Beta

Slashdot: News for Nerds

×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Israeli Startup Claims SSD Breakthrough

kdawson posted more than 4 years ago | from the believe-in-what-you-write dept.

Data Storage 159

Lucas123 writes "Anobit Technologies announced it has come to market with its first solid state drive using a proprietary processor intended to boost reliability in a big way. In addition to the usual hardware-based ECC already present on most non-volatile memory products, the new drive's processor will add an additional layer of error correction, boosting the reliability of consumer-class (multi-level cell) NAND to that of expensive, data center-class (single-level cell) NAND. 'Anobit is the first company to commercialize its signal-processing technology, which uses software in the controller to increase the signal-to-noise ratio, making it possible to continue reading data even as electrical interference increases.' The company claims its processor, which is already being used by other SSD manufacturers, can sustain up to 4TB worth of writes per day for five years, or more than 50,000 program/erase cycles — as contrasted with the 3,000 cycles typically achieved by MLC drives. The company is not revealing pricing yet."

cancel ×

159 comments

hmm... (0)

Anonymous Coward | more than 4 years ago | (#32587016)

promoting your own company via slashdot much?

Re:hmm... (-1, Troll)

Anonymous Coward | more than 4 years ago | (#32587788)

What do you expect from a jew?

Re:hmm... (-1, Troll)

Anonymous Coward | more than 4 years ago | (#32588032)

lol, so true. They do look after each other's interests, and actively try to supress people of other races.

Cost? (4, Informative)

Manfre (631065) | more than 4 years ago | (#32587034)

If we have to ask how much it costs, we definitely cannot afford it.

Re:Cost? (5, Insightful)

the linux geek (799780) | more than 4 years ago | (#32587044)

Early adopters will pay for continued R&D, which will then make this affordable for most people down the line. It's how these things work.

Re:Cost? (5, Interesting)

Anonymous Coward | more than 4 years ago | (#32587194)

You have an interesting point there.

Several years ago, maybe back in 2005, Anobit visited us and showed off what they were working on. They were little guys in the flash/solid state business and had come out with this nifty algorithm that would allow the flash with really low read/writes with perform like today's current SSDs.

They were the first (that I know of) to come up with a way to spread the writes across unused portions of memory so that on average, every bit of memory would have the same amount of wear on them. It wasn't until several years later that I saw on Slashdot that Intel had come up with this "new" idea in their SSDs.

Back at the time, the Anobit technology was really cool. But unfortunately, they were prohibitively expensive and we could not use them in our rugged systems.

Seems that they have still been hard at work over there. Very cool. They deserve the success.

Re:Cost? (0, Troll)

gandhi_2 (1108023) | more than 4 years ago | (#32587260)

astroturf much?

Re:Cost? (0)

logjon (1411219) | more than 4 years ago | (#32587282)

Yeah, for a minute, I thought 'Cool, maybe this really is an innovative company,' until I saw that it was an AC post.

Re:Cost? (2, Insightful)

morcego (260031) | more than 4 years ago | (#32587430)

If this is really astroturfing, they just shot themselves on the foot. I mean, I've just got the message that this new technology of theirs will be "prohibitively expensive" ...

Re:Cost? (2, Insightful)

bm_luethke (253362) | more than 4 years ago | (#32587476)

So, lets assume what you say is true - is this really a nice business that deserves success? Hard to say.

Obviously if they can do all that is claimed then they "deserve success", though of course that depends on your definition of success. If success means being the richest company in the world showered with personal sex slaves then, no, they really didn't deserve that. If you mean deserve to pay their employees a slightly above average salary for their area and have a slightly above average return for their investors then certainly - I would say they deserve more than that.

Of course that is the crux of the problem that is asked and the one you bring up - they took a cheap system and through software made it perform as well as the high dollar items. They then apparently turned around and charged the similar to the high end items which kinda defeats the whole "cheaper" angle. They do not deserve to do that because they found a nifty way to do something.

Since you are an AC there are already a few posts accusing you of astroturfing, if so then it is a poor attempt. You tell us a story where someone is charging WAY too much for their product and basically failed due to a bad marketing department (marketing isn't just there to hype a product, in a successful business it has a real impact on how profitable things are). If they can take a cheapo drive and through software/firmware make it perform like a high dollar one and then charge me most of what the high dollar one costs - why purchase theirs? They would have to have nearly totally equal guarantees that the enterprise level devices did.

In short getting 95% the benefit at 90% the cost isn't really worth it - that extra percentage in costs is usually worth other intangibles ("Who ever got fired because of purchasing IBM" was an effective marketing tool for a reason even when you got 90% the benefit at 110% the cost), getting 90% at 70% the cost very much is. In the longer run if true then this will make a difference - if they have a patent then selling/licensing it can generate a decent amount of money if done well. But if they follow the pricing model you allude too then it will be a dead end.

Wear balancing is 1999 (0)

Anonymous Coward | more than 4 years ago | (#32587938)

Except we've been wear balancing as a standard since the 1990's and we certainly didn't invent it.

Re:Wear balancing is 1999 (1)

hairyfeet (841228) | more than 4 years ago | (#32588006)

Question: Has anybody really sat down and pounded the fuck out of these SSDs to see what the REAL numbers are, or is everyone simply taking the companies word for it? I mean with HDDs we've all (well most of us geeks here at /.) have pounded the shit out of a drive with heavy I/O so we have a pretty good idea what the MTBF is, but I haven't actually seen any sites where they have just taken these new SSDs and seen how many actual read/write cycles it takes to really kill the cells.

So does anybody have any links with real numbers, so we can judge what kind of risk we are looking at here? I mean having more speed is nice, but if it ends up as risky as RAID-0 you can keep it, thanks anyway. with heavy audio/video editing I get about 3 years out of a HDD, which by that time I'm ready for a larger size anyway. So anyone have any hard data? Hell even some anecdotes on how long they have lasted on your server would be nice.

Re:Wear balancing is 1999 (1, Informative)

Anonymous Coward | more than 4 years ago | (#32589268)

I can't give exact figures but for a little while I was involved with an 1MH MTBF test on STEC SSDs from a major OEM. The consensus from the OEM's engineers was that so far it had been impressive. That was a while back though.

they didn't invent wear leveling (4, Informative)

YesIAmAScript (886271) | more than 4 years ago | (#32588216)

Wear leveling was normal for NAND long before that.

What kind of n00b are you?

http://www.google.com/patents?vid=6850443 [google.com]

Re:Cost? (0)

Anonymous Coward | more than 4 years ago | (#32588284)

This is called Wear Leveling [wikipedia.org] .

Better ECC (2, Interesting)

Anonymous Coward | more than 4 years ago | (#32588852)

It's just a matter of time before someone would use a stronger ECC. Now each 512-byte sector has extra 16 bytes for ECC checksum, which is enough to recover one bit. Given enough space for the checksum it's possible to recover as much data as needed. There are a lot of implementations in hardware. Every wireless tech designed in the last 20 years uses one, typically amount of extra data is in range 1/6 - 1/2. Hard drives certainly implenent better ECC too.

Now the problem is where to place extra checksums in current NAND chips, but it should be solvable. This problem is about as difficult as implementing wear leveling.

Re:Cost? (-1, Troll)

Anonymous Coward | more than 4 years ago | (#32589440)

(Score:-1, Jew)

Re:Cost? (-1, Troll)

spyder-implee (864295) | more than 4 years ago | (#32587236)

"we definitely cannot afford it." Oh don't be such a Jew.

Re:Cost? (0)

Anonymous Coward | more than 4 years ago | (#32587450)

"we definitely cannot afford it."

Oh don't be such a Jew.

yes you're a big, talking about cheap jews. i bet i donate more money to charity in a year than you have in your entire lifetime.

Re:Cost? (-1, Troll)

Anonymous Coward | more than 4 years ago | (#32587540)

i bet i donate more money to charity in a year than you have in your entire lifetime.

You have to have some way to feel better about cutting up little boys' penises.

That's why you... (-1, Troll)

Anonymous Coward | more than 4 years ago | (#32587708)

i bet i donate more money to charity in a year than you have in your entire lifetime.

You have to have some way to feel better about cutting up little boys' penises.

Keep the tips.

Re:Cost? (-1, Troll)

Anonymous Coward | more than 4 years ago | (#32587714)

"we definitely cannot afford it."

Oh don't be such a Jew.

yes you're a big, talking about cheap jews. i bet i donate more money to charity in a year than you have in your entire lifetime.

And I'll bet they're all jewish charities, too.

Hint: Donations to AIPAC don't count as charity.

Re:Cost? (-1, Troll)

spyder-implee (864295) | more than 4 years ago | (#32587840)

I would donate more, but the Jews who run the global economy stole all my money in the great GFC of 09.

Re:Cost? (2, Informative)

renoX (11677) | more than 4 years ago | (#32588182)

Not really: their technology is used to make MLC as robust as SLC, so if it cost more than SLC's price, then it's useless..

Re:Cost? (0)

Anonymous Coward | more than 4 years ago | (#32589204)

Does this breaktrough affect X4 or X6-like MLC flash durability?

Not to mention counteract the increased degradation by the onslaught of scaling nand.

Big Deal. (1)

Phybersyk0 (513618) | more than 4 years ago | (#32587052)

Call me when it's 75% cheaper than other "solutions".

Re:Big Deal. (1)

TouchAndGo (1799300) | more than 4 years ago | (#32587408)

Cause technological advances are only progress if they mean you can get a cheaper netbook right this second.

Re:Big Deal. (0)

Anonymous Coward | more than 4 years ago | (#32587544)

Speak for yourself, I can afford it.

Re:Big Deal. (-1)

Anonymous Coward | more than 4 years ago | (#32587518)

Call me when it's 75% cheaper than other "solutions".

What, are you looking for a final "solution" or something?

Re:Big Deal. (1, Interesting)

mlts (1038732) | more than 4 years ago | (#32587732)

Actually, I'd love something with any of the following:

1: Noticeably better price, but without sacrificing reliability. An average HDD in the enterprise has 1 million hours MTBF with constant reads/writes. A SSD should be similar, or perhaps a lot more because there are no moving parts.

2: An archival grade SSD that can hold data for hundreds, if not thousands of years before so many electrons escape the cells to make a 1 or a zero impossible to tell apart. I don't know any media that can last for more than 10 years reliably. Yes, maybe a CD-R or two may last that long, but it is more of a matter of luck than anything else.

3: SSDs using a different port than SATA. Perhaps have it interface as a direct PCI-E device with a custom bus to add more SSD capacity in a similar form factor to RAM DIMMs.

4: A SSD drive built onto the motherboard. This way, a laptop can be a bit thinner due to not worrying about a 2.5" drive.

5: Combine #1 and #2, and make a device like a tape library that can take SSDs in an optimized form factor and switch them in and out. This way, backups can be copied to a SSD module, module can be dumped in a bin for Iron Mountain to take off.

6: Combine a cryptographic token and a SSD array, so one can have an encrypted hard disk where the PIN is typed on the device itself before it can be used. This way, no keyloggers on a compromised PC can intercept the data. Add to this volumes where various PINs protect certain volumes and too many wrong guesses would have the device zero out the key for that volume, and this would be a way to back up PCs securely without needing any additional encryption software.

7: Combine a fast flash array with a tape library for an easier way to do D2D2T backups.

8: Put some flash onto a tape format, so a tape can be encrypted with one key, but the flash storage on the tape would store an access list of who can unlock the tape's master key. This way, a passphrase, a smart card, and a PGP/gpg key on someone's machine all work to recover data from a tape.

9: A read-only format that can be made very cheaply with a decent capacity. If done right, this might be able to replace Blu-Ray for a movie or audio format. To boot, libraries can be made where all the disks could be readable at once.

10: A standardized full disk encryption format. This way, I insert a flash disk into my camera or phone, enter a password, and it can read/write to that. Then, put it into my computer, type the passphrase, copy the data. If the flash disk is stolen, the data is protected unless the attacker can yank the key out of the computer or phone's memory (a lot harder feat than just picking up an accidentally lost flash drive.)

Re:Big Deal. (1)

Zakabog (603757) | more than 4 years ago | (#32587772)

3: SSDs using a different port than SATA. Perhaps have it interface as a direct PCI-E device with a custom bus to add more SSD capacity in a similar form factor to RAM DIMMs.

Seriously...? [newegg.com]

Re:Big Deal. (0)

Anonymous Coward | more than 4 years ago | (#32588120)

wow, I save 100$!

Re:Big Deal. (2, Informative)

vadim_t (324782) | more than 4 years ago | (#32588846)

1: Noticeably better price, but without sacrificing reliability. An average HDD in the enterprise has 1 million hours MTBF with constant reads/writes. A SSD should be similar, or perhaps a lot more because there are no moving parts.

It's a tradeoff. Reliability needs redundancy, and redundancy costs money. So either take the financial hit, or wait until the reliable devices get cheap enough.

2: An archival grade SSD that can hold data for hundreds, if not thousands of years before so many electrons escape the cells to make a 1 or a zero impossible to tell apart. I don't know any media that can last for more than 10 years reliably. Yes, maybe a CD-R or two may last that long, but it is more of a matter of luck than anything else.

I think it's early for that still. SSDs are too expensive to be used for archiving stuff. Their strength is performance. For archiving there's tape.

3: SSDs using a different port than SATA. Perhaps have it interface as a direct PCI-E device with a custom bus to add more SSD capacity in a similar form factor to RAM DIMMs.

Exists, in several versions. Like PCI-e cards that take DIMMs, and SSDs too.

4: A SSD drive built onto the motherboard. This way, a laptop can be a bit thinner due to not worrying about a 2.5" drive.

Exists as well I think.

8: Put some flash onto a tape format, so a tape can be encrypted with one key, but the flash storage on the tape would store an access list of who can unlock the tape's master key. This way, a passphrase, a smart card, and a PGP/gpg key on someone's machine all work to recover data from a tape.

LTO already includes [wikipedia.org] a chip for metadata and stuff like that.

10: A standardized full disk encryption format. This way, I insert a flash disk into my camera or phone, enter a password, and it can read/write to that. Then, put it into my computer, type the passphrase, copy the data. If the flash disk is stolen, the data is protected unless the attacker can yank the key out of the computer or phone's memory (a lot harder feat than just picking up an accidentally lost flash drive.)

IDE has support for password protection [wikipedia.org] . I don't think anything stops the disk from encrypting the data, and since it's part of the standard modern hardware should support it. Laptops have options for this in the BIOS.

Re:Big Deal. (1)

dargaud (518470) | more than 4 years ago | (#32589024)

3: SSDs using a different port than SATA. Perhaps have it interface as a direct PCI-E device with a custom bus to add more SSD capacity in a similar form factor to RAM DIMMs.

Yes, I want SSDs that can replace CD readers in my older laptops (just slide out the whole thing), and/or SSDs that I can plug into the usually unused miniPCI port of my older laptop. None existed last time I looked.

A standardized full disk encryption format. This way, I insert a flash disk into my camera or phone

Yes, with an easy way to enter the password on keyboard-less devices, so I won't be afraid to pass through customs with an mp3 player.

Re:Big Deal. (1)

fuzzyfuzzyfungus (1223518) | more than 4 years ago | (#32589232)

MiniPCI based SSDs, if they exist at all(I've never seen one) are doomed to forever be super-niche items. Why? Because miniPCIe SSDs became a fairly major product category with the rise of the netbook. (a randomly chosen example [newegg.com] . No endorsement is implied; just to demonstrate how easy to find they are.) Since basically no new laptops are coming out with miniPCI slots, only miniPCIe slots, there just isn't a whole lot of demand. If you actually meant PCIe, though, shop away!(assuming your laptop has a large enough empty space. The SSD cards are usually rather longer than the wifi or cell cards.

As for CD-ROM replacements, the trick is that there is no standard for the actual modules that swap in and out of laptops. The CD-rom drives themselves, are standardish(not "standard" as in "you can get replacements and all the cables and connectors you could want wherever parts are sold"; but they all seem to be approximately the same). By the time the manufacturer has put a custom plastic housing around them, and possibly a custom hot-swap connector, anything goes. Many; but by no means all, laptop models have a module available(from the manufacturer, or a third party) that will allow you to put an HDD in the CD-ROM slot. They are just dumb mechanical adapters and will work just as well with an 2.5 inch format SSD.

RAID (1)

CarpetShark (865376) | more than 4 years ago | (#32588476)

Call me when it's 75% cheaper than other "solutions".

From the description (and a lot of guesswork), it sounds a bit like they might have put in a basic RAID system, but using separate memory chips instead of drives. In terms of price vs performance/capacity, RAID has been a good solution, so this might well make sense, IF they don't try to make it out to be some black box filled with magical gold dust, rather than a simple application of existing tech in a new area.

kdawson and Josh Knarr's balls have touched (-1, Troll)

Anonymous Coward | more than 4 years ago | (#32587060)

mainly when Josh was barebacking kdawson. It was just an accident, or so they'd have us believe, but I'm here to tell the truth.

Josh doesn't get barebacked because his asshole is distended from MichaelCrawford's horsecock.

Re:kdawson and Josh Knarr's balls have touched (0)

Anonymous Coward | more than 4 years ago | (#32587832)

Hello, mirko

Old adage(Slightly screwed up) (4, Funny)

moogied (1175879) | more than 4 years ago | (#32587068)

Never do what you can in hardware, in software. ...and we can't do this in hardware! :)

Re:Old adage(Slightly screwed up) (0)

Anonymous Coward | more than 4 years ago | (#32587114)

May we ask, why?

Re:Old adage(Slightly screwed up) (1, Informative)

logjon (1411219) | more than 4 years ago | (#32587302)

Because dedicated circuitry is more stable and requires less computing overhead?

Re:Old adage(Slightly screwed up) (2, Insightful)

Trepidity (597) | more than 4 years ago | (#32587586)

It also often costs more and is less upgradable, though. These days Linux's software RAID, for example, beats out hardware RAID in a lot of ways (except on the high end).

Re:Old adage(Slightly screwed up) (1)

sourcerror (1718066) | more than 4 years ago | (#32588456)

Because dedicated circuitry is more stable and requires less computing overhead?

What about RISC?

Re:Old adage(Slightly screwed up) (0)

Anonymous Coward | more than 4 years ago | (#32587798)

Software is field programmable and code grunts are cheaper.

Price is the biggest issue (5, Informative)

guruevi (827432) | more than 4 years ago | (#32587106)

With Enterprise SSD's (SLC) still in the $100/GB range, we're far away from general acceptance in the datacenter. MLC also has the problem of being slow to write to vs. SLC which is one of the important metrics when considering SSD's to accelerate your classic spindles. SLC's are reliable enough to last for at least 3 years even fully loaded at 3 or 6 Gbps.

I used some Intel X-25-M and Intel X-25-E's in my environment as they are affordable and generally get the highest scores in IOPS and throughput respectively read and write caches and the performance is way under my expectations. The Intel X-25-E's don't work well under heavy loads on LSI controllers (throws errors and SCSI bus resets) while he Intel X-25-M's do work fine. Every other month there is fresh firmware to fix some or another problem and firmware updating is manual labor with a boot CD, not something you can simply schedule at night or do while the system is online so they are what I would call beta-quality. Especially once fully filled the IOPS performance drops from ~3000 IOPS like a brick to ~1000 IOPS which a small set of hard drives can fulfill so the only good thing it's left for is latency.

We'll see what the Vertex 2 EX brings (Sandforce 1500 controller) which has an advertised 50k IOPS although that might be more marketing than anything. I'm still waiting on a decent priced SAS SSD which can actually sustain 5-10000 IOPS by itself even when fully loaded.

Re:Price is the biggest issue (2, Informative)

XanC (644172) | more than 4 years ago | (#32587148)

Isn't it more like $10/GB?

Re:Price is the biggest issue (1)

worx101 (1799560) | more than 4 years ago | (#32587254)

Probably just a typo or maybe they just trying to express how really expensive it is? :P

Re:Price is the biggest issue (2, Interesting)

Shikaku (1129753) | more than 4 years ago | (#32587190)

Every other month there is fresh firmware to fix some or another problem and firmware updating is manual labor with a boot CD, not something you can simply schedule at night or do while the system is online so they are what I would call beta-quality.

Why can't firmware be upgraded on SSD drives thusly:

there are x-MB where they are labeled bad blocks, always. The firmware updater (which can be written in a script since writes to these bad blocks are just a dd in a specific place), the controller checks a signature, and if passed then halts all writes and reads while it upgrades the firmware.

Then when it completes all reads and writes resume. ;) Yes I know that can be disastrous but that seems like a good way to live update.

Re:Price is the biggest issue (5, Interesting)

Anonymous Coward | more than 4 years ago | (#32587482)

...

there are x-MB where they are labeled bad blocks, always. The firmware updater (which can be written in a script since writes to these bad blocks are just a dd in a specific place), the controller checks a signature, and if passed then halts all writes and reads while it upgrades the firmware.

Then when it completes all reads and writes resume. ;) Yes I know that can be disastrous but that seems like a good way to live update.

Several years ago, I wrote an ATA drive firmware flash driver and utility, to allow my company's customers to upgrade firmware in the field. Let me explain how drive firmware flash works.

Most/all modern drives (or at least Enterprise versions) support the ATA DOWNLOAD_MICROCODE command. The flash chips on the electronics board (or reserved sectors on the platters, depending on the implementation) have sufficient capacity to hold the running firmware, and to hold the new version. The new version is buffered in the drive, validated, then written to the chips/spindle, validated again, then activated and the drive reset.

Modulo some minor drive-specific quirks, the DOWNLOAD_MICROCODE command works as specified. Other than adding model strings to the utility's whitelist, the Intel X25-Es worked without issue. While we've always recommended performing the flash from single-user mode and immediately rebooting, I've done it during normal operations plenty of times. The main things are to remember to quiesce the channel before the doing the flash, and properly reinitializing it afterwards.

Posting anonymously because I'm revealing details about my job.

Re:Price is the biggest issue (1)

StarsAreAlsoFire (738726) | more than 4 years ago | (#32588246)

"Especially once fully filled the IOPS performance drops from ~3000 IOPS like a brick to ~1000 IOPS which a small set of hard drives can fulfill so the only good thing it's left for is latency."

Does your environment support trim natively? Just curious.

My environment does not, and after a week or two I start to notice performance going south and remember to run the 'optimization' utility intel offers. This on an X-25M, G2.

As an aside, I've noticed that your average Dell workstation cannot support two X-25's. End up with I/O deadlocks. It is very sad. Pathetic even.

Amazing (-1, Flamebait)

Anonymous Coward | more than 4 years ago | (#32587196)

I'm amazed that Israeli researchers have found the time to do this. After all, trolling Arabs and tricking the US into covering their ass seems to use an insane amount of manpower.

I just glanced at the specs, but Sandforce? (3, Insightful)

drizek (1481461) | more than 4 years ago | (#32587222)

How is this different/better than the sandforce controllers we already have?

Re:I just glanced at the specs, but Sandforce? (1)

Concern Is A Faggot (859837) | more than 4 years ago | (#32587930)

How is this different/better than the sandforce controllers we already have?

Well, this one is kosher.

Re:I just glanced at the specs, but Sandforce? (0, Troll)

should_be_linear (779431) | more than 4 years ago | (#32588506)

I would't buy Israeli product, given I have several choices. This principle helped in the case of South Africa, so why not repeating it.

Re:I just glanced at the specs, but Sandforce? (0)

Anonymous Coward | more than 4 years ago | (#32588728)

you're probably too late; a huge number of networking and security intellectual property originated there - from firewalls, routers and cryptography for a start

Re:I just glanced at the specs, but Sandforce? (0)

Anonymous Coward | more than 4 years ago | (#32589026)

mod this man up!

Re:I just glanced at the specs, but Sandforce? (1)

Shikaku (1129753) | more than 4 years ago | (#32589328)

They invented Algebra.

And 0.

So you use one of their products every second of your life.

If anything (4, Interesting)

Gordo_1 (256312) | more than 4 years ago | (#32587244)

I suspect this will eventually bring down the manufacturing costs of Enterprise class drives, rather than making consumer drives "more reliable". I think reliability concerns with current consumer-oriented MLC designs to be overstated.

Anecdotally, my Intel 160GB G2 drive is going on 7 months of usage as a primary drive on a daily used Win7-64 box, and has averaged about 6GB per day of writes over that period (according to Intel's SSD toolbox utility). Given that rate of use over a sustained period (which theoretically means it could last decades, assuming that some as yet undiscovered manufacturing defect doesn't cut it short) combined with the fact that even when SSDs fail, they do so gracefully on the next write operation, I just don't see the need for consumer-oriented drives to sport such fancy reliability tricks.

Re:If anything (1)

worx101 (1799560) | more than 4 years ago | (#32587280)

Could be they are just trying to counter all the unfounded bad opinions that seem to exist about SSD drives. For one, I have met more than one IT engineer who seems to believe that a SSD will fail(and be rendered completely unusuable) after 1 or 2 years of regular use :/

Re:If anything (2, Interesting)

afidel (530433) | more than 4 years ago | (#32587506)

It totally depends on the use case. Some of my larger san volumes show 2TB/day of writes which means according to Intel's x-25e datasheet a 64GB drive would last ~1,000 days or under 3 years.

Re:If anything (1)

Biogenesis (670772) | more than 4 years ago | (#32587536)

Also don't forget that the size of the writes can make a big difference. If it writes in 512-byte sectors then writing one byte causes the same wear as writing 512. I've got no idea how to predict a shortened lifespan given this fact, it's highly dependent on the user's usage habits. All I can say for sure is that the only time a drive will get close to it's expected lifespan is if it's used in something like a video editing environment where all writes are large, contiguous files. God help you if you ran squid on one though, or accidentally let Windows use it for virtual memory.

Re:If anything (0)

Anonymous Coward | more than 4 years ago | (#32588414)

I hear they have these nifty things called "blocks"...

Re:If anything (0)

Anonymous Coward | more than 4 years ago | (#32587610)

If one of your larger san volumes is in the 64GB range then I have news for you.

Re:If anything (1)

afidel (530433) | more than 4 years ago | (#32587658)

I was referring to larger in the sense of writes per day, they are only a few tens of GB each, they are the redo log volumes for our OLTP Oracle servers.

Re:If anything (2, Interesting)

timeOday (582209) | more than 4 years ago | (#32587758)

Some of my larger san volumes show 2TB/day of writes which means according to Intel's x-25e datasheet a 64GB drive would last ~1,000 days or under 3 years.

I don't get it. Is that 2TB/day per 64GB of storage? (Approx 40 total rewrites of your entire storage capacity per day?) Or 2TB/day spread across a much larger storage capacity? I would guess the latter, in which case the writes would be spread across a large number of drives and less intensive on each drive.

Re:If anything (2, Informative)

afidel (530433) | more than 4 years ago | (#32587852)

Nope, that's 2TB/day across 20GB (I believe, logged off my corp systems a while ago but it's in the low 10's of GB regardless of the actual size). It's the redo log volumes for a fairly high transaction load OLTP Oracle server.

Re:If anything (1)

Rockoon (1252108) | more than 4 years ago | (#32589012)

If you are writing 2TB/day to a 64GB drive then you already expect to replace the thing every few years, even if it was a platter, at least in the median case.

If you are on the extreme end, then platter failures are quite common.

Re:If anything (1)

seanadams.com (463190) | more than 4 years ago | (#32587644)

You're probably making too high of an assumption about the incremental cost to add this to consumer products. I would be surprised if it's even a single square mm of die area. All depends how they price the IP.

Re:If anything (1)

mysidia (191772) | more than 4 years ago | (#32587668)

Makes sense... it will make it less expensive to manufacture reliable enterprise drives.

New enterprise SSDs can be MLCs using this technology, they may be higher capacity, or provide more profits to the SSD part manufacturers, but will be just as expensive. Enterprises pay for reliability that meets the requirements for their market.

Consumer market has a lower level of reliability... consumers aren't willing to pay as much for reliability, so reliability will be less.

You can't provide greater reliability to a market that's not willing to pay for that extra -- they'll buy the competitor's product instead that's cheaper (and less reliable)

Signal to noise ratio in FLASH MEMORY? (2, Interesting)

Anonymous Coward | more than 4 years ago | (#32587318)

How can a solid state drive have a "signal to noise ratio"?

It's all digital. Either the voltages are within their valid thresholds or they are not.

Wouldn't you need the world's fastest DSP to "clean up" noisy digital signals and still maintain the type of transfer rates they claim?

There is nothing about this breakthrough that makes any sense. Snake oil?

Re:Signal to noise ratio in FLASH MEMORY? (5, Informative)

Ster (556540) | more than 4 years ago | (#32587572)

Say you're talking about a 4-level MLC cell, and say it runs at 3.3V. If the voltage is on [0V, 0.825V), that's 00b; [0.825, 1.65V) is 01b; [1.65V, 2.475V) is 10b, and [2.475V, 3.3V) is 11b. But those are analog voltages - the controller has to read the voltage, do an analog-to-digital conversion, and figure out which level it corresponds to. The ranges listed above are for if you have perfect discrimination - in most cases, it's difficult to differentiate small differences, so they don't use the full range. With better A-to-D and signal processing, they can resolve the differences better, which in turn lets them get more write cycles.

Those numbers are pulled out of the air for illustrative purposes; I have no idea what the real values are.

Re:Signal to noise ratio in FLASH MEMORY? (0)

Anonymous Coward | more than 4 years ago | (#32588114)

This explanation is correct, but it is still odd how an SSD manufacturer can do this, since flash chips
expose only a digital interface. Flash memory chips do not typically expose the analog interface and
not even the internal error correction to the outside circuitry, so how can a SSD developer do this?
Surely they are not making their own flash chips?

Re:Signal to noise ratio in FLASH MEMORY? (0)

Anonymous Coward | more than 4 years ago | (#32588888)

Quite right. Doing "signal processing" on the raw voltage levels from each cell would be prohibitively expensive and/or slow, as they would basically be bypassing the fast, custom, hard-wired ADC logic inside each Flash module (assuming that it's even possible, which I doubt it is).

Re:Signal to noise ratio in FLASH MEMORY? (-1, Troll)

Anonymous Coward | more than 4 years ago | (#32589526)

What, your closing-square-bracket key not working? /troll

Re:Signal to noise ratio in FLASH MEMORY? (0)

Anonymous Coward | more than 4 years ago | (#32587584)

I believe they may be referring to interconnect noise due to variations in power supply.

Re:Signal to noise ratio in FLASH MEMORY? (3, Insightful)

Anonymous Coward | more than 4 years ago | (#32587614)

It's all digital.

Actually, once you get far down enough, nothing is :)

Re:Signal to noise ratio in FLASH MEMORY? (1, Insightful)

Anonymous Coward | more than 4 years ago | (#32588382)

Onc you get far down enough, everything is. Consider Planck time: it's the smallest quantum of time for which there can be "a difference that makes a difference".

Re:Signal to noise ratio in FLASH MEMORY? (0)

Anonymous Coward | more than 4 years ago | (#32587682)

In the end a digital signal (1/0) is just another abstraction that is used so that those who aren't engineers will not have to care about signal levels and stuff. It does not matter how you set the tresholds or how high signal voltage you use, there will always be a possiblity that an external disturbance makes a bit readout turn wrong. (That is why we have checksums and restransmissions in TCP/IP.)
In MLC they use multiple tresholds to store multiple bits in the same memory cell, when reading the cell the resulting sample/timeframe also has the same tresholds and is more sensitive to noise. Higher read frequencies also gives the signal less time to stabilize.
And no, you would not need the worlds fastest DSP to clean up the signal. The filtering parts of the DSP are not general purpose and can perform some simple calculations at almost the same speed that a generec CPU is able to just transfer the data. Don't expect a generic CPU to be able to process data at the same speed as a DSP.

Old technology (1)

RKBA (622932) | more than 4 years ago | (#32587364)

We already did something very similar to this on the BAIL backup subsystem of the Cassini spacecraft many years ago, and it didn't require a "special" processor.

jew lover's (-1, Troll)

Anonymous Coward | more than 4 years ago | (#32587380)

slashdot has them.

Re:jew lover's (0)

Anonymous Coward | more than 4 years ago | (#32587652)

Jew lover's what ? That's a possessive apostrophe you twit.
At least you show that you're a bigoted idiot instead of making people work it out for themselves.

Re:jew lover's (0)

Anonymous Coward | more than 4 years ago | (#32587770)

Jew lover's what ? That's a possessive apostrophe you twit. At least you show that you're a bigoted idiot instead of making people work it out for themselves.

Great, Jew lover vs Grammer Nazi. This could be fun in a few minutes

New trend (3, Funny)

gringofrijolero (1489395) | more than 4 years ago | (#32587428)

The SSD will have a more powerful CPU than the computer.. All it will need is a graphics and audio chip, more RAM and.. oh... nevermind..

http://www.imdb.com/title/tt0848228/ (0)

Anonymous Coward | more than 4 years ago | (#32587432)

Spaceships?!? (0)

Anonymous Coward | more than 4 years ago | (#32587446)

The Israelis have Super Star Destroyers?!?

Wait, crap, I just left http://bbs.stardestroyer.net/. My bad.

Re:Spaceships?!? (-1, Troll)

Anonymous Coward | more than 4 years ago | (#32587484)

No, of course not. The destructive little bastards only spend money on things that let them directly kill Arabs. Since Arabs (being another bunch of dirt worshippers) are incapable of going into space, the Jews will just kill them in the old fashioned ways. (Starving them out seems to be a favorite of theirs.)

Re:Spaceships?!? (-1, Offtopic)

Anonymous Coward | more than 4 years ago | (#32587570)

No, it's because the local Arabs have spent all their money on buying weapons.
Then starved themselves out [bignewsnetwork.com] Or they've dug up their sewage pipes to make rockets [sweetness-light.com] . "Oh no, blame the Israelis for the raw sewage everywhere. If they'd just stand still and let the rockets hit them we could stop ripping up our pipes to make more!"
Maybe they should spend some time on useful R&D like real people.

Yay.... (0)

Anonymous Coward | more than 4 years ago | (#32587488)

...for Moore's Law!

Another Product from Israel (-1, Troll)

Anonymous Coward | more than 4 years ago | (#32587530)

Yet another product that all the anti-Semitic jerks out there can boycott. Too bad that when all the consumer SSD drives are using it it'll be no SSDs for you !

Re:Another Product from Israel (0, Troll)

jjohnson (62583) | more than 4 years ago | (#32587860)

Well if they'd stop oiling the spindle with blood and pituitary glands of Palestinian babies, I'd buy from them again. Christ, it's just about impossible to get that shit out of the rug.

Oh sure (1)

TheRealQuestor (1750940) | more than 4 years ago | (#32587596)

Just great, another awesome piece of tech I so desire in my machine that I can't afford. CURSES YOU!

It's expensive (1)

mysidia (191772) | more than 4 years ago | (#32587626)

The company is not revealing pricing yet."

They are competing on reliability, so it makes sense the price would be higher.

The fact they are not advertising the price, strongly suggests they do not intend to compete based on price, and price will be high.

Marketing rule #1 is shove all the positive aspects of your product in the customer's face.

Don't talk about the negatives or the disadvantages, if you can avoid it.

In this case the product's not out yet, so they can avoid talking about the high price it will cost at launch :)

Great tech, but MLC still remains bad news. (2, Insightful)

blind biker (1066130) | more than 4 years ago | (#32587710)

So we can have 50.000 instead of 3000 rewrite cycles. That's great. However, I still like the 100.000 to 1.000.000 rewrite cycles of SLC. Actually, SLC is only 50% more expensive to manufacture (per bit) than two-level MLC - I really don't understand why are manufacturers so enamoured with MLC.

Re:Great tech, but MLC still remains bad news. (1)

nyctopterus (717502) | more than 4 years ago | (#32588346)

Because price is the most important factor here? Reliability has got to good enough, what needs to happen now is a sharp reduction in price.

Re:Great tech, but MLC still remains bad news. (1)

blind biker (1066130) | more than 4 years ago | (#32589128)

As I said, SLC is only 50% more expensive, per bit, than 4-level (2 bit/cell) MLC. That's hardly helping in a "sharp" decrease in price.

Re:Great tech, but MLC still remains bad news. (1, Informative)

Anonymous Coward | more than 4 years ago | (#32589220)

If I'm buying 100,000 parts, SLC costs 5x more (per bit) than MLC at the present. I'm pretty certain the reason is supply - there's factories churning out an ungodly amount of MLC for use in memory cards, thumbdrives, MP3 players, etc. but SLC really only finds use in the embedded (where I've used it) and enterprise-SSD space.

MLC isn't *that* bad - the reliability issues you'll find with it are bit errors, not entire lost blocks of data. Add an extra level of error protection and plenty of spare area to handle the extra errors you'll see and you'll be fine.

This is what TFA seems to be doing. Mind you, I wouldn't call it a breakthrough (I hate that word), just the logical thing to do when your storage medium has a lower "SNR" because it's using MLC. If they've got an innovative technique/algorithm for maintaining lots of IOPS through their multiple ECC layers, or an innovative ECC algorithm then that's, well, innovative.

This article is IMPOSSIBLE to decode (5, Insightful)

pslam (97660) | more than 4 years ago | (#32587774)

This sounds absolutely no different to how all wear-leveled, error correcting flash controllers work. They all use multiple levels of ECC to decrease the error rate. The 'signal processing' they're doing doesn't sound like anything new.

If there is something new going on here, it's absolutely impossible to decode from the layman's language used in the article. All I hear is "Other vendors use X bits for ECC. We use Y bits and we do it in software instead of hardware.", which is basically just another way of saying "Other vendors have 4 blades, we have 5 blades."

SSD? (1)

Loki_666 (824073) | more than 4 years ago | (#32588316)

Thats a shame... i thought they had developed a Super Star Destroyed. Nothing to see here... move along.

How many write cycles SLC/MLC? (1)

raynet (51803) | more than 4 years ago | (#32589040)

The article says this new technology boosts the number of write cycles from 3000 to 50000. Sounds good, but then again, SLC flash in 1991 supported 1million writes and MLC 100.000 writes. Later consumer grade MLC flash claimed to handle 10000 writes and Micron is selling MLC flash that supports 30000 writes and I recall AMD having MLCs with 100.000 writes. Maybe the 3000 writes MLC is high density & as cheap as possible kind of flash and this new Israeli technology works on that. But unless it is cheaper than Micron flash, I don't see why would anyone use it.

"In a big way" (1)

SpaghettiPattern (609814) | more than 4 years ago | (#32589140)

Call me old fashioned but "in a big way" simply doesn't cut it for me. It is language used by pikeys. Or by bullies which are a linguistic or intellect stone's throw away from pikeys.

Do the geek proud and make a bit of an effort when writing. After all, the typical geek reads more than Joe Average -well "he" claims so and I personally do anyway- and hence trains his brain in appreciating well formed sentences.

Besides, there are so many alternatives to "in a big way".
Load More Comments
Slashdot Account

Need an Account?

Forgot your password?

Don't worry, we never post anything without your permission.

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>
Create a Slashdot Account

Loading...