Samsung's Hybrid Hard Drive Exposed 255
Erica Campbell writes "Samsung is preparing to release a new
Flash memory-assisted computer hard drive
that boasts improved performance, reduced energy consumption, a faster boot time, and better reliability. The new hybrid hard drive will be released around the same time as the upcoming Windows Vista operating system and will be one of the first hardware designed specifically to benefit from it."
So awesome (Score:5, Insightful)
Re: (Score:2)
This was in the news a year ago (Score:5, Informative)
http://www.samsung.com/Products/HardDiskDrive/new
It was on display at WinHEC in April 2005.
Re: (Score:2)
TFA (Score:5, Informative)
Samsung's HHD prototype
Samsung is preparing to release a new Flash memory-assisted computer hard drive that boasts improved performance, reduced energy consumption, a faster boot time, and better reliability. The new hybrid hard drive will be released around the same time as the upcoming Windows Vista operating system and will be one of the first hardware designed specifically to benefit from it.
Samsung's HHD - faster boot and resume on Vista
In mid-May 2006, Samsung unveiled a prototype hybrid hard drive (HHD) at WinHEC, the Windows Hardware Engineering Conference. Samsung's prototype HHDs have a buffer of 128 or 256 MB, much larger than the 8-16 MB of cache in current hard drives. This new buffer differs from the existing cache buffer on hard drives not only in size but also in structure, composition, and qualities. Conventional cache is made out of volatile memory that is erased when the drive is powered down. HHDs add another layer of cache consisting of Flash memory that is non-volatile and can be accessed quickly when the drive is powered on. Adding a large buffer to a hard drive can also reduce the drive's power consumption, thereby increasing the battery life, and reducing the time required for the system to resume its operation after suspension. Indeed, boot or resume time will occur about twice as fast as conventional hard disk drives, saving 8-25 seconds, and laptop batteries will provide 20 - 30 minutes more power. Another added bonus of the HHD is the improved reliability due to less mechanical wear and tear.
Samsung and other manufacturers are currently pursuing Solid State Drive (SSD) technology (to be covered in an upcoming TFOT article). Currently Flash prices are too high to allow SSDs to replace standard hard drives of any reasonable size and, although Flash prices are continually falling, it will be several years until such a drive will become affordable to most users. Here enters the near-term solution for enjoying improved performance at a reasonable price - the hybrid hard drive, combining the low cost and large storage capacity of conventional hard drive technology with quick and low-power Flash memory.
Apart from the reduction in Flash memory prices, hard drive manufacturers such as Samsung believe that we are about to undergo a major storage revolution in the next few years due to the upcoming release of Windows Vista. This new operating system from Microsoft will introduce three new performance-enhancing technologies: SuperFetch, ReadyBoost, and ReadyDrive. According to Microsoft, "SuperFetch understands which applications you use most, and preloads these applications into memory, so your system is more responsive". Windows ReadyBoost allows users to use a removable Flash memory device such as a USB thumb drive to improve system performance. ReadyBoost retrieves data stored on the Flash memory more quickly than data stored on the hard disk, decreasing the interval until the PC responds. Windows ReadyDrive enables Vista-based PCs equipped with an HHD to boot up faster, resume from hibernate in less time, preserve battery power, and improve hard disk reliability.
Hard drive platters won't have to spin as much
Hard disk platters are components of hard disk drives that consist of circular rigid disks that store magnetic data. While the platters in conventional hard drives rotate most of the time, thereby consuming a great deal of power, the platters in HHDs are usually at rest, as if they were off. In HHDs, incoming data is generally written to the Flash buffer and any saved documents are saved to the buffer, instead of being written to the hard drive each time. Only when the Flash buffer is almost full or when the user accesses a new file that is not stored on the buffer, will the HHD platter rotate or "spin up". Thus, the battery power of laptops with HHDs is preserved, extending battery life.
To learn more about Samsung's hybrid hard drive technology, TF
What's so special about Vista? (Score:5, Interesting)
Re:What's so special about Vista? (Score:5, Interesting)
Re:What's so special about Vista? (Score:5, Interesting)
Re:What's so special about Vista? (Score:5, Funny)
Oh wait...
Re: (Score:3)
Re: (Score:2)
It is usually the first thing I turn off. But then, I do not boot my systems very often.
Re: (Score:3, Insightful)
Re: (Score:3, Informative)
You're not running a shitload of security updates if you haven't rebooted in 55 days.
Re:What's so special about Vista? (Score:4, Interesting)
Oh yeah, and it'll be fast as hell, too.
Re:What's so special about Vista? (Score:4, Insightful)
Re:What's so special about Vista? (Score:4, Interesting)
The access time is also VERY low compared to a HDD, and unless the controller itself fries, its almost impossible to have catastrophic data loss.
Basically, we cant switch fast enough, there are no downsides but price.
Re: (Score:3, Informative)
It depends. I have one of those "IDE Flash disk" modules in a system I want to keep as silent and lowpower as possible.
It looks like a normal IDE connector (a bit larger) and plugs directly in the motherboard, looking just like a normal IDE disk to the BIOS, the OS, etc.
(so you can just install your system on it and boot, read/write, etc. no special drivers or trouble with booting from USB)
However, this device is easily outperformed by any modern harddisk.
funny? (Score:3, Interesting)
That is actually reason enough for me to re-think that whole Vista thing.
Has the ability to boot and run Linux off flash made you "re-think that whole Linux thing"?
With partial flash drives and eventually 100% flash drives, the last major component of computer hardware failure, namely, all of those closely moving parts in a hard drive, will be wiped out.
They'll be replaced by a medium that has a much higher MTBF for writes.
Oh yeah, and it'll be fast as hell, to
Re: (Score:2)
Re: (Score:2)
http://channel9.msdn.com/Showpost.aspx?postid=238
Re:What's so special about Vista? (Score:5, Funny)
Actually, it's spelled 'collusion'.
How long until failure? (Score:2, Interesting)
When the cache dies off, what happens?
Re:How long until failure? (Score:4, Interesting)
Re: (Score:3, Insightful)
Re:How long until failure? (Score:4, Informative)
Linux Next? (Score:2, Interesting)
Re: (Score:2, Insightful)
Re: (Score:3, Insightful)
Open source coders are good, but they're not Godlike. If the specs aren't open they get practically nowhere sometimes, and if they are - they'll still take as long to iron out the bugs and get it stable than anybody else.
Re:Linux Next? (Score:5, Interesting)
Re: (Score:2)
Why? If your machine is hitting swap that often, you need to get more RAM. That is a HUGE performance hit. Ideally, your system should barely touch swap. At least on Linux. I guess Windows can be pretty liberal about swapping things out...
-matthew
Re:Linux Next? (Score:4, Interesting)
Re: (Score:3, Interesting)
Monitor swap usage on any healthy Linux system and you'll notice that usage remains pretty low most of the time. Anything you DO swap out should be largely unused anyway. So I don't really get how using flash for swap woudl wear it out faster unless you were using it as a substitute for more RAM.
-matthew
Re: (Score:2, Insightful)
Re: (Score:2, Funny)
Re:Linux Next? (Score:5, Funny)
Forever, then?
Apple? (Score:5, Interesting)
Given Apple's strong relationship with Samsung (iPod shuffle+nano memory both come from Samsung, I believe- and I'm almost positive Samsung has supplied RAM to apple on+off since the golden olden days), what do others think about the possibility of this ending up in a Powerbook, er, Macbook Pro- and 10.5 being designed to take advantage of it?
Apple can be hit or miss with the latest and greatest- they took forever with USB2 (yeah yeah, firewire blah blah) and lagged behind a lot of the smaller laptop mafacturers with Expresscard (given there's next to nothing for expresscard, who can blame them?)...it'll be interesting to see if Apple thinks this is a win or lose technology...
Re:Apple? (Score:4, Informative)
In short: Intel apparently has a similar technology (presumably with the flash memory being on the motherboard, rather than in the hard drive, which seems like a better idea), and it's rumored Apple is working with them to get it implemented for next year's Mac laptops.
Investing in flash technology (Score:5, Insightful)
Spansion (Score:2, Informative)
Re: (Score:3, Informative)
http://www.samsung.com/AboutSAMSUNG/ELECTRONICSGLO BAL/InvestorRelations/IRFAQs/StockDividend/index.h tm#a2 [samsung.com]
It's listed in London and Luxemburg too, and in the US, you can buy stock through Citibank.
It only took me a minute to find this information, it wasn't secret, hidden or hard to find. I only needed two clicks on the Samsung site.
tricky marketing (Score:5, Funny)
Why don't they just flat out say they don't know when it's going to be released?
Super Enthused (Score:2)
Sure faster boot ups will be great and eventually bootup will equal Flash -> DDR2 memory transfer speed but this seems like more of a limited upgrade.
Except the clear shell that's just too sexy for words!
Re: (Score:2)
Why does the CF have to go on the disk? (Score:5, Interesting)
Re:Why does the CF have to go on the disk? (Score:5, Informative)
Who knows how much benefit it really provides, but it sets the direction. Nice for the software to be ahead of the hardware.
Re: (Score:2)
So what? [addonics.com]
Re: (Score:2)
Neither are hard drives (with the possible exception of those expensive 10K RPM ones). Besides, the point of the flash memory is to handle small, random-access stuff -- exactly the area disks are worst at.
Re: (Score:2)
Nearly flash memory nor hard drives are anywhere near as fast as USB2 or SATA 300. It's not going to make much difference to performance, unless you're using a whole lot of them (in which case SATA 300 has the advantage because it's several busses, while USB 2 is typically just the one shared bus).
Re: (Score:3, Interesting)
Head to Head Power Consumption (Score:3, Insightful)
If a standard current notebook 40GB HD were replaced with 10 standard 4GB Flash drives, how much less power would the Flash consume than the HD?
oh? (Score:3, Funny)
Oh? Last time I checked...my xp seems to stop working after only several hundered read/writes, funny that.
Re: (Score:2)
YES!
"MONEY MONEY MONEY!" -- from the horse himself
Since the site is down (Score:2)
Fixing software problems in Hardware (Score:2, Interesting)
Use Flash for directory structure not cache! (Score:5, Interesting)
Our goal was to minimize energy consumption for mobile devices (i.e. not a lot of ram available for caching and the device is switched off repeatedly to save energy).
Using a very sensitive (time resolution wise) energy measurement device, we determined, that most energy was consumed by moving the heads into position. The difference was substancial: Around 0.63W for the HDD spinning idle and about 5.3W during heavy seeking (e.g. trigered by a "find
We decided to not use the flash as cache (flash is quick to read, but slow to write) and just put the relatively static metadata (directory structure, inode tables...) onto the Flash drive, but keep there files and data on the HDD, as each directory access triggered a expensive seek, but delivered very few data, compared to reading a file.
To simulate our mobile device we used a Linux-System limited to 32 ram to prevent the system from excessive caching.
We observed up to a factor 8 reduced energy consumption and as a surprising side effect a factor 6 increase in speed!
When increasing the available Ram, this advantage quickly vanished on repated benchmark runs, as the System appearently cached the directory structure very effectively. The first run after booting however still performed substancially better with our system, no matter the amout of ram. (And this was our target useage profile: Power on, search something, Power off).
As the code was an embarrassingly ugly hack to the ext2 driver and we envisioned trouble keeping the hdd with the data and the flash-hdd in sync, it was not persued further.
However with hybrid drives becoming available, it might be worth a more detailed analysis...
Neat... not new (Score:2)
Interface (Score:3)
My main question is what the interface is going to be to this. Is it going to appear as regular flash media? Will there be extended PATA and SATA commands to address the Flash/modify the drive priorities? The re-posted article says that it's only designed for Windows Vista and will not support XP; does that mean that the interface is now totally different from anything else and these drives won't work?
Finally, why the hell haven't they given Linux hackers a go at the drives? There are certainly those who would be interested in supporting the technology. AMD and Intel sure seem to (note that Linux supported x86_64 before it even shipped!)
Re:Ship time (Score:5, Informative)
Re: (Score:2, Interesting)
I hope.
Re:Ship time (Score:5, Informative)
Has it changed in 3 years? (Score:5, Interesting)
Re:Has it changed in 3 years? (Score:4, Insightful)
Re: (Score:3, Funny)
Flash parts die in 3 weeks of solid write tests (Score:5, Informative)
The flash fanatics keep modding down these facts to -1 for some insane reason here.
Flash has LIMITED write life.
The devices spread the data around to hide the limited write cycle life, and uses error correction to hide the limited write cycle life.
At some point its worthless.
Flash is idiotic for a backing store (virtual memory) based hard drive. And atomic-commit algorithms and other safety mechanisms for structure preservation and corruption avoidance such as "Journaling" only make the chatter worse.
All the disk chatter destroys the lifespan of the flash part.
Worse... flash is SLOW for lots of non-paralell-capable individual 512 byte requests, which typically are not spread across multiple flash parts.
True, a megabyte read can be fast in flash, but lots of random 512 byte reads or writes are far slower than a modern hard drive STILL in 2006. (15,000 rpm scsi from 7 diff manufacturers for example).
But the article is about hard drives... still.. its hopeless and foolish.
people who use their computers a lot will have data corruption earlier... all due to flash problems
Re: (Score:3, Interesting)
Really? What are the seek times on these 15,000 rpm scsi drives that out-perform solid-state devices, and where can I buy them?
Re: (Score:3, Interesting)
Enable swap on a flash volume. Install it in your grandmother's computer (256MB RAM, with the OS recommending 512MB). This is a real cause for concern, IMHO.
Not all wear leveling algorithms are created equal. In the worst case, your writes get hashed across a relatively small percentage of the cells in a particular flash part. Even in the best case, your wear leveling is still per flash part, not across the entire hard drive. Thus, unless the drive is spreading the cache load out evenly across all p
Re:Ship time (Score:5, Insightful)
Re:Ship time (Score:5, Informative)
Well then, good news for you: Vista supports a feature called ReadyBoost [microsoft.com], which can use just about any flash memory device (e.g. a cheap USB thumb drive) as a cache to improve performance.
Re: (Score:2)
Re: (Score:3, Interesting)
And is there any setting in Linux to tweak to let the system know you've got a fast swap partition, other than simply monkeying with
Re:Ship time (Score:4, Informative)
Not really similar at all.
Can you hot-unplug the drive in Linux if it's being used for swap?
Nope, your system will crash unless you swapoff first (and of course that will fail if you're using more memory than you have physical RAM).
According to a FAQ on ReadyBoost I found, Vista will back up the pagefile to disk so it's not a catastrophe if you yank out the USB stick.
Correct. The data on the USB stick is used as a cache, not swap.
And is there any setting in Linux to tweak to let the system know you've got a fast swap partition, other than simply monkeying with
If there were, how would you want this information to affect Linux's behavior?
Re: (Score:2)
You might think that flash memory is much faster than harddisk, but this is not really true (certainly for write).
Try to benchmark a USB key and a modern harddisk. The disk will easily do 50-60 MB/s bulk transfers. Try to make the USB key do that.
You may gain a little because a flash key does not need to seek, and thus has less latency when a single disk is used as swap and filesystem and needs to seek between the swapspace
Re:Ship time (Score:5, Insightful)
Additionally, do you honestly think any company (Intel, Microsoft, Samsung) would back this technology if it was limited to R/W cycles in thousands?
Last but not least, such hard drives will also store data which stays more consistent than regular data. It could store vital boot files, files to your most common applications, etcetera. In other words, files that do not change much over time. It's not like you're going to save your most frequently used documents to this section of the drive.
So to sum things up, you will not have to worry about the SSD part of the drive. It will probably even outlast the mechanical part of the drive.
Re: (Score:3, Insightful)
I would imagine that all of the boot files plus commonly used .dll files would get stored to the flash section. Then when the system shuts down, it would write the page file to the flash in addition to all of persistent application data necessary to quickly boot the hibernated session.
Flash has gotten better, but it can still fail... (Score:2, Interesting)
Re: (Score:2)
Intel and Microsoft are obviously trying to make as big profit as possible, but that doesn't mean they're idiots. Yes, Windows Me sucked, but it was not developed to provide excellent stability and security. It was well known that as long a
Re: (Score:2)
I am sure Microsoft knew that. But Windows ME was still marketed as an improvement, and that is the point:
Selling something often has higher priority than making sure the customer is happy and will return.
Re:Ship time (Score:4, Insightful)
Than previous editions of Windows, of course, and they're right.
I just had to clean my wife's laptop that is SP2 and fully patched with MS Windows Defender, MS Windows firewall and AVG anti virus and the thing has spyware crap on it that was bringing it to its knees.
And are Defender and AVG kept up to date? Is she running as an admin and installing any old crap she comes across? Is the firewall actually running?
A single anecdote proves nothing; I can attest to three XP machines that I personally use that are perfectly clean and have been for serveral years. Before blaming the OS, I'd check with your wife about how she was actually using the machine.
Yes, I do think any one of those companies would back any technology if that technology would make them a profit.
I can see that from Samsung, but neither Intel nor MS are going to be producing or selling these things, nor any hardware or software that relies on them. They're not going to stand to make any money on them, but will take a knock to their reputations if they back them and they're crap. Perhaps MS won't care, but Intel has serious competition from AMD, and can't be quite that cavalier.
Re:This site could benefit (Score:5, Funny)
Re:This site could benefit (Score:4, Funny)
So maybe if they had preloaded the site into memory, we wouldn't have this problem...
Re:SuperFetch uncool... (Score:5, Insightful)
I'm sure that Vista is smart enough to free up the RAM that SuperFetch is using if it could be better used for something else. It's really nothing more than a more pro-active version of the disc-cacheing that every operating system already uses.
Re: (Score:3, Interesting)
It's a tweaked XP not something newer than plan9 - it will probably swap it out to disk so you get a big page file and a delay while it is doing it, which is probably one reason this new drive will help.
Personally I think it is stupider than doublespace since memory limited programs like image editors are commonplace now. The annoyance of not being able to print for a couple of mi
Re: (Score:2)
Re: (Score:2)
No. I'm talking about the preloading into memory of a pile of applications and then having to swap that out of memory when you start something different. You get that now with office and some other stuff and I really don't want to see that happen with anything else let alone every major application on the PC at once. Perhaps some reading comprehension would be in order before putting something I never wrote or even implied in quotation marks.
Re: (Score:3, Informative)
Re: (Score:2)
I'm assuming SuperFetch will be like the MS Office caching from the same company and will swap out to virtual memory instead of discarding the cached data. Unfortunately I haven't read anything yet that convinces me otherwise although I would like to be proved wrong - do you have any links?
Re: (Score:3, Insightful)
Re: (Score:2)
But since SuperFetch preloads program data, the data is already backed on disk, it just needs to update the SuperFetch cache table and voila, fresh memory page ready to serve the hungry hippo. Should be almost as quick as a regular alloc. At least that's my take on it.
Re: (Score:2)
1/ Vista boots, starts a pile of services and asks for a login.
2/ Vista looks up a list of recently used applications and preloads them into memor
Re: (Score:2)
I don't think that Microsoft programmers are so dumb that they would write memory info which they loaded programs (from disk) to a different part of the disk, taking time.
Maybe YOU should take some time. To study how a virtual memory system works, and what is done with clean and dirty pages when they have to make room for other data.
Re: (Score:2)
Why on earth would it do that? This is permanent data we're talking about, not transient; if the RAM is needed for something else, it will simply be dumped. There is absolutely no reason whatsoever to write it to the page file.
It is paticularly stupid on the MS Windows platform where people typically only perform one application task at a time
Well, I'll grant you that the user is typically only interacting with one app at a time. However, I can't remember the last time I
Re: (Score:2, Informative)
Re: (Score:2)
Re: (Score:2)
-matthew
Re:Flash (Score:5, Funny)
Re:Flash (Score:4, Informative)
The same thing that happens when your hard drive crashes - kiss the data goobye. That's what backups are for. You DO backup every day, don't you?
Re: (Score:3, Funny)
Re: (Score:2, Interesting)
Flash also can only be written onto so many times before it's rewriting capabilities start to suffer badly (don't remember the exact num
Better than HDDs (Score:3, Informative)
Re:Is ReadyBoost really worth a crap? (Score:4, Informative)
How is this an improvement?
Because the _latency_ of flash is dramatically lower than mechanical hard disks.
You are looking at throughput, not latency, which is _vastly_ more important when talking about average access patterns. This is why an older SCSI drive with markedly lower throughput, but significantly better latency, will often perform better (especially for things like swap).
(Not to mention, your estimate of a 7200rpm drive is pretty generous to the tune of nearly 2x real-life performance).
I understand that there are other factors in play when accessing the hard disk, but.. I digress. Is this supposed to be a cheap way for Joe Schmoe to upgrade performance?
Yes. More accurately, cheap *and easy*.
"Don't buy 1GB of RAM for $100, but a 1GB flash drive for $30 and get 1/109th of the performance upgrade!!"
Firstly, it's going to deliver a significantly better benefit than than.
Secondly, upgrading RAM requires opening the case and putting it in. Most people are not comfortable with opening the case in the first place, let alone mucking around inside the thing possibly breaking stuff.