Inside the Windows Vista Kernel, Part 2 290
A user writes "Mark Russinovich takes a look at the Windows Kernel and the changes made in Vista. In this second part he describes the workings of the features SuperFetch, ReadyBoost, ReadyBoot, and ReadyDrive and how they improve system performance."
Why 'Ready'? (Score:4, Funny)
Re:Why 'Ready'? (Score:5, Funny)
Re:Why 'Ready'? (Score:4, Funny)
Well, they Microsoft was gonna go with 'Hyper', but after frequent crashes, one employee, a Star Wars fan, put on a clip from Empire Strikes Back.
"Prepare to make the jump to lightspeed. If Lando's people fixed the HyperDrive."
"Punch it!"
*cough*sputter*cack*hack*pzzzsst*
"That can't be. They told me they fixed it! It's not my fault!"
Re:Why 'Ready'? - More Absorbed IP (Score:4, Funny)
Poke 53280,0
Poke 53281,0
Ready.
Re:Why 'Ready'? (Score:5, Funny)
Re: (Score:2, Redundant)
If there was truth in advertising, they'd be called: SuperBloat, ReadyBloat, ReBoot, and BloatDrive.
Where's the room for incremental improvement? (Score:5, Insightful)
Really the title of this article should be "Microsoft Implements Fresh New Names for Existing and Obvious Technology in Vista Kernel."
Re: (Score:2)
Hyper was 3 years ago and 'Ready' is so 90s.
Re: (Score:3)
Re: (Score:2, Interesting)
Re: (Score:2)
After Y2K, everything was X this and X that.
Re:Why 'Ready'? (Score:5, Informative)
Re: (Score:2)
But I suppose ReadyBoost might have a point, dunno. However it's not this one.
Re: (Score:3, Interesting)
I don't think it would be for frequent writes -- that can kill flash. Especially if there is a fixed area for these writes (unless there is a write spreader thingum in the flash).
Flash does retain information over a power-cycle, and the "seek time" is zero.
I think I would put commonly used small files on the flash that are NOT written very much. Stuff like the old "CONFIG.SYS" of DOS days. Perhaps application relocation information, and resolved load information (seek to
Re: (Score:2, Informative)
Re: (Score:3, Interesting)
"USB 2.0 hi-speed" is 60MB/sec, not 10. Although that's still less than your 80+MB/sec figure, it might be reasonable to assume that it's higher than the sustained transfer speed of the SATA drive. Since ReadyBoost (or whatever) uses memory on the order of hundreds or thousands of megabytes while hard drives have caches on the order of one megabyte, ReadyBoost could still provide a significant speedup for reads larger than 8MB but smaller than 2GB.
Besides, I think the intent is more to have high-speed flas
Re:Why 'Ready'? (Score:5, Interesting)
At least, that's how I'd design it if I were much of an engineer
Re: (Score:2)
Re: (Score:2)
Where's the Beef? (Score:5, Interesting)
Many have fallen into the trap of building "intelligent" cache systems that perform worse than the "dumb" cache systems. Remember, every MB of RAM caching an app that you might use is not caching part of the photo that you are editing; caching is subtle work.
So, as I have not used Vista and have no plans to (I'm with Linux), a question: Can anybody tell me that they put Vista on their computer and things are now noticably faster? I've heard from people with the opposite experience, now I'm soliciting evidence that all these Ready* things actually help people.
Re:Where's the Beef? (Score:5, Informative)
Re: (Score:2)
People like to bitch, but if you listen to nothing but people bitching and only consider the negatives you get anything but an accurate view of the situation.
Re:Where's the Beef? (Score:5, Interesting)
Athlon X2, 2GB RAM, Go 7300. Vista in default configuration runs at about 75% of the speed of XP. Switching the 'Ready' crap off gets it up to about 85-90%.
Power management is unusable - XP 3-3.5 hours, Vista default, 1 hour, Vista with crap off, 2 hours.
Re:Where's the Beef? (Score:5, Informative)
I imagine that if I ran solid benchmarks for a single type of task that it would come out less than for XP, but when I multitask my perception is definately that Vista runs smoother.
Re: (Score:3, Interesting)
It's not as fast as my main system which is similar to the parent poster, but overall on my two machines, Vista is a significant improvement and I think worth the upgrade price.
Re: (Score:2)
Re: (Score:2)
Watching SuperFetch After you've used a Windows Vista system a while, you'll see a low number for the Free Physical Memory counter on Task Manager's Performance page. That's because SuperFetch and standard Windows caching make use of all available physical memory to cache disk data. For example, when you first boot, if you immediately run Task Manager you should notice the Free Memory value decreasing as Cached Memory number rises. Or, if you run a memory-hungry program and then exit it (any of the freeware "RAM optimizers" that allocate large amounts of memory and then release the memory will work), or just copy a very large file, the Free number will rise and the Physical Memory Usage graph will drop as the system reclaims the deallocated memory. Over time, however, SuperFetch repopulates the cache with the data that was forced out of memory, so the Cached number will rise and the Free number will decline.
As far as end user experiences "speed" on a system upgraded from XP.... well it is pretty similar for most applications... gaming has been showing somewhat lower frame rates....but I think that the state of Nvidia's Vista drivers has had more to do with that than Vista taking perform
For a good read on how superfetch works... (Score:2)
Re: (Score:2)
If only other kernels had developed some way utilizing the full amount of physical memory for caching purposes nearly a decade ago.... But then, I guess people will always be excited by the incorporation of old features into modern operating systems if their expectations are kept low.
Assuming you're referring to Linux; I was under the impressions that the Linux caching system was similar to Windows XP's Prefetch, as opposed to Vista's Superfetch. Could you confirm otherwise, and/or point me to a source that does so?
Re:Where's the Beef? (Score:5, Informative)
I've been using Vista for quite a while now for primarily programming and gaming. "faster" has two areas for me:
I think Microsoft may have unknowingly shot themselves in the foot by making some of the betas public. This made a lot of the "almost-enthusiast, but not really knowledgable" people decide that because the beta had some performance quirks, the RTM must too. And they've been surprisingly loud with it.
Other than some old hardware not having drivers yet, every person I've talked to who has actually ran Vista for a week agreed it is an improvement.
Re: (Score:2)
It's always been this way. I remember when I got the first NT 3.1 Beta (wasn't it called Daytona??). It was dog slow, unbelievably slow - way slower than OS/2 2.1 at the time. It was just like the anti-Vista
Re: (Score:2, Interesting)
As DWM shuts down whenever app locks front buffer (and d
Re: (Score:2, Interesting)
I suspect that any performance improvements in Vista were soon eaten up by added overhead elsewhere. Something I've noticed with Windows (since Windows 95) is that with every 'upgrade' Microsoft decides to run more stuff in the background for no real gain and I imagine that vista is no different.
Re: (Score:2)
Disclaimer: have not used Vista on anything but a demo machine in PC World.
Re: (Score:3, Funny)
Of course not. That's why they're called SuperFetch, ReadyBoost, ReadyBoot, and ReadyDrive.
My motherboard for example, comes with: BuzzFree, LifePro, PowerPro, SpeedStar, and ActiveArmor. I'm pretty sure all that means is that it, by now, obsolete.
If these features were of any use besides being marketing snakeoil and/or painfully obvious, they'd be called "the hvuk__k() tweak" or "deloop_64" or "-O3" or someth
Re: (Score:3, Insightful)
Yes, it should.
The fact that performance has not improved is the reason behind articles like this in which Microsoft is talking about how great Vista is, when it really is disappointment.
Vista seems quite slow to me (Score:5, Insightful)
my first impression of vista.
Re: (Score:2)
Anything non-budget will run vista fast. My core 2 duo runs vista noticeably faster than XP, wit the exception of games (which is mostly the fault of nvidia drivers, I'm seriously considering pi
Re: (Score:2)
Re: (Score:2, Informative)
Re: (Score:2)
BTW, the cheapo home model is a 1.8 solo processor.
Re:Vista seems quite slow to me (Score:5, Insightful)
You can run DOS or a small *NIX distribution quite happily on a low-end 486 (a 286 lets you run a lot of DOS apps pretty fast). You certainly don't need anything like a 1.6GHz machine.
Re: (Score:2)
Maybe you should try a core2duo sometime, or equivalent AMD. Everything after that will be painfully slow.
Re: (Score:2)
What, so $2000 ultraportable laptops are "budget" now? 'Cause, you know, even the highest-end of those use low-voltage (1.83 or 1.66 GHz) or even ultra-low-voltage (1.1 GHz) Core Duos! It's entirely possible that the "1.6 GHz Dell" he was referring to was one with a (1.66 GHz) L2400 Core Duo.
Re: (Score:2)
That doesn't have anything to do with how quick Vista can be. Yesterday it took me a good ten minutes to figure out how to setup a shortcut to a network drive on Mac OSX so that it would automatically appear on the desktop when the user logs on. The nine minutes and thirty seconds longer than it should have taken was because I don't know jack a
Re: (Score:2)
For example, my new Acer came with so much shit pre-installed that it was practically unusable - the hard drive wouldn't stop rattling log enough to even do a simple defrag, and it took over 90 seconds to boot and shut down
Improve? (Score:5, Informative)
However, this slew of benchmarks [tomshardware.com] shows Vista to be slower across the board then XP.
Re: (Score:2)
Re: (Score:2)
A good example would be your activity as you start the PC in the morning: You launch Outlook to fetch email, a messenger, a web browser and probably additional applications such as a development environment. If you do this repeatedly and ideally in the same order, SuperFetch will recognize this and then proactively populate these applications into all available main memory the next time you start the PC. You should only wait for a few minutes before you commence work to give the SuperFetch service the time to "superfetch" your applications.
This is amusing to me because when I had a separate Windows machine I would boot it every other morning because otherwise it would be too slow to be usable (WinXP+some big Adobe apps). My OS X box, however, gets rebooted pretty much only when their is a software update that requires it. Windows XP "boots" in about 2 seconds, because I have a VM running on top of OS X so I just restore from a known good state every time.
It seems rather archaic to consider how long it takes to boot and start applications
Re: (Score:2)
Funny thing is, I have a Dual G5 to my right, and a Core Duo-powered HP laptop (same spe
Re: (Score:2)
I have a Dual G5 to my right, and a Core Duo-powered HP laptop (same specs/chips as MBP, but with nVidia instead of crap ATI graphics) and the Mac is the machine I have to reboot at least once during the week.
Umm, why? Are you actually experiencing a gradual leak of resources that cannot be fixed by just quitting and reopening an application? The only person I know who had to reboot OS X regularly was a person who experienced regular crashes because of some bad RAM and the problem went away when they swapped it for a good pair of chips. I have plenty of apps on OS X that leak resources (often the same ones as leak on Windows) but I've never had to reboot the mac in order to solve the issue.
Re: (Score:2)
It's not because it slows down. It's because some Adobe app craps all over itself to some extent that is only repaired by a reboot. No idea whose fault that is, but it doesn't happen to me on Windows (same apps.)
OSX is also the only OS that refuses to remember where I put my hard disk icon :(
Re: (Score:2)
It's not because it slows down. It's because some Adobe app craps all over itself to some extent that is only repaired by a reboot. No idea whose fault that is, but it doesn't happen to me on Windows (same apps.)
What app in particular? I use Photoshop, InDesign, Illustrator, Bridge, and Acrobat very regularly on both platforms, as well as the occasional use of Dreamweaver and regular use of Framemaker on Windows. While I have had them crap out to the point that Windows needed a reboot, I don't think any have ever done so on OS X. InDesign, in particular, has about 2 days of use on Windows before Windows needs rebooting and about 5 days on OS X, but just restarting InDesign solves my problems (any more time than e
Re: (Score:2)
Apps you mean; namely InDesign and Illustrator CS2 both do it to me on a somewhat regular basis.
If you did display them on the desktop, you might know what I'm talking about.
Re: (Score:2)
Worse, SuperFetch and the indexer fight to get at the hard drive so the head is moving like nuts on a bare install.
When I first tried vista I switched the indexer off fast enough, but had never heard of SuperFetch - took another we
Re: (Score:2)
That probably means less than the recommended 1 GB?
Re: (Score:2)
So from the past couple of Slashdotter comments, it would appear that Vista is tuned to give performance boosts to those with substantially lower or substantially higher system specs than the average.
What about the middle of the curve? You know, where the vast majority of users are?
bah same old (Score:5, Funny)
Tom
Re: (Score:2)
I don't know what you're talking about. I installed RAMDoubler on my machine years ago and had it convert my 8MB stick into a 16MB stick. I then pulled that out and sold it for considerably more than the software cost me. Best investment ever...
On a more serious note, RAMDoubler for the Mac was actually a decent piece of software in the OS 7.5 days. It certainly was a better virtual memory manager than the one included with the OS. Can't sa
Inside the kerne;l (Score:5, Funny)
Re:Inside the kerne;l (Score:4, Funny)
Slowing down over time? (Score:4, Interesting)
Does Vista suffer from this same problem?
Re: (Score:2)
The only time I've noticed anything like this problem you speak of is if I install SP1 over XP. Then my boot time doubles or more. However whenever I slipstreamed SP2 onto my XP CD and installed from there I kept the fast boot time...
As for Vista, I'll let you know in nine months... :P
Re: (Score:3, Insightful)
Granted, the OS could
Re: (Score:2)
Beat that
Re: (Score:2)
Inside the Windows Vista Kernel ... (Score:4, Funny)
Inside the Windows Vista kernel... (Score:5, Funny)
int main() {
uac_alert("You are attempting to initialize variables. Cancel or allow?");
int i;
uac_alert("You are attempting to enter a loop. Cancel or allow?");
for (i = 0; i 100; i++) {
uac_alert("You are attempting to iterate a loop. Cancel or allow?");
i++;
}
uac_alert("You are attempting to exit program. Cancel or allow?");
return 0;
}
Re: (Score:2)
Re: (Score:2)
-nB
Re: (Score:3, Funny)
Re: (Score:2)
Think Netburst (Score:2)
Every release of Windows® improves scalabilit (Score:2)
WTF (Score:3, Insightful)
Okay, so I just wanted to nitpick a sentence here. What happens between 512 and 700. I presume it does the same thing at XP would have. But this sentence is confusing, and perhaps implies that perhaps Ms. PacMan will get launched in this scenario.
Overall though, an interesting series. Kudos to the author.
Re:WTF (Score:4, Funny)
If you have between 512 and 700 MB of memory, Vista tears a rift in the space-time continuum. IMPORTANT: whatever you do, DO NOT install Vista on a computer with between 512 and 700 MB of RAM.
All PR-speak, notice the lack of actual info (Score:2)
Notice all the blab about these new features, but a notable lack of bottom-line-- i.e. how much faster is bootup, shutdown, and file i/o. Funny, you'd think if the numbers were good, they'd crow about them? Hmmm....
Also note that with the boot information in a database instead of a text file, it's no longer possible to fix partition or booting problems with a text editor.
Danger to FOSS Development (Score:2)
I believe posting a comment should be perfectly safe, since this is Slashdot and nobody RTFA anyway.
Re:Is this secure (Score:5, Informative)
http://blogs.msdn.com/tomarcher/archive/2006/06/0
A: This was one of our first concerns and to mitigate this risk, we use AES-128 to encrypt everything that we write to the device.
Re:Is this REALLY secure? (Score:3, Informative)
For example, where are they storing the encryption key? It's certainly on the PC somewhere accessible to all for now.
Security programming is hard, really hard. I don't doubt that Microsoft has very gifted security programmers, but I very much doubt that they were given free reign. Most likely they were forced to implement managerial compromises that, well, compromis
Re: (Score:3, Interesting)
For example, where are they storing the encryption key?
I would imagine in RAM, in ring-0, so it's lost when you reboot (it's just a cache, so it doesn't matter if it's unrecoverable) and it should be impossible for a userspace process to get at it while the system is running.
Also consider the CPU cycles required to do the encrypting/decrypting and that this is just one of MANY tasks the OS is doing with encryption-bound services.
A modern CPU can execute around 300 million instructions per hard disk seek. AES decrypting a block of data is trivial next to that. This is why ZFS adds a SHA hash to every block; it's a tiny overhead on a modern CPU.
Re: (Score:2)
if on the other hand you find the USB flash drive laying on the ground.... cause someone dropped it... the key residing somewhere on the HD of the person that dropped the flash drive isn't really going to help you get at the information on it.
obviously the encryption/decryption is going to entail "some" overhead... if they had implemented it with out encryption it would doubtlessly be faster and of course t
Re:Trust Issues (Score:2)
Namely, that Microsoft implements security perfectly. This conveniently ignores their consistent and very public record of high-profile failures on security matters.
[shrugs]
Re: (Score:2)
I am not saying there is any security flaw in this issue. But bigotry doesn't really fit when someone bases their performance expectations on a proven performance track record. Microsoft has a well earned reputation for faulty security and poor implementation that is backed by a solid (or unsolid as the case may be) track record that dates back as far as the company and those problems have gotten worse over time. The
Re: (Score:2)
Re: (Score:3, Interesting)
Re: (Score:2, Interesting)
Re: (Score:2)
Re: (Score:2)
Re: (Score:3, Interesting)
The last thing I need is to have data corrupted as it moves through a bad flash stick, and is then potentially written back out to the hard drive later.
Re: (Score:2)
Well, Ironicly, in previous versions of windows when you connect more devices to the USB, it will reserve bandwidth for those devices so placing more then one flash drive onto the same controler willinhearantly make the ability of those devices to be slower yet. It will increase this limiting effect upto the total amount devices per controler. And since you can have over 200 devices conected to one controle
Re: (Score:2)
Based on what people are saying, it really seems like the sweet spot for Vista is at least a dual core system with 1 gb of RAM and a good video card.
Spend 599 and have a 19" monitor while your at it (Score:2)
2 grand my ass. Just where do you buy your pcs?
Re: (Score:2)
I think I will be ReadyNever (Score:2)
Well... this is yet another review of features I don't like in a product I don't want from a company I don't trust. *Yawn*
Re: (Score:2, Funny)
*Yawn* Let me know when they get some REAL developers over in Redmond.
Re: (Score:3, Informative)
That's hardly the same thing. Simply putting the swap file on a flash device is unlikely to be beneficial, and probably harmful. From what I read in the article, the Windows feature selectively uses flash when it would be faster (random access reads)
Re: (Score:3)
Basically, using flash memory for swap. Linux has been able to do this for a long time.
This is not what ReadyBoost is doing.
Re: (Score:2)
Q: Won't this wear out the drive?
A: Nope. We're aware of the lifecycle issues with flash drives and are smart about how and when we do our writes to the device. Our research shows that we will get at least 10+ years out of flash devices that we support.
Of course, I don't personally know whether that's true or not, but at least it shows they've put *some* thought into the issue.
Re: (Score:2)
I wouldn't worry about it if I were you.