Samsung 256GB SSD is World's Fastest

i4u submitted one of many holiday weekend slow news day stories which starts "Samsung Electronics announced today the world's fastest, 2.5", 256GB multi-level cell (MLC) based solid state drive (SSD) using a SATA II interface. Performance data of the new Samsung 256GB SSD features a sequential read speed of 200 megabytes per second (MB/s) and sequential write speed of 160MB/s. The Samsung MLC-based 2.5-inch 256GB SSD is about 2.4 times faster than a typical HDD. Furthermore, the new 256 GB SSD is only 9.5 millimeters (mm) thick, and measures 100.3x69.85 mm. Samsung is expected to begin mass producing the 2.5-inch, 256GB SSD by year end, with customer samples available in September. A 256GB capacity is getting large enough to replace hard-drives for good — now just the prices just need to come down further for large capacity SSDs."

Summary

[Mark Trade (172948)]

Don't buy any other similar products. Ours will come out Really Soon (TM). At least we hope so.

Re:Summary

[TheRaven64 (641858)]

And since it's using MLCs, expect to buy another one quite soon after. While SLC flash is up to the 100,000 to 1,000,000 rewrites level, MLC is still closer to 10,000. This, combined with the larger cell sizes on most MLC products means that it is likely to wear out much faster. This is why most flash manufacturers are only pushing MLC technology for consumer electronics type applications (e.g. MP3 players), where you want high density and low cost but don't perform many writes.

Wear leveling

[tepples (727027)]

And since it's using MLCs, expect to buy another one quite soon after. While SLC flash is up to the 100,000 to 1,000,000 rewrites level, MLC is still closer to 10,000. This, combined with the larger cell sizes on most MLC products means that it is likely to wear out much faster.

MLC products use wear leveling [wikipedia.org] at the controller level to spread writes to high-traffic areas such as directories and extent maps around the physical medium. That's also why they store 256 GB and not 256 GiB: that's 7 percent for spare sectors. Even if this wear leveing is only 10 percent effective, how long does it take to write to all 256 GB of the drive 1,000 times?

Seems like the complexity is lower

[Eccles (932)]

Looking at a hard drive, it's got lots of moving parts, the need for sealing, etc. One would think that in the long run a solid state drive that is just a few chips and connecting logic would be cheaper to produce once you have the facilities.

Re:

[berwiki (989827)]

you're probably right.

but just like CD's are cheaper to produce than cassettes, that doesn't mean the cost will ever come down.

Apples to Celery

[benhattman (1258918)]

You can't just compare different markets. As another poster said, you can buy CD-R for less than a penny each. What you are referring to is how record companies have used the lower medium price to make an even larger profit off of the content.

However, how does an oligopoly selling copyrighted content compare to a commodity market? Basic economics tells you they don't, and you can count on one of two things happening. A) SSD prices fall in line with hard drives. Or B) hard drive capacity moves beyond the needs of most consumers and SSD takes up that niche while being only marginally more expensive per GB than hard drives.

Re:

[Kjella (173770)]

Easier to miniaturize, certainly. Right now they're doing massive RAID0 to get performance, I wonder what it'd be like if they could do RAID1/5/6 for example - forget hard disk crashes more or less, just replace some flash plug-in modules in your SSD. Ok the electronics could still fry, it could get lost or stolen but mechanical failure seems to be the typical killer.

BAARF

[tepples (727027)]

Easier to miniaturize, certainly. Right now they're doing massive RAID0 to get performance, I wonder what it'd be like if they could do RAID1/5/6 for example - forget hard disk crashes more or less, just replace some flash plug-in modules in your SSD. Ok the electronics could still fry, it could get lost or stolen but mechanical failure seems to be the typical killer.

I've read that RAID 3/4/5 is unreliable [baarf.com]. As capacities grow, it takes longer to reconstruct a new spare from the surviving drives when one dies. In fact, BAARF contends that capacities have grown to the point that it's likely that another drive will fail during reconstruction. Are there any big drawbacks to RAID 6?

Re:BAARF

[WuphonsReach (684551)]

I've read that RAID 3/4/5 is unreliable. As capacities grow, it takes longer to reconstruct a new spare from the surviving drives when one dies. In fact, BAARF contends that capacities have grown to the point that it's likely that another drive will fail during reconstruction. Are there any big drawbacks to RAID 6?

RAID6 is a far better option then RAID5. At least it makes it less likely that you'll end up with a double-drive failure that takes out the entire array.

OTOH, the failure mode of both RAID5 and RAID6 leaves a lot to be desired. Rebuild time increases linearly as you add more disks to the array. So a 10+ RAID5/RAID6 array can have huge rebuild times, leaving you vulnerable for a lot longer. As in half a day or longer to rebuild the array (or at least a few hours).

Personally, my preference is the more conservative RAID10 approach. Rebuild times are based on the size of an individual disk in the array (not the total array size), which means your vulnerability window is a lot smaller. And depending on luck, you can survive a multi-disk failure. Rebuild times are typically under 2 hours for arrays that are based on 300-500GB drives.

(My preference is to have 1 spare disk for every 6-8 drives in the array. So a 12 disk RAID10 array would probably be RAID10 over 10 disks with the other two as spares.)

Re:

[canuck57 (662392)]

Looking at a hard drive, it's got lots of moving parts, the need for sealing, etc. One would think that in the long run a solid state drive that is just a few chips and connecting logic would be cheaper to produce once you have the facilities.

Given sufficient amount of time, solid state SSD will likely overtake hard drives. But I think many industry analysts are far too quick to estimate wide adoption if the SSD media over hard drives. It will be slow. And I have heard those predictions 10 years ago.

Problems exist in SSD adoption, 3 huge ones.

• density, hard drives seem to be always many steps ahead in density
• costs, a $100 hard drive w. 1TB version the SSD 1TB cost?
• write speed/reliability issues with SSD

Oh, the SSD will creep in, but I

42 zillion dollars?

[billcopc (196330)]

I like the idea of the SSD, but I think they need to concentrate on lowering costs down to earth before flaunting their capacity achievements. Hell, any monkey can build a 500-TB mega-RAID stripe with a large enough budget.

When this SSD is cheap enough that I can buy 3-4 of them and stripe that into a bus-raping powerhouse, for less than a mortgage payment, then we'll talk.

Re:42 zillion dollars?

[Sascha J. (803853)]

If the SSD's price only increases very slightly with greatly increasing capacity, they already lowered the cost.

Also, it doesn't help to have cheap 32GB SSDs when nobody buys them and you can't really launch into mass production because you are stuck with a niche market. To drive down the price you need to be able to produce them en mass and in order to do that you need to catch up (or outstrip) existing technology.

Re:Did we not already have?

[PopeRatzo (965947)]

$19,200 for a 640 GB Hard Drive

We all know that's more expensive than computer storage has ever been before.

Right?

And if hard disk storage had ever been that expensive, it would have meant the abandonment of the hard disk technology forever.

Right?

This is good news...

[Tastecicles (1153671)]

...if it can cope with high definition capture it'll be handy for me and my shutterbug family who're always out with various still and video cameras. Nothing worse than shortdropping a notebook and killing the hard disk.

MLC, not SLC.

[by Anonymous Coward]

But it's a Multi-Level Cell based Flash drive, not a Single-Level Cell based Flash drive. The cells hold 4 states, not 2.

High capacity, yes, and apparently high speed as well. Excellent... but also lower reliability. SLC Flash is extremely durable these days, but MLC Flash is not, last I checked, even one tenth as long-lasting.

How much lower? Well... ...frankly, we don't really know yet. We won't really know, as such, until they start to die - which could well be 5-10 years, and if so, that's really not bad - and you might not see the same type of can't-write-blocks failure, but rather a more conventional can't-read-blocks failure. Which would be about as bad as a hard disk crash (and we might have to develop whole new data recovery techniques).

Maybe it might last years longer than a hard drive owing to fewer moving parts. Perhaps it will slowly die, but good write levelling will largely mitigate the issue and overall it'll come out better, or about the same. Or perhaps we're looking at a flaky brick with lower reliability than a Quantum Fireball.

Early adopters, start your engines, because someone's gotta find out.

For enterprise use, it might be wiser to stick to more conservative SLC flash. Past that, all bets are off.

But we're seeing the beginning, here. Hard drives are, slowly, on the way out. It'll be a long phase-out where they are much more cost-effective for a long time... but it is coming. And I, for one, welcome our new nanosecond-seek-time overlords.

Re:

[by Anonymous Coward]

Normal SSD drives die in a matter of months on a typical developer's machine so it shouldn't be that hard to test.

I have first hand experience with this so I laugh when people say flash drives will last longer than their mechanical counterparts. The rewrite cycle count needs to be way, way higher than it currently is. Wear leveling can only do so much and it just gets worse as the drive gets full.

Technology: Still new! Still Improving! Surprised?

[PC and Sony Fanboy (1248258)]

Well, since the technology isn't developed, is it really that surprising that we read a story about 'Worlds Fastest' every couple weeks?

Solid State Drives for computers? They aren't really out of beta!

Re:Technology: Still new! Still Improving! Surpris

[Daniel Phillips (238627)]

Solid State Drives for computers? They aren't really out of beta!

400,000 eee PCs say you're wrong.

256gigs is a lot

[FudRucker (866063)]

I don't requires that much disk storage space, I could get by on 40 gigs and 80 would never run out of disk space for my purposes, make an 80 gig SSD that would sell for less than 200 USD and I will use my disk platters for target practice...

Re:

[flyingfsck (986395)]

I am getting by just fine on my Eee PC with a 4GB SSD and a 8GB SD card, for a total of 12GB.

The trick is to have a server somewhere with enough disk space to keep the bulk of the crap online.

Primary SSD + Storage HDD = Gold

[SD-Arcadia (1146999)]

Once the prices come down and the tech matures a little more, a nice small 32-64GB SSD for the apps and a 1TB+ for storage should be a great overall solution. This could even happen in form of an elegant hybrid unit.

DBAs: Index tablespaces? Logfiles?

[Jeppe Salvesen (101622)]

How would this perform for index tablespaces and logfiles? I imagine lifetime/health will have to be monitored, but that's already being done with regular platterspinners.

Re:Large enough? No way.

[Aenoxi (946506)]

I fully agree with your conclusion that capacity is king for moist consumers, but... ...this is a 2.5 inch drive.

I'd like to subscribe to your reality if it has Terabyte-sized 2.5 inch drives. Where do I sign up?

Re:

[Bobby Onions (735795)]

Don't be so wet; there's no need to puch a dampener on things.

Re:Large enough? No way.

[mfnickster (182520)]

Agreed, GP needs a lesson in humidity.

Re:Large enough? No way.

[wamatt (782485)]

Remember the intended target market is the laptop crowd. 256GB is big enough to compete nicely. When it comes with those sort of performance figures, it's a no brainer if you have the money.

The current largest widely available 7200rpm is only 200GB. The majority of notebooks ship with 200GB of HD space.

Re:

[aproposofwhat (1019098)]

Try &lt; - it <hubris>works for me</hubris> :o)

Re:Large enough? No way.

[jht (5006)]

I dunno - I think once you hit that kind of capacity you can pretty much own the notebook market. Right now, mainstream notebook disk sizes are in the 160-250GB size range, with 320 generally available and I believe 500 GB drives are just starting to arrive. Most notebooks aren't at the high end of capacity, though.

I don't think SSD will make an impact in desktops anytime soon, but if I can put an SSD in my notebook and gain a little speed, some battery life, and better shock resistance without giving up any serious capacity (heck, my 2-month-old MacBook Pro has a 250GB HDD in it right now), depending on the price differential I'll probably be all over it.

Also worth thinking about (though it's not in the submitter's link) - I read a couple of releases on this drive yesterday, and though they aren't giving production prices yet they claim that multi-level cells will make it cheaper than the older models. Between that and the natural speed of price cuts, this drive may be at competitive HD pricing levels sooner than we expect. If I can get a 256GB SSD at a 25% price premium to a HDD of the same size (like you suggest), I think it would be pretty much a no-brainer. That 250GB HDD is only about $150 or so - maybe even less.

Re:Large enough? No way.

[amorsen (7485)]

For most consumers, capacity is king, not speed.

For most consumers, price is king. Not price per gigabyte, just price. The only thing most consumers might need more than 32GB for is video -- and flash is almost as cheap as hard disks in the 32GB 2 1/2" segment.

Re:Large enough? No way.

[benhattman (1258918)]

Mod parent up.

We are far past the point where the average consumer cares very much about capacity. What do you think they are going to do with 2 terabytes? Unless you are talking about someone who is frequently downloading movies and the like, I don't see how they would use that content. OK, there are probably a handful of people who are doing their own hi-def video editing or processing the output of large sensor arrays, but in what would do you define these guys as "most consumers?"

The reality is SSD doesn't have to come anywhere near the price of hard drives. It just needs to provide enough capacity (256-512 GB today) at a reasonable price. If you tell a consumer they can get a regular old hard drive, or pay 10% more for a SSD that doesn't fail when dropped and runs way faster, a lot of regular consumers will pony up for that.

Re:

[Kjella (173770)]

2.5" HDDs are only in 500GB territory, that's only halfway there. If only prices would come down, they could easily stack a TB in 3.5" already. Prices aren't quite there yet but right now at newegg you got 80$/500GB = 0.63$/GB for regular HDDs and SUPER TALENT FTM20GK25H SSD 669$/120GB = 5.57$/GB so they're within one order of magnitude now. There's an incredible price development on SSD now and I figure they'll come close in a year or two.

Re:

[ozamosi (615254)]

I bought a new 120GB 2.5" disc last week - 256GB is "large enough" for now - if only the price was low enough...

*Easily* large enough.

[Whiney Mac Fanboy (963289)]

Hard drives have entered terabytes territory, and you think 256GB SSD drives are "large enough"?

Yup, even 64GB is easily large enough for my primary hdd on my laptop - I'd pay a premium far larger than 30% if the price/performance relationship was linear.

Until SSD drives cost only around 10-25% more than a regular drive of the same capacity, they're not replacing them at all. For most consumers, capacity is king, not speed.

But, the bulk of my content resides on network servers (same holds true for my less g

Re:Large enough? No way.

[cecil_turtle (820519)]

For most consumers, capacity is king, not speed.

I don't know how you qualify "most consumers", but "sufficient capacity" is all most consumers need, after which price and speed absolutely do come into play. For most people 40GB is still sufficient capacity. Only people who download or rip very large amounts of music or movies need more than that, and that is pretty far from "most consumers" - your 14 year old son who tries to download every movie he's never heard of isn't "most consumers". Not to mention that IO speed is the performance limiting factor on pretty much every consumer PC nowadays, CPUs have been fast enough for a couple of years now.

SSDs and spinning disks can still co-exist - in a year or two you will be able to run your OS and programs on a 100GB-200GB SSD and go buy a 2TB disk or 5TB array to store your data on that is less performance critical.

Re:

[Firethorn (177587)]

Discounting microsoft bloat, when I look at stuff like this I think about people like my parents and grandparents.

You know, people who after having and using their machine for four years still has 80% of their 80GB HD free. Where the biggest increase in HD usage in the last year was microsoft patches.

For power users like me that DO get into games, video, and music on the computer, a 250GB SSD is enough to last quite a while. Heck, from initial build I'm likely to throw my OS and programs on the SSD and g

Re:

[by Anonymous Coward]

You are comparing to the wrong technology. SLC drives are extremely expensive, but this is a MLC drive. You should look at these items instead to extrapolate cost:

Super Talent MLC Solid State Disks on Newegg [newegg.com]

The Samsung drive is much higher performance than these, but the fabrication costs should not be too far off. I'd guess $1500 for the 256 GB model when it comes out.

Re:Random write ops?

[Kjella (173770)]

Uh, the last SSD review I saw that had considerably worse specs than this just barely came behind the VelociRaptor in the random write tests. Unless you've got a special disk trashing benchmark to make SSDs look bad, I'm fairly sure this wins on all counts. In fact, 20 random writes/sec sounds more like trolling than insigthful to me...

Re:Random write ops?

[Fweeky (41046)]

Every benchmark I've seen on SSD's have shown random IOPS of between 20 and 120/sec, ranging between cheaper consumer drives and more expensive enterprisey models; writing single blocks to random locations completely demolish their performance because such small writes often require the drive to erase huge blocks.

New techniques try to avoid this by basically turning random writes into sequential ones; once you've erased a 4+MB block, you put all new writes into that block (you can turn a 0 into a 1 without an expensive erase cycle) and remap it similarly to how it's done with wear leveling. I'm not aware of anyone actually doing this yet, though.

Re:The serializing of the random read-writes

[hairyfeet (841228)]

Which is why I have been wondering: You know how a HDD will have a bit of RAM as a cache to make write more efficient,why aren't they doing that for SSDs? It seems like it would me a lot more efficient if lets say,the SSD has 4Mb blocks to have 8Mb of cache on them so the data can be cached and written in efficient blocks. I'll admit I haven't gotten to read up on the algorithms used with SSD so I don't know if there is a technical problem with that idea or not,but it would seem to me to be a "best of both worlds" kind of solution.

And speaking of "best of both worlds" what happened to everything is going to be hybrid? A couple of years back all you read was they were going to add anywhere from 256Mb to 8Gb in addition to the 8-16Mb of RAM cache on HDDs to boost the data access and make them even more efficient at writes. What happened? I know I would personally like a hybrid that had,say 8Gb on it so I could have the OS stored in flash with my data and swap stored on the platters. But that is my take on it anyway,YMMV

Re:

[Wesley Felter (138342)]

High-end SSDs have a RAM write buffer, but it complicates the controller significantly. I expect sophisticated controllers to trickle down to all SSDs eventually.

Re:

[Daniel Phillips (238627)]

if I have a SSD I want to use the main memory for either HD io caching or programs. Caching disk blocks from the fast SSD in main memory seems suboptimal

Bandwidth to the SSD is 300 MB/sec (sata 2) while bandwidth to main memory is more than 10 GB/sec, 33 times faster.

The Power of 1000 Hard Drives

[StCredZero (169093)]

This pales in comparison to the ioFusion drive [tgdaily.com]. The videos show tests being run where they are doing 8 operations at the same time, at blazing speeds, copying multiple DVDs in 5 seconds, and simulating swapping a blizzard of 4kb blocks as fast as RAM. Instead of 2 channels, their cards use 160 channels at the same time. This gives a single card the parallel random access bandwidth of a 1000 disk drive SAN.

http://www.tgdaily.com/content/view/34065/135/ [tgdaily.com]

At $30 per gigabyte, it would be great to have a 10-gig for OS and your current favorite MMO game.

Re:

[Fweeky (41046)]

No, SSD's have always shined at random *reads*. Small random writes have traditionally been where they're very weak; you might manage 160MB/s writing large chunks, but if you're droping 16k blocks all over the place (as, e.g, databases are apt to do) you'll be lucky to manage 1MB/s because of the overhead each write incurrs, certainly on cheaper drives aimed at portable use.

Hence, it's a perfectly reasonable question; depending on how they've implemented it, they could be anywhere from 20-20,000 random wri

Re:

[GreyWolf3000 (468618)]

No, SSD's have always shined at random *reads*. Small random writes have traditionally been where they're very weak; you might manage 160MB/s writing large chunks, but if you're droping 16k blocks all over the place (as, e.g, databases are apt to do) you'll be lucky to manage 1MB/s because of the overhead each write incurrs, certainly on cheaper drives aimed at portable use. Hence, it's a perfectly reasonable question; depending on how they've implemented it, they could be anywhere from 20-20,000 random writes/sec.

To expound, NAND flash chips are broken up into 128KB 'blocks' which in turn comprise 64 2KB 'pages.' You can read any page you want on the entire chip in the same amount of time (no moving parts), but to *write* any particular page, you need to perform an erase on the *entire* block. Let me repeat, to write one page to NAND flash (2 KB), you have to erase a 128 KB block. The reset operation will transition all bits on that block to a 1, and you have to go back and tell it which bits to set to zero.

Re:Random write ops?

[TheRaven64 (641858)]

Unless flash has changed a lot since I last looked at it, this isn't quite true. To write a 2KB page, you first need to erase a 128KB block, but you can then write into the remaining 126KB without needing an erase first. If you're using something like LFS or ZFS on your disk, this translates to very fast writes. If you're using a filesystem that doesn't have copy-on-write semantics, then this will still be quite slow because you will rarely encounter this kind of access pattern (you will be more likely to read 128KB, modify 2KB in a buffer and then re-write 128KB, which, as you explained, is very slow since it requires a 128KB read followed by a 128KB write just to write 2KB - the same reason that RAID-5 is slow for writes).

Re:Random write ops?

[GreyWolf3000 (468618)]

What you said doesn't contradict what I said at all. You can definitely achieve much better performance by not scattering your writes; sequential access is very fast. For random writes, you're going to have to seriously buffer to avoid wasting erase cycles. Fortunately, the same algorithm that avoids erase cycles for performance is also the same algorithm that does wear leveling. I don't know too much about ZFS or how copy-on-write would help except on a purely abstract level.

Smart controllers

[Joce640k (829181)]

If you fix things so that every 2Kb block on the disk can be remapped then those 2Kb writes can mostly be tagged onto the end of recently erased blocks, no erase needed.

(In practice NTFS usually uses 4Kb blocks so you'd optimize for that but the argument stands...)

This would also help a lto with wear levelling, etc. as you'd write the entire disk in a round-robin fashion, remapping blocks as you go.

The controller would need static RAM to hold the remapping table but that's no big deal these days.

Re:

[4D6963 (933028)]

A most interesting and pertinent question! I think that if such a memory reached the speed of RAM with the capacity of a HDD then we could merge the two concepts into a central memory that would be used for anything. The first real gain with that type of design is that instead of loading (uncompressed) files (from the HDD to the RAM) you could simply point to them, and directly access them. Virtual machines could benefit greatly from that by pausing and resuming their execution instantly, for all their virt

Re:

[menace3society (768451)]

I think the problem is, if you try to use the flash as a sort of buffer, you end up with the worst of both worlds. You're still subject to the same mechanical failure risks for long-term storage as a simple hard disk, but you're also limited by the number of writes you can do to the buffer.

You can accomplish the same thing, with fewer flaws, by just having two drives.

It's a game of numbers.

[Joce640k (829181)]

Have you seen the average notebook buy in a shop? It's all a game of "find the biggest number".

As a geek I'm always being asked if such-and-such a laptop is "fast enough", if XX is enough disk space, etc.

People have no idea what the numbers mean, or how they compare to the numbers six months ago. They don't even know the difference between RAM and hard disk. All they know is they don't want low numbers.

Bottom line ... "disk capacity" is a number on the little label so it has to keep increasing no matter wha