing how this machine was so "hot" in the hardware section, it could be that the bottleneck wasn't in the OS at all. IT could be that it has cycles to spare but is waiting on the memory bus to see any increase in performance. They could have been maxing out everything that would have restricted the OS from performing and never saw the "issue" in the first place.

Of course there was/is an issue, Vista just seems slow. In the former example, they wouldn't have seen the issue because something else would be slowing it down. But on a lesser machine, I'm wondering if the optimizations would have a more dramatic effect. I mean a machine where the memory or processor is limited and the actual execution of the code was keeping it slow. Will it allow the code to be executed faster on a processor that is maxed out all the time?

What is not a performance dud today?

[3seas]

I have an old Dell Latitude xp450c that cost someone (not me) probably about $2500 in 1995 but today its not worth anything except to battery, memory and ac adaptor sellers who have more of these to sell, then there are such laptops existing.

This is a 50Mhz 486dx laptop with a 8megs of ram. What OS can I reasonable run on it besides DOS, baslinux (basic linux - damn small linux is to big). and some floppy based OSs like maybe if I can even QNX demo of i can even find it anymore? To bad I can't get AROS to run on it.

I also have an Amiga 4000 Toaster that runs at a warp engine speed of 28Mhz though I have more ram in it. and its still useful.

The point is, when it comes to OSs today the performance is pretty much a dud in a fair comparison to the better OSs of yesterday.

There has been a code bloat to use up increased speed, memory and storage in OSs today.

Today you can buy 1 gig thumb drives that could hold your whole system, personal files and duplicate backups of the same and still have plenty of room.

In fact, we should today have such sub-gig personal thumb drive based systems. Expecially considering what the more common applications are.

Performance sucks today, and its not just a windows bloatware matter.

   

Re:How to "speed up" Vista

[Drencrom]

It seems you have to do a lot of research to get vista working decently. I guess this proves that it is not yet ready for the desktop :)

Bias

[Nanite]

I'm sure the only thing tying you to Windows these days is your own aging skill-set. Let's face it, Windows has always been your bread-and-butter as a programmer right? Well one could see why you would feel slighted when others bash what you've spent a large amount of your life learning and suffering with. The cold truth is: The Windows skill-set is in danger if MS keeps dropping the ball. Every time MS drops a steaming pile of OS on the market, more people make the switch to Apple, or Linux, and your skill-set degrades just a notch. The thought of mass defections from Windows probably makes you wake up in a cold sweat at night. Well, I'm not going to sugar-coat it: Vista is turning many people elsewhere, and Apple is making all the right moves in the market right now to swiftly pick those disenfranchised folks up. It's only a matter of time before the market tips and non-windows machines are the minority in many areas. It may not be tomorrow, or even ten years from now, but I've lost all hope in MS pulling up from the tailspin they are in.

In closing, I think that there is no better time then RIGHT NOW to expand your skill-set to include Windows agnostic developing. Because I'm of the opinion that there is a huge shift happening in the market right now, just very slowly...

Re:Are we shocked?

[king-manic]

To be fair, my Dell Vostro 1000 came preloaded with Vista home basic, and it bluescreened after 30 minutes. I installed opensuse 10.3 shortly thereafter. Not that the Linux ATI X200 drivers are any better - I get X corruption all over the place and 1 month later I still can't get compiz working right.

And you haven't returned it?

Re:Are we shocked?

[Lachlan Hunt]

Although it certainly had it's problems, at least Win ME was usable. Vista gets in the way of absolutely everything! I have never been so irritated with an OS in under 5 minutes of use, until vista came along.

Using a friend's laptop running vista, logged in as an administrator, trying to copy harmless files from a public folder on my mac to the my documents folder on vista was forbidden. I had to copy to my Win XP machine first and then from there to Vista. Once tried to use ipconfig /release and /renew to fix a conflicting IP address, but it gave permission denied error! I had to explicitly select Run As Administrator from the context menu to get elevated permissions just to run ipconfig. Bloody oath! Also, the windows explorer UI is so bloody awful and unusable, it's not even funny.

Seriously, if my only choice was ME or Vista, I'd go back to ME any day. But luckily I can just stick with OS X Leopard and Win XP.

Re:Straw Man?

[QRDeNameland]

Actually, yes, I can. If you can't determine the actual truth value of an individual argument and instead have to broadly lump what could be a valid argument into the domain of the "straw people", then maybe you should, with all due respect, shut the fuck up.

Woo hoo

[JRHelgeson]

So my DRM is being upgraded? Should I be excited?
The worst thing Microsoft has ever done was put Mickey Mouse in charge of kernel development. Letting Hollywood dictate the kernel design will prove to be the undoing of the Windows platform.

Re:Are we shocked?

[syousef]

So what you're saying is that you don't care because it's not your primary OS. Those that do care may be thinking of it running as their primary OS. Heck they may be forced to do so at work in a couple of years. Their LIVING may depend on it.

I do use XP as my primary OS at home and at work and you bet I care. It ain't my spare car. It's my primary ride.

How is the parent modded as insightful? He's saying he doesn't give a shit because he hardly uses it.

Re:How to "speed up" Vista

[stewbacca]

Anyway, if you actually know how Windows works, you'll know what you don't want running and what you do.

I think that sentence basically makes the point for all Mac users on the planet.

Re:Straw Man?

[QRDeNameland]

No, you see, *that* was good as far as an argument against the OP's claim of "straw man". You actually made an argument as to why the article is not making a straw man argument, with evidence to back it up, though it is extacly the same one the the first response from 'faloi'. Great, so far I agree with that, and I said as much.

But that was not *my* argument. My argument was that you can't simply deny any claim of "straw man" based solely upon your perception that it is often misused, which is where you started. And appropriately enough, that makes your last response to me......a "straw man" argument! To which I can only respond...refer to my previous post.

Re:Optimization

[daviddennis]

Not always.

Mac OS X Leopard is faster than Tiger, which was faster than Jaguar.

Apple's a bloody impressive company nowadays :-).

D

Re:Straw Man?

[Daniel Phillips]

It's fair to call a straw man when someone puts words in someone else's mouth and then defeats that argument.

Is it fair to try to divert attention away from an actual issue (Vista performance is terrible and is not improved by the latest service pack) to a stupid wankfest about whether Microsoft actually claimed they would improve the poor Vista performance? Either way, Vista performance is poor and not getting better.

Meanwhile, I hear the Walmart Green PC at $199 is selling like hotcakes, because it performs very well running Linux + Enlightenment. Perhaps this shows that people really do care about poor Vista performance. And not what Microsoft claimed they would try to do about it.

Re:Optimization

[billcopc]

As a guy who used to write entire applications and games in pure assembler (a loooong time ago), optimization is something I do on-the-fly, but to some degree of restraint. If something can be dramatically improved with one or two extra lines of code, I do it, otherwise I leave it as-is.

Keep in mind that only one other person ever sees my code, and he tends to figure out my hacks with relative ease (or asks me if he's stumped). If I were at Microsoft, such code-level optimization would be murder as I'd be the only guy in the building able to work on it.

One thing that can help tremendously in optimization is a virtual machine, then you can profile the whole thing from boot to shutdown. I used it extensively when I was producing games, though I was doing tricks that would be considered profane today, like self-modifying code and interleaving. People always gave me confused stares when I showed off my real-time loop unroller. How better to sync graphics, audio and input than to smush them all into one dynamically-interleaved refresh-synced loop ? You could call it extreme time-slicing minus the context switches, and it made that old 486 scream!

As much as I'd enjoy that sort of wizardry in today's software, there just isn't time for it anymore. I must have spent a good 40hrs on that arcane unroller, it was a labor of love by a teenage demo-coder. Today, I'd just throw more hardware at it and bill the client. Microsoft is no different, they're just a whole lot bigger.

Re:Vista's not slow

[BosstonesOwn]

Power users are always the first to notice even the little things. Because we see them based on experiences from other systems.

Most end users who are not power users don't really see the sluggishness unless it gets real bad.

Case in point is look at the spyware apps. I can tell when they are running on a persons computer , but they can't they just think windows got slower, when we realize something is wrong they just keep using.

I have a family friend who bought a debranded refurbed HP box , cheap and with a 22 ws monitor came in under $500. It runs Vista , it runs at the moment like new because I taught them how to clean out the system every week. And they have a kid who surfs all kinds of sites , but yet it remains pretty much effortless for them. They use it for all sorts of stuff , the kid surfs youtube and all the sites and gets nasties but they cleaned out quickly.

Also I would not take your grandparents as a benchmark. Usually give it to a kid or a teen who is just realizing women exist and can be seen nude. That is a true test for any OS.

Re:DX10

[trolltalk.com]

"DX10. It's inevitable that games will eventually require it"

Why? To get an extra 10 fps? The normal hardware upgrade cycle will fix that, and let game manufacturers continue to ship with DX9. Heck, there are still games being sold that run fine under Win9x.

As Nintendo showed, its not necessary to require the latest and greatest hardware to have the best product.

Re:Are we shocked?

[roystgnr]

Bad permissions cause Vista to copy files VERY slowly because it has to reset them on all files.

On the Lame Excuses List, this falls somewhere above "You can't take bottled water on an airplane or the terrorists might win" but still doesn't beat out "He only hits me because he loves me."

If the equivalents of "cp -r" and "cp -pr" take noticeably different amounts of time to complete on your operating system, something is broken, because a multi-gigahertz processor can finish fiddling with even complicated permission bits long before a 50MB/s disk needs to have them ready to write.

Re:Vista's not slow

[drsmithy]

Vista could be a great OS , we just won't know until they decide to get the drm out of the system and remove what people feel is slowing down everything.

DRM is an utterly irrelevant criticism of Vista. If you're not using DRM-encumbered media, it's simply not active. If you *are* using DRM-encumbered media, Vista isn't imposing any more restrictions than any other player would.

I would like to see a total rewrite of the windows kernel to take advantage of newer ways of doing things. And I mean completely throw out backward compatability much like Linux does when they change core components in the system. Relying on a kernel that is going on almost what 20 years old ? Tells me this company has way to much mucking up the highway.

By that measure, both Linux (ca. 1991) and OS X (NeXTSTEP, ca. 1989) have older kernels than Vista (Windows NT 3.1, ca. 1993).

Re:Anonymous King Sours on Slashdot

[Ngarrang]

Simple: Eventually M$ is going to force you to run it. The corporate lapdog U.S. DOJ won't do anything to stop them either, just like they folded a winning hand against them last time.

The corporate world, the big companies, will ultimately determine Microsoft's course. At this point, Microsoft is kinda stuck. They own the desktop OS market, but the real money is made in licensing to the truly large companies. If those companies will not upgrade, they have the clout to look at Microsoft and say, "No. Extend support for another year. It would be ashame to switch those 100,000 desktops over to Linux." At which point, the Microsoft lackey does what they say. Microsoft only appears to be in charge, they have become pawns themselves.