Slashdot Mirror
Next Generation SSDs Delayed Due To Vista
PoliTech notes in a journal entry that "Vista is the gift that just keeps on giving." "Speaking during SanDisk's second-quarter earnings conference call, Chairman and [CEO] Eli Harari said that Windows Vista will present a special challenge for solid state drive makers. 'As soon as you get into Vista applications in notebook and desktop, you start running into very demanding applications because Vista is not optimized for flash memory solid state disk,' he said... 'The next generation controllers need to basically compensate for Vista shortfalls,' he said. 'Unfortunately, (SSDs) performance in the Vista environment falls short of what the market really needs and that is why we need to develop the next generation, which we'll start sampling end of this year, early next year.' Harari said this challenge alone is putting SanDisk behind schedule. "We have very good internal controller technology... That said, I'd say that we are now behind because we did not fully understand, frankly, the limitations in the Vista environment.'"
It seems hardly a day goes by without seeing yet another example of Microsoft's utter disregard for the needs and desires of virtually every market -- consumer, enterprise, and OEM. Rarely in the history of American business has any company shot themselves in the foot in such a spectacular manner, earning the ire of so many. I almost feel sorry for them. They really need to regain some sense regarding Win7, bring back the MinWin idea and use a good, transparent virtualization scheme for backwards compatability. Otherwise I think they will be pretty well finished in the OS market. The OEMs are not going down with them if they can help it, you can be sure of that. And once Windows is no longer the defacto preloaded OS it's all over.
Caveat Utilitor
TFA doesn't go into much detail - by "not optimized" do they mean that Vista pages frequently, and thus would wear out the SSD rapidly? Or is it possibly something to do with sustained read speeds?
It greatly upsets me that they view this as a question of optimization.
Seek speed is nice, but it's only one aspect of SSD technology. Heat is another, and for a large segment of us the noise generated is the dominant feature. The HD is the only piece of the machine standing in the way of silent operation, and unlike power use or speed that's something that can affect the owner all day long even when they're not actually using the machine.
Holding up silent drives because they aren't quite fast enough is just disheartening. :-( I'm guessing for others, holding up cooler drives is equally sad.
rage, rage against the dying of the light
For some reason 'rpm' from mandrake is surprisingly inefficient on SSD's. It makes mandrake practically unusable for me on my eeepc. Yet dpkg/apt-get/aptitude on debian and ubuntu is just zippy.
--jeffk++
ipv6 is my vpn
It's more like Vista's disk scheduler and disk usage patterns are complete incompetent on modern hardware.
While Linux has modern filesystems and gets optimized and fixed almost constantly, Windows Vista still uses the same basic NTFS layout and associated algorithms that were finalised around 10 years ago, and weren't even very good back then. There have been only very minor revisions to NTFS and virtually none of them have improved its performance or reduced its fragmentation.
Sam ty sig.
'As soon as you get into Vista applications in notebook and desktop, you start running into very demanding applications because Vista is not optimized for flash memory solid state disk,'
Based on the statement, it earns the Vista Capable sticker...
On a serious note, I would try not to think that this is a case of -insert company- blaming MS for their own shortfall. Although I am more likely to believe that this is Vista's fault and in this case MS should be the one issuing some patches...
Driver is for supporting device abstraction layer in an OS.
If the fault is within the file system not optimizing for flash wear leveling or have frequent unnecessary writes to a device, would you suggest a hardware device vendor to make the file system too? How far in the OS do you want a 3rd party hardware vendor to work on?
Flash memory has a certain "read-write" lifespan, after X thousands of reads/writes, the media becomes damaged and eventually becomes unusable.
Thus, lots of reads/writes via the swap file or web browser caches accelerate the death of Flash SSDs.
I wish newer OSes made tinier footprints and would use RAMDrives more like Damn Small Linux, thus prolonging the life of the "hard drives" of machines like the Asus EEE.
http://www.object404.com
"We did not fully understand the limitations of the Vista environment" - Neither did anybody else, including Microsoft... no one can be told how limited Vista is - you have to suffer it for yourself.
Unicode killed the ASCII-art *
Vista absoloutely randomly thrashes your hard disk almost constantly for the first few weeks of installation, all you can hear is tickety tick, clickety click from the damn machine.
What is it doing? I'm not sure, auto defrag? file index? superfetch? I can't be sure, what I can be sure of is that it's *apparently* meant to run at idle priority, in reality I can clearly visibly see the performance decrease of say loading firefox or nero or any application under Vista compared to XP, while the drive thrashes about like a 'special person' thrown in the deep end of a swimming pool.
I am sadly 'oldschool' I remember running DOS 5 and 6 and I recall watching my drive light, I used to be able to spot a machine with a virus purely from the damned disk activity on the machine, because it simply isn't supposed to do anything when you're not, how that has changed over the years, it's sad, even smartdrv would stop fiddling with the drive after about 5 or 10 seconds under 6.22
Win 95, 98, virus scanners, spyware detectors, 2k, XP - it's all slowly gotten worse over the years but Vista really takes the cake, I'd love to see a laptop power consumption test of XP vs Vista on an identically spec'd machine. (tickety tick, thrashity thrash)
The short story is, I agree with the article entirely, SSD's would be worn out substantially faster under Vista than previous versions of Windows.
The interesting thing is the Ingo Molnar has said outright that none of the current Linux filesystems is GOOD ENOUGH for SSD's - he has his hopes on BTRFS to save us in the longer run - and the Linux filesystems are a damn-sight better at it than Vista...
Intriguing how Linux was already the best, and yet working on improvement when the competition hasn't even considered the problem yet.
Unicode killed the ASCII-art *
Sandisk SSD drives are poorly made and perform poorly (much worse than others..). This is just Sandisk trying to shift the blame elsewhere..
I am the maverick of Slashdot
Another way to look at it is that SSDs aren't optimized for Vista.
Here's a basic issue with NAND. NAND is most efficient when written in chunks of at least 128KB in size. Some NAND chips aren't even efficient until 256KB. Because this is the smallest unit that can be erased in NAND. If you write a smaller amount (say 8KB), it actually has to erase a new block, copy 120KB to the new block from the old, then write in the new 8KB. Then, if you write another 8KB, might have to do it again!
So these SSDs would be fastest if Vista would write in larger blocks. Unfortunately, 512B is the block size for ATA. There are extensions for 2KB, 4KB and 8KB blocks, but Vista doesn't implement them. And it doesn't have to, as they're optional.
Also notable is that even some regular magnetic hard drives now have native 2KB or 4KB blocks and it is written in 512B chunks, it might have to do a read-modify-write cycle to do it.
Anyway, if you know ATA until recently the LARGEST possible write was 128KB (256 blocks), to expect Vista to use writes this large or larger when many drives (like almost any under 137GB) doesn't even implement them is perhaps too optimistic. To expect it to use 2KB or 4KB blocks when 95% of drives don't implement them is perhaps too optimistic.
In the end, drive (including SSD) companies can't operate in a vacuum. They know they have to make what is useful for the customer, which means usable by the OS.
As an additional note, MacOS recently (10.4.something) added support for 2KB, 4KB, etc. blocks, but it still has difficulty using large writes too. I think when operating through the file system, it never generates a write larger than 256 blocks either (which is 128KB or more depending on block size).
http://lkml.org/lkml/2005/8/20/95
When I read this, a certain quote comes to mind:
"The Wise adapts himself to the world. The Fool adapts the world to himself. Therefore, all progress depends on the Fool." -Unknown
So perhaps on some plane of reality we might be grateful to the good people at Microsoft for forcing SSD makers to make improvements they might not otherwise have made?
"Nine times out of ten, starting a fire is not the best way to solve the problem." - my wife
Sandisk SSD drives are poorly made and perform poorly (much worse than others..). This is just Sandisk trying to shift the blame elsewhere..
DailyTech's article (and others) have also added opinions similar to yours. From the DT article:
In fact, it's not uncommon to see SanDisk SSDs rank last in testing in almost every benchmark and by a large margin -- even in Windows XP. Recent testing showed that MSI's Wind netbook was no faster with a SanDisk SATA 5000 SSD than with the standard 80GB HDD -- an Eee PC 1000h featuring similar specifications was significantly faster with a competing SSD from Samsung.
While Vista may be a performance inhibitor compared to Windows XP for SSDs, it appears that most new, current-generation SSDs are having no problems performing well with the operating system. The problem appears to be SanDisk's low reads and writes (67 MB/sec and 50 MB/sec respectively) compared to the competition (i.e., OCZ's new Core Series SSDs which clock in at 120 to 143 MB/sec for reads and 80 to 93 MB/sec for writes)."
TO START
PRESS ANY KEY
Where's the 'ANY' key? I see Esk, Kitarl, and Pig-Up...
Not exactly what you were looking for, but at least on the macbook air the SSD doesnt seem to improve performance, but there are other reasons to get SSDs besides peformance. For starters, you can create a laptop with almost no moving parts, which can be very nice for certain environments. Plus, the SSD is less likely to have a catastrophic crash than traditional hds(provided you aren't doing an inordinate amount of writes, all the more reason to have as much ram as possible!)
Monstar L
... I did not fully understand, frankly, the limitations in the Vista environment."
Be warned, it only works once.
Unless she is also using Vista, but then dinner will be late anyway.
http://cafepress.com/spankymm - for the Masturbating Monkey in you!
Comment removed based on user account deletion
They did intend to change the filesystem when designing Vista, to WinFS. WinFS turned out to stink for a lot of reasons, and seems to have quietly vanished off the product release schedule. This is a good thing: WinFS is XML based and apparently severely patent encumbered, and would mean a nightmare writing and publishing new drivers for Linux and other OS's that can comfortably read and write FAT32 and NTFS now.
So basically, Vista murders your disks? Steve Ballmer should be worried. Didn't they put Hans Reiser in jail for something like this?
Caesar si viveret, ad remum dareris.
Vista does lots and lots of writing - especially lots of small writes... Then again so does XP - just Vista does more.
Trust me, Vista is vicious to a hard drive. I got a new Quad6600 with 3GB and it felt slow... sometimes absolutely crawling because it had a slower 8MB cache 500GB drive installed. I finally figured out that the HD was the performance bottle neck. I just bought a WD Velociraptor (10K RPM 32MB cache) for $300 and my computer feels about twice as fast for daily usage.
Ok, even on SlashDot, this deserves to be bashed for what it is, instead of the we hate MS lovefest that it will probably get.
Why is this the only manufacturer that seems to be having production issues, performance issues and general reliability problems on all OSes? SanDisk is the joke of Flash in all forms, especially SSD.
Motives against Vista...
Hmm, maybe when Vista was released and 80% of the SanDisk Flash Memory failed to perform well enough to be used for Readyboost, they were a bit Pissed Off? How about the devices Vista won't even see properly because they don't meet basic USB or SD specifications, that also POed SanDisk a bit.
SanDisk also has a horrible reputation with USB Card readers, as the devices won't even work at the basic BIOS levels, and people buying them that 'only' used them in Devices were POed and returning them because they started expecting them to work in their computers now too. (Issues like can't see device, SD card, or see it as 1GB when it is a 2GB card are some of the basic problems with SanDisk SD and Flash USB devices.)
99% of all other SD/Flash brands work fine with Vista, see a pattern yet?
Ok, now on to the Vista Issue - This is where it gets borderline insane...
Vista is the only OS that has internal optimizations to work with SSD read/write array patterns. Even with as 'crappy' as the SanDisk people would like everyone to believe Vista handles SSD, Vista actually squeezes about 10-15% more performance out of a hybrid or SSD than XP or other OSes in general. (Sure there are some arguments about how MFRs implemented the SSD array controllers, and SanDisk again seems to be the odd dog out in this discussion.)
So are SanDisk's problems because of Vista or because of SanDisk's 'own' issues?
I guess everyone here should decide for themselves. A few searches on both Vista and SSD or Flash devices in general and a search or two on SanDisk should put this article in perspective.
This would be a lot less laughable if they used any excuse except Vista, the main OS to have SSD kernel level support and the only OS(Windows) to outperform XP and previous versions of NT on SSD drives.
(Be sure to check out the SanDisk demonstrations that specifically use Vista to 'show off' the performance of their drives, that even makes it more goofy.)
My immediate impression is this is somebody trying to blame M$ for their own failings.
How well does this work on Linux (with the various filesystems) and OS/X? Is Vista really doing something stupid, or is it being blamed for the same mistake as everybody else? What about XP?
Other thing is I remember the disk-thrashing bug in Linux Ubuntu. I have it and have to run a startup program to turn off the hard disk power savings to stop the head-park every half second. I did a lot of searching of the web, looking for an explanation of why XP works, and the only real experiments I found indicated that XP just kept reading the disk, so often that it *never* parked the heads. Thus Linux's reduced (but non-zero) use of the disk made things worse. All other tests seemed to indicate they left the power saving settings the same and I never saw any other explanation. This does sound like it might be related to the SSD problems, but those tests were certainly with XP and not Vista-only. Anybody know anything about this?
Oh, also. Vista has a great tool for seeing how much disk activity is going on. Hit CTRL-ALT-DEL then click on "Start Task Manager". On the "Performance" tab, click "Resource Manager". UAC will prompt you to continue. Then click to expand the "Disk" section.
You can see even when you think your computer should be idle that Vista has anywhere from several dozen to over a hundred outstanding writes queued up to the hard drive at just about any time.
The interesting thing is the Ingo Molnar has said outright that none of the current Linux filesystems is GOOD ENOUGH for SSD's - he has his hopes on BTRFS to save us in the longer run -
Precisely. Linux WILL have a fix soon, and it will be incorporated into all the major distros at the next release.
When are we going to see a MS filesystem that doesn't suck? (Alright, I thought about it. Make one with a BSD licence...)
What about OS X? And what is this "Vista" thing everyone is referring to?
Vista actually does contribute to global warming.
Requires big beefy CPUs and wastes cycles on DRM and other assorted nonsense? Check.
Constantly "optimizes" the disk in background, thereby disabling a power-saving measure? Check.
$
http://www.sandisk.com/Corporate/PressRoom/PressReleases/PressRelease.aspx?ID=3785
If Vista's not optimized for these SSDs, are you going to now tell me that an earlier version of Windows IS?
No? Right.
Vista's just fine. It's everyone's favorite punching bag, but much of the bad rap is undeserved and reactive bandwagoning.
Hardware might be further behind. Gone are the days of the heady acceleration in hardware performance found during the 98->2K and 2K->XP transitions.
I've a beefy four year-old desktop which started life in XP and now runs Vista with an experience index of 4.8. That's better than almost all the PCs offered for sale right now! That's the sad bit. The hardware isn't as stupefyingly better in so short a time now, like it was in the past.
USNG: 14TPU4605
The problem SanDisk had is they expected the OS to batch writes to an erase block size (at least 128Kb) and were surprised to find this isn't how operating systems typically work. That's not specific to Vista; it applies to every previous release of Windows, and most other mainstream OSes.
On random writes, the performance of SSDs is terrible, since they need to perform read/modify/write on every small write. So sequential write performance looks fine, and random write performance looks bad.
What filesystem guarantees to write its metadata (directories, bitmaps, etc) in 128/256Kb chunks? None do. Every time the filesystem writes a small chunk of data, the disk has to work extra hard. Any app writing small, random chunks also performs badly (eg Outlook); this is true on XP and Vista (equally.)
Really, SanDisk would have been well advised to speak to OS developers (any) before releasing their first attempt at and SSD. Experience with removable flash (typically file copies) does not equate to experience with fixed disk scenarios (eg registry & log flushes.)
Old does indeed not mean bad. But there are some issues that seem to be impossible to address without a major change in how OS works. Security, stability, predictability and resource use are nowhere to be seen in the bigger OS implementations today.
Security is an afterthought thats solved by endlessly patch defects in applications. This is something that can be solved in the OS and compiler level to a very high degree, just not with todays methods and tools.
Stability is at pretty flaky and fault tolerance at a bare minimum (i don't count bad hardware into this). One would expect a modern computer to be more stable than a Dos, CP/M or MacOS machine that has 20 years of age.
Predictability is much better in Linux than in Windows. In Linux things mostly work if done right and don't work at all if done wrong and theres rarely a gray area there. Applications is another matter where much work is needed in both the Linux and the Windows world. I should be able to do something and know it will be the same no matter how many times i do it. That means stable API's, stable input/outputs, punishing bad behavior and good fault tolerance.
Resource use is the biggest problem and probably something that affects all of the above. When doing stuff in high level languages we sacrifice control and deep knowledge for faster development. The time saved is then spent tenfold throughout the applications entire life in fixing all the little errors that went into it because of lack of both knowledge and planning.
HTTP/1.1 400
My experiences with Vista have been largely underwhelming, at best(and yes, this was on new, Vista compatible hardware, purchased with Vista. Family unit needed a new computer with some sort of bare metal to win32 layer, at the time it would have cost 50ish more to get XP, don't laugh, please). However, I find my credulity rather painfully strained by SanDisk's whining.
Unless there is some fairly subtle malinteraction between Vista and one or more SSD chipset, I have difficulty imagining what sort of pathological interaction there could be that wouldn't also create massive havoc for platter HDD setups(which are by far the majority). SSDs lag behind HDDs a bit for long, continuous read or write operations; but absolutely clean up at scattered read/write. A pattern weird enough to give SSDs real trouble would thrash the daylights out of an HDD setup. At worst, one might expect to see naive optimization for HDDs underusing the SSD's talent for ignoring fragmentation; but that wouldn't be a performance crisis. I'm the first to admit that Vista is pretty unimpressive; but my eyebrows are migrating north on this one.
Working on improvements "just" to see one's program run better seems to be typical for Open Source projects, while the commercial competition tends to invest the man-hours only when there is an immediate need. Mostly for new features, sometimes for performance (but the latter only if customers are complaining).
I've had it made clear by my boss at work that we don't rework our programs unless there is a project for it. Which happens only when our customer are complaining, see above. Something like the repeated rewrite of the Linux scheduler, while the previous version already yields reasonable performance, would be unthinkable in this environment.
C - the footgun of programming languages
While Linux has modern filesystems and gets optimized and fixed almost constantly, Windows Vista still uses the same basic NTFS layout and associated algorithms that were finalised around 10 years ago, and weren't even very good back then. There have been only very minor revisions to NTFS and virtually none of them have improved its performance or reduced its fragmentation.
I don't know if you're blatantly lying or just very misinformed.
Let's take age and revisions first. Ext2 was introduced to Linux in January 1993. NTFS was introduced to Windows in July 1993 (in NT 3.1). So your implication that NTFS is much older than ext is nonsense.
You say that there have been "only minor" revisions to NTFS in comparison to ext2. Ext2 has in fact had only one (stable) revision, ext3, and it introduced only one new feature, journalling (something NTFS has had from the start). Various new revisions of NTFS, on the other hand, have added: transparent compression, named streams, disk quotas, filesystem-level encryption, sparse files, reparse points, update sequence number journaling, $Extend, distributed link tracking, and atomic transactioning, among others.
Some of these features, such as sparse files, are things that ext2 has had from the start. But many, such as transparent compression and file-system level encryption, are not only not, but have even now not found their way into mainstream Linux. To take those two features as an example, the only filesystems even close to mainstream that have them are Resier4 and ZFS, neither of which are ready for widespread use in Linux.
You say "Vista still uses the same basic NTFS layout and associated algorithms that were finalised around 10 years ago" -- conventiently not mentioning that that that 'ten-year-old layout policy' uses a number of modern layout features, such as extents, that have also still not yet found their way into mainstream Linux (ext4 and Reiser4 both support them, but neither are yet out of beta; neither ext3 nor ReiserFS 3 do). Directory contents in NTFS, incidentally, is stored as a B+ tree, which is the same structure that ReiserFS uses due to its scalability.
What's purple and commutes? An Abelian grape.
I would understand that a certain file system would not be optimized for a certain type of media like SSD, but how can a modern operating system be that much hardware dependant?
A logical first step would be to decouple the OS from the file system; and then some day to take advantage of improvements like ZFS...
I'm saying you don't have a 10GB RAM disk, and your assertion that Vista makes RAM run poorly is pure conjecture. Let's say you somehow made a 10GB RAM disk, ignoring for the moment that you would have no RAM to run system, why you would go about installing any programs on a RAM disk is really amazingly stupid, the moment you restarted your computer the program would be annaliated. But clearly you don't have 10GB in your system, or for that matter 10GB of RAM at all, but you're fully willing to give performance descriptions of this imaginary setup, all the way down to the why of "why it runs poorly". THAT is the lie part.
And, as if in an effort to display your complete ignorance, you said:
Please explain why you would make a swap drive out of RAM? Are you so bereft of knowledge about memory management that you don't know that 10GB on a system would never require a swap file? Didn't anyone tell you that a swap file is used when the system cannot use the faster physical memory because there is not enough. Why on earth you have a swap now with 4GB RAM is really beyond my meager understanding, and when you said you'd make an 8GB RAM drive to use as swap file, well, then you really jumped the shark.
All insults aside, If you really want to take advantage of the 4GB you have try shutting off the swap file. For that matter, if you want disk performance, shut off the indexer and system restore too and see if Vista doesn't run faster for you. Vista was really made for people who are going to fuck up their computers, if you promise not to fuck it up, you can turn off all the protection and it will run just as fast as XP on the same hardware. And you'll get the all new DX10 fuzzy feeling when you splash in the water in crysys.
I agree with you however, that crysys is a piece of shit though! I have a 9800GX2 and 4GB and still can't run that bitch in native resolution (1920x1080)! I'll just chalk that up to poor coding, it's not like crytek had a machine that ran the game well, so they had to know it runs like shit. Then, all the reviewers just don't do their jobs. They give it high ratings based on... well, obviously not on playing it.
WinFS was never a file system, it was a layer that got inserted on TOP of the existing NTFS filesystem and the technology is still used by Microsoft today, just for different applications.
+1 IDisagreeSoHeMustBeATrollOrAnAstroturferOrAShill
Vista (and NTFS) were around long before this generation of SSDs were designed.
No sig today...
Comment removed based on user account deletion
I used Vista for a while. I didn't experience any crash, as far as I recall.
But it also happens to be quite resource-hungry, and the interface is (still) terrible.
Circumcision is child abuse.
According to microsoft, germany is vistaland. As if they haven't done enough damage some decades ago...
"Die endgueltige Teilung Deutschlands - das ist unser Auftrag." - Chlodwig Poth
I think you overestimate Vista market penetration
This is true - I feel penetrated every time I'm even NEAR a computer running Vista. Lucky it's not often...
In related news, other companies are moving forward with MLC SSD despite this. Users of other platforms won't have to wait unless they have some undying loyalty to San Disk. http://www.electronista.com/articles/08/07/22/sandisk.on.vista.and.ssds/
Unless your working set is larger than your physical RAM, you shouldn't need a pagefile or swap partition at all.
This is certainly not true for VISTA and many other modern OS's. VISTA performa aggressive background prefetching of commonly used applications. It also builds a prefetch file in the background. This takes a big chunk of memory and a big of HD space. In cases like this where your OS is constantly doing lots of stuff with any of your extra memory in the background, sometimes it makes sense to swap out infrequently used memory to increase performance even if your entire working set fits into RAM. VISTA will run faster with a swap file even if you have 3GB of RAM and do little other than browsing the web. The extra memory from swapping out pages is used as file cache and for background operations that can be sped up by extra memory.
Oh, and why does NTFS need to be defragmented?
For the most part NTFS doesn't need to be defragmented. I've gone long periods of time without defragging on XP. However, if your disk starts getting over 80% full or you get more than 20% fragmentation on the HD, then your performance begins to suffer due to seeking. VISTA defragmentation is actually "smarter" internally than XP even though the interface has been dumbed down. It realizes that some fragments aren't a bad thing as long as the ratio of fragments to file size is reasonable. I believe it tries to make fragments be at least 64MB in size. Therefore a 2GB VOB file could be split into as many as 32 fragments before the file would be considered fragmented. This makes the defragmenter run much faster than XP (which tries to coalesce the whole 2GB file) with very little penalty in performance on the final defragged image. It also makes finding free space for coalescing fragments much easier.
It's a terrible shame that MS dumbed down the VISTA defragmenter interface and makes it hard for you to exclude drives (like SSD's which don't need defragging) from the automatic defrag schedule. It would have been much smarter for them to have the "dumb" interface with a single button to go to "advanced" or "power user" mode that had more options like drive exclusion.
In fact, Linux has at least one filesystem designed for flash.
So why doesn't Microsoft? Obviously, it was more important for them to meet once a week to debate the structure of "shut down" in the start menu.
I'm not making either of these things up, but I can't verify them right now. No time.
Don't thank God, thank a doctor!
I think you overestimate Vista market penetration,
No, as with most Microsoft products, Vista penetrates the market quite thoroughly, violently, and in every possible orifice.
09 F9 11 02 9D 74 E3 5B D8 41 56 C5 63 56 88 C0 is the magic number.