Slashdot Mirror
Samsung's Hybrid Hard Drive Exposed
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."
that buffer is fucking huge. Laptops awesome, wonder when they'll actually work on a regular size one though. Then again, seeing as it's gonna be the first batch out the door, potential issues from what is practically a new drive type will scare me, and my wallet away.
Wonderful idea for the manufacturers, flash drives only get so many read/write cycles before they go T.U. Not so good for the consumers.
Looks like Samsung and Microsoft designed this together.s /HardDiskDrive_20050425_0000117556.htm
http://www.samsung.com/Products/HardDiskDrive/new
It was on display at WinHEC in April 2005.
Sorry, don't know how to link to one of the Caches, but here is the text of the article:
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 different about Vista that makes this drive benefit from Vista. Will the drive not work in Windows XP, Linux or Mac OSX machines?
Anthropic principle: We see the universe the way it is because if it were different we would not be here to see it.
[nitpick]I know you're just trying to be funny, but the site was suspended due to exceeding its CPU quota, not its memory quota.[/nitpick]
Sadly, I can't RTFA as the account has already suffered a slashdotting, but I have a question about this drive. Isn't there an upper limit to how many times you can write to flash memory before it ceases to function? Granted, hard drives wear out eventually, but unless this stuff is of high quality then the cache is going to wear out before the rest of the drive.
When the cache dies off, what happens?
It's designed for Vista, but I want it for Linux. How long until then I wonder?
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...
Please help metamoderate.
Excellent point. TFA has been Slashdotted so I can't see the specs without an undue amount of initiative on my part, but presumably if they put enough flash memory in, and used a proper distributive algorithm to make sure the same sectors aren't constantly written to - there might be little danger of this drive failing any sooner than a conventional drive.
I hope.
The number of read/write cycles is now typically sufficient to write at full speed 24/7 for 3-4 years.
"Who is the Journal of Quantum Physics going to believe?" --Stephen Hawking
"It's a tarp!" -- Dyslexic Admiral Ackbar
You're mentioning aged technology. Flash mems have improved since then, plus, it's slightly different technology.
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.
Full Tilt
Flash technology seems promising and looks poised to take over devices that would be better off using solid state components (laptops, etc) that traditionally don't. I've wanted to invest in Samsung and flash technology in general. Samsung seems to only be on the Asian markets, is this so? Does anyone know of and good mutual funds/ETFs that allows one to invest in this specific tech sector?
why run from Vincenzo?
Why don't they just flat out say they don't know when it's going to be released?
Why would you want your RAM to be unused? Unused RAM is useless RAM. Seriously.
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.
If Vista knows about the CF, why does it need to be on the hard disk itself? It sounds like all the heavy lifting is being done by Vista anyways. WOuldn't it make more sense just to use any CF attached to the system for this caching, etc, and use normal hard disks instead? That way adding CF to a PC would improve its performance, no matter what type of hard disks you have attached.
Check out Spansion if you want to support an American company. They are a spin off of AMD, and have some impressive technology when it comes to flash memory.
Captain Cold takes over the world.
What happens when the flash dies?
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?
Seven puppies were harmed during the making of this post.
the site was suspended due to exceeding its CPU quota, not its memory quota.
So maybe if they had preloaded the site into memory, we wouldn't have this problem...
Seven puppies were harmed during the making of this post.
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 minute while the memory swaps out can come to everyone. It is paticularly stupid on the MS Windows platform where people typically only perform one application task at a time - you do not want the behemoth that is office in memory while you run some graphicly intensive thing or vice versa - you almost always only have one user with one desktop and one application being worked on.
That article mentions power savings a lot, but never boils them down to raw consumption numbers.
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?
--
make install -not war
Back ups are for wimps, back in my day we used Apple's TimeMachine and have done for ages. Think about it.
Jonathanjk.com
The problem here is if we're talking about fully flash hard drives. If you bought two, one for backup (even in a ghost or RAID ghost setting), how can you rely on the fact that one won't die when it was written onto the same exact number of times, byte for byte, and used for the same amount of time? It's similar to current HD's, but these tend to not break at the same time.
Flash also can only be written onto so many times before it's rewriting capabilities start to suffer badly (don't remember the exact number, but this is when flash drives die).
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.
Additionally, do you honestly think any company (Intel, Microsoft, Samsung) would back this technology if it was limited to R/W cycles in thousands?
Oh? Last time I checked...my xp seems to stop working after only several hundered read/writes, funny that.
We wrote a driver to read and write fat 16 flash drives for an embeded system. The testing for it wrote and read full speed 24/7 for two weeks before they died. I assumed that was because of the limited read write settings. Or is it possible the low quality connection was to blame? Doesn't really matter they were only used to transfer settings. As any one whos had to support them knows, they often just die for no apparent reason. I'm not convinced that this is a system I'd want my data on.
Well.. maybe. Or Maybe not. But Definitely not sort of.
What would be neat is if you could swap out flash drives in the event of a failure. Or upgrade the flash drive capacity. I'd be more interested in that than a permanently integrated flash drive. You're correct to be skeptical of its lifespan.
Well then, good news for you: Vista supports a feature called ReadyBoost, which can use just about any flash memory device (e.g. a cheap USB thumb drive) as a cache to improve performance.
$x='S24;r)>63/* h@<5+oZ)32"5cz';$me='phroggy'x$];
$x=~y+ -xz+\0-Tx+;print$_^chop$me for split'',$x;
I can't tell whether you're trying to be funny.
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, too.
Not really. Flash memory is not all that fast, and a lot of boot time is spent doing other things. On all my machines, most of the booting process is concerned with checking and initializing hardware.
AFAIK, the flash is only used for caching small files and for faster booting, all the data will eventually be stored on the HDD. Also, they assumably use algorithms that check the flash for bad sectors and marks them unusable if they stop functioning. HDDs also use similar methods, but a flash drive will be able to die more gracefully, as there is no mechanical parts that can fail abruptly.
Not true. If you write to ALL of the writable adressable area of a flashram , you will not get over 200,000 full writes on average despite the lies. In fact, the parts fail in 2 or 3 weeks of lab benchtests.
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
I retract the statement just made. I tried "grep -R foo" in /etc, and after running it 5 times it ran diskless. The only argument to be made would be about who has the best cache replacement algorithm.
Mark of the Coder fades from you. You perform Opening on World of Warcraft. Warcraft crits GPA for 4. GPA dies.
Actually I think it's more like fixing software problems in Hardware. The situation in which this technology will improve access time is when you have to randomly seek on your harddrive. Unfortunately that is needed in Windows as there is little possibility to keep all your bootup files one after another in the order you need them. With Linux, however that is rather easily possible. You can create an initial ramdisk which the computer can load very quickly without much booting and then boot from it. Theoretically, if you have enough RAM, you can even load your complete system into it.
So now you essentially have to spend a lot of money (Flash and Patents!) on a technology which will, at most, give you an decrease in boot-times and will be obsolete once the power management of the drivers support Suspend to Disk or Suspend to RAM. Just look at Linux or MacOS 8 on an old clamshell iBook. You just close it and it's "Off", you open it again, and after very few seconds it's completely back again.
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.
Heck, MS says XP is "more secure". More secure than what?
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.
It's official. Most of you are morons.
Out of curiosity, how similar is Vista's ReadyBoost feature to just mounting a USB drive as swap in Linux? Can you hot-unplug the drive in Linux if it's being used for swap? 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.
/proc/sys/vm/swappiness ?
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
http://cltracker.net -- powerful craigslist multi-city search
Preloading applications into memory is called caching. And suggesting that these preloaded applications would be swapped into the page file when they could simply be discarded and reloaded from the HDD when more RAM becomes available is silly. The act of swapping running programs and their data into the page file is a different thing altogether, and has nothing to do with SuperFetch. SuperFetch won't prestart the applications, only copy their data into RAM, and then if you happen to start the application in question the cached copy will be loaded instead of the HDD copy.
Sources:
http://www.techworld.com/storage/features/index. cfm?featureid=2814&pagtype=samecat
http://www.bitmicro.com/press_resources_flash_ss d.php
http://en.wikipedia.org/wiki/Flash_memory#Limita tions (yeah, yeah, Wikipedia isn't authoritative, but it's good enough)
Boycott Sony
Out of curiosity, how similar is Vista's ReadyBoost feature to just mounting a USB drive as swap in Linux?
/proc/sys/vm/swappiness ?
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?
$x='S24;r)>63/* h@<5+oZ)32"5cz';$me='phroggy'x$];
$x=~y+ -xz+\0-Tx+;print$_^chop$me for split'',$x;
I decided to dig up a source for my claim and failed to produce one. Additionally, I found a source that makes it seem like SuperFetch does in fact swap cached data to the page file. Looks like me giving Microsoft the benefit of doubt has backfired, as I'm now looking forward to SuperFetch a lot less. I apologize for bashing you, I was the one being silly here.
We did some basic research with Flash / HDD hybrids two years ago. As such disks weren't available, yet, we were using a real (Notebook)HDD and a IDE-Flash-HDD in parallel.
." in the root of a freshly booted system).
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...
It would also be ideal for laptop systems to save power...
95% of all computer errors occur between chair and keyboard (TM)
As often as I have had memory cards fail for no reason with my digital cameras, I'd hate to see this on a PC or Laptop, and sure as hell not in a Server.
Why not just make it 128MB or 256MB battery-backed cache, with a mirror on the HD. Part of the spin-up process could be to verify the code is in memory, and let it boot off cache RAM or something...
Sorry, flash is great when you need portability, not in data-intensive operations.
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!)
--
Given enough personal experience, all stereotypes are shallow.
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 parts (in a way that is persistent across power cycles for the drive), it is really easy to construct a case where you would artificially wear one part of the unit faster and start getting errors when the drive is much less than 3-4 years.
The issue has been partially worked around, but the workaround is only sufficient for devices that don't have heavy write loads (e.g. digital cameras), not for a main system volume or even necessarily for a cache, though it -might- be good enough for a cache. Without a lot of implementation details, I wouldn't be comfortable with this feature on a hard drive. Thus, I'm not going to jump on this bandwagon until they've been out there for several years just so I can see the failure rate figures before making that call. I also want a guarantee that I'll be able to pull or install a jumper and disable the flash entirely so that when it eventually fails, the drive will still be usable, albeit slower.
Check out my sci-fi/humor trilogy at PatriotsBooks.