Beta
×

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

Thank you!

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

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

MS Responds To Vista's Network / Audio Problems

kdawson posted about 7 years ago | from the designed-that-way dept.

Windows 528

quirdan writes "With the discovery last week of the connection between Vista's poor networking performance and audio activities, word quickly spread around the Net. No doubt this got Microsoft's attention, and they have responded to the issue. Microsoft states that 'some of what we are seeing is expected behavior, and some of it is not'; and that they are working on technical documentation, as well as applying a slight sugar coating to the symptoms. Apparently they believe an almost 90% drop in networking performance is 'slight,' only affects reception of data, and that this performance trade-off is necessary to simply play an MP3."

cancel ×

528 comments

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

Nice error, the drop is 10% (-1)

Anonymous Coward | about 7 years ago | (#20363571)

That would be a 10% reduction or drop, not a 90% drop. You could say it operated at 90% of design or something like that, but your description is plain wrong.

Re:Nice error, the drop is 10% (5, Informative)

LinuxGeek (6139) | about 7 years ago | (#20363631)

No, the network speed drops to ~10-15% of non-audio playing speed. Very significant issue.

Re:Nice error, the drop is 10% (0, Flamebait)

Achromatic1978 (916097) | about 7 years ago | (#20363973)

Uhh, based on what tests? Guys in forums saying "My FTP ran at this speed before, now it runs at this speed."? That isn't a reliable metric, shocking as it may seem to people on Slashdot.

Re:Nice error, the drop is 10% (5, Informative)

Anonymous Coward | about 7 years ago | (#20364367)

Typical (4, Funny)

Etrias (1121031) | about 7 years ago | (#20363577)

Remember folks, this is a feature, not a bug.

Two plus two is five. War is peace. Rinse, repeat.

Re:Typical (5, Insightful)

Brian Gordon (987471) | about 7 years ago | (#20363609)

How many lights are there again? Five?

Re:Typical (1)

Etrias (1121031) | about 7 years ago | (#20363831)

Nice. One of my favorite episodes.

THERE...ARE...FOUR...LIGHTS!

Classic.

Re:Typical (5, Funny)

Anonymous Coward | about 7 years ago | (#20364031)

How many lights are there again?

...buffering...

Re:Typical (2, Funny)

Anonymous Coward | about 7 years ago | (#20363633)

What about lathering? How do you expect me to get clean WITHOUT FUCKING LATHERING!

Re:Typical (0)

Anonymous Coward | about 7 years ago | (#20363645)

LOL

Re:Typical (0)

Anonymous Coward | about 7 years ago | (#20363763)

I don't get the reference (this is one, right?)

care to explain?

Re:Typical (0)

Anonymous Coward | about 7 years ago | (#20363823)

Rinse, repeat (from my GGP) are the 2nd and 3rd steps of washing hair.

Lather (from my GP) is the first step.

Re:Typical (1)

Etrias (1121031) | about 7 years ago | (#20363857)

Oh nice, suddenly this is all about you getting clean? We are talking about Vista here...and only doing a half-assed job anyway. You HAVE to have a missing step.

missing tag? (0, Redundant)

v1 (525388) | about 7 years ago | (#20363583)

They just said a 90% performance hit to an unrelated system is normal? So where's the "defective by design" tag?

Re:missing tag? (1)

ILuvRamen (1026668) | about 7 years ago | (#20363727)

unrelated isn't completely true. I'm thinking they're gonna say the sound card might use up too much electricity so it scales back the network card's performance just in case lol. Either that or they'll just say "It's a feature not a bug because Vista is just so bulky and badly thrown together that completely unrelated things can completely screw each other up and there's no way around it but to redeign Vista."

Re:missing tag? (5, Funny)

cp.tar (871488) | about 7 years ago | (#20363743)

They just said a 90% performance hit to an unrelated system is normal? So where's the "defective by design" tag?
Well, the article summary does state that

Microsoft states that 'some of what we are seeing is expected behavior, and some of it is not'

All in all, the performance hit is obviously expected behaviour. I guess it's just the severity of the hit that's unexpected.

They'd probably planned just a 70% performance hit, but we can see their software performs better than expected.

Re:missing tag? (4, Funny)

Original Replica (908688) | about 7 years ago | (#20363907)

All in all, the performance hit is obviously expected behaviour.

Well of course they are expecting a performance hit, after all they aren't "just trying to play an MP3" they have to do 7 different DRM related processes while playing an MP3, on top of Sony's hack of your webcam doing a biometrics check to verify that you are the original purchaser. Seriously though, does the drop still happen if you play a DRM free MP3 on a non-MS player?

M$ expected behaviour! (4, Informative)

MindKata (957167) | about 7 years ago | (#20363917)

"performance hit is obviously expected behaviour" and from the article, "Windows Vista will trade off network performance in order to improve multimedia playback"

That is utter BS. On a decade old machine, its possible to run a network and audio playback at real time speeds. Given the power of even low end PCs these days (minimum spec Vista machines) its crazy they cannot handle both together.

Re:M$ expected behaviour! (5, Funny)

cp.tar (871488) | about 7 years ago | (#20364329)

Given the power of even low end PCs these days (minimum spec Vista machines) its crazy they cannot handle both together.

Sure they can.

They just cannot run Vista at the same time.

Re:missing tag? (0, Troll)

cabinetsoft (923481) | about 7 years ago | (#20363777)

They just said a 90% performance hit to an unrelated system is normal?
The blurb has an error... is not a 90% peformance hit but a 10% performance hit. Playing audio files won't get you down to 10% of the non-audio-playing throughput but to 90%.

Re:missing tag? (5, Informative)

stinerman (812158) | about 7 years ago | (#20363867)

No, it's not. Read the old FA:

However, some users over at the 2CPU forums have discovered an unexplained connection with audio playback resulting in a cap at approximately 5%-10% of total network throughput.

Re:missing tag? (1)

Tuoqui (1091447) | about 7 years ago | (#20363995)

So when is someone going to say 'YOU DO NOT NEED TO SEND STUFF OVER THE INTERNET TO LISTEN TO AN MP3?'

I mean honestly, XP shows that you do not need this. Microsoft should just tell the RIAA/MPAA to go fuck off. Seriously.

New OS has old problems (5, Insightful)

Boa Constrictor (810560) | about 7 years ago | (#20363589)

I suppose this explains why MS has been so reticent to start afresh with the codebase until now. Even basic things are buggy and it's costing the reputation of the latest roll-out.

Pushing Vista too early is only going to hinder long-term deployment.

Re:New OS has old problems (3, Insightful)

Anonymous Coward | about 7 years ago | (#20363695)

Even basic things are buggy and it's costing the reputation of the latest roll-out.

Pushing Vista too early is only going to hinder long-term deployment.

Only among the geek crowd, who don't want Vista anyway. The "general public" doesn't care. The computers they buy new come with Vista, and that's what they will use.

Re: Deployment (4, Interesting)

TaoPhoenix (980487) | about 7 years ago | (#20364061)

Maybe they don't care at all about deployment of Vista.

We harp on MS a lot, but they ARE clever in certain ways. Suppose someone is thinking Big Picture in some kind of twisted sense. They can play a variant of GoodGuy/BadGuy by having a "Sacrificial OS" every 8 years. They're somehow getting us to pay for their beta testing. They HAD to get Vista out, period, and rely on their patented brand of bluster to get through it. They were getting serious heat from inactivity. I bet someone got utterly crushed when they had to switch codebases during that dev setback.

I barely heard of Win Me - consecutive tips told me to get Win2000, which lasted me through 2.5 OS changes from MS. Then in the early days, I saw a lovely crash&burn act on XP *SP2* until everyone repaired their firmware. I even had some flash devices that I had to return until the factory shipped ones with newer firmware.

Now XP is their heavy duty workhorse while they experiment with their new codebase. Suppose just for a moment that Vista NEVER works... but what they learned from Vista SP1 gets applied to Windows 7 (anyone got a codename yet?). Then maybe by 2010 all the results of history on the media scene will be in, maybe they will back off from DRM, and take some other focus. If they don't screw it up, Vista will be that smile in techie's forums, Windows 7 will be the new 8 year workhorse, and off we go ever after.

Having cash flow the size of a country must be fun.

Re: Deployment (1)

Tom (822) | about 7 years ago | (#20364203)

Nice theory, but flawed.

ME was released 2 years after '98. It wasn't announced with 10% of the media hype that Vista was announce with. It also wasn't the default for all future OEM deals.

I'm certain a company the size of MS pays a few people to think about the big picture. I'm likewise sure the big picture right now isn't "great move", but more like "how do we get out of this mess?".

Back in 1994... (5, Interesting)

Anonymous Coward | about 7 years ago | (#20363639)

Back in 1994, I bought a Power Macintosh 7100. One of the first PPC chips, about 66MHz, and running a positively archaic operating system.

I still have the machine, and drag it out from time to time. When this story broke, I pulled it out of storage to test it, and see how it compared. With a 10/100 ethernet card in, running the mac's System 7.5.3, it could successfully play an MP3 while transferring, and it made no difference whatsoever to send or receive speed over the network.

Take note Microsoft: 1994, 66MHz, System 7.5.3, more than 13 fricken years ago.

Re:Back in 1994... (0)

anagama (611277) | about 7 years ago | (#20363771)

MS' answer to this is:

"The connection between media playback and networking is not immediately obvious. But as you know, the drivers involved in both activities run at extremely high priority. As a result, the network driver can cause media playback to degrade. This shows up to the user as things like popping and crackling during audio playback. Users generally hate this, hence the trade off."

Then they intersperse several other excuses before stating

Second, this trade-off scheme only kicks in on the receive side. Transmit is not affected."
Perhaps they are relying on short attention spans and the inability to think critically because it would seem that low level driver processes involved in receiving would also come into play while sending.

Re:Back in 1994... (1)

Neon Spiral Injector (21234) | about 7 years ago | (#20363945)

Except that the OS knows there is data to send, and can schedule it well enough to keep the speeds up and not underflow the audio buffer.

But receives can happen at any time, so the data sits in the NIC's buffer until the OS gets around to picking it up.

Parent is a troll. (-1)

Anonymous Coward | about 7 years ago | (#20363797)

System 7.5.3 is a much simpler operating system than Windows Vista (NT). System 7.5.3 used cooperative multitasking. This meant that if the program playing the MP3 (which I hope is legal) could bring down the whole system if it didn't feel like giving the CPU back to the kernel. A lot of things were faster on older hardware because the software was simpler. I am sure Windows 95 could do the same thing. But software is much more complicated today. Operating systems much do much more such as keeping usermode applications in ring 3. While this isn't probably why this is happening, it means you can't compare apples to oranges. Because Windows has to maintain excellent backwards compatibility and satisfy many needs of a large userbase without compromising an intuitive user experience, problems like this are more likely. Apple has a good product, but they don't have to support the vast hardware that Windows supports. Besides, Microsoft will likely address this. It takes time to come up with a solution.
Anonymous Coward Sig 2.0:
--
Madonna is the only artist with any talent. The others are lame imitations!

This parent is a troll. (2, Insightful)

Anonymous Coward | about 7 years ago | (#20363875)

Oh, please. You're right that Vista is a more capable operating system than Mac OS 7. You're wrong that it would have any implication on audio playback.

I can encode a 320mbit VBR MP3 at about 20X playback speed. That's encoding, the slow phase. MP3 playback is NOT a real-time task. It hasn't been for ages. The system decodes the next several seconds of audio, stores it in an audio buffer, and tells the system to play it. If you hit pause, it then stops the active playback immediately, but there's still more audio data available. This way, there's no reason for the audio to skip, and the audio program doesn't need to be top priority or realtime.

Ironically the only audio program I've had problems with skipping under Windows is iTunes, and only when running some other task at 100%.

In any case, audio programs don't need realtime priority and there's no reason why playing audio should cause network performance to degrade in a properly designed system. I can see a poorly designed system manage to completely screw things up with interrupt handling, though.
--
Sigs are lame.

Re:This parent is a troll. (1)

karnal (22275) | about 7 years ago | (#20364239)

There were some drivers (S3 Virge card I had) back in the day for PCI video cards that would cause the video card to hog all of the PCI bandwidth. This was so that the card could be touted as #1 in benchmarks, but it left a weird after-affect --> you could play an mp3, but any time you did anything close to a full screen update such as scrolling in internet explorer, the audio would skip.

The sound card buffer would run out since the video card was taking the bus and not releasing it.

There was a registry patch I searched out one day and that solved the issue. Funny thing was is that I couldn't tell a difference in casual windows refresh performance - only in benchmarks (2d) could I see a degradation of performance. So sometimes it's an architecture/driver issue....

Re:Parent is a troll. (1)

spottedkangaroo (451692) | about 7 years ago | (#20363889)

...maintain excellent backwards compatibility...

Oh, yeah, Vista is famous for it's backwards compatibility these days; particularly with it's drivers, internets and multimedia applications. Those are known to work flawlessly and without intentional downgrades in quality and so on.

Re:Parent is a troll. (0)

Anonymous Coward | about 7 years ago | (#20364071)

You mean to say "its." Don't use "it's" for possessive. Windows Vista may not be completely backwards compatible, but it comes a lot closer than their closed competitor (Apple).

Anonymous Coward Sig 2.0:
--
Madonna is the only artist with any talent. The others are lame imitations!

Re:Back in 1994... (1, Interesting)

CastrTroy (595695) | about 7 years ago | (#20363799)

That's pretty impressive. I remember having a 486 DX4 100, and not being able to play MP3s on it because they would skip too much. However, what I do remember is finding an MP2 encoder, and enconding my files into MP2, because that could play without skipping. Maybe it was just bad software or something, because this was probably around 1996-1998. I think that the machine should be capable of decoding MP3 files, but for some reason it didn't work.

Re:Back in 1994... (1)

domatic (1128127) | about 7 years ago | (#20363859)

I've played mp3s on machines with those specs with Linux 2.4.x kernels in the 2000ish timeframe. It took something like 85% CPU but it did play them.

Re:Back in 1994... (1)

CastrTroy (595695) | about 7 years ago | (#20363885)

Yeah, it probably was due to the fact that I was still running windows 3.1. I probably could have played them running in DOS. I also recall having an 8-bit soundcard (left over from an old 386, but it worked, so why bother replacing it, sound cards weren't $15 back then) so the downsampling might have been what pushed it over the edge, along with running a 16 bit OS.

Re:Back in 1994... (1)

Mr. Shiny And New (525071) | about 7 years ago | (#20363927)

It's possible you were using too many ISA devices in your 486. I had a DX4-100 as a server for a while and it wasn't able to transfer files and play music at the same time until I changed all the devices to PCI, and then it worked fine.

Re:Back in 1994... (1)

David Gerard (12369) | about 7 years ago | (#20363965)

MP3 (MPEG 1 Layer 3) and MPEG2 audio are pretty much the same, with slight differences in the profiles. MPEG2 is likely to sound slightly better at stream rates over 224kbps. Otherwise the decoders take the same amount of CPU.

Re:Back in 1994... (1)

Bert64 (520050) | about 7 years ago | (#20364337)

I coule get MP3 files playing perfectly well on a DX2/66 and a 50mhz Amiga... I had them playing on a 33mhz Amiga too, but i had to reduce the output quality...
This was ofcourse 128kbit mp3s, commonplace in those days.
I would have thought a DX4/100 would have no issues whatsoever playing mp3 files, maybe something else in your machine was letting it down, slow memory, slow/nondma ide controller, slow soundcard etc.

Re:Back in 1994... (2, Insightful)

Poromenos1 (830658) | about 7 years ago | (#20363833)

Don't take this as an attack, but your comment is rather sensationalist. What difference does it make that your 13 year old PC plays mp3s over the network? It's not like MS is 13 years behind, it's a BUG. Hell, XP is fine, you don't see me saying "Watch out, 2007 MS, 2004 MS has you beaten!".

Re:Back in 1994... (5, Insightful)

Anonymous Coward | about 7 years ago | (#20363913)

Yeah, but uh... Microsoft's answer is that it's a nescessary trade-off for good sound performance. If they acknowledged it as a bug there wouldn't be such a bitch-fest going on.

Re:Back in 1994... (5, Funny)

Reaperducer (871695) | about 7 years ago | (#20364067)

Geez. Even the Commodore 64 can play MP3's. [wikipedia.org]

Windows can't compete with a 1 Mhz computer made in 1992 with 38,911 BASIC BYTES FREE
READY.
[]

Re:Back in 1994... (2, Insightful)

Lars T. (470328) | about 7 years ago | (#20364313)

Geez. Even the Commodore 64 can play MP3's. [wikipedia.org]

Windows can't compete with a 1 Mhz computer made in 1992 with 38,911 BASIC BYTES FREE
READY.
[]
Yeah, if you plug an SD-Card reader into the C64, and then a DSP-board onto that reader which then accesses the SD-Cards, completely bypassing anything original to the C64. I'm to lazy to check whether you can still use the 10MBit Ethernet card at the same time.

Re:Back in 1994... (2)

Craig Ringer (302899) | about 7 years ago | (#20364221)

One poster has already pointed out one part of why your argument is oversimplified (cooperative multitasking).

In fact, Mac OS 7/8/9 are still hard to beat for soft realtime, because you can basically control the machine exclusively for as long as you want, giving access back to the OS only when it's convenient. If there are no other processes running (you've killed the Finder and aren't running anything but your app) it's impressive for audio etc.

There's another big reason, too. Your M601 based PowerMac didn't have gigabit ethernet. If it had, it couldn't have even processed the interrupts fast enough to count the packets it was dropping. (It didn't help that the 601 machines were NuBus based, but even had they been PCI it'd still be hopeless). I very much doubt a 601-based machine could even fully saturate 100baseTX. I know ours at work couldn't in network file I/O. On the other hand, with a 66MHz CPU that's hardly surprising.

I'm still very surprised that these effects are so significant. Soft realtime CPU scheduling guarantees to multimedia apps should not have to so dramatically affect machine throughput, though they'll probably have some effect. Look at Linux - it copes pretty well. Vista performing poorly in this area is unfortunate, but not so incomprehensible as many claim, especially since IIRC it does provide quite low latencies for audio apps.

--
Craig Ringer

Re:Back in 1994... (0)

Anonymous Coward | about 7 years ago | (#20364265)

I call bullshit
66mhz PPC can't decode an MP3 in realtime

"It's not a bug, it's a limitation." (3, Interesting)

John Jorsett (171560) | about 7 years ago | (#20363641)

That was the response of a MS tech regarding a defect that a bunch of us found in one of their C libraries some years ago. They must have had that guy train his successors.

Because only MS ever uses that excuse.. (2, Insightful)

Junta (36770) | about 7 years ago | (#20363673)

I couldn't begin to keep track of how many times I've heard that one in the industry. 'X is broken'. 'Well, our new architecture can't theoretically acheive X anymore, so it's a design limitation, not a bug'.

Re:Because only MS ever uses that excuse.. (1)

marcosdumay (620877) | about 7 years ago | (#20364253)

We have the term "design bug" for that. But it seems it still isn't an enterprize grade term :(

Re:"It's not a bug, it's a limitation." (2, Interesting)

koh (124962) | about 7 years ago | (#20363747)

Wait a minute. Could this be done to limit streaming capabilities? It is the main side effect after all...

Re:"It's not a bug, it's a limitation." (1)

Nate B. (2907) | about 7 years ago | (#20363919)

That was my first thought upon reading the original article last week.

I would almost bet that this was a concession to RIAA during Vista's design phase. I would also bet that they were counting on this particular "feature" going unnoticed until XP was cleared out of the sales channels and Vista had gained acceptance as the OS of choice amongst MS' vendors.

And there are people that want to accept MS into the FOSS community with open arms? MS apparently no longer regards its customers as its first priority. How then could they be trusted to put playing fair a priority in the FOSS community?

Re:"It's not a bug, it's a limitation." (1)

Tom (822) | about 7 years ago | (#20364165)

MS apparently no longer regards its customers as its first priority.
MS never regarded its customers as first priority. From the first days on, it switched between con artist ("I have an OS in Cairo for sale, and it's gonna be the best, THE best, I tell you!") and mobster ("nice data you have there, would be a shame if you couldn't read it anymore just because you switched to another office package...").

MS for a long time regarded developers with a high priority.

ITS (3, Insightful)

Brian Gordon (987471) | about 7 years ago | (#20363659)

To say nothing of traditional multithreading, how do they explain how the entire OS could be run on either of my cores, but just networking and multimedia can't run together on both of them without some kind of tradeoff?

REally? (5, Insightful)

Lumpy (12016) | about 7 years ago | (#20363693)

Apparently they believe an almost 10% drop in networking performance is 'slight,' only affects reception of data, and that this performance trade-off is necessary to simply play an MP3.

Interesting, VERY interesting. This either means that Microsoft Programmers are incredibly incompetent or they are hiding something. I can take a really old Linux kernel (or windows 98 install) on a Pentium 233 mmx processor and see less than 0.05% drop in networking performance while playing an mp3. In fact I dont see that drop playing 2 mp3's at the same time while transferring large amounts of data over 100 base T. I do this daily on my whole house mp3 jukebox that is linux based, it has 2 seperate sound cards that plays 2 different mp3 files while I upload another 60-80 mp3 files I corrected the data tags on. I do not see the performance hit of 10% on hardware that is at least 20 to 30 times slower than the typical Vista machine.

What are they hiding?

Re:REally? (1)

CastrTroy (595695) | about 7 years ago | (#20363837)

But an old Linux kernel or Windows 98 aren't the big beast OSes that Windows Vista is. I recently bought a laptop (Celeron M 1.6 GHz, and 512 MB of RAM). Vista runs extremely slow, but I installed Mandriva and the thing runs really fast. The short answer to all this is that MS Windows Vista is a big hog of an OS, and slows things down way more than it really should. Linux and MacOS seem to be getting faster with every release, meanwhile, Windows seems to be getting slower. I really think they are in kahoots with the hardware manufacturers, so that computers never get "fast enough". My $500 laptop would be all I or most people ever needed if Windows was programmed to be as resource friendly as Linux.

Re:REally? (4, Insightful)

doodleboy (263186) | about 7 years ago | (#20363849)

What are they hiding?

That it's caused by the DRM subsystem.

Re:REally? (4, Informative)

arivanov (12034) | about 7 years ago | (#20363931)

Good thinking.

If it accessing the onboard TPM this is quite likely. I cann bet that they smacked a few global locks around those accesses just in case to ensure that a silly race condition in the access will not allow someone to break through the precious DRM. PC TPMs are disgustingly slow so every access leads to a fairly long period when interrupts are not being serviced. As a result the system capability to process interrupts drastically decreases whenever the DRM subsystem has been activated. Add to that some priority to multimedia and the picture will be exactly as observed.

This is all hypothetical of course, but it more or less makes sense. I would not be surprised if that is the case.

Re:REally? (1)

VariableGHz (1099185) | about 7 years ago | (#20363879)

I'd test this out on WindowsME, but, I know I won't be able to get it started ;P

Re:REally? (0)

Anonymous Coward | about 7 years ago | (#20363909)

It's a security issue at heart.
For a users audio application to have glitch free low latency it needs real time privalages.
This is dangerous as real time applications can preempt all other processes.

In Linux, everyday audio is not considered to need low latency, so large buffers are adequate.
Real time users need special permission, and must accept the consequences of a real time app running out of control. A sound server with a watchdog timer like Jackd can kill off misbehaving apps. Real time apps will slow other processes by preemptimg them.

In Vista, every user is assumed to need low latency real time audio.
So even an everyday application like playing an mp3 is assumed to be critical.
The MMCCS does have a seperate 'pro audio' scheduling setting, which was meant to be used for this, but it appears that has been ignored, or else app writers are abusing it for everyday audio.
Low latency real time apps should be able to preempt network etc, which is why Microsoft don't quite call this a bug.

Your Linux box was not playing mp3s at a particulally high priority, so the network is fine.
Try playing audio using jackd+ardour at 2ms latency under linux and you will see some degradation, though not nearly as much as in vista.

Re:REally? (1)

langelgjm (860756) | about 7 years ago | (#20364033)

So is it a 10% drop or a 90% drop? The summary says 90, but you've quoted 10. I could live with one of those, though I shouldn't have to.

90% (1)

laing (303349) | about 7 years ago | (#20364183)

It is a 90% drop. The network bandwidth drops to 10% of what it should be. From what I recall reading about this last week, I thought it only became apparent with a GIGABIT ethernet NIC. All of these posts discussing no effects with mp3 players and 10/100 cards have missed the mark. A 10/100 card running at 100 megabits has 10% of the network bandwidth of a gigabit nic. Nonetheless, MS Windows sucks and this is just another fine example.

Re:REally? (5, Insightful)

myrdos2 (989497) | about 7 years ago | (#20364075)

Napoleon: "Never ascribe to malice that which can be explained by incompetence."

Me, after using Vista: "Any sufficiently advanced incompetence is indistinguishable from malice."

Re:REally? (5, Interesting)

gad_zuki! (70830) | about 7 years ago | (#20364181)

Maybe we should start using the slashtards tag. Did you even bother to click on the link? Hell, the article is written in the ADD-style of "dummy quotes." The author doesnt even present the full email! In short, what was left out is that MS has acknowledged the bug but the tech wrote that there is going to be some kind of performance hit. Its not like MS wrote "THIS IS NOT A BUG. GO AWAY." Contrast:

"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."

"In most cases the user does not notice the impact of this as the decrease in network performance is slight. Of course some users, especially ones on Gigabit based networks, are seeing a much greater decrease than is expected and that is clearly a problem that we need to address."


In other words they see a bug especially on gigabit connections.

Now back to yoru regularly scheduled bitching and "ZOMG my calculator gets better performance" fact-free discussion.

Fucking MPAA (1)

Anonymous Coward | about 7 years ago | (#20363699)

I knew it, they finally broke internet radio.

Re:Fucking MPAA (1)

datapharmer (1099455) | about 7 years ago | (#20363843)

haha! awesome. you get the A.C. of the year award. :-)

Internet is all that counts! (4, Funny)

mishehu (712452) | about 7 years ago | (#20363709)

First, we have not seen any cases where a users internet performance would be degraded, in our tests this issue only shows up with local network operations.

So I see! All that matters is the Internet performance of the average user, which is probably what, less than 5Mbps anyway! How silly of me to think there would be a problem with say... trying to access a corporate file server to work with say really big data files? Wow, I'm really going to recommend Vista to my clients now!

Re:Internet is all that counts! (1)

lukas84 (912874) | about 7 years ago | (#20363895)

Yeah, because corporate policies allow you to play MP3 files ;)

Re:Internet is all that counts! (1)

maharg (182366) | about 7 years ago | (#20364357)

Actually many do. I'm in the media industry. Not only does my employer allow and encourage viewing listening of all manner of compressed and uncompressed content (let's not even talk about uncompressed content on 'Fister'), for many of my (000s of..) colleagues, it is a central part of their job. Next !

"..slight.."?? (5, Funny)

biomech (44405) | about 7 years ago | (#20363717)

Oh, I see,

as in "slightly pregnant" or "slightly dead"??

Same s***, different defect. (0)

Anonymous Coward | about 7 years ago | (#20363733)

You know its crap like this that contributed to a modestly minor personal project of mine that I undertook at the end of last week.

I bought a laptop at best buy (well, it was sort of a back to school gift), just a cheap 350 buck one, nothing fancy, just something to take notes and do powerpoint on. Its a 1.6 pentium M with 512 of ram....but oh, guess what It came with? Yes thats right, vista. Not only did the thing take 5 whole minutes to boot up to display the draconian EULA, it actually froze when I rejected it.

After a reformat and a night of fetching drivers off the internet (the only CD that came with the laptop is a Vista restore disc that I will be returning when I demand my OS refund), I installed XP on it.

From post to desktop in 40 seconds, and with 95% less draconian DRM (lowsy WGA crap).

Re:Same s***, different defect. (-1, Flamebait)

Anonymous Coward | about 7 years ago | (#20364025)

You know its crap like this that contributed to a modestly minor personal project of mine that I undertook at the end of last week.
No it isn't! Do you have any idea what a 'modestly minor personal project' is? Obviously not, or you'd realized you have nothing to do with it in any way, shape, whey, or form.

I bought a laptop at best buy (well, it was sort of a back to school gift)
So you just lied? A bold-face lie, to our readers. Thank you. Liar.

, just a cheap 350 buck one, nothing fancy, just something to take notes and do powerpoint on.
Okay, that is a cheap laptop. That isn't even fancy. You could probably only use that to take notes on, and maybe if you overclocked it, run PowerPoint.

Its a 1.6 pentium M with 512 of ram....but oh, guess what It came with?
What a piece of crap laptop. What did that set you back, 350 dollars? Wow. I bet it came with a load of crap, in case your laptop broke (which it probably will), you can just rub the crap on your body. That would give you the same effect as using your non-fancy craptop.

Yes thats right, vista.
Based on your earlier lies, I'm going to say that without further proof, that isn't right. The only thing that is right is that you have a sick addiction to lying.

Not only did the thing take 5 whole minutes to boot up to display the draconian EULA, it actually froze when I rejected it.
So? That'd be like me buying a hybrid car, then complaining it finished in last place at the Daytona 500. Your logic simply does not follow.

After a reformat and a night of fetching drivers off the internet
AKA, a night of surfing the internet for porn, and then emailing lies to children.

(the only CD that came with the laptop is a Vista restore disc that I will be returning when I demand my OS refund),
One word: Communist. Look in the dictionary, you'll find a picture of you. Returning your stupid Vista restore CD. I hope you're happy!

I installed XP on it.
I don't even know where to begin with this. So I won't

From post to desktop in 40 seconds, and with 95% less draconian DRM (lowsy WGA crap).
I salute Windows XP, for that is 40 seconds less the children have to put up with your email lies.

What!? (0, Redundant)

Jugalator (259273) | about 7 years ago | (#20363759)

Apparently they believe an almost 90% drop in networking performance is 'slight,'

Huh?? When? Surely not here if playing music anyway. That sounds like a bug, but is it a driver problem or exactly what?

Re:What!? (1)

should_be_linear (779431) | about 7 years ago | (#20364275)

It sounds to me like scheduler problem in kernel. Mp3 playback looks to kernel like very important desktop multimedia task so kernel assign big chunks of time to it, regardless fact that task is mostly sleeping. As a kernel bug, it is difficult to fix unless you want to break many other important stuff, like games or video playback, for example. Each tuning needs months of testing. That would explain why MS is not promising to release fix anytime soon.

the makers of zune why are we surprised by this!? (0)

Anonymous Coward | about 7 years ago | (#20363795)

Microsoft states that 'some of what we are seeing is expected behavior
this is the same copany that crippled their Zune's ability to transfer music like you want and created Vista with a thing for DRM, why is it surprising that they have this problem? Microsoft isn't going to fix it anytime soon if at all unless it starts threatening their cash flow.

Question (1)

Joseph1337 (1146047) | about 7 years ago | (#20363805)

Can I run Vista on Linux? ... VISTA IS A OS?! No... you`re kidding me...

From the horse's mouth (5, Interesting)

stinerman (812158) | about 7 years ago | (#20363829)

FTA:

"The connection between media playback and networking is not immediately obvious. But as you know, the drivers involved in both activities run at extremely high priority. As a result, the network driver can cause media playback to degrade. This shows up to the user as things like popping and crackling during audio playback. Users generally hate this, hence the trade off."

Granted, I don't want my audio stuttering, but the idea that the CPU can't keep up because of file transfer is insane. Maxing out an ethernet connection doesn't take much CPU. Even if we put the audio at a very high priority, I don't see how that would immediately degrade ethernet performance by 90%. I could accept no more than about 5% in a worse case scenario.

To be fair if I renice rhythmbox to 18 and transfer a file, things go to hell. Renicing to 10 clears it up. I saw no degradation of speed. Apparently Debian can do file transfers at full speed while playing an mp3 on a rather old PC*. Something isn't right here...

*Athlon XP 2400+, 1GB DDR

Re:From the horse's mouth (0)

Anonymous Coward | about 7 years ago | (#20363937)

ah but you are comparing linux [about a third the memory usage if that] to an OS that was designed to distract people from its flaws by having its design centered around eye candy that uses over twice the memory of any eye candy on Mac or linux as well as being entangled deeply in DRM whose sole purpose is to strangle your ability to copy/use music like you should. this isn't a bug it is by design.

Re:From the horse's mouth (1)

Dude McDude (938516) | about 7 years ago | (#20364073)

....entangled deeply in DRM whose sole purpose is to strangle your ability to copy/use music like you should.
Vista doesn't "strangle" a user's ability to copy/use music. You can rip your music to any format you wish, and share it with all and sundry, with no restrictions whatsoever.

Re:From the horse's mouth (5, Funny)

freeweed (309734) | about 7 years ago | (#20364223)

a rather old PC*

*Athlon XP 2400+, 1GB DDR


Holy shit, get off my lawn x 1 billion!

Re:From the horse's mouth (0)

Anonymous Coward | about 7 years ago | (#20364229)

I had the exact same thought when I saw that.

Re:From the horse's mouth (4, Interesting)

Xtravar (725372) | about 7 years ago | (#20364311)

Generally, audio goes through many buffers before being sent out to the device. In Vista, perhaps all audio is streamlined as high-priority.

For example, when audio recording, you don't want to use Microsoft's typical sound system - you want to record using ASIO which goes through less buffering and latency. If you record using the regular sound system, you end up with perhaps 100s of ms of lag, which is a bitch when you're trying to record to a metronome.

As some AC above noted, Linux only has a direct audio IO path when using jackd. Otherwise, everything is buffered a plenty.

So I think it has nothing to do with CPU power, and more to do with "Vista is a real-time multimedia machine!" When you're interrupting a LOT to be attentive to the audio device, this is going to interfere with the network, whereas if you just interrupt less regularly but send larger amounts of buffered data you don't have that problem.

*Fair warning, my facts may not be 100% accurate, but I think this is the gist of the problem.

Not Sure (1)

JamesRose (1062530) | about 7 years ago | (#20363851)

When I used vista I didn't see a slow down in network speeds, but at the time I was reorganising media on my hard disk, I started at 10gigabyte file transfer, vista stopped, completely stopped literrally, its like i was running vista on a 66mhz processor, it was not funny, 1hour later when I had reinstalled XP it was much better.

Funny (1)

canuck57 (662392) | about 7 years ago | (#20364149)

...not funny, 1hour later when I had reinstalled XP it was much better.

It is funny. Microsoft has been around long enough that you know the old saying. Just never, and I mean never buy in pre-SP1 as your are in effect a beta-tester. It might even take 2-3 years or more before it gets as stable as XP is today. And drivers for the stuff you might have bought 6 months ago, good luck.

That is why I bought my last PC at a discount, XP with a free mail in rebate for the Vista. Licensed for when MS gets it together but not going to run it now. I wish I had bought 3. I have two relatives wanting XP and trying to drag me down the Vista hole.

I figure the first vendor of PCs to ask the user on boot, "Shall this be XP or Vista?" will enjoy a nice bump in sales. Even more if it said "Will this be XP, Vista, Solaris 86/64 or Linux?"

FTA (5, Interesting)

flummoxd (1017734) | about 7 years ago | (#20363891)

"In certain circumstances Windows Vista will trade off network performance in order to improve multimedia playback. This is by design."

I know we've been over this before. But for whom are we 'improv[ing] multimedia playback'? Is it really an issue in 2007, to perform a network transfer and play an MP3? Or is it Vista's "secure audio path" that is responsible for this? Remember, this is the same Vista that polls your hardware every few ms to check if you're playing 'premium content'.

I know not everything bad Microsoft does is done with forethought and malice (..) but really now. After reading the 'cost analysis of Vista content protection [auckland.ac.nz] ', can you not understand the apprehension? If some "multimedia" (albeit not 'premium content', but who's counting) is played, other parts of the system deliberately go into a 'limited' state? After reading that, does it sound like a bug to you?

"But as you know, the drivers involved in both activities run at extremely high priority. As a result, the network driver can cause media playback to degrade. This shows up to the user as things like popping and crackling during audio playback."

I call shenanigans.

Even if this is a legitimate "bug", i.e. the Vista testers were actually experiencing crackling audio while performing high bandwidth network transfers, who made the conscious decision to throttle the *network* instead of fixing the audio path and audio drivers? Windows XP had no problems performing high-bandwidth transfers and using the sound simultaneously. Besides normal operating system scheduling there was no 'throttling' of any device A when any device B activates. This is Vista content protection backfiring, plain and simple.

100% agreement (1)

argent (18001) | about 7 years ago | (#20364103)

The decoding process is the only computationally intensive part of playback and that can go on in the background at low priority... so long as there's decoded audio queued up it doesn't matter if the mp3 decoding is deferred even *seconds* at a time on occasion. The latency sensitive part, the audio playback, can be performed using traditional device drivers and queues even on computers a thousand times slower than anything that runs Vista.

The only computationally intensive processes introduced by Vista that's latency-sensitive are the encryption and decryption operations in the trusted audio path. As you say, this is most likely content protection showing its igly face.

Enough with the Microsoft bashing (5, Funny)

symbolset (646467) | about 7 years ago | (#20363901)

Nobody could expect Microsoft to come up with an OS that does two things well at the same time. That would be multitasking. We're decades away from the invention of computers that can do that.

Networking is overrated also. It's probably just a fad that will fade away once we all get high density flash storage for our sneakernets.

Music? If you wanted to do artsy iLife stuff like that you should have bought an iFruit.

Their response is sensible (0, Troll)

Anonymous Coward | about 7 years ago | (#20363943)

There are two interesting things about this matter:
1. How retarded the predictions of the Slashdot user base were. Look at this [slashdot.org] for example, which along with all of the other DRM blather was from another universe.
2. How retarded the response from the Slashdot user base to their explanation is. Despite explaining the purpose of the scheduling trade-off, people harp on about their 20 year old computers and their stellar mp3 playback over slow links. You've sure showed Microsoft, tough guys!

What they've said makes sense. It sounds buggy though, as it should be difficult for GbE or audio playback to saturate the CPU enough to legitimately run into the scheduling conflicts that would starve network performance significantly.

It seems that most of the technically-oriented people left Slashdot for greener pastures, leaving a pool of insipid teenagers in their wake. Thanks for reminding me why I didn't read this site for three years, you monkeys.

Multimedia Scheduling Service (1)

The MAZZTer (911996) | about 7 years ago | (#20364007)

Or something by that name is probably what is responsible for this behavior (I'm in Ubuntu right now, which I'm noting is running games better than XP and way better than Vista...)

its 2007 not 1997 - why is this needed??? (0)

Anonymous Coward | about 7 years ago | (#20364019)

"In certain circumstances Windows Vista will trade off network performance in order to improve multimedia playback. This is by design" - but why is this needed?? Any computer capable of running Vista should have no problem playing back all but the most highest quality HD content and any computer with a good performance rating should be able to do this as well.

I have been running Vista Ultimate x64 (with most shit turned off) on a dual core 4200+ with 4GB of RAM since RTM and my overall satisfactory level is not good at all. I ran XP x64 for about a year before this and I absolutely loved it!!

The big question I have with Vista is why Microsoft choose to do all these little gimmics and tricks. ReadyBoost, SuperFetch, and most importanly Multimedia Class Schedualer are all jokes. I would love to turn off Multimedia Class Scheduler but you cant - the entire audio system depends on it.

The service description reads "Enables relative prioritization of work based on system-wide task priorities. This is intended mainly for multimedia applications. If this service is stopped, individual tasks resort to their default priority."

Makes you wonder (1)

BCW2 (168187) | about 7 years ago | (#20364043)

If common sense was dynamite, could anyone in Redmond blow their nose?

We've upped our optimizations, so up yours! (0)

Anonymous Coward | about 7 years ago | (#20364055)

I spent a few hours un-optimizing the optimization services, etc.. in Vista to get it to run semi-smooth on a 1 gig of memory "built for vista" system this last weekend. There is still disk access when the computer is fully booted and entirely idle, that I can not get rid of for some reason. I suspect alot of R&D went into several layers of the optimization process, probably mostly because Vista is a 800 lb hog, and the network/audio one will be the first of many to pop up during it's lifetime.

Oh and PS dear MS, pre-loading apps into memory for the possibility they will be launched = bad idea and waste of resource. Ditto on constant indexing.

What a Load of... (5, Insightful)

Nom du Keyboard (633989) | about 7 years ago | (#20364079)

Apparently they believe an almost 90% drop in networking performance is 'slight,' only affects reception of data, and that this performance trade-off is necessary to simply play an MP3.

What a load of utter Crap! If such a trade-ff was ever necessary, then we would have been seeing it in Win XP as well, and obviously we don't.

Vista networking is broken! Try copying over files from your XP machine on a mapped drive if you don't believe me. And audio/video functions in Vista are equally broken. And I bet its for the same reason: Kiss-Up To Hollywood DRM.

Microsoft has caved to the almighty Hollywood dollar, and with Vista you're pwned more than ever!

It's the New and Improved Anti-Piracy (5, Funny)

Tom (822) | about 7 years ago | (#20364117)

You see, they couldn't stop people from cracking DRM and copying music. And they couldn't stop people from going online and sharing their music. But, Billy has one last ace up his sleave: You can't do both at the same time! There! Ha!

What? (1)

Monoliath (738369) | about 7 years ago | (#20364125)

"Microsoft states that 'some of what we are seeing is expected behavior, and some of it is not'"

If it was expected...then why didn't you fix the 'some of it' that you were expecting...before it happened?

Thats quite an odd comment for them to make...

All MP3 Players? (3, Interesting)

Nom du Keyboard (633989) | about 7 years ago | (#20364135)

So does this affect all Windows media players (e.g. WinAmp), or just WMP? Could be a great argument to jump ship to non-MS software.

everything works for me (0)

Anonymous Coward | about 7 years ago | (#20364163)

File transfer to/from a Samba system while streaming music from teh same Samba share. no drop in performance.

Either stupid or jerks. (1)

dtmancom (925636) | about 7 years ago | (#20364243)

Most IT peeps I know would be fired for writing and putting into production an app that hogged hardware resources.

They are either incompetent, or it was on purpose and there is a reason.

I haven't seen a performance hit. (1)

Charcharodon (611187) | about 7 years ago | (#20364257)

I've been streaming everything from MP3's all the way up to HD-DVD's accross a 100bT wired LAN with no problems.

What I have seen though is one of my machines absolutley insists on connecting as if it were on a public network everytime I restart it. In short you can do little or nothing until you change it back to private, since Vista immediately circles the wagons and refuses to let anything work because it's scary to be out in public. It has been driving me nuts, I can't find any setting that nixes this behavior.

I will no longer complain about MS (1)

gelfling (6534) | about 7 years ago | (#20364283)

I have officially stopped complaining or worrying about MS, their code their product or anything else they produce or support. If people think that they're getting a fair shake from Redmond, at this point, no amount contraindication is going to make any difference. My only activism will be to simply work around them.

I run a gaggle of XP machines at home (and one Win95 machine) and this will be the last turn of the MS OS crank for each of them. By the time they are ready for a refresh in the next 2-3 years I will be replacing them with either Freespire or Ubuntu.

You are of course free to do whatever you like. Any comments back to me telling me I'm misinformed, stupid, wrong or silly will be ignored. I no longer care or am interested in what anyone else on the planet has to say about this. Thank you.

What Microsoft said makes sense (0)

microbee (682094) | about 7 years ago | (#20364289)

Linux has struggled for years to have a scheduler that does NOT skip audios when CPU hog processes are running. And it's still not there.

Windows puts much more emphasis on the desktop and audio playback has been much smoother. This comes at a cost, of course, as the article says. This is a simple trade-off between interactivity (for desktop) and throughput (for server).

But the throughput is only mostly affected if you actually are fully using the CPU and network bandwidth resources. For most people it is not the case (especially for the slow Internet). But if you are transferring huge data in a LAN, this will show up.

Of course the impact may be not necessarily so big, but by design I don't think it's wrong. It's just a trade off.
Load More Comments
Slashdot Login

Need an Account?

Forgot your password?

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>