TB-Sized Solid State Drives Announced

prostoalex writes "Several companies have announced solid state hard drives in excess of one terrabyte in size. ComputerWorld describes one from BitMicro that's just 3.5". Their flash drive will support up to 4 Gbps data transfer rate. From the article: 'SSDs access data in microseconds, instead of the millliseconds that traditional hard drives use to retrieve data. The BitMicro E-Disk Altima 4Gb FC delivers more than 55,000 I/O operations per second (IOPS) and has a sustained data transfer rate over 230MB/sec. By comparison, a fast hard drive for example will run at around 300 IOPS.'" Ah, the speed of tech. Seems like only last month we were talking about 500GB drives.

Don't Forget Fusion IO's PCIe Card Drive

[eldavojohn]

Ah, the speed of tech. Seems like only last month we were talking about 500GB drives.

We also discussed 640GB PCIe cards [slashdot.org] with sustained data rates of 800Mb/sec for reading, 600Mb/sec for writing and 1,000,000 operations per second.

The Texas Memory Systems datasheet claims 24 GB/second of random sustainable data bandwidth which is much higher than the Fusion IO card but it looks like they are serializing this possibly across multiple drives. They also claim higher (3.2 million) operations per second.

The BitMicro drive is groin grabbingly amazing in size but claims only 55k operations per second & sustained data transfer rate over 230MB/sec.

So what I would wager is that PCIe might provide more throughput than SATA but don't quote me on that. I'm interested to see where this goes & also curious to see whether we continue dumping drives on channels like the Texas Memory solution or if it just goes back to a server with a ton of PCIe slots on it and hot pluggable card swapping for 'drives.'

Worth revisiting is the fact that Fusion IO claims to be releasing the cards for sale next month. As we all know, sometimes it's just a case of who gets to market first that wins in the technology world.

Re:

[Jeff DeMaagd]

The BitMicro drive is groin grabbingly amazing...

Ouch!

Re:Don't Forget Fusion IO's PCIe Card Drive

[Gr8Apes]

The Texas Memory Systems RAMSan requires 2500W of power.

For the BitMicro SSD: 230MB/s >> 800 Mb/s card, and 55K IOPS >> 300 IOPS for todays hard drives.

It sounds to me like the BitMicro is a clear winner, especially considering that today's fastest HDs deliver about 300 IOPS and a max of about 40MB/s sustained data transfer. You can RAID the drives to increase performance, but I imagine the same will hold true of the SSDs. The only issue is price. The Texas Memory System is out of the question - it makes an Intel P4 Extreme look like a power miser.

Re:Don't Forget Fusion IO's PCIe Card Drive

[arminw]

.....The Texas Memory Systems RAMSan requires 2500W of power........

It appears that one of these is NOT ready to be used in your next laptop in the near future!

Re:

[Gr8Apes]

.....The Texas Memory Systems RAMSan requires 2500W of power........

It appears that one of these is NOT ready to be used in your next laptop in the near future!

Well, if you're looking for the quick and easy cure to procreation....

You mis-converted...

[tempest69]

BitMicro is 230 MB/SEC + 55K iops fantastic.

??$/gig up to 1.5 tb, plus the cost of a 4G fiber card.

FusionIO is 700 MB/SEC + 87K iops (3x more bandwith, Exceeds SATA 2)

30$/gig up to a 640GB card (19k$)

TMS, its huge and heavy, and blows the doors off either product, and expensive. They have a $150/gb

product that is still pretty fast. 2GB/sec 100K iops (8x more than bitMicro)

Unless the Bitmicro comes in at a price that is below fusionIO ($30/gig) I don't see the point, just buy 3 fusionIO devices in raid-0

Re:

[RzUpAnmsCwrds]

a max of about 40MB/s sustained data

Modern 7200 RPM SATA drives can deliver 70-100MB/s in sequential reads, depending on where the data is stored on the platters.

Most people don't know it, but hard drives have been getting steadily faster. Not crazy-insane-faster like semiconductors, but they have been making some sizable gains.

Re:

[Gr8Apes]

Just took a look at a few sites reviews on drives. It appears that the current crop of drives in more realistic tests approach 40-60 MB/s. So I'll up my statement to 60MB/s. Still well short of 100MB/s. (Don't believe drive manufacturers or their ad-driven reviewers).

Just FYI: the 60 MB/s surprises me for non SCSI hardware, that's a pretty darn good number.

Re:

[Emetophobe]

From the FusionIO website [fusionio.com]:

The ioDrive(TM) is designed to deliver 87,500 IOPS (input/output per second @ 8K packets) per PCIe x4 card, while achieving sustained data rates of 700MB/sec (Read) and 600MB/sec (Write) -- making the ioDrive(TM) almost a thousand times faster than any existing disk drive.

The OP apparently confused you when he incorrectly used Mb instead of MB.

Re:

[Emetophobe]

I'm sure the "1000 times faster" figure is is just marketing, but the device does seem to have huge potential. Check out the two videos with the CTO doing a demonstration of the ioDrive: http://www.tgdaily.com/content/view/34065/135/ [tgdaily.com]

In the first video, at one point the CTO claims that a "regular hard drive can do around 100 IOPS" and that their device can do 100,000 IOPS. So that's probably where they get the 1000 times faster figure from.

Re:

[had3l]

"As we all know, sometimes it's just a case of who gets to market first that wins in the technology world."

As long as your product doesn't suck, that is.

Re:Don't Forget Fusion IO's PCIe Card Drive

[Junta]

The Texas Memory Systems datasheet claims 24 GB/second of random sustainable data bandwidth which is much higher than the Fusion IO card but it looks like they are serializing this possibly across multiple drives. They also claim higher (3.2 million) operations per second.

The Texas memory product is cramming a bunch of ram in 24U and putting a whopping 25 minutes of battery backup. If you disconnect power for more thon 25 minutes, the only thing left is whatever was committed to 'real' peristant storage. They provide Infiniband and FC ports, so it's more akin to an EMC or Engenio storage controller than a hard drive. 1 TB/24U is actually kind of sad when hard drives can easily yield 3 TB/U nowadays. There is a place for this (ramdisk performance is pretty nifty), but it's not even remotely relevant to anything a normal person would think of when they hear SSD (they picture a drive intended to connect directly to a system some how, not participate in a SAN directly.

The BitMicro drive is groin grabbingly amazing in size but claims only 55k operations per second & sustained data transfer rate over 230MB/sec.

And it *actually* is flash based storage, meaning it can fairly be called persistant storage. Of course, the clear hint is there when they talk IOps and only mention FC connection that they are targetting only deep pockets with the product as of this press release or whatever. 55k operations and 230 MB/s is ludicrously insane performance for a single drive relative to current spinning disks. You can fit 144 of these into a 24U space and have a theoretical aggregation that exceeds the ram based system specs. Of course, RAM should be able to trounce it so the limiting factor is a controller setup to push the IOPs and throughput, so both solutions would probably perform comprably.

So what I would wager is that PCIe might provide more throughput than SATA but don't quote me on that. I'm interested to see where this goes & also curious to see whether we continue dumping drives on channels like the Texas Memory solution or if it just goes back to a server with a ton of PCIe slots on it and hot pluggable card swapping for 'drives.'

Well, considering that SATA controllers at best currently use PCI-e as the method to communicate with the chipset, PCI-e slots better be capable of better than SATA... Ok, it's over-simplyfying, a 1x PCIe first gen slot yields about 2.5 Gb/s or so, and a SATA II port is 3.0 Gb/s, so a single lane PCI-e slot would be slower than a SATA port. However commonly PCIe appears in 4/8/16 lane configurations, I assume you meant 880 MB/s, which would point to PCIe 4x slot sort of throughput, which makes sense, it's not unreasonable to expect at least a 4x lane slot to be free, requiring anything more could waste limited hardware resources.

Re:

[Znork]

"55k operations and 230 MB/s is ludicrously insane performance for a single drive relative to current spinning disks."

Yep. Still, in the pricerange they're in it's hardly single disks they're competing against, so comparing to those is about as useful as comparing with the performance of 5 1/4 inch floppys. Perhaps they want to have a market position as an SAN accelerator, but SAN cabinets in that range are pretty generous with RAM caches anyway and stripe storage over many spindles.

I tend to be sceptical a

Re:

[booch]

What gets me is that they have the nerve to call it non-volatile memory. If that's non-volatile memory, then what memory ISN'T non-volatile?

"You keep using that word. I do not think it means, what you think it means."

Clarification to the Summary required.

[AmIAnAi]

The TMS link is for a 9U rack of non-volatile DDRRAM, consuming 2.5KW and weighing up to 720lbs, so not quite suitable for the desktop.

The BitMicro article goes on to say that the maximum capacity in a standard 3.5"x1" format is 640GB, so requiring around 2.5" for the full 1TB.

This is Slashdot, so we don't expect facts in the summary to be correct. However, this is still amazing progress.

Re:

[Jeff DeMaagd]

I don't see any factual errors, maybe too much is left for the reader to assume. That first item is still solid state drive, even if it's not flash.

Re:Clarification to the Summary required.

[dpaton.net]

The TMS link is for a 9U rack of non-volatile DDRRAM, consuming 2.5KW and weighing up to 720lbs, so not quite suitable for the desktop.

It's actually 24U, and it consists of (what appear to be) 8 3U racked computers that each manage 128GB of RAM storage for the network, and have a 4 drive hot-swap array for backup.

Source: http://www.texmemsys.com/files/f000225.pdf [texmemsys.com]

It's a Ram Disk.

[camperdave]

a 9U rack of non-volatile DDRRAM

So, it's a giant ram disk with either flash or hard drive backup.

Will I lose data if I lose power to a RamSan?

No. The RamSan-300 and RamSan-400 systems are equipped with redundant batteries and four internal hard disk drives. When external power is lost, the batteries will power the system under full operation for five minutes (this is just in case the power outage is temporary). After five minutes, the system will turn off Input/Output for the system and complete backing up all data that is in memory to the internal hard disk drives. Even if the system is fully loaded with memory, backing up to the internal disks will take no more than 12 minutes to back up. The batteries in the system are N+1 redundant, which means that there is enough battery capacity with just two of the three batteries to power the unit and complete backup after external power fails. The hard disk drives in the system are RAID protected which means that even if a hard disk drive fails, the other disk drives will be able to backup the system in the event of power outage.

No. The RamSan-500 systems are equipped with redundant batteries to power the DDR cache long enough to flush the DDR cache to the Flash memory RAID. Flash memory is inherently non-volatile and does not require power to save data.

http://www.superssd.com/faq.htm [superssd.com]

Re:

[camperdave]

So what happens two years down the road when the batteries can no longer hold out for the needed time?

By that time they'll upgrade to the ten terabyte version which comes with fresh batteries.

Re:

[Mattsson]

So what happens two years down the road when the batteries can no longer hold out for the needed time?

If someone hasn't horribly neglected his/her job, the batteries will not reach such a state.
All UPS-systems have specifications on how long the batteries will last and any UPS that's in professional use should be services properly.
So should those in private use too actually, but it isn't part of anyones job-description to actually keep it serviced so most probably isn't.

Re:

[camperdave]

Not only that, on a rig like this, there's probably a monitoring system that will call for help if the batteries start failing.

In other news

[moogied]

Wells Fargo, Bank of America, Washington Mutual, and Chase all annouced there new "PC Home Equity Loans". Averaging at 5.8% APR(OAC) you can take out a home equity loan for the purpose of purchasing a 1TB SSD.

Re:

[EvanED]

What I want to know is whether I can get something that's the equivalent of a mortgage for this. In other words, use the drive itself for collateral. Do they offer this service?

Re:In other news

[SatanicPuppy]

Well, at 2500W you could probably buy it as a space heater with a home improvement loan, and snip it off your taxes for the year as well.

Re:

[dosguru]

Here in Wells' IT, we'd like to encourge you to take out the new loan so we can afford to buy a disk array of these things to keep track of your loans.

This is not a drive... its an array

[segfaultcoredump]

The linked to press release for TMS systems are not a single drive. They are a half rack sized array. Dont try and put one in your desktop anytime soon.
Their systems have been in use for years by folks who need speed at any cost.

Now, the BitMicro drives... those look interesting. I wonder if I can slot them into my StorageTek 6140 :-)

Re:

[vidarh]

The key being "any cost". I talked to them at one point, and was quoted a price for one of their devices that was about as much as my company pays in hardware lease, bandwidth and power for hosting 4 racks worth of high end servers for a year...

Re:

[hedwards]

That doesn't surprise me, a few companies with a need for this kind of speed and deep, deep pockets will buy them. And in time the cost of producing them will come down in price to the point where I'll have one.

I must admit that I'm drooling over this, there are times when having a drive that ridiculously fast would really come in handy. Of course I can't afford one of those just so that I can compile my software with the bottle neck being largely elsewhere.

And again...

[SharpFang]

...how does it compare to capacity equivalent in SD cards plus RAID/reader glue logic piece of hardware?

the bus will be the bottleneck

[petes_PoV]

To get the best performance out of these things we need to move away from IDE/SATA architectures and have the storage directly on the PCI or PCI-E bus.

Once that happens, PCs will really start to get useful!

Re:

[not already in use]

Yes, because until then, PC's are just a commodity. :)

Re:

[Kjella]

Right now, even the best prosumer SSDs aren't close to matching the SATA2 interface speed of 300MB/s. Their access time is already minimal (I saw 0.2ms in a test for one disk). Remember that there's a lot of headroom in the SATA interface that isn't used except for buffer bursts today. So I don't really see the point. Having an standard connector and making them drop-in replacements for HDDs sounds to me like the logical way to go...

Re:

[Junta]

The performance of the BitMicro SSD isn't even up to a SATA-II 3.0 Gb/s speed. And to top it off, they only seem to support FC, which is currently commonly 4.0 Gb/s and moving toward 8.0 Gb/s. If you have more than one drive, yes, you'll exceed 3.0, but you'll also be using more SATA ports, so in the aggregate, still staying below the SATA standard limits. Maybe a different standard will come, but for now, SATA is perfectly capable. The likes of PCI-e has not been extended in a standardized way to allow

Re:

[afidel]

An interesting concept for a really fast SSD is to use the SATA/SAS software presentation layer on a card that plugs directly into PCIe. That way you have the standards support from the OS level and are not restricted by SATA physical signaling limitations.

Re:

[drinkypoo]

That way you have the standards support from the OS level and are not restricted by SATA physical signaling limitations.

Except that you're still subject to driver limitations, and the driver probably makes assumptions about the maximum performance of the device that will limit you anyway :P

Re:

[Junta]

Except they *can't* make such assumptions at a higher layer. For example, the generic layer has to anticipate that a single presented block device could represent a RAID-0 of devices. The specific driver, would, of course, be written for that card or else it would probably emulate a controller with hardware raid-0 capability.

Re:

[aaronvegh]

Once that happens, PCs will really start to get useful!

Sure! Because right now these damn PCs are nothing but expensive paperweights!

Very nice

[Bullfish]

But for now the cost isn't worth the performance differential. With enough ram, generally you aren't hitting the hard drive too often except for a few tasks. With 64 bit computing, you get to have even more useful ram. When the price of solid state drives is competitive with hard disks, I'll pay attention.

Re:

[itsdapead]

When the price of solid state drives is competitive with hard disks, I'll pay attention.

Hah. When I were a lad you could get a 7 MEGABYTE Winchester Hard Disk for a mere £3500 (what, about $5000?). (Source, 1981 copy of Personal Computer World).

That's about £10k in modern money (according to this calculator [thisismoney.co.uk] - a.k.a. $20k dollars (or $10k at Microsoft/Adobe screw-the-Brits rates).

Now, if you think that 1981 was, like, ancient history then GET OFF MY LAWN! If the usual growth rate applies, 1TB

Re:

[richlv]

http://photofile.ru/photo/fishki_net/3273658/70316241.jpg [photofile.ru]

Re:

[PitaBred]

Just as an FYI, a lot of people get annoyed at the "screw the Brits" rates, and quite fairly most of the time. But realize that prices in the US are quoted WITHOUT tax. The British prices include VAT charges, because you have sensible price advertising rules :P So, in reality, when you see a US price of $1000, add 8.235% [64.233.167.104] (or so) to get the actual price we'd pay. That $1000 price is actually $1082.35 (on average) in the US. Just some food for thought :)

Re:

[Poromenos1]

I'd rather pay $1082.35 (on average) than $2000...

Its a bit more that VAT...

[itsdapead]

Correct me if I am wrong, but can't USAians avoid tax by buying from out-of-state?

Anyway, although you may need to ignore the tax to get the full £1=$1 ripoff story, the price differences in question are often far more than the tax.

E.g. Adobe CS 3 Design Standard Full from the Adobe online store: UK Price £895 *excluding* tax, US price $1,199 (About £600)...

Anyway, in the past (certainly in the era of that HD drive I quoted) the "VAT inclusive" rule only applied to "retail" shops and

Re:

[PitaBred]

Only if that business doesn't have a presence in your state. So, the answer is "sometimes". If I buy from HP online, I still pay tax since they have plants and such in Colorado.

Re:

[SanityInAnarchy]

Hah. When I were a lad you could get a 7 MEGABYTE Winchester Hard Disk for a mere £3500 (what, about $5000?). (Source, 1981 copy of Personal Computer World).

What I'm sure was meant was when they become competitive with their current hard drives.

In other words, right now, going to any solid-state storage system only makes sense in various specialized places. For example: You need performance at any cost, so you buy some battery-backed RAM with hard-disk backups. Or, you need something smaller and mor

Re:

[KrackHouse]

If your apps only read data then yeah, but if you have a bulletin board or log a bunch of data the RAM doesn't really help for write caching.

ReadyBoost, et al

[inKubus]

These could be used with some sort of intelligent prefetch (ala ReadyBoost [wikipedia.org]) with good results. I know they use them currently in high-performance systems to swap out table indexes and the like. Since the indexes are relatively small files--but there are many of them--seek time becomes the bottleneck, rather than throughput.

I've heard about doing this in Linux by mounting a USB key and using it as extra swap. Here's how in Ubuntu (from http://ubuntuforums.org/showthread.php?t=395435:

1) Plug the USB drive in your USB connector;
2) If Ubuntu automount the device (usually in /media/usbdisk), umount the device (ie., sudo umount /media/usbdisk);
3) sudo mkswap /dev/sda1 (assuming /dev/sda1 is the correct device for the connected usb device)
4) sudo swapon -p 32767 /dev/sda1

"cat /proc/swaps" to check if everything is ok; on my laptop I get the following output:

Filename Type Size Used Priority /dev/hda4 partition 2353512 116 -1 (standard HD swap partition) /dev/sda1 partition 1981928 123900 32767 ("ReadyBoost"-style pen drive)

Quite obviously, performance is not the same as with real additional ram; however, I feel REAL gain in speed while using eclipse+tomcat+mysql for development on my laptop (which is equipped with just 512MB ram).

To turn it off, type:

"swapoff /dev/sda1", assuming /dev/sda1 is the correct device.

Obviously you are going to be write limited due to the physical limitations of the flash disk, but reads will be very fast. ReadyBoost will keep a table of files that get read a lot, but written infrequently and then cache them on the flash device. It would probably be possible to do this at the disk driver level in linux with a fast database like BDB, keep a table of the last 1000 files read, if there's a write, remove them from the table. Then move those files up to the flash drive as a disk cache... there may be something like this already, like the Google Prefetch [google.com] project that's in the works.

Re:

[mikiN]

Interesting idea, but somehow I can't escape thinking this is like mashing up an iPod in a blender because the resulting grey powder looks nice in the mock-up fireplace for your Christmas stall.

Unless there have been some really important changes in the performance of Flash memory, using it as swap would be like the second worst possible scenario in terms of it's life expectancy (using it for main memory would be the worst). Just how long is a typical Flash chip with a guaranteed average of 1 million write

Re:

[inKubus]

Don't know til you try ;)

Since they are only a few dollars now, it's worth a shot. However, as I said, it would be better if it only used frequently READ files.

Windows XP

[edxwelch]

Apparently this works on Windows XP too: http://www.windowsxlive.net/?p=1337 [windowsxlive.net]

One terrabyte!

[ArAgost]

Finally! One terrabyte! I was hoping to get more than mere giggabytes (or, even worse, meggabytes) for SSD. I still remember the epic moment when SSD reached killobytes, after years struggling with just some bbytes.

Re:

[Clueless Moron]

I'm eagerly awaiting the unit "arrhabyte". I propose that it should stand for the amount of software you can pirate in a 24 hour period.

"Dude", I've got a whopping sixteen arrhabytes of warez here in my backpack!"

Just amazing.

[had3l]

A big improvement from the predicted "State-Sized Solid TB Drives".

Drive Life?

[JCSoRocks]

AFAIK all of these SSDs have a limited number of writes that can be performed before they start having bad "sectors" (dunno the flash memory name equivalent of a sector off the top of my head). I don't see any information on those sites, but I'd be interested in knowing - how long until they start to fail? At what rate will it fail (in other words, how long to go from say, 500GB to 0GB)? These drives are great, but if you drop that kind of coin and then they fail in a year... that would suck.

Re:

[Yetihehe]

This is not funny anymore.

Re:

[LighterShadeOfBlack]

This comes up every single time flash drives get mentioned on Slashdot. Go search around and you'll dozens of posts in every article asking and answering this question. The short answer is that with the wear levelling used on all modern flash drives they work out at at least an order of magnitude more reliable than current HDDs despite the write limit.

Re:

[DeadChobi]

These are RAM drives with a battery backup. They aren't flash drives. RTFA.

Re:

[yakumo.unr]

from the the article : "Competing products include Texas Memory Systems Inc.'s RamSan 500, a flash SSD with a dynamic RAM cache. That drive achieves up to 400,000 IOPS. Dutch company Attorn's HyperDrive 4 is a DRAM-based SSD that runs at 44,000 IOPS. Theoretically, DRAM should be faster than flash, but BitMicro's ASICS have made their flash faster."

The TMS RamSan is flash ssd with dynamic cache.
Attorns Hyperdrive is DRAM.
Bitmicros system is flash.

Re:

[CastrTroy]

Yes, it would suck, because we all know that standard hard drives with spinning platters, and magnetic read/write heads, almost never break down. :)

My point is, is that if solid state drives had better known failure times, they could be better than the spinning platter types. Spinning platter drives tend to die whenever, for unknown reasons, and they also die if they just get too old. If using solid state drives could solve the first problem, and only have drives die at a known point in the future, whe

Re:

[Khyber]

If the people in charge of making SSDs would quit using NAND Flash and move to OUM you wouldn't even need to worry about wear leveling. 10^8 is much better than 10^5 that we generally get now.

Re:

[JCSoRocks]

Soooo I'm asking a serious question and I get troll? Ok... Anyway, thanks to those of you that gave intelligent responses. I learned somethin'.

Infiniband

[NetJunkie]

The big feature here is the included Infiniband support. Without digging real far in to the specs if this array supports RDMA it would make a very nice shared memory array for a grid type implementation.

TB-sized?

[peacefinder]

Is it really a good idea to make a hard drive the size of mycobacterium tuberculosis? I'm just sure I'd lose it before I figured out how to plug it in.

Re:

[QRDeNameland]

Reminds of the reason why I'll never own an AM radio...what good is a radio that won't work after noon?

Re:

[smoker2]

Oh dear,
First it was sneakernet, then the internet.
What are the ?iaa going to do now you can transfer a couple of movies just by sneezing !
Pretty soon, all information exchange is gonna be viral.

About time too

[mollymoo]

I'm glad news of solid-state drives is getting more common. Disk seek times have been the number one cause of annoying delays on my desktop systems for several years now, and I certainly don't have exotic hardware. Perhaps I can ditch my plan for a Solaris box in the garage and diskless clients and just wait a year or two for >100GB $400 solid-state disks.

Re:

[glop]

You might not wait long: Newegg is selling 16GB of Flash for less than 130$ (in CF,USB and SD).
This means you could build a little >100G RAID of those for 800$ or so.
And I believe the prices go down really fast (I paid 70$ for 2G in May 2006 and thought it was a good deal. Now I could get 8G for that price).
I guess you will get your 100GB flash before September 2008 :-)
Enjoy!

Re:

[Tom Womack]

It'll take only about a year or so; Samsung 8Gbit Flash chips are $9 on the spot market at the moment.

Though the interface for connecting eighty of them onto a single SATA channel wouldn't be completely straightforward just from the point of view of I/O pins; each chip presents eight data pins and nine control pins, so you need a total of about 1500 pins on the disc-controller ICs.

For the early market you'd probably use FPGAs, you'd need six XC3S400A in one of the larger packages to get enough I/Os, which w

Quick Erase?

[Jah-Wren Ryel]

Many of the predecessors to these models were aimed at military applications and contained a really cool feature - instant erase. They could erase themselves very quickly (seconds) to a level believed to be reasonably secure from recovery.

I would like to see that feature incorporated into these consumer level drives. You never know when you might need to ditch that terabyte of pr0n in a hurry...

Re:Quick Erase?

[LighterShadeOfBlack]

Right, because when your house gets raided and the police see you erased your hard drive they just turn around and say "well played". 'Obstruction of justice' ringing any bells?

Not to mention the British police will assume it's just encrypted and you'll get 5 years jail-time for not providing the key.

Re:

[Jherek Carnelian]

Right, because when your house gets raided and the police see you erased your hard drive they just turn around and say "well played". 'Obstruction of justice' ringing any bells?

Since when is pr0n illegal? However, since you want to go down that path...

If whatever your drive contained was 'illegal' or sufficiently incriminating, it may very well be that an "obstruction of justice" charge is preferable to whatever charges would have come about from confiscation of the actual drive contents.

Re:

[LighterShadeOfBlack]

Since when is pr0n illegal?

Well, why would you need to erase your entire drive for anyone besides the police? You'd have to have a serious lack of crisis management skills to erase your hard drive every time you heard your wife coming. It wouldn't exactly avert suspicion either...

'What are you doing in here honey? Why is the screen black?'
'Oh I'm just err.. reformatting it. Damn thing got corrupted'
'That new "solid state" thingie is useless, this is the third time this week you've had to do that!'

And yes, I know what you're thinking

Re:

[kylemonger]

Plenty of open positions at the moment.

Re:

[Jherek Carnelian]

Well, why would you need to erase your entire drive for anyone besides the police?

Well, why would you need to encrypt your entire drive for anyone besides the police?

A laptop with a "quick erase" button would be useful to many businesses with people who travel in less than the safe regions. Same goes for people in less than free countries who are working for change. Full disk encryption doesn't stand up to rubber-hose cryptography very well.

I'm sure with more than 30 seconds to think about I could come up with any number of 'legitimate' uses.

Re:

[PitaBred]

I don't think you mean rubber-hose cryptography [answers.com]. Torturing someone to get them to... encrypt information? Maybe rubber-hose decryption...

Re:

[dossen]

Just to pick nits - the commonly used term is rubber-hose cryptanalysis (http://en.wikipedia.org/wiki/Rubber-hose_cryptanalysis [wikipedia.org]).

Re:Quick Erase?

[noidentity]

Not to mention the British police will assume it's just encrypted and you'll get 5 years jail-time for not providing the key.

All those zeroes... there must be something hidden in them. Produce the key at once!

Pseudocode

[Weaselmancer]

Right, because when your house gets raided and the police see you erased your hard drive they just turn around and say "well played". 'Obstruction of justice' ringing any bells?

if (time_in_jail(OBSTRUCTION_OF_JUSTICE) < time_in_jail(WHATS_ON_MY_HARD_DRIVE)) wipedrive();

Re:

[Lost Engineer]

Yeah, and the government is the only entity that can afford these things. Your tax dollars at work, covering their asses.

WANT!!!!!!!

[billcopc]

How much?

This would be a whole lot nicer than my current stack of SCSI 15k drives, and I'll bet they put out a lot less heat too!

If you have to ask

[sammyo]

You really can't afford it.

EVE Online uses the TMS RamSan

[LakeSolon]

As has been mentioned already, TMS sells a solution that fills a rack. The article is about something to fill a drive bay.

We've had a few EVE-Online stories lately, so I thought it might be interesting to some to point out that one of the users of the TMS setup is CCP Games, the makers of EVE Online. In fact if you click on 'success stories' in right sidebar of the first link in the summary you'll see a short article about CCP's first install of the TMS RamSan [superssd.com] a while back.

When?

[rice_burners_suck]

When can I drop one of these into my laptop?

getoffmylawn

[ronadams]

Yeah, these look pretty nice, but you can't beat those old tube drives for that warm, acoustic sound.

Re:

[rubycodez]

but they're prone to getting all clogged up with electric mails, and those technicolor Flash moving pictures don't help any either. and they never should have got rid of those nice operator ladies with rolls of wire under their desks of blinky lights and plugholes to route calls, replacing them with those tabulator contraptions with only four or five plugholes to move packages has got the tubes so backed up

Re:

[Anonymous Coward]

I prefer non-acoustic sound, thanks very much.

New! Improved!

[JohnnyBigodes]

Now available with a terabyte-sized pricetag!

The marketing slogan should be...

[StressGuy]

A Tera-Byte and a Tera-ble price

{feel free to groan}

All This For the Modest Price Of..

[nimr0d]

RamSan-400

The starting capacity of a RamSan-400 (32GB) is $35,000. It includes:
-32GB DDRRAM storage
-one dual-ported 4Gb Fibre Channel controller
-hot swappable RAID 3 hard disk drives
-hot swappable and redundant power supplies
-redundant battery and fans
-IBM Chipkill in memory (redundant RAM)
-1 year return to factory warranty

Each additional 4Gb FC controller is $3,000 (up to 4 in each chassis).

The RamSan-400 can upgrade in 32GB increments for $18,000 (up to 128GB).

RamSan-400 (64GB) - $50,400
RamSan-400 (96GB) - $65,800
RamSan-400 (128GB) - $81,200

RamSan-500

The 1TB base-level system of a RamSan-500 (1TB SLC NAND Flash, 16GB DDR) is $200,000. It includes:
-one dual-ported 4Gb Fibre Channel controller
-hot swappable and redundant power supplies
-redundant battery and fans
-1 year return to factory warranty

The 2TB base-level system of a RamSan-500 (2TB SLC NAND Flash, 32GB DDR) is $300,000. It includes:
-two dual-ported 4Gb Fibre Channel controllers
-hot swappable and redundant power supplies
-redundant battery and fans
-1 year return to factory warranty

The RamSan-500 can upgrade DDR Cache.
-16GB to 32GB is $10,000
-32GB to 64GB is $20,000

Each additional 4Gb FC controller is $3,000 (up to 4 in each chassis).

In 24U? wow

[JustNiz]

This only gets interesting when I can get a 1TB SD drive the same physical size and approximate price as a 1TB mechanical (conventional) drive.

Black book

[ROMRIX]

I want one so I can load it up with all my girl friends phone numbers cause I have so many!
Ya, and I'm rich too so I might get two, one for girls I like and one for girls I used to like! Ya!

Filesystems

[peterlombardo]

Since filesystems are so closely tied to cylinders, tracks, sectors and blocks...how does this play on SSDs? If I'm not mistaken, when allocating new extents, filesystems take into account physical locations to minimize future seek times...is that valid on a SSD?

That's so 1980's ;)

[Moraelin]

Since filesystems are so closely tied to cylinders, tracks, sectors and blocks...how does this play on SSDs? If I'm not mistaken, when allocating new extents, filesystems take into account physical locations to minimize future seek times...is that valid on a SSD?

Actually,

1. Even for low level disk access, that hasn't been so since the days of MFM hard drives. Nowadays everything uses LBA (Logical Block Addressing) [wikipedia.org]. Meaning that when the computer wants a certain sector it tells the hard drive, quite literall

the best part is

[Jarik C-Bol]

that if you have to ask what they cost, it means you cant afford one.

Woopity doo! Another announcement.

[inotocracy]

How about we see some of these large solid state drives actually for sale?

monster

[eleitl]

http://en.wikipedia.org/wiki/Tera- [wikipedia.org]

Tera- (symbol: T) is a prefix in the SI system of units denoting 1012, or 1,000,000,000,000 (1 million million).

Confirmed in 1960, it comes from the Greek , meaning monster.[1] It also bears a resemblance to the Greek prefix - meaning four; the coincidence of it signifying the fourth power of 1000 served as a model for the higher-order prefixes peta-, exa-, zetta- and yotta-, all of which are deliberately distorted forms of the Latin or Greek roots for the corresponding pow

2500 watss of power?

[NuMessiah]

From the "Tera-RamSan Details" page:

"Requires 2,500 watts of power."

Huh?

bb4now,
PMC

Not Yet Convinced

[Nom du Keyboard]

I'm not yet convinced that paying a premium price for a hard drive using a more expensive technology with a very (compared to rotating storage) limited lifetime in terms of write cycles is a wise idea. There are parts of my hard drive (swap areas) that get beat-up pretty badly at times. Don't want to wear this thing out in a year or two.

That's also why I don't have a plasma big screen yet. I'm using an alternative technology there as well.

What would OS/400's do? a huge leap into the SLS

[gelfling]

Or as I believe they are called now, iSeries eServer machines. OS/400 is what's called an SLS architecture. There are no devices in the system nor are there file systems. It's simply one huge 64bit address space. The hardware and software abstraction layers intercept the call from an application or a hardware interface and pipe it to the SLS which just does one reach into the address table. An SSD would be ideal for that architecture. It would be essentially one huge non volatile RAM address space at bus sp

Re:

[Falladir]

This is a 3.5 inch drive.