Intel unveils itsy-bitsy, teeny-weeny SSDs Intel announced on Wednesday a new line of tiny solid-state drives, the SSD 310 series, that have performance specs comparable to those of their 2.5-inch X-25 and 1.8-inch X-18 SSD brethren – and at least one manufacturer is already on board to put the little fellows into dual-drive notebooks. "The Intel SSD 310 series will …
Let the HDD controller decide what should reside on the SSD based on simple caching algorithms. That way the 2TB drive will perform exactly like an SSD 99% of the time. Worst case scenario is HDD speeds 1% of the time.
95% of an Win7 is never accessed in a week of use. Why dedicate a $100 drive to it.
Seagate make the momentus XT, it's only a 4GB cache but it's SLC so it's a decent bit of kit. I almost bought one for my laptop, but in the end decided I didn't need to store loads of data on a portable computer so opted for an SSD instead. I'm still tempted to get one for my media centre PC though.
Hybrid storage works on a basic level, for caching frequent blocks, but it works a lot better if the OS is involved in the decisions predictably moving associated files in and out of the cache in response to the application being used. Put a large enough cache onboard and this becomes less and less of a gain, but at only 4G, its a fraction of what's needed without Os intelligence.
Make the cache 24 or 36GB, and at a less than $50 price bump, and we have a winning combination.
This post has been deleted by its author
I agree with the sentiment but having looked into the performance of my Adaptec raid controller with specific algorithms built to do exactly what you say using a hybrid RAID of SSD and SAS drives.
Though the numbers align closer to 85% of the time not 99%, but your point is incredibly valid.
The speed increase is amazing and it is stunning that they've not started doing this in more computers.
Surely seagate will have something like this within the year? please? pretty please?
A beer for telling it like it is :D
Intel is rather late to the party here. Seagate already ships and it fits into a standard laptop build, no modification required. It also rocks. You really get SSD boot and load times while still having 250-500G of storage. I have seen how it works and I will definitely consider it for the next upgrade cycle.
The funny bit is that SSD+HD support was supposed to be the key feature of Vista. So where is it? Another EPIC FAIL from Redmond.
What connector is that? it looks like sata of some sort.
It'll be really nice when it gets cheap enough to use for NAS or media purposes, but dual drive storage is a great step in the right direction, especially now that they're large enough to store a modern OS w/applications.
Also, have SSD's moved read/write speed bottlenecks elsewhere?
Well, you'll find in most cases with a decent RAID + controller the bottleneck moves from the HDDs (even old platters) to the PCIe Bus or southbridge if you're lacking the controller...
The throughput of 4 1TB Seagate ES 2's in RAID is somewhere in the realm of 1GB/s which is in excess of the bus. However, those can be upgraded without TOO much hassle, they mostly have been limited where they are due to a lack of purpose than out of technical concerns.
These would make rather nice netbook drives. My only problem is whether I should replace the 3G modem or wireless N PCIe cards in my acer aspire one to accommodate one .. obviously I'd rather not lose either but with these SSDs and 6-9 cell batteries they look good for mobile use.
>>The days of old style spinning hard drives are numbered. I reckon within 2-5 years they will be slmost completely obsolete.
Floppy drives have only just gone, CDs are still sold, DVDs are still sold, BD is too expensive.
It's always changing, but, it's down to capacity/cost, tapes are still used (LTO etc.), 2-5 years is very broad, but you won't see mechanical hard drives disappear until you can get 4Tb SSD for < £100 which of course will happen, but I wouldn't like to predict when (and of course, as manufacturing technology shifts it will be cheaper to fab chips than moving glass/ceramics and that will speed it up)
4TB SSDs below £100 means nothing if you can get 16TB spinning disks for the same price. SSDs won't wreck spinning disks until:
A) They solve the write limit issue.
B) Cost for SSDs gets within 1.25 of spinning disks.
Until then, the ever increasing demand for bulk storage will keep disks living on for decades. They may not be the primary disk in your next PC, but they will be the data disk. Corporations will maintian RAIDs and MAIDs in order to keep data easily accesible.
And decades form now, they'll still be backing up to tape. (At least they will until somone funds InPhase properly.)
I remember about 6 or 7 years ago I used an iPaq 3870 with a jacket for PCMCIA cards. The card in particular was a converter that allowed me to use Compact Flash. The CF was an IBM Microdrive containing a colossal 540Mb of storage space, working in much the same way as a normal hard drive does.
Could anyone explain what those shock statistics actually mean. The units are all over the place.
400G/2ms means what exactly?
OK let's start with 400G/2ms == 200G/ms. Why is it listed in a non normal form?
What is a G? I learned that as being the universal unit of gravity at skool - 6.67 x 10^-something.
the gravitational constant «g» or «G» is indeed 6.67428 × 10^-11 m3 kg^-1 s^-2 - or something like that ! However, I suspect that the «G» here rather refers to result of the application of this constant to a more specific situation, i e, the acceleration at which a (relatively small) body falls at the surface of the Earth, or between 9.78 and 9.82 ms^-2, discounting air resistance. 400G/2ms would mean that the unit in question is calculated to survive an acceleration of 400G over a period of 2ms - consider how swiftly motion is brought to a full stop after e g, a 1 m fall to the floor and you will understand the relevance of these parameters and why it's not a good idea to drop HDDs....
Henri
So G = gravity and ms = time.
So 1500G/0.5ms means the drive can survive the impact of accelerating to/from 1500G to in a time of 0.5ms...
The time also indicate the minimum time the device requires to park any read write heads before impact, etc, which is why this number is larger for conventional moving head magnetic drives.
A device with a [n]G/2ms shock figure would be damage if the impact occured within 1ms - so changing 400G/2ms does not equal 200G/1ms, as the latter incident described would result in a damaged drive.
http://en.wikipedia.org/wiki/Hard_disk_drive#Shock_resistance
G in this respect will be the acceleration due to gravity at the Earth's surface, not the universal gravitational constant. The former being or rather more practical use to the average person, not to mention the units of the universal gravitational constant make no sense at all in this context.
As for 400G/2ms this is not a single unit, but a statement that the device can withstand a rate of deceleration of 400G (or about 3,924 metres per second squared) for 2 milliseconds. That is not the same as 200G for 1 millisecond (which would be half the rate of deceleration for half the period). Do the mathematics on this, and you find that this will allow for this to be installed into a device that can be dropped a metre or two (depending on the degree of bounce) provided that the SSD is decelerated over a few millimetres (which can be achieved through a deformable case, rubber mountings or some combination of such). Most laptops won't survive a 2 metre fall onto a concrete surface, although they might on a heavily carpeted one.
So the 1,500G in 0.5 ms means that the device will stand almost 4 times the rate of deceleration albeit for a quarter of the time. What this means is that for the same collision speed it can be slowed a lot faster and hence the mounting and casing needs to allow for less movement for the same drop height.
As this device is only 10gms, then the 1,500G is equivalent to a force of about 15N or about that experience by a 1.5Kg mass at the Earth's surface. On that basis I suspect that force could well be sustained much longer than 0.5ms, possibly indefinitely. However, it has to be installed into real devices and those will probably have to be designed for real world situations (like being dropped off a 1 metre worktop).
G is the universal gravitational constant, but it is clearly not what was meant in the bloody article. They clearly meant what is normally written as "g", which is an acceleration of about 9.81 metres per second squared.
We were equipped with common sense for a reason, and it's not to go blindly down case-sensitive rat-holes as you would head.
I think something will have to be done about wear rates on SSDs before the old hard-drive finally bows out. Of course, if you can make a "disk" of say four of these new SSDs, where 20% of capacity is set aside for RAIDing and wear wastage, you then only need to bring the price down to get it competitive with the large capacity platter spinners. Until then, platters still have a function for large capacity drives at a relatively cheap price per GB.
These 'end of the hard drive' coments are so PC centered...
The problem is that SSDs are fast but expensive and small compared with hard drives. This year (2011) will see the introduction of 4TB 3.5" disks - I do not see SSD densities getting near that any time soon.
Also, sheer speed is handy in some applications but others required bulk storage. In a data center people would generally prefer to have big storage capacity as they can access drives in parallel for speed. The greater density allows more storage for the power and cooling required.
So for a home PC maybe but in enterprise applications HDDs will be around for a long time yet.
"In a data center people would generally prefer to have big storage capacity as they can access drives in parallel for speed. The greater density allows more storage for the power and cooling required."
It's perfectly true that you can get more IOPs (and throughput) by installing more drives at the cost of power consumption, cost and data centre footprint. However, there is one think hard drives can never do, and that is consistently achieve random read latency times of less than about 6ms. With SSDs you can get down to tens of microseconds (or, realistically, on a SAN hundres of milliseconds). If you have an application which is I/O bound on random reads, then only SSDs will get you out of it once you;'ve exhausted the practicalities of caching. (Random writes are not such an issue - enterprise arrays will cache those in NV store).
As for 4TB drives in the enterprise, then we have had real issues with the reliability of high density drives. They are OK for some semi-archival uses (for which you'd never use SSD anyway - at least not for the forseeable future). However, use them hard, and they fail at a much higher rate than the lower density enterprise drives. Then there is the problem that re-building RAID sets with such high density drives takes a very long time as capacity inevitably outgrows throughput (read/write throughput goes up in proportion to linear bit density, capacity as to square of linear bit density). That pushes you to double parity which removes some of the capacity advantages and can also impact performance.
SSDs will erode the top end of the enterprise drive market as prices drop. Realistically, write endurance is not going to be too much of an issue. Enterprise drives fail too, and once they get to the limit of their practical operating life, failure rates start to increase and swap-outs happen more frequently. Of course it's generally covered by maintenance contracts, and exactly the same thing will happen with enterprise SSDs.
Disks won't go away, at least for the forseeable future, it will just get pushed more and more to the bulk storage area.
Yeah, 400G/2ms is a misleading notation, 400G x 2ms would be better.
A few sums later using v = at, v^2 = 2as, 400G for 2ms kills 8m/s speed.
8m/s speed is what you get from a drop of about 3.2m here on earth. So a 10 foot drop.
But stopping from 8m/s at 400G takes 8mm, which is either a very soft carpet or very pliable mountings/case corners &c...
Stopping in only 2mm takes 1600G for 1/2 a ms. That's your hard surface example.
These 'end of the hard drive' coments are so PC centered...
The problem is that SSDs are fast but expensive and small compared with hard drives. This year (2011) will see the introduction of 4TB 3.5" disks - I do not see SSD densities getting near that any time soon.
Also, sheer speed is handy in some applications but others required bulk storage. In a data center people would generally prefer to have big storage capacity as they can access drives in parallel for speed. The greater density allows more storage for the power and cooling required.
So for a home PC maybe but in enterprise applications HDDs will be around for a long time yet.
Why is that SSDs seem to be exclusively aimed at laptops, when surely desktops could do with some SSD-love too? Why is almost impossible to buy an OEM PC with an SSD drive included (unless you go to the very top-end gamer models that cost 1000+ quid)? Surely the combo of an 80GB SSD and 2TB hard drive is cheap enough for OEMs to put them in their mainstream desktop ranges now?
The top of the range Vaio Z series notebooks have dual SSD drives - 256 GB in a RAID array. Well, they describe it as being two 128 GB drives per unit, and two units per machine although I get the impression from the forums that this just complicates matters.
Mind you the machine is >£3000 so not exactly a price/performance "sweetspot"...
The Register 
Biting the hand that feeds IT
Copyright. All rights reserved © 1998–2025
