Linux 2.6.20-rc6 Kernel Performance

Michael writes "The Linux 2.6.20 kernel will feature KVM support, Playstation 3 support, and a variety of other improvements. With the Linux 2.6.20-rc6 kernel out the door, Phoronix has written a performance comparison of the Linux 2.6.20-rc6 kernel against the 2.6.19 and 2.6.19.2 kernels in a variety of benchmarks."

Comments

PS-3

[kevin_conaway]

Why is playstation support being included in the kernel? Is that really necessary?

Furthermore, the article didn't exactly make it clear what the support is. Can anyone clarify?

Re:PS-3

[Anonymous Coward]

Why is anything in the kernel tree? Jeesh -- why don't you complain about the whole gamut of processors included. Just because it's supported doesn't mean you have to build for that arch. To each his own -- pick the proc(s) you need.

Re:PS-3

[jimstapleton]

I think that means that it is bootable on a PS3. This kind of thing would only be included if it was compiled for a PS3, and as for "is it required", only if you want to run arbitrary distros on a PS3, which there are people who'd want to do that.

Re:PS-3

[qwertphobia]

Why is playstation support being included in the kernel? Is that really necessary?

Yeah, don't forget why most folks start tinkering with Linux in the first place.

• We love to tinker
• We want closer access to the hardware
• Somebody told us we can't, so that just makes us want to all the more

All three apply to the PS3, as far as I'm concerned!

Re:PS-3

[Ultra64]

Why is playstation support being included in the kernel?

Why is there x86 support in the kernel? why is there PowerPC support in the kernel?

To make linux run on these systems. Duh.

Re:PS-3

[Bluesman]

I bought a PS-3 for the sole reason that I want to run Linux on it to use as a cheap, quiet server, and play with the Cell processor, which I think should be pretty fast for DSP and software radio applications.

I'm pretty excited about the Cell, and the Playstation is an incredible value for a small form-factor computer that you can put next to your TV without having fan noise be a bother.

Why not support it in the Linux kernel?

Re:PS-3

[0racle]

Who told you you couldn't put linux on the PS3?

Re:PS-3

[misleb]

I must admit that I was also little puzzled by "PS3 support in the kernel." For some reason my first thought was that you could play PS3 games under some kind of kernel based emulation. So this is a "duh" moment for me as well.

-matthew

Re:PS-3

[Anonymous Coward]

Why was this modded redundant? It was the first comment in the article!

Re:PS-3

[Anonymous Coward]

Because at the very least by the end of the generation tens of millions of people are going to have a shiny new piece of hardware they can and many will be willing to install Linux on.

Re:PS-3

[Lord Bitman]

you bought the PS3 to be a cheap server?
1) Server of what exactly?
2) How's that workin' out for you?

Re:PS-3

[Bluesman]

1) A file/subversion server for my home network.
2) It's not, yet. It's arriving today via UPS.

And the main reason I bought it was not as a server, although that's certainly a benefit. I'm more interested in development on the Cell.

Re:PS-3

[MikeBabcock]

Did you miss something? Go check the PS3's specs aside from RAM and get back to me about the price/performance for server workloads.

Re:PS-3

[Lord Bitman]

I was all ready to do the same 'til I heard $800.

Re:PS-3

[Rodness]

Or you can buy a Mac Mini for 600, declare immediate victory, and have actual warranty support.

Re:PS-3

[Anonymous Coward]

> I'm pretty excited about the Cell, and the Playstation is an incredible value for a small form-factor computer that you can put next to your TV without having fan noise be a bother.

You're bound to be disappointed. It certainly has a fan. And the aftermarket intercooler you'll need to keep the thing cool enough to run continuously is going to be pretty loud.

Re:PS-3

[Hitto]

- Where's the tinkering involved? Don't take this the wrong way, but today's linux distros install themselves if you ask me. Oh, you mean, managing to make anything prettier than e17 run on a 256-megs-of-ram-machine? English isn't my native language, but I don't call that "tinkering", more like "believing in magic".

  - Accessing specific parts of the hardware is just as crippled on the PS3 as it is on the PS2. Hopefully, this update will allow us to bypass sony's fucktardery.

  - So making it a big selling point and advertising this feature countless times in countless slashvertisements ("A CELL PROCESSOR BASED LINUX, FORGET ABOUT OUR ROOTKIT, YOU CAN EVEN RUN FOLDING@HOME ON IT!!!") means "DO NOT INSTALL LINUX ON THE PS3, PLEASE, YOU DASHING REBEL, YOU"?

Re:PS-3

[Anonymous Coward]

How many Cell cores are enabled on the Mac mini? I heard 1 was disabled on the PS3. I'm sure Apple can do better than that.

Re:PS-3

[Hackeron]

why is this modded as flamebait??

Re:PS-3

[Anonymous Coward]

Why has it been modded up "insightful"? If anything it's just trolling...

Re:PS-3

[mjsottile77]

...and no cell, which was the point of the parent poster buying the PS3 to run linux in the first place.

Re:PS-3

[ChrisA90278]

Why support the Playstation? Because it's cool to be able to run linux on the Sony Playstation. Game consoles make great computers because typically the makers sell these things at a loss hoping to make money on the games. So you can get a computer at a lower price then you otherwise could. These new generation consoles are actually very powerfull computers and Linux lets you use them for non-gamming.like say a robot controller

Re:PS-3

[Anonymous Coward]

I bought a PS-3 for the sole reason that I want to run Linux on it to use as a cheap, quiet server

And the main reason I bought it was not as a server

Huh?

Re:PS-3

[Anonymous Coward]

Except, it was Sony that wrote the code to allow Linux to run on the PS3. And it only runs on their hypervisor - we don't have direct access to the hardware (you won't see Compiz running on the PS3 - it's only usable for plotting ICBM courses and other scientific tasks - ask Persia), and we won't until the PS3 is cracked.

Re:PS-3

[ourcraft]

ok ok i want a tuner card that fits this box-- is there one? this is perfect

gosh - quiet enough - power - finaly the right box for tivo replacement myth box!

No really lets do this -

Can I help? I don't code well enough for this . . . but I could test and... someone help me out here, I _want_ to contibute

Re:PS-3

[644bd346996]

How many cell cores are used by your httpd?

That's what I thought. Troll!

Re:PS-3

[Anonymous Coward]

YDL give real support for their disto on the PS3. Installing Linux on the PS3 does not invalidate your Sony warranty, and they actually contacted YDL for their PPC expertise to get Linux on to the PS3 several months before it was launched. The PS3 has 7 cell processors, and a blu-ray drive. Last time I looked, the mini had neither. And no, I'm not a Linux/sony zealot and have a mac pro with 17" powerbook. I also have fun with a PS3.

Re:PS-3

[drinkypoo]

Did you miss something? Go check the PS3's specs aside from RAM and get back to me about the price/performance for server workloads.

First of all, you cannot discount the importance of RAM. For typical server loads, it's dramatically more important than, say, CPU.

Second, the PS3 is a horrible deal in terms of a server. The SPEs, which give it basically all its power, will be virtually unutilized in any typical server context. The Processor is about equivalent to a mid-to-late Pentium III. I/O bandwidth to the hard drive might be good (I have no idea) but you cannot add any significant hardware like a RAID controller. The ports are 4xUSB2, and there's no firewire. USB adds significant processor overhead while transferring data, so you're basically buying yourself a server without any useful expandability. $500 (20GB) or $600 (60GB) is an absolutely terrible price for what you are getting in the PS3.

I understand buying one for experimentation with the Cell, although of course I think you are a bad corporate citizen for supporting Sony by buying their products. Then again, if you never buy a game for the unit, Sony loses money on you... Given the price of the unit, Sony will probably never get the system to be profitable during its significant lifespan. But face facts, the PS3 is not a credible server and never will be. If you just want to shovel some files out to some clients, its processing power is overkill and its I/O is lacking. If you just wanted to hand some mp3s to some clients, a linksys (or similar) cheapie-NAS product would serve you better.

Re:PS-3

[Anonymous Coward]

Why is playstation support being included in the kernel? Is that really necessary?
It's a typo. they meant PS/2

Re:PS-3

[nschubach]

What are you talking about? My PS3 has run non-stop for about 2 months now except the reboots for updates. You obviously have no idea.

Re:PS-3

[deceased comrade]

The man said we couldn't.

Re:PS-3

[Fordiman]

Special drivers for PS3 hardware? If you don't need 'em, don't compile 'em. If you probably wont need 'em, compile 'em as modules.

Cool thing about the Linux Kernel; it's got drivers for a whole RANGE of things you'll likely never use. But if you do, they're there.

Re:PS-3

[Fordiman]

He's not trolling. Note that GGPP said 'I want to play with the cell processor'

The fileserver isn't the only goal, otherwise any random lump of hardware would do.

Re:PS-3

[Anonymous Coward]

And no, I'm not a Linux/sony zealot and have a mac pro with 17" powerbook. I also have fun with a PS3.

Yea, recompiling your kernel is loads of fun kids. In fact, you can use the gamepad to play Freecell in another window while it's compiling... hehe just kidding, the gamepad probably isn't supported under Linux. Sheesh, just buy a god damn $299 Dell if you want a Linux box and buy a $250 Wii if you want a gaming system. PS3 sucks.

Re:PS-3

[Lord Bitman]

So, not as a server, obviously not to be cheap...
I have a rock that makes even less noise than the PS3, maybe it's not too late to cancel the PS3 order- I'll even sell my solution for less. :D

Re:PS-3

[Trogre]

So tell me, when you boot up your kernel how many penguins do you see?

Inquiring minds want to know. Thanks.

Re:PS-3

[manno]

Because it was done in a very impolite way. He could have take the opportunity to politely explain what it means to build PS3 support into the kernel, to some one who's obviously ignorant about it. Instead he decided to fly off the handle. ...I wonder why Linux hacks get labeled elitist snobs?...

-manno

Re:PS-3

[solafide]

And e17 isn't pretty enough?

Re:PS-3

[Gulthek]

rude != flamebait

Re:PS-3

[Mongoose]

I take you never worked on PS2 RTE or PS3 Hypervisor? It's not crippled at all, and in fact you can write all the Cell code you want from PS3 Linux. IBM and others provide SDKs and introductory articles on writing and managing SPE code bases. If you want to learn how to do the future of development then you should jump at the chance. We're never going back to single threaded models ever again.

The only current restriction is there isn't accelerated OpenGL from the RSX. You can write an OpenGL ES implementation for Cell and get pretty good performance. I ran OpenGL on top of just the VUs on PS2 RTE and got good enough performance to get my TombRaider reimplementation running at a good framerate for a console. I even had enough memory to fit the PC game paks into memory at the time. My point is so what if you don't have OpenGL provided by RSX. You can still do a software implementation optimized for Cell. You can do a lot more than you think with what is provided so far.

When I see fanboys like you marked 'Insightful' I fear for young teens learning anything. I wonder what you consider 'real development'. This is one of the few ways you can learn streaming / distributed / realtime development techniques on an embedded system at an affordable price. Have you even read any job requirements lately? People already drool over these skills. If you're not a developer then please don't speak about issues you don't even understand. You should be rated 'Funny'.

Re:PS-3

[Pingla]

The PS3 has got one 'Install other OS' and this is said to be specifically for Linux. So point three does not really apply.

Re:PS-3

[Trogre]

(Score:3, Funny)

What? I was being serious!

When the linux kernel boots up these days, at CPU detection time you see at least one little tux penguin icon in the top-left corner of the screen, one for each processor it finds. So in a Duron box you see one penguin, and on a 2-way dual-core Opteron machine you see a row of four penguins. /proc/cpuinfo will give you the same information post-boot, but it's not as pretty.

I was just curious how many cell processors the YD Linux kernel was going to pick up. All seven that are active in the PS3 or fewer.

Re:PS-3

[canci]

Why having PS3 support? Hmm... the PS3 software locks the DVDs to a certain standard resolution and you cannot watch compressed video. Furthermore, filters and stuff also cannot be applied in the PS3 software. As you can imagine, any Linux distro would let you do exactly that. Of course, installing OpenOffice on it is a bit funny, but imagine having MythTV along with an external DVB card you plug in via USB... that makes a great media centre, and the pricy PS3 has to pay off somehow.

Re:PS-3

[BrokenHalo]

rude != flamebait

Actually, it probably does. If you want to start a fight with someone, one of the best ways is to be rude to him.

QED.

Re:PS-3

[Anonymous Coward]

Not tinkering? How about tinkering like porting the kernel?

I'm sorry, but not all of us consider the word "tinkering" to be a user activity like you do, like installing Ubuntu as you seem to suggest. I hear "tinkering", I think of writing actual code.

Re:PS-3

[Bluesman]

I can answer this today since my PS3 is here :-)

On initial boot, you get two penguins. The linux kernel runs on the PowerPC core and one SPE.

After that, you see two yellow dogs and six small penguins, which I assume indicate the other SPE's available. (One is indeed disabled)

So, you get 6 free SPE's to play around with.

Re:PS-3

[Bluesman]

I don't think you'll find a tuner card that would work. (But don't let that stop you from looking!)

But, one exciting possibility may be the ability to decode over-the-air HDTV signals in real time.

Of course, that's an extra investment in exterior hardware capable of down-converting the carrier frequency to something you can transmit over USB, (like the USRP from www.ettus.com) but just the fact that it's possible to do with the PS-3 makes me want to give it a try.

Re:PS-3

[Trogre]

Fascinating. So, for bragging rights, how many whetstones do you get?

See http://fresh.t-systems-sfr.com/linux/src/whetstone _linux.tar.gz:t/whets.c

Re:PS-3

[sethstorm]

Or you can build one of these and not have an underpowered G4. As the unit was practically built up from a board there is no warranty to speak of- you do save a good deal on markup if you look in the right places. Not to mention, the case is whatever you make it, from any country of origin you want source the parts.

That and you can develop for ppc64 natively, not having the expense or heft of the other solutions.

Looks like it got worse!?

[CockMonster]

Not the most scientific benchmarks in the world

Re:Looks like it got worse!?

[IflyRC]

You can't say it got worse! This is /. - your eyes will be pecked out by the beaks of a million penguins!

Re:Looks like it got worse!?

[CockMonster]

They must have forgotten to inline all the functions when they compiled the kernel! gheylordz!

Re:Looks like it got worse!?

[Enderandrew]

Did you only skip to the last page? If you looked over every benchmark, the new kernel had improved performance in almost every test, save for two of the last three.

Re:Looks like it got worse!?

[FuzzyDaddy]

I'd disagree. I'd say the benchmark results show the performance differences in the kernel are so trivial as to be essentially zero. Which isn't a huge surprise, was there any kernel change which was suppose to improve the performance of any of these tasks?

This isn't to say that there isn't a lot of good stuff in the kernel, but mostly what these benchmarks show is that nothing affecting these particular tasks got broken.

Re:Looks like it got worse!?

[Enderandrew]

Fair enough. You could say the differences are minute, but it isn't fair to say performance worsened on the whole. That was my point.

Re:Looks like it got worse!?

[Spacelord]

Did you only skip to the last page? If you looked over every benchmark, the new kernel had improved performance in almost every test, save for two of the last three.
Erm ... to me it looks like the new kernel is performing consistently (but only marginally) better on all tests. Keep in mind, on the LAME tests, a lower score means better performance. Not that the whole thing is very scientific of course. What about multitasking efficiency for instance?

Re:Looks like it got worse!?

[Enderandrew]

Personally, I think they shouldn't have tested on a laptop with a 5400 RPM HDD.

I'd go with a system that spouts pretty fast dual-channel memory and a fast HDD and focus heavily on I/O tests.

Wasn't http://members.optusnet.com.au/ckolivas/interbench / designed with this in mind?

Or http://ck.kolivas.org/kernbench/

I'd rather see interbench scores than FPS.

Re:Looks like it got worse!?

[Anonymous Coward]

Did you only skip to the last page? If you looked over every benchmark, the new kernel had improved performance in almost every test, save for two of the last three.

I'm having a hard time finding that in your post.

Re:Looks like it got worse!?

[hackstraw]

If you looked over every benchmark, the new kernel had improved performance in almost every test, save for two of the last three.

I calculated differences in the range of 0.42% to 2.67%

Which in my eye are the same, which is what I would expect.

Also, these tests were on a laptop.

I love benchmarks and all that, but WTF?

Linux is Rubbish

[Anonymous Coward]

Now that Vista is out I see Linux taking a quick dive into Commodore Country. Good Riddance.

Great, now linux...

[Anonymous Coward]

The Sony Playstation 3 support in the 2.6.20 kernel is coming because of Sony engineers contributing the patches, which add machine-specific support for various items.

Great, so now Sony is starting to put their rootkit^H^H^H^H^H^H^Hcode into the Linux kernel now...

Re:Great, now linux...

[Stephan Seidt]

You mean the $sys$rootkit?

So wait..

[Anonymous Coward]

All it takes to get a /. front page link to my ad-word laden website is to create a few bar graphs showing that nothing has changed in the last few kernel revisions and add 2 paragraphs of filler text?

Re:So wait..

[Anonymous Coward]

All it takes to get a /. front page link to my ad-word laden website is to create a few bar graphs showing that nothing has changed in the last few kernel revisions and add 2 paragraphs of filler text?

You could also add some remarks about Vista and global climate change, but yeah - basically bar graphs should be enough. Or pie chart. If you really want to troll Slashdot, make them link to Power Point files.

Re:So wait..

[Anpheus]

Powerpoint files accompanied by PDFs and a video requiring the latest release of Flash.

Is this a really a RELEASE CANDIDATE or a beta?

[Anonymous Coward]

I remember the good old days when "RC" meant "Release Candidate" and didn't necessarily mean "It's a Beta and we want you to test it out"
Microsoft Vista: I'm looking a you.

So, does Linux 2.6.20-rc6 really mean it's a stable release candidate that I can copy onto all of my servers which control the nuclear missles in the continental United States, or is this just a beta and I should wait a week?

Re:Is this a really a RELEASE CANDIDATE or a beta?

[tolan-b]

Well it's a release *candidate* so you certainly shouldn't install it on mission critical systems no. The point of an RC is that it's believed to be 'complete' but should still be tested before use in production.

Re:Is this a really a RELEASE CANDIDATE or a beta?

[Knuckles]

So, does Linux 2.6.20-rc6 really mean it's a stable release candidate that I can copy onto all of my servers which control the nuclear missles in the continental United States, or is this just a beta and I should wait a week?

This is an RC by the core kernel team . Once the release is final, you should still interpret it as being "released to the distros" for further testing and stabilization. All critical servers should stick to the kernels provided by their distros, unless they can afford extensive testing on their own.

What the...

[Jethro]

So the bottom line here is that they're almost exactly the same?

Re:What the...

[ZachPruckowski]

Well, that's good. The whole point is that 2.16.20 adds features, and manages to do so at basically no cost. It would have been reasonable to expect such additions to inflict a minor speed penalty, but there was no penalty. This is a situation where nothing speaks far louder than something.

Re:What the...

[joshetc]

Yeh I was a bit confused as to what they expected to change. Isn't that the reason its going from 2.6.19 to 2.6.20?

Then again I'm sure they made some decent $ out of all the friendly visitors they have to their website now...

ThinkPad?

[Anonymous Coward]

Is this a joke?

He's running kernel benchmarks on a laptop?

Looks like half the things he was measuring were I/O bound? On a laptop?

Phoronix.... more like Moronix.

Re:ThinkPad?

[Zapman]

Yes, he was largely doing things that were IO bound, on a platform that's notorious for having bad IO performance (a laptop).

But, there were some IO changes. I haven't run the numbers to see if they were statistically significant changes, but tests that show improvements in such a 'poor case' scenario are useful...

Re:ThinkPad?

[Anonymous Coward]

Remember the kernel is handling the disk/memory io.
It's not such a bad thing to test as kernel io results are kinda more useful in real life than just adding 20000 integers or whatever.

Re:ThinkPad?

[beh]

Why should that be a negative point, as long as ALL comparisons were made on the same machine?

While the potentially slower disk in a laptop might reduce the overall speed - the negative impact of the hardware should be equal on all three tested versions, since they all run on the same hardware.

The point of the comparison would be just as valid, if ALL tests were conducted on some old Pentium II box - as long as it's the same machine/identical machines in all three tests.

Article is vandalised

[victim]

I tried to read the article, but someone has vandalized it with double underlined words all over the place and annoying popups when your mouse slides over them. I closed the window.

Re:Article is vandalised

[gerrysteele]

Yea, they pissed me off too. I've seen articles from that site on several news syndicators and each has been crappy amateur and annoying.

Re:Article is vandalised

[sjaskow]

Um, be a good net citizen and block kontera.com with Adblock or Adblock plus. You are using Firefox, right?

Hell, Ad Block Pro is _so_ enthusiastic about it, it almost feels like the days before banner ads. :)

Re:Article is vandalised

[ajs318]

What are you talking about? Looks fine in Konqueror, no popups or nothing. Just the crappy double-underlining thing.

I'm also running through a Squid proxy that blocks all known advertising sites.

What a waste of time

[Duncan3]

Since the article doesn't have any content, I assume this was a badly disguised slashvertisement? None of those are even kernel benchmarks.

Stop the bullshit ads or just shut /. down already. You're not even trying to compete with sites like Digg are you.

Re:What a waste of time

[Anonymous Coward]

And who wants KVM to be Kernel Virtual Machine? Most people use that to refer to Keyboard, Video, Mouse. This in usually in conjunction with KVM switches or KVM extenders.

Re:What a waste of time

[Frosty Piss]

You're not even trying to compete with sites like Digg are you.

No, I don't think they are. Should they be? Why?

They used games for benchmarking a kernel?

[Ant P.]

Seems pretty pointless. It'd be more interesting if they threw a few NT kernels in there though...

Somebody owes me two minutes.

[Kadin2048]

So the bottom line here is that they're almost exactly the same?

Yeah, that was a totally worthwhile read, no?

Let me give everyone else the bottom line, and save you two or three minutes of your life, that you'll otherwise never get back:

Sony Playstation 3 support and Kernel-based Virtual Machine support are among the exciting features in this release. From today's testing in our environment used and set of benchmarks, there were no definitive performance gains or losses seen throughout the set of tests.

Now, back to our regularly scheduled Slashvertising....

Re:Somebody owes me two minutes.

[Atzanteol]

Next: Can bees think? A new study shows that no! In fact, they cannot...

Not really meaningful

[fullpunk]

The values are so close, they should have run it many times to at least get a variance and know if those minor differences are "consistent".

Agree with other posts

[the_humeister]

Not the most scientific. At least give us a standard deviation or even a range of what the results are. There's a slight difference, but are they statistically significant? Can't tell with the data provided. And given how close the results are, I don't think it matters.

Bottom Line

[shirizaki]

With the Linux 2.6.19 kernel coming out last November and only two additional releases in the 2.6.19 branch, the Linux 2.6.20 kernel is certainly coming quickly. Linus Torvalds had mentioned in the 2.6.20-rc6 release announcement that this is likely the last release candidate. However, even with this quick kernel release coming the features are definitively impressive. Sony Playstation 3 support and Kernel-based Virtual Machine support are among the exciting features in this release. From today's testing in our environment used and set of benchmarks, there were no definitive performance gains or losses seen throughout the set of tests.

It's nice to get features without sacrificing performance. The added PS3 support would nab those ubuntu people to put it on PS3. Not only that, but yellow dog might get some competition if some peoepl decide to make their own PS3-based distro with all kinds of extras.

Why not?

[brunes69]

It's support for the cell, and some PS3 hardware.

Why would it not be included? If the kernel is still shipping support for 15 year old legacy ISA hardware (yes it is) and Cyrix X86 optimization s(yes it is), it can include support for the PS3, which is likely more in use than either of the above.

There is support for hardware in the kernel that is so obscure that there are probably less than 100 people in the world still using it. There's nothing wrong with this - this is why Open Source beats closed source for overall hardware support - as long as someone is around using it, and someone else maintaining it, there is no reason to remove support for it.

Re:Why not?

[steveha]

There is support for hardware in the kernel that is so obscure that there are probably less than 100 people in the world still using it.

I attended FreedomHEC in Seattle last year. Greg Kroah-Hartman gave a talk, and one point he made was that there are devices supported by the Linux kernel that are literally known to have only one or two users in the whole world; we are talking devices that are so obscure that only one or two people are known to even possess the hardware.

The point he was making is: if you make some hardware, and you are wondering whether your device is too obscure for Linux to accept drivers for it... don't wonder, just submit the drivers.

steveha

Re:Why not?

[VWJedi]

as long as someone is around using it, and someone else maintaining it, there is no reason to remove support for it.

Someone else maintaining it?! Wouldn't the person(s) maintaining it typically be a subset of the persons using it? I would imagine most obscure hardware gets supports because someone thinks, "I really wish Linux supported this X that I own. I guess I'll have to write my own drivers."

I don't know about you, but I wouldn't spend my time maintaining support for hardware I don't personally have access to. Testing is a bit tough...

Re:Why not?

[nschubach]

But my Linux does support X...


Sorry, I had to.

Re:Why not?

[VWJedi]

Yes, but we're talking about hardware X. Linux currently supports only the software version.

Re:Why not?

[runderwo]

Such as? I have hardware where the already existing driver has been removed from the kernel because supposedly there aren't enough users to justify maintaining it. Also I have had hardware where the driver has been rejected from the kernel because the hardware is "ugly" or the driver could be done in userspace instead (regardless of whether or not userspace is the right approach for the particular device).

Re:Why not?

[ady1]

Mine supports it three times in a row.

Create the next gen gaming machine?

[Rukie]

Personally I do not own any gaming consoles, but I do love to play games on my linux machine. If we can make a large gaming society on linux, we may start to get more PC vendors interested in linux, and supporting linux. The more I think about it, the more I think this is a great idea.

Regarding Playstation Support

[Kadin2048]

Does anyone know how much of the PS3's hardware is actually supported? When you run Linux on Cell, is it actually using all of the Cell cores, or is it just using the main (PPC-like) one?

It seems like Cell is probably going to be a lackluster performer, if only the single main processor is used; at that point it's just like using a 3 or 4 year old PowerPC system. But if Linux can support its additional hardware and coprocessors, it seems like you could do some neat stuff with it; I'd think that you could make a nice media-PC frontend on it, for pushing HD video around.

Seems like getting software to take advantage of it, would require changes both to the kernel, and also to GCC, in order to produce optimized binaries for it, not to mention various pieces of software themselves (rewriting for greater parallelizability).

Still, it's a neat hardware platform (that's about all I have nice to say about it, actually), and it's a good bet that at some time in the future, they'll be available inexpensively on the used market. Anything that starts the process of getting better support now, seems like a good thing to me.

Re:Regarding Playstation Support

[Anonymous Coward]

7SPE's are accessible via Linux, as long as you use the Cell BBE SDK..

Re:Regarding Playstation Support

[Enderandrew]

The only thing that is limited is GPU support. Sony doesn't want you running pirated or homebrew games on it, so now graphics hardware acceleration (until someone writes an unofficial driver).

Re:Regarding Playstation Support

[drinkypoo]

Does anyone know how much of the PS3's hardware is actually supported? When you run Linux on Cell, is it actually using all of the Cell cores, or is it just using the main (PPC-like) one?

Cell as implemented in the PS3 has 8 cells. One is disabled (probably due to poor yields when demanding that all 8 be working.) In Linux, one is devoted to kernel tasks. That leaves you with six Cell SPEs to work with besides the PPC PPE.

Seems like getting software to take advantage of it, would require changes both to the kernel, and also to GCC, in order to produce optimized binaries for it, not to mention various pieces of software themselves (rewriting for greater parallelizability).

Well, yes and no. The real problem is that the SPEs are only good for vector data. Anything else requires that you underutilize them. For instance if you have just two numbers and not a whole matrix to multiply, it takes equally long - you just have one useful result and a bunch of useless results that you didn't want. So certain kinds of tasks will be easier to optimize on the SPEs than others. But in many cases you can probably get good results by just using libraries... for instance if libz and libm were accelerated, that would probably make a big difference. Likewise for widget libraries, sound processing libraries, 3d...

3d brings us to the other point, which is that Linux runs in the PS3 "hypervisor" environment and you do not have unfettered access to the video hardware. I don't know precisely what you're not allowed to do that you can do in the commercial environment though; I've never seen a complete description of that.

Re:Regarding Playstation Support

[eno2001]

Well... I saw a video on Youtube of a guy booting Fedora Core 6 on a PS3. When it booted, two big Tux penguins were displayed indicating dual CPUs. Then after a bit of booting six more smaller Tux penguins appeared beneath the first two. So I suspect all eight cores are in use.

Re:Regarding Playstation Support

[morgan_greywolf]

Does anyone know how much of the PS3's hardware is actually supported? When you run Linux on Cell, is it actually using all of the Cell cores, or is it just using the main (PPC-like) one?

Cell as implemented in the PS3 has 8 cells. One is disabled (probably due to poor yields when demanding that all 8 be working.) In Linux, one is devoted to kernel tasks. That leaves you with six Cell SPEs to work with besides the PPC PPE.

You didn't answer the parent's question completely, I think. Which cell is the kernel using (I'm assuming the PPC PPE), and more importantly, does the PS3 support in the Linux kernel enable access to the Six Cell SPEs in anyway, or are you basically on your own.

3d brings us to the other point, which is that Linux runs in the PS3 "hypervisor" environment and you do not have unfettered access to the video hardware. I don't know precisely what you're not allowed to do that you can do in the commercial environment though; I've never seen a complete description of that.

Seems like that defeats the whole purpose doesn't it? PS3 is all about the 3D graphics.

Re:Regarding Playstation Support

[tlhIngan]

The only thing that is limited is GPU support. Sony doesn't want you running pirated or homebrew games on it, so now graphics hardware acceleration (until someone writes an unofficial driver).

I've played with PS3 linux. I can tell you, the hypervisor is just that. It virtualizes the PS3 hardware. About the only thing Linux has "raw" access to (which could also be virtualized) are the USB ports.

The hard disk must be PS3-formatted before Linux will see it. Otherwise the hypervisor will not see it and make it available.

BTW: /dev/sda - hard disk, if available (else this node is the following devices.) /dev/sdb - flash memory - configuration area storing the bootloader (kboot), and a few configuration flags /dev/sdc - Memory stick, I believe /dev/sdd - SD Card /dev/sde - CompactFlash card /dev/sr0 - blu-ray drive.

The hypervisor is a lot like VMWare/Virtual PC/etc. I suspect the Power Processing Elements aren't even fully accessible and that the hypervisor is trapping everything and passing it on as appropriate, like virtualization software you run.

BTW, the virtualization also causes some issues. When I bought a new hard disk for PS3 Linux, it had bad sectors on it (I returned it in the end), but instead of the usual IDE error messages (DriveError) or SCSI errors (with media sense keys), you get nothing, other than a generic "I/O Error reading sector XXXX", which causes the filesystem in use to suddenly go read-only (not sure if ext3 did that or if the hypervisor just disabled the ability to write to the disk - I never had many bad disks with ext3). Basically, you don't even know it's a bad sector as it isn't reported. I suspected it when I could get dd to consistently put the filesystem into read-only mode 16GB in. Another system helped prove the point.

The video hardware is identical - it's virtualized the same way. It's not a driver issue - it's just that Sony has virtualized the video hardware away, and there's no direct access available. Heck, there aren't any WiFi devices accessible either - not for lack of a driver, but that Sony didn't make the WiFi hardware accessible.

Re:Regarding Playstation Support

[acidrain]

With the exception of the SPU, most modern hardware spends almost all of it's time on cache misses and branch stalls. The spu however, doesn't have a deep pipeline, or have cache misses, meaning it gets a lot more done than the PPU even while running non-vector math code. Just because you haven't switched up your code to take advantage of vector math optimizations doesn't make it under-utilized, it just means that you skip past the typical bottle-neck and now vector math *may* be your next bottle-neck.

However, programming for only 256k ram with a modern workload is hell. Once you have a task that doesn't naturally stream via DMA, and requires you to mangle your data structures and algorithms to DMA tiny buffers around, well then you are in the suck. Think 3x programming, debugging and overall lines of code. Forget nice deep call stacks, you don't have code space for that, instead you are going to spend your time juggling buffers of indices to things that aren't in local memory.

Assembly optimization is the least of your SPU utilization problems. Just getting code and data to fit is.

Re:Regarding Playstation Support

[eno2001]

Here is the link to the video I mentioned above... Definitely not faked.

Re:Regarding Playstation Support

[drinkypoo]

You didn't answer the parent's question completely, I think. Which cell is the kernel using (I'm assuming the PPC PPE), and more importantly, does the PS3 support in the Linux kernel enable access to the Six Cell SPEs in anyway, or are you basically on your own.

This paragraph proves that you do not know what we are talking about.

The PowerPC in the "Cell" processor in the PS3 is not, repeat NOT a "Cell". It is known as the PPE, or Primary Processing Element (IIRC.) The actual Cell processors in the PS3 are known as the SPEs. I forget what the S stands for, maybe synergistic or something like that. I honestly cannot remember and the information is out there so YOU can look it up :)

The chip in the PS3 has one PPE (a PowerPC with VERY roughly the processing power of a late-model pentium III) and eight SPEs or Cell cores. One of those cores is disabled, probably in order to improve yields. The Linux kernel runs on both the PPE, and ONE of the SPEs. The other six available SPEs are available to the user. Note that all of this information appears in the comment to which you replied, but I am now being more redundant and overusing emphasis in an attempt to get you to actually read it.

3d brings us to the other point, which is that Linux runs in the PS3 "hypervisor" environment and you do not have unfettered access to the video hardware. [...]

Seems like that defeats the whole purpose doesn't it? PS3 is all about the 3D graphics.

Well, I agree that I wouldn't buy one, even if I weren't boycotting Sony. This is hardly the only major flaw; another is that unlike the Xbox 360 which utilizes a unified memory architecture (UMA) the PS3's memory is both physically and logically broken into two pools of 256MB each; one for programs and other resources, and one for graphics. This means that the PS3 has only 256MB (minus whatever hypervisor overhead there is) of user-addressable memory.

There are basically two purposes to using the PS3 for other than its design purpose. One is for scientific computing. For certain types of highly-parallelizable problems, the PS3 is by far the cheapest bang-for-your-buck. Anything that can be broken up into data sets which can reasonably be transferred over 100Mbps ethernet and processed on systems with only 256MB RAM, and which furthermore can be executed as a series of matrix operations, will probably run faster (or for less money, depending on how you look at things) on a cluster of PS3s than any other option available today. Of course, only certain types of data are amenable to this type of manipulation. The other purpose is for use as a media center system. An HD decoder which utilized the available SPEs would certainly be able to handle decoding HD video on the fly (The PS3 does it already, of course, for playing Blu-Ray) and with a little hacking it should even be possible to get the Xbox 360's HD-DVD drive working on it so that you could have one system capable of playing both HD video formats before hybrid players even hit.

Re:Regarding Playstation Support

[Anonymous Coward]

You are boycotting sony for anti-consumer practices but you have no problem buying and promoting the XBOX which is from Microsoft, a company famous for its anti-consumer practices? You are either stupid or a paid shill. My guess is both.

Re:Regarding Playstation Support

[drinkypoo]

You are boycotting sony for anti-consumer practices but you have no problem buying and promoting the XBOX which is from Microsoft, a company famous for its anti-consumer practices? You are either stupid or a paid shill. My guess is both.

Actually, I am purchasing neither, and someone who is not a complete idiot coward would have noticed that nowhere do I suggest purchasing an Xbox 360. I mention it because I feel that Sony has produced a system useless for running Linux aside from the applications which I have outlined and I felt that Microsoft did a better job of making a game console, although of course you cannot run Linux on the Xbox 360 (yet?)

I plan to purchase a Wii, at some later date. Right now I'm concerned with trying to get high-speed internet access in the fucking boonies. Hughes pulled some half-assed wannabe credit report and said there was "not enough information" to give us service (in spite of the fact that unlike me, my lady has excellent credit, and we used her info to apply) and no one else is actually selling service in our area except the VSAT people and having to send data via dialup modem is bullshit.

If you were actually able to comprehend English, you would see that nowhere do I suggest purchasing the Xbox 360. My comments were on technical merits alone.

Next time, learn to read before commenting. And try to grow a pair and log in, too, so I can foe you.

Re:Regarding Playstation Support

[ultranova]

Assembly optimization is the least of your SPU utilization problems. Just getting code and data to fit is.

But isn't that where hand-optimized assembly really shines ? If you really only have 256kB of RAM, you'll want to forget procedural programming and go with goto's; by hard-coding each variable to a specific memory location can you utilize the tiny memory fully and be absolutely sure there won't be stack overflow.

Each layer of abstraction adds at least a bit overhead, so if resources are tight, strip them all off.

Re:Regarding Playstation Support

[nschubach]

I forget what the S stands for

Synergistic

Re:Regarding Playstation Support

[nschubach]

I think the second main processor you see is for the PS2 EE chip. I'm not positive though. The only other thing I could think of is that possibly the SPE does two threads and they split these into two seperate /dev(s).

Re:Regarding Playstation Support

[Fordiman]

"Cell as implemented in the PS3 has 8 cells. One is disabled (probably due to poor yields when demanding that all 8 be working.) In Linux, one is devoted to kernel tasks. That leaves you with six Cell SPEs to work with besides the PPC PPE."

Which makes you wonder why they didn't let Linux's SMP support take over the seven.

Re:Regarding Playstation Support

[cxreg]

About the only thing Linux has "raw" access to (which could also be virtualized) are the USB ports.

Not even that. The USB bus appears to linux to be on top of a PCI bus, which the ps3 does not have.

Re:Regarding Playstation Support

[cxreg]

I think that the big penguins are for the main CPU (2 SMT units) and the little ones are for the SPEs

Re:Regarding Playstation Support

[drinkypoo]

Which makes you wonder why they didn't let Linux's SMP support take over the seven.

No, it makes you wonder. I know it's for the following reasons:

1. Cell SPEs do not have direct access to main memory. They have a 256kB memory space into which data and code must be inserted before anything can be done.
2. Cell SPEs are not the same as the cell PPE. Symmetric Multitasking implies Symmetric CPUs. PPE is not symmetric to SPE.

The Cells are entirely unsuited to general purpose computing. They are only really capable of performing vector functions, and of using those vector functions to (unnecessarily slowly) emulate non-vector functions. Every task that you want to carry out on Cell is going to require intense platform-specific optimization.

It's quite simply impossible to just throw the Cell SPEs into SMP. They don't execute the right kind of code and they don't have access to system resources. The sad thing is that you are going to have to do a lot of data-shoveling with the PPE as a result, so you basically have to figure out how to do almost everything in the context of the SPEs in order to get anything like performance out of the PS3. The PowerPC in the Cell is pretty weak.

Re:Regarding Playstation Support

[drinkypoo]

Assembly optimization is the least of your SPU utilization problems. Just getting code and data to fit is.

But isn't that where hand-optimized assembly really shines ?

Yes, absolutely. Unfortunately hand-optimized code is the opposite of the direction in which programming is going, which is to say, with everything running in virtual machines.

Even today, though, where operating systems and even some programs normally run on the bare metal, we don't typically write very much assembler. Since it is axiomatic that 95% of your optimization occurs in 5% of your code, you want to write everything in a high level language, do some profiling to figure out where you need to optimize, and then go work on that 5%. Even then, not all of your optimization is going to be done in assembler. Some part of it will be done in your high level language, just finding more efficient ways to accomplish tasks.

By contrast, the PowerPC in the Cell can mostly be seen as a traffic cop. Aside from handling things that aren't efficiently passed off to SPEs (like input processing) it's probably going to be spending an awful lot of time passing data to and from the SPEs. And you're not going to be able to take this approach. You're going to have to plan from moment one that you've got a slow (by modern standards) processor with a bunch of very very fast vector coprocessors. You have to submit data to them, wait for it to be processed, and fetch it back. Because they have such a tiny memory space, this will be an endlessly entertaining game of shuffle-the-data. And unless you want to be dumping data AND code to them on a regular basis, you're going to want to find functions for them that they can stick with, rather than re-assigning the SPEs to various tasks.

Programmers criticized the Sega Saturn even before the Playstation came out for having two symmetric processors that they were forced to utilize - to be fair, this was a reasonable complaint given the lack of an operating system. One developer characterized the Saturn as a pile of chips on a board. The PS3 has solved some of these issues; it has a relatively robust toolchain, and it has an operating system that does some of the work for you. But it also has the most complex architecture ever seen in a console system, and that translates into more difficulty for developers. It's incredibly powerful, true. Well, so is a nuclear hand grenade...

Re:Regarding Playstation Support

[Anonymous Coward]

So you have NEITHER box and you feel you are qualified to judge their ability to run linux? And with all that "experience" you then go on to proclaim that the XBOX360 would run Linux better, despite the fact that it cant run it at all? I misjudged you, you are not stupid, you are fucking completely RETARDED.

Re:Regarding Playstation Support

[SpectreHiro]

This paragraph proves that you do not know what we are talking about.

Well, I think that's self-evident, since he's asking a question about it.

The PowerPC in the "Cell" processor in the PS3 is not, repeat NOT a "Cell". It is known as the PPE, or Primary Processing Element (IIRC.) The actual Cell processors in the PS3 are known as the SPEs. I forget what the S stands for, maybe synergistic or something like that. I honestly cannot remember and the information is out there so YOU can look it up :)

The chip in the PS3 has one PPE (a PowerPC with VERY roughly the processing power of a late-model pentium III) and eight SPEs or Cell cores. One of those cores is disabled, probably in order to improve yields. The Linux kernel runs on both the PPE, and ONE of the SPEs. The other six available SPEs are available to the user. Note that all of this information appears in the comment to which you replied, but I am now being more redundant and overusing emphasis in an attempt to get you to actually read it.

If I could offer a couple clarifications (although I'm surely no expert):

1. The PPE stands for Power Processing Element (IIRC).
2. The S in SPE does in fact stand for Synergistic.
3. I've never heard anyone, in any article or any of the whitepapers I've read, refer to the SPEs as Cell processors, Cell cores or Cells. The Cell Broadband Engine is the entire chip, while the SPEs are precisely that... SPEs. The root of the confusion in this thread stems from A) Referring to processing elements as Cells (etc.) and B) Arbitrarily deciding that the term applies to the SPEs and not the PPE.

I can't really blame the fellow for being confused at your reply. I suppose this is a fine example of why people should do their own research instead of asking around on /.

I usually really enjoy your posts, drinkypoo, but, with all respect, in this case, I think you could stand to fling around a little less attitude.

Re:Regarding Playstation Support

[Agripa]

Maybe you could rebuke his argument with a technical analysis of your own instead of executing an attack on his character?

Re:Regarding Playstation Support

[Fordiman]

You, lad, would get modded informative had I not already posted in this area. Thank you!

Re:Regarding Playstation Support

[Fordiman]

That said, though...

Why would Sony do things that way? Without direct memory access - even in 'user mode' or equivalent - I can't think of a single thing for which having eight CPUs would be useful. Why wouldn't they have one Kernel mode CPU that can dole out memory allocations and do the under the hood stuff, and seven others that can ask for RAM ('pleeeeeeeze? It's really important! I need to be an AI in MGS!) and handle the brute stuff.

Seems like a chip designed by a retar- I mean, committee.

Re:Regarding Playstation Support

[drinkypoo]

Seems like a chip designed by a retar- I mean, committee.

I think it was just the most economical way to wrap a bunch of vector processors around a PowerPC core. It's IBM's way of saying "Altivec? Altivec who?"

The architecture is amenable to game development, but it does make portability essentially nonexistent. One might speculate that Sony planned to lock game developers into their platform by making them write code that just won't port to any other platform in use today - you have to rewrite huge swaths of it.

Of course, the developers are not amused. They might have gone alone with it if Sony had come along with the PS3 before anyone else showed up, or even if it had just looked like they would ship the promised number of units. It didn't, they didn't, the PS3 has no chance to survive so it should make its time. Okay, that's not really true, marketing and fanboyism can still save it, but it is very much anyone's race right now as a result of Sony's bumbling and their decision to package blu-ray, and all the logistical problems that has presented.

Re:Regarding Playstation Support

[statusbar]

Most USB chipsets connect via PCI to a bridge to the PCI express port nowadays... So PCI would be involved, I believe...

jeffk

Re:Regarding Playstation Support

[cxreg]

I thought so too, but no.

http://moss.csc.ncsu.edu/~mueller/cluster/ps3/doc/ LinuxKernelOverview.html

USB

PS3 equips industry standard USB EHCI host controller and its companion OHCI host controllers. Although most USB host controllers are PCI devices, PS3 USB host controller exists in the companion chip. The PCI probe routines of Linux are modified so that PS3 USB host controller can imitate PCI device. After initialization, all operational registers of USB host controllers are directly accessed by PPE, so no modification to original Linux USB host controller driver is needed. PS3 has internal high speed USB hub. The USB ports of PS3 front panel is connected to the hub, not to USB host controller directly. This PCI probe modification would be change later to get better device driver maintainer acceptance.

Re:Regarding Playstation Support

[Achromatic1978]

A sterling sale for Open Source - all the people here debating what the penguins mean. So much for "You can just read the source code and know, yourself!" ... or you can ignorantly ponder and debate on /. (not you, specifically).

Re:Regarding Playstation Support

[Fordiman]

"the PS3 has no chance to survive so it should make its time"

For great justice, lauch every Cell!

Pointless article.

[M1000]

Pointless article. Michael Just want ad impressions for its site, and that small useless article... on 3 pages !!!

Re:Pointless article.

['nother poster]

Well, that's three presentations/impressions per person for each ad. Just because he is a greedy slashvertising asshole doesn't meant that he is a total moron. He is smart enough to know impressions mean money, at least for him if not his advertisers.

Linux to remain confined to the maladjusted few

[Anonymous Coward]

So much for the year on the desktop for Linux...

Isn't it just Microsoft-style "bloat"?

[Frosty Piss]

I think it's a big mistake to include things like Playstation 3 support "in the kernel". It distracts from the idea that Linux is a "serious" OS, not some half-baked platform cobbled together by "gamers". Isn't there a better way to deal with game support? Is the kernel of a general purpose OS really the place? Isn't it just Microsoft-style "bloat"?

Re:Isn't it just Microsoft-style "bloat"?

[timeOday]

I think supporting multiple hardware platforms is a good thing, and does not detract from an OS. Especially if the hardware in question has awesome floating point performance. A beefy dual-core processor plus 6 RISC stream processors thrown in? Sign me up. Since the PS3 isn't panning out as a game machine, perhaps Sony should refocus its marketing on the scientific community :) Or port RenderMan to it.

Re:Isn't it just Microsoft-style "bloat"?

[radarsat1]

You misunderstand the Linux kernel ethos. The idea is to include *everything* "in the kernel", but you only have to compile the parts that you want. That way there is a central place to track all changes and maintain compatibility and consistency between all parts of the kernel, without having to set an internal interfaces in stone.
It's not "bloat" if it's only in the source. Simply put, you don't have to include PS3 support in your binary version. In other words, the only way it affects you is a few extra bytes to download when you want to compile it.

Re:Isn't it just Microsoft-style "bloat"?

[simm1701]

Have you ever rolled your own kernel?

You might want to try it sometime as its an educational experiance.

For almost every hardware option you can include whether to build it in, build the module and have the module hooks for it built in or not to include it.

So if you know exactly what hardware you are going to be using you can build a very very small kernel (the theory being it should still be possible to boot a full OS from a floppy, though I haven't tried to do that myself for a while)

If you just want compatability you can build modules for everything, the kernel itself remains fairly small though you do end up with a lot of modules you will likely never use.

Most people go for something inbetween (as do most distros)

About the only way you would get bloat int he kernel is to build everythign built in - and I can't think of a reason anyone would want to do that - ok make that a sensible reason - with geeks the "because I can" argument will always come up :)

Re:Isn't it just Microsoft-style "bloat"?

[Anonymous Coward]

I was waiting for someone who's actually compiled a kernel to say this...

Re:Isn't it just Microsoft-style "bloat"?

[I_can_not_believe_I_]

Given the comments recently about multicore processors being the norm, and the greater push for specialized silicon, optimizing Linux for Cell processors could be a positive step if we see these innovations move into more mainstream use.

Having said that, has anyone benchmarked the performance of the kernel on the Playstation? Is it only at a "it runs" point, or is there actually decent tailoring to the Cell processor, so that it takes advantage of the architecture?

Re:Isn't it just Microsoft-style "bloat"?

[XanC]

This doesn't have a thing to do with games. It's simply another hardware platform for Linux to run on.

Re:Isn't it just Microsoft-style "bloat"?

[blank]

It's a bit misleading to say that it gives the kernel PS3 support. What it does give is Cell support and other PS3 hardware support. The Cell is made for a gaming machine but the design itself is for a more general use. They even have blade servers with them. This is serious Internet Business we're talking about with support from IBM.

Right now you only get frame buffer support so even playing serious Internet games is not really enjoyable. No GPU support yet.

What sane person is going to think that Linux is a gaming platform off the bat? And what is even wrong with that? Is someone going to take IBM less seriously now that they are supporting CPUs that are specialized for crunching numbers and give you stunning real time visuals?

Re:Isn't it just Microsoft-style "bloat"?

[iabervon]

It's not Microsoft-style bloat, it's Linux-style bloat. It doesn't have any effect on the kernel binary unless you enable it. And you can't enable it in an x86 or x86_64 kernel, because it's a PPC platform configuration. Linux-style bloat is that the kernel source tree has everything possible in it, but it only gets built if you actually manage to ask for it, and then it's generally a module and only gets loaded if you actually need it. But it's in the source tree, because developers want to know about as much as possible of the code that might need to get updated if things change or might have bugs or incorrect assumptions.

Re:Isn't it just Microsoft-style "bloat"?

[Klowner]

This binary is HUGE, the idiot programmer must have put comments ALL THROUGHOUT his code!!

Re:Isn't it just Microsoft-style "bloat"?

[Lord Bitman]

Windows supports lots and lots of hardware (different usage of the word "supports lots of hardware" than Linux uses, to be sure). New manufacturers come about and write drivers for their own stuff, and distribute those drivers themselves.

The Linux model is suprisingly backward for something "Open Source". In a world where customizing things is considered the norm, with drivers it's just plain /weird/ to retrieve a driver from a third party. You need to compile something yourself (eek) or hope that it gets included in the mainline.

But then, why should I download code for Steve's Magic USB Vibrator if I'm not even going to use it?

I dont understand the idea of "Well, if you dont want it, don't build it!"
If I don't want to build it, why should I even get it in the first place?

This is a problem which can easily be fixed, may already have been fixed. But for now (or then), it'[wa]s annoying.

Re:Isn't it just Microsoft-style "bloat"?

[rbanffy]

Yeah. Gamers have Windows. Let them play. They may come when they grow up.

As for the PS3, it's an incredibly fast computer for its price. Of course, it's incredibly hard to program, but we don't do such things because they are easy, right?

Re:Isn't it just Microsoft-style "bloat"?

[Anonymous Coward]

What you're missing is the PS3 uses one of the more advanced processors of modern day. It's actively being used in a number of clusters. IBM has plans to deploy it in their largest clusters. WHile the PS3 may be a toy to you, it's the development platform for a number of hpcc folks, myself included. IBM even supplied the IDE kit etc....

Re:Isn't it just Microsoft-style "bloat"?

[Short Circuit]

"this..."

I've been compiling my own kernels for years. He speaks the truth.

Re:Isn't it just Microsoft-style "bloat"?

[Anonymous Coward]

Oh come the fuck on! "Troll"?

Re:Isn't it just Microsoft-style "bloat"?

[vadim_t]

People suggested it multiple times already, but it never gets done, probably because it's complicated.

For example, if you actually compile from source, this is undesirable. If you're compiling from source instead of using your distribution's kernel you probably have some specific reason for it, like wanting to apply a patch. Now what if this patch touches some kernel internals (say, the USB subsystem), and updates multiple drivers? Then applying the patch would fail.

Also, having the full source is a VERY good thing if you just replaced your network card, have no net access, and need to build a new kernel to get it. Then what if you didn't download any other network drivers? Bootstrapping problem there too: if you download drivers, how do you download the modem/network card driver? If you ship those, why not others since they're all in the kernel to start with? Making arbitrary distinctions is strange.

If you use binaries, you again have the same problems. If you have all the drivers installed that takes what, 20MB disk space? And in exchange if you swap the network card, a recent distribution will detect the new one and automatically load it, instead of making you mess with burning a driver CD on some other computer.

Then, Windows has exactly the same behavior! When you connect say, USB speakers (those with an integrated soundcard) they just work, because the driver for them was installed with the OS, even though it was unused at the time. It doesn't ask for the CD, or download anything.

Basically, making it download drivers is just more complication, extra things that can go wrong and less user friendliness in exchange for just a few MB of disk space, which doesn't amount to anything noticeable on a disk bought in the last 5 years anyway. Now if you're for some bizarre reason still booting Linux from a floppy, or work on something embedded that runs on 8MB of flash, then this makes sense, but that's a very uncommon situation.

Re:Isn't it just Microsoft-style "bloat"?

[tinkerghost]

IBM is starting to push out Cell based hardware. That means heavy iron with multiple processors each with multiple types of cores. You know what people are using to learn how to program that? PS3s. You get all the techniques down on a sub $1K chunk of plastic then you migrate those techniques up to $1M+ big iron.

I think if you look at the people contributing to the Cell frameworks & libraries, you're going to find IBM investing heavily in time & lines.

Re:Isn't it just Microsoft-style "bloat"?

[markov_chain]

If I don't want to build it, why should I even get it in the first place?

That's an interesting question, that I believe will come up more and more in the future as the amount of hardware and drivers increases. For now, I think the main reason for the current model is that it makes things simple for the kernel developers, with a minimal impact on the users-- a few extra megabytes of source code. (Users here being the people who compile their own kernels.)

I personally like this distribution model because it is very enriching. I can't count the number of times I went browsing kernel source looking for code examples or designs, and found something interesting in some obscure driver I would never actively go get otherwise. This is very similar to how many Linux distros come with an enormous mountain of applications that cover most things one would ever want to do with a computer, and it gives me warm fuzzies.

It is a very different experience from how commercial OS works. Using any new Windows installation for me always came with an uncomfortable nagging fear of the "feature wall;" there was inevitably something interesting I would want to do with the system that doesn't come with the OS, and costs money. Want to actually modify this Word document? Buy Office. Want to *gasp* compile your own programs? $$$ Visual Basic, Studio, etc. Want to edit photos? Buy photoshop. Oh, you wanted to make drop shadows? You'll also need this random Plugin that costs extra. It always felt like a fundraising dinner or movie theater with their expensive popcorn. I still have bad memories of college where we always fought for a seat at the non-lame Sun workstation that came with cc.

Re:Isn't it just Microsoft-style "bloat"?

[Anonymous Coward]

the only way it affects you is a few extra bytes to download when you want to compile it.

That's not true, the code must have declarations to evaluate if we have XYZ feature loaded wich DOES impact in the performance

Also, it affects in the kernel development since the coder must be aware that a billion of features to watch in order to not to break any of them

Re:Isn't it just Microsoft-style "bloat"?

[LiENUS]

That's not true, the code must have declarations to evaluate if we have XYZ feature loaded wich DOES impact in the performance
Those code declarations are called #defines, and the C preproscessor automatically removes them, the C compiler itself never even sees them

Re:Isn't it just Microsoft-style "bloat"?

[dbIII]

But then, why should I download code for Steve's Magic USB Vibrator if I'm not even going to use it?

Good point - from your comments above you fill that role yourself perfectly.

To be serious - the idea is you don't have to hunt for drivers from weird spyware ridden corners of the net. The people who put together your distro will have most likely compiled the kernel modules for it (all those bits you don't want but might someday) unless it is new, in which case you need to download an updated binary kernel and binary modules or compile it yourself and only get the bits you do want.

You know what?...

[ilovegeorgebush]

...It was so nice, for once, to actually read a benchmark article that didn't have an abundance of tech-related paragraphs that are way to deep and technical. This article had the meat and information I wanted, in nice and easy to understand graphs (I like pictures!!!) and it was quick to read. Thanks, /.

Can anyone explain the PS3 support? Had any experience with it?

Re:You know what?...

[loonicks]

i thought quite the opposite. though, honestly, after seeing a couple of the graphs, i decided not to read the content. comparing application performance on different versions of the kernel seems rather stupid.. like seeing if your car goes faster when you give it nicer seats. consumer application performance is largely dictated by the application code itself and the hardware it runs on. maybe it can handle multi-user I/O and multi-process scheduling better, but I didn't see much of that here.

Re:You know what?...

[Anonymous Coward]

Translation: I'm in cahoots with the author.

Re:You know what?...

[Kadin2048]

YHBT, I think.

(I'm hoping the GP was a troll...I've always assumed that people like that were too stupid to use anything other than phpBB-based boards.)

not newsworthy

[sloth jr]

With a great article title like "Linux 2.6.20-rc6 Kernel Performance", I figured there must be something really notable about this release - and yet, there isn't. Summary: some things a neglible amount faster, some a negligible amount slower. If the "firehose" feature I've seen is anything like a preview of how submitted articles are reviewed for publication, I'd say an important part of this process would be at least a review of the linked content to determine whether or not it satisfies any reasonable criteria of newsworthiness.

Re:not newsworthy

[garcia]

Even if it did have content, I don't consider a Mobile processor a worthwhile CPU to benchmark anything against.

PS3 eh?

[pkcs11]

So support PS3, cyrx86 and other obscure hardware but lets not include things like slightly uncommon LCD monitors, and a myriad of other far more common bits of hardware.
Make way for more sony rootkits!

Re:PS3 eh?

[Anonymous Coward]

Support for LCD monitors in the kernel? Are you fucking dense?
You're looking at the wrong program.

Re:PS3 eh?

[Anonymous Coward]

Oh really, faggot? What is EDID for? Is that not in the kernel?

Lame

[misleb]

I'm not so much worried about the "science" behind the benchmarks. I'm still wondering about the point of the benchmarks. I can't think of a more boring set of benchmarks than comparing minor revisions of the same kernel on the same hardware. That is, unless there was some reason to believe that one would be faster. Somehow their "LAME" comparison seems appropriate. "In this set of benchmarks, what we are comparing is LAME."

-matthew

Re:Lame

[jd]

Oh, I imagine some things have changed. Just not the things they benchmarked. I'll be fair and accept that this was their first attempt at a kernel benchmark, but there's no point in comparing the identical. The vanilla and stable 2.6.19 kernels are fair only if you test the things that make 2.6.20 significantly different.

A better comparison would be against the kernels in the unpatched Fedora Core 6 and Red Hat Enterprise.

Re:Lame

[OldBus]

Surely if you are going to benchmark the kernel, you would compare different revisions (even minor ones) on the same hardware? Otherwise it'd be a hardware benchmark. I think they should be benchmarking on lots of different hardware, but the comparison has to be on the same hardware.

Also, I think they should be comparing each minor revision, not just those where "there was some reason to believe that one would be faster". Only benchmarking if you expect a faster resultis not very rigorous.

I do agree, however, that for those of us not involved in kernel development, a set of benchmarks across minor revisions that show no change are boring and not worthy of a Slashdot article. If you need to know that stuff, you will know where to find it.

Single most pointless article I've ever read

[Anonymous Coward]

I don't understand what any of these benchmarks have to do with the kernel, is it implied that he's benchmarking the scheduler? I suspect not. A slightly retarded pre-pubescent could write a better article than this.

KVM support

[kokoko1]

KVM is another virtualization which make into linux main line kernel one must have latest processors with VT support to play with kvm virtualization. we are using UML from years which is also part of main line kernel thanks to Jdike for maintaining UML. I heard that j.Dike is working on to making UML run under KVM, I am sure this will make UML much faster. I don't know why big brothers Redhat etc only supporting one virtualizaton ie Xen, pity on xen which doesn't make into main line kernel from last two years and i am sure they have already stopped struggling for it :S, look like xen is going death end. In my personal experience xen is PITA. I am sure in end linux will become itself virtual, where no one will need to look into xen.

How about some fucking stability testing?

[Anonymous Coward]

Loading I2C drivers causes drivers that load external firmware (ie ipw2200) to crash when they also load dependency modules (ie arc4, wep).

It doesn't matter how fast it goes if it crashes when you try to use it.

Short answer: no

[Wooky_linuxer]

No. as kernel developers are concerned, the PS3 is just another computer. A heck of a powerful one, BTW, even if it's a wild beast to tame, but I digress. This has nothing to do with MS bloat, since MS only support one major platform in Windows, while Linux is known to run in a plethora of different archs, and the support must be in the kernel for it to work. I understand PS3 support might not have been in the kernel main tree, and possibly that's what you talking about, but there is no good reason not to; this way basically any distro can provide a PS3 version with less effort, and the support becomes standart instead of consisting of different patches. As I said, to the kernel devs the PS3 is just another arch; this has nothing to do with game support either. The PS3 is capable of a plethora of things, and having Linux available allows you to use a PS3 as a "general purpose computer". If whether this leads public perception to think of Linux as a "gamer OS"... that is another story, but I highly doubt it. Anyway, can't be much worse than being a "hacker OS" right?

mo;d up

[Anonymous Coward]

netwOrking test.

A 2% improvement is HUGE

[amorsen]

Kernel developers regularly hunt elusive speed boosts which can only be detected by specialized benchmark. 2% on something as generic as kernel compilation is fantastic.

Of course the tests probably weren't conducted in a sufficiently scientific way, so the measurement error probably swamps the 2% improvement. If it can be independently repeated, congratulations are definitely in order!

Re:I disagree!

[Lord Bitman]

Having all these things "supported" is nice, but I think the idea of constantly piling more and more things into the mainline kernel is A Bad Thing. With the way things are going, it's probably more efficient to download just the files required for a configure script to run, then have /that/ retrieve the things you actually care about, rather than downloading all 9 gigs* of source (*projected for inflation so this post is relevent next week) at once, only to discard most of it.

Actually, that sounds like a good idea. Does anything like that already exist? (I havent bothered to build the kernel in a year or so, but KVM may have me jumping on it.. and I dont know if debian supports my game pad..)

are those effective anyways?

[1800maxim]

Tom's Hardware started using them, I was disappointed, as the site is riddled with ads.

However, turning off JavaScript is helpful. Get Web Developer's toolbar for Firefox which allows you to turn such functions on/off on the fly.

Re:are those effective anyways?

[kwark]

Installing NoScript and creating a whitelist might be easier.

yay, ps3 support!

[Lord Ender]

I can run it on a PS3, but I still can't run it on an Asus A8V motherboard, because there are no working drivers for the onboard SATA controller. Boo.

Re:yay, ps3 support!

[Anonymous Coward]

If a vendor (in this case Asus) decides to not support Linux then you should complain to Asus not kernel developers. One of the biggest misunderstandings in the world of Linux comes from the assumption that support will come for everything.

The reality is that Microsoft is squeezing the hardware vendors even harder to not support Linux. The way they do this is by shifting easy Windows kernel support around to favor a different hardware "partner" if an offending "partner" starts to sleeze around with Linux support.

Case in point is when HP released the standards for PCL6...All of a sudden Microsoft made some sweetheart deals with Dell and Dell started to walk away with HP's lunch.

Case 2 Intel released a C compiler for Linux which gave Linux smp optimizations and a real stab at the lower end server market..bingo AMD stepped up and got lots of help kicking Intel's but. So now Intel has started to make onboard crap device sets (especially wifi and ethernet) that require proprietary onboard driver support. The end result being we are now seeing tons of new hardware that is almost impossible to support under the Linux. The one saving grace is that there will be one huge swack of really good Linux friendly hardware available cheap to geeks in a few years when small businesses are forced to upgrade again by Microshaft and their so called software "partners" like Quicken.

Up until recently Asus has been very well supported by Linux. My old Asus Dual p3 server board is completely supported but now with the advent of the push from Redmond to close up driver support and use more braindead device drivers that require driver loads like Dlink wifi cards and some of the newer onboard ethernet drivers, companies like Asus have been bullied into submission. The only way this can change is if the United States government steps in and finally shoots down the Microsoft hardware cartel.

Re:yay, ps3 support!

[whoever57]

but I still can't run it on an Asus A8V motherboard, because there are no working drivers for the onboard SATA controller. Boo.

I call BS on this. That motherboard was shown to work with several distros in 2005. Another test report confirms this

Re:yay, ps3 support!

[Lord Ender]

Yeah it works fine as long as you only use ONE of the four SATA ports on it. Use any more and your screen gets flooded with driver errors and locks up!

I have tested this extensively. I compiled the latest kernel from scratch. Apparently being able to use only 1 of your four ports is someone's idea of "works perfectly."

Re:yay, ps3 support!

[whoever57]

Look on the newsgroup alt.os.linux.gentoo -- there was a posting just today from someone who has this MB working with 2 disks in a RAID1 configuration. He doesn't use the on-board RAID, instead he uses dm-raid.

Adblock Slashvertizement

[Anonymous Coward]

Add http://.kontera.com/* to your adblock filter to remove the retarded adword crap. Also http://.intellitxt.com/* for other sites that use this crap.

KVM support?

[Vellmont]

Can the creators of this technology choose a better word for it? KVM is already widely known as a KVM switch, Keyboard, Video, Mouse. It lets you connect multiple computers to the same monitor,keyboard and mouse and switch between them.

Choosing the same acronym for this new technology is only bound to cause confusion.

Re:KVM support?

[thewils]

Yeah, especially since I can never get my Belkin KVM switch to work properly with Linux, I always lose the mouse or keyboard. I thought the problem had been fixed now, oh well...

Re:KVM support?

[Trevin]

Since kvm.qumranet.com appears to be slashdotted at the moment, would someone care to explain what KVM means in this context?

KVM is an abbreviation that can refer to:

• KVM switch (KVM standing for "Keyboard, Video, Mouse"), a hardware device that allows a user, or multiple users, to control multiple computers from a single keyboard, video monitor and mouse
• K virtual machine, an extremely compact Java Virtual Machine (JVM) that is designed for small devices and has a tiny memory footprint
• Kernel virtual memory, a BSD library provides a uniform interface for accessing kernel virtual memory images, including live systems and crash dumps.
• Kernel-based Virtual Machine, a full virtualization solution for Linux on x86 hardware, consisting of a loadable kernel module (kvm.ko) and a userspace component
• K. V. Mahadevan (before 1940), a South Indian music composer

Re:KVM support?

[Anonymous Coward]

Kernel Virtual Machine - http://sourceforge.net/projects/kvm/

Re:KVM support?

[Anonymous Coward]

I think you can cat something >> /dev/psaux if your mouse goes haywire. I can't remember what, but happy googling.

Re:KVM support?

[Vellmont]

Yeah, especially since I can never get my Belkin KVM switch to work properly with Linux, I always lose the mouse or keyboard

I had this problem for years until I decided to finally ditch the Belkin KVM switch. Eventually the trick of switching to the text console and back stopped working, so that was the end of the line for the Belkin KVM.

I doubt it's ever going to be fixed. You can buy a good KVM switch these days for $40, I'd do that.

Re:KVM support?

[dbIII]

Choosing the same acronym for this new technology is only bound to cause confusion.

Not necessarily - it is well known that copyright lawyers and the internet both work at intermediate pressure (IP).

The New Inproved Kernel.

[Gno]

Popcorn will never be the same! Now 0.5% faster on average! Don't wait more than 3 minutes for your kernels to pop. Use our new improverd kernals for popping times of 3 minutes!

Even more WOW than Vista!

[xoundmind]

With that kind of performance increase, my Gentoo laptop is going to be screaming along after the release of 2.6.20.

Ok...was that sarcastic enough? With this crowd, one can never quite know.

Re:I disagree!

[Anonymous Coward]

Seriously, though, even the most recent kernel is roughly 41 MB when bzipped. Is that so horrible? Oh no, it'll take a few minutes to download over a decent broadband connection. Oh, I dread the horrible day when the kernel is so bloated that it's 50 MB. I think you're massively overestimating how bad this "bloat" is.

Keyboard, Video, Mouse?

[aszaidi]

It's about time this Linux thing added support for these input/output devices. Even M$DOS has supported these for quite a while. I was getting tired of controlling my lappy by sending brain signals alone and attempting to understand the reply just from the sound of the clicking hard disk.

Re:Adblock Slashvertizement

[Anonymous Coward]

Erm, rather h ttp://*.kontera.com/* and h ttp://*.intellitxt.com/* (slashdot removes the first *).

PS3 as MythTV frontend???

[jbr439]

Gotta ask: will PS3 support in 2.6.20 allow me to turn a PS3 into a MythTV frontend?

Re:PS3 as MythTV frontend???

[Anonymous Coward]

There are already PS3 Linux distros around. If you already have a PS3, then install one install the MythTV frontend and try it. I reckon it should work, it probably depends on how much the PS3s video is crippled by running under the hypervisor, but if it can play videos okay under Linux, then I don't see why the MythTV frontend wouldn't work.

Re:PS3 as MythTV frontend???

[tji]

You can compile & run the MythTV frontend on it. You could probably do SDTV MythTV playback, using the unaccelerated video of the PS3. But, the reports I have seen form other people that have tried say that it can't do HD video.

If Sony enabled accelerated video support, it would make a great frontend. With some code to take advantage of the cell processors, it could be an incredible frontend. But, that's not the case yet.

Inline functions

[shani]

I know you were joking, but actually removing inline functions can make the kernel faster in some cases, and the effect on kernel size is dramatic:

http://lwn.net/Articles/82495/
http://lwn.net/Articles/166172/

And let me say, LWN kicks ass. :)

KVM support for Win 98

[Anonymous Coward]

I'm running 2.6.18+KVM now, and it works well except for having to disable the kvm module and use straight qemu emulation when running Windows 98. Any idea if this will be resolved before 2.6.20 is release?

You mean...

[Anonymous Coward]

"All three apply to the PS3, as far as I'm concerned!"

You must mean "It applies to all three PS3's, as far as I'm concerned!"

So in other words...

[ZakuSage]

It's slightly faster.... TO THE MAX!

Unstable I/O?

[the_greywolf]

On 2.6.19-ck1, I ran into a number of show-stopping problems with I/O resulting in several severe hangs (which I never bothered to debug) which I have linked to I/O. I've been hearing reports from other users of the -ck patchset that they are experiencing similar problems with 2.6.20-rc5/6.

I think I'll wait a bit and stick with 2.6.18 for now.

Re:Unstable I/O?

[Slashcrap]

On 2.6.19-ck1, I ran into a number of show-stopping problems with I/O resulting in several severe hangs (which I never bothered to debug) which I have linked to I/O. I've been hearing reports from other users of the -ck patchset that they are experiencing similar problems with 2.6.20-rc5/6.

What? You mean that users applying the experimental, performance oriented CK patchset to their release candidate kernels are experiencing instability?

Fuck! This is worse than Windows 98! There's only one solution - release a 2.7 kernel, add a binary driver interface and convert everything to C++ under the GPL v3!

Re:Unstable I/O?

[the_greywolf]

Hey now, even Con says he only makes it available for testing. His patches against release kernels are generally quite stable, and he rarely has to fix anything. What I'm talking about is a problem I've been having with the 2.6.19 series specificaly that other people are complaining about in 2.6.20-rc. What I clearly failed to mention is that this is a mainline problem.

Where does the hypervisor live?

[Kadin2048]

I've played with PS3 linux. I can tell you, the hypervisor is just that. It virtualizes the PS3 hardware. ...

I don't know about anybody else, but I find this just conceptually fascinating. Where does the hypervisor run from, anyway? Is it in the machine's ROM, so that there's no way to prevent it from booting? (Without irreversible hardware modifications.)

I was just wondering whether it's possible to get rid of it, and boot Linux on the bare metal, or whether the hypervisor is tied into the hardware so tightly, it's impossible to remove and install a new Domain 0 operating system.

Getting Linux to run on the bare metal, 'below' the hypervisor, will be an interesting exercise in what I suspect may be a large part of the future of "unauthorized" computing. I don't think it'll be long before most consumer systems have something like that in place, so it'll be a good intellectual challenge, if nothing else, to see if it can be gotten around.

Re:Where does the hypervisor live?

[Anonymous Coward]

Come on now. If there is a hypervisor emulating all the hardware . . . ALL THE HARDWARE, I'm sure it's emulating how to talk to and access the Cell processor. Circumventing the hypervisor probably will not allow you to run Linux compiled for Cell. Development for all the hardware would have to start all over. But then, I don't know all the details surounding the Cell's specifications, nor have I taken a look at the code support in the source yet.

Re:Where does the hypervisor live?

[faragon]

... has been done before, also on a fully virtualized context, memory protection, blablabla... PS2 Linux anyone? ;-) (greetings to Marcus R. Brown, damn great hacker!)

KVM

[Anonymous Coward]

In this case

KVM = Kernel based Virtual Machine (site is /.ed)

KVM != Keyboard-Video-Mouse switch. (Which would be odd for a kernel to try to support. In fact it makes no sense at all, which is the only reason I looked at this story at all)

Go ahead, mod this post as flamebait or a troll. I know how well facts are received here.

Re:I disagree!

[dreddnott]

If your gamepad uses USB and is HID spec compliant then Linux should have no problem. It was literally silent plug and play with no configuration necessary in both DOSBOX and ZSNES for my Logitech gamepad and joystick, all I had to do was compile in the right modules.

I don't think kernel download size will outpace technology (or even the sense of efficiency). In 1993 or even 1998 downloading 40.8MB of source might have been a bit excessive.

Still I find what you are proposing to be intriguing and I wish to subscribe to your newsletter. Basically you mean something like an apt-kernel-config tool?

Hardware support

[Ki6AMD]

Hardware support belongs in the kernel. We're talking about another processor architecture which has historically always been shoved in. Would someone ask why MIPS support was added or why any number of other architectures was added that are rarely used (compared to x86)?

Now the better question is if someone can/will make a standardized PC with the Cell /proc. That is something I'd be more interested in. While the cell proc has some great features, I don't see a platform that I like yet. (Sorry a game box isn't a solid platform for the computing I want to do.)

Same here

[this great guy]

I also bought a PS3 two weeks ago primarily to develop on the Cell processor. So far, I have written a prototype application that runs 5x faster on the PS3's Cell than on the highest end Woodcrest Xeon at 3.0 GHz. When I am not coding on it, I am also using it as a Blu-ray player. Given all this, plus the fact that the PS3 is a next-gen console (though I don't plan to buy any game), I am probably one of the few to recognize that $500 is dirty cheap for such a polyvant device !

Re:Same here

[Slashcrap]

So far, I have written a prototype application that runs 5x faster on the PS3's Cell than on the highest end Woodcrest Xeon at 3.0 GHz.

Let me guess - it adds together two 64 bit numbers and then discards the result?

Re:Same here

[this great guy]

No, it is a password cracker. More info in a couple of week, when I release it as open source.

WARNING: DON'T READ THE ARTICLE

[ratboy666]

Given that the article, obstensibly about kernel performance, makes no effort to actually cover kernel performance...

I was suckered in; it looked like a worthy topic. Now, I ask myself: Why did I bother?

Penguins?

[Kadin2048]

When it booted, two big Tux penguins were displayed indicating dual CPUs. Then after a bit of booting six more smaller Tux penguins appeared beneath the first two. So I suspect all eight cores are in use.

Well, hell -- eight penguins? I know that's all the benchmarks I need. Now, where's my credit card?

Re:Penguins?

[Anonymous Coward]

What good is eight cores when they only run at less than 2 GHz each and have the processing power of a flea? Yeah, only buy it if you like running Linux on the modern equivalent of a 486 DX2 66. What's the saying? A fool and his mommy are soon parted.

Lots of features.

[Anonymous Coward]

Pretty scary to slip in such big features. When people may be tracking the latest for small changes, they have to go with the big change as well, bad bad bad.

Inefficient microkernel architectures?

[noz]

Some of the figures went up by ~1%! Did they move something out of the kernel?

So what?

[BigBlockMopar]

He's running kernel benchmarks on a laptop? Looks like half the things he was measuring were I/O bound? On a laptop?

Point well taken, but I have no problem with this.

At least the notebook computer was built by one manufacturer, who (presumably) ensured that all the components played well with each other. Other than that, I don't care what machine he ran it on - an AST Pentium I would have been fine with me.

The notebook may be slower than a comparable prefab desktop or server, but we still had A/B comparisons taken on the same hardware.

Despite the slower IO, it also more accurately simulates bottlenecks seen in older hardware, or hardware where the BIOS has been "tweaked" by a "tuner" who knows nothing about what he's doing (we've all seen hardware like this, my favorite was back in the days of the 486, someone who wasn't smart enough to know how to buy jeans which fit properly had disabled the cache because it "slowed him down").

Remember, we have an A/B comparison. Performance differences between kernel versions should scale by the same linear coefficient as the comparison between this notebook and whatever else you plan on running on.

And furthermore, notebooks are a very common platform today, and their usage does reflect a real world condition under which any new kernel will have to operate.

Re:I disagree!

[Lord Bitman]

Basically you mean something like an apt-kernel-config tool?

Why qualify it? I mean I want to type$ apt-kernel config

It's not actually at the point where it matters for the most part yet, or at least it wasn't last time I built a kernel (a year or so ago), but it's the principle of the thing more than anything else.

Of course, some of the most numerous drivers are network drivers... not the kind of thing you want to be picking and choosing piecemeal while reliant on a network source to get at them.

So switch to KVAM!

[Medievalist]

Although I agree with you in principle, KVM switches are obsolete anyway.

You want a KVAM (pronounced to rhyme with "shazam!" for marketing purposes) switch.

Keyboard, Video, Audio, Mouse.

This was fixed some time ago

[dbIII]

I can run it on a PS3, but I still can't run it on an Asus A8V motherboard

I put a standard Fedora Core install on a machine with one of those motherboards. I didn't notice anything unusual at all during the install and the user has had no problems with it in the months it has been in use. I can't remember what it had to start with (it was the kernel on the install CDs) but it now has kernel 2.6.17 - which matches the new Fedora Core6. I know old knoppix disks with old kernels don't have the nforce driver but linux distributions less than a year or two old should work with your SATA controller.

Re:This was fixed some time ago

[Lord Ender]

As long as you only use one of the four SATA ports, it works fine. If you use two, and you try to read more than a few gigs into the second drive, your computer will lock up spitting "controller timeout" errors all the way.

This is the 2.6.19 kernel. Tested with several different 500GB drives.

KVM no. Xen yes.

[Macka]

I wouldn't worry too much about it. KVM is not going to be championed by the likes of Redhat, SuSE or any other mainstream distro, so you won't really see or hear much about it in the real world. Their VM of choice is Xen and with good reason. Xen Paravirtualization narrows the gap between native and virtualized performance, and Xen's killer feature, Live Migration, turns the world of HA clustering on its head.

No, you get more CPUs than that.

[r00t]

You get:

1 disabled SPE
7 working SPEs (each has 128 128-bit registers)
2 PowerPC 64-bit w/ vector units (one PPE is two-way SMT Power 970)

That is 9 CPUs total, 7 weird and 2 normal. Linux mainly runs on the 64-bit PPE cores, but there are ways to run code on the SPE cores.

Decent SPE documentation is nowhere to be found AFAIK. Perhaps it can be derived from a gcc port.

When you make a measurement..

[bunbuntheminilop]

it's good to include an error calculation. The first page of benchmarks could really be sampled from the same population (effectively), but its hard to say. I think for many of the tests shown, there would be variation.

If this were done, it would make the interpretation more straight-forward.

No Cell

[Anonymous Coward]

Sheesh, just buy a god damn $299 Dell if you want a Linux box and buy a $250 Wii if you want a gaming system. PS3 sucks.

Since they bought the PS3 to play with its Cell processor, and neither your Dell nor your Wii have a Cell, you're just a total moron.

It's about like a G5

[reaktor]

The Processor is about equivalent to a mid-to-late Pentium III.

No, it's actually about the same as a Powermac G5 at the moment. Read more here.

"Results
Overall Score
PlayStation 3
105.2
Power Mac G5
106.9"

Re:It's about like a G5

[drinkypoo]

The Linux kernel runs on both the PPE and one SPE. Not sure if the kernel is exercised much in these benchmarks or not.

Re:I disagree!

[Anonymous Coward]

Ah, but you're missing the cheap points of 'know-how' you can get by crying 'bloat' every time someone mentions a new feature in a package... ;)

gotta compile this for my REAL power MAC.. a 970MP

[MrJerryNormandinSir]

I gotta compile this for my 970MP with 8GB of RAM. I just wish Nvidia would get thier head ouf thier ass and open source the driver since I need to compile it for my powermac G5. other than that Linux is much faster than os/x. And with the new
X server enhancements, damn I won't miss OS/X much. gotta love the new 3D desktop. It's awesome on my AMD Linux box.
I gotta get it on my G5, then I can sell my AMD box and put more memory in my G5. Or save up for a quad AMD box.