What I want to see is 5.25 inch form factor HDDs. It will be a tremendously boost not only to capacity, but also to sequential performance as well. Larger head count, independently operating heads, increased cache size - 512 mb at least with in memory defragmentation for small random writes, and integrated nano UPS, capable of supporting the drive until all cache is hard stored in case of a power failure.
This will make possible 30-50TB HDDs, capable of sustaining 1+ GB/sec transfers on workloads which are well distributed over the platters.
While 5.25" platters seem a good idea, this is probably not true. 5.25" platter would be much vibration-prone, with resulting lower RPM (< 4000, probably). Moreover, a bigger platter size implied bigger/heavier actuator and heads, with lower precision and consequently lower platter density.
Platters with multiple, concurrent heads were tried in the past, but with current high platter density they are probably not feasible.
On the other hand, I +1 the idea of power-protected write caches (which _are_ already available on selected enterprise-class disk).
Lots of speculation, no facts, just a load of "probably" without argumentation. The difference in radius is ~35%, the difference in surface area is over 100%. Independently operating heads and actuators, even if 35% larger, will actually be lighter than current approach where they are stuck together. Tried in the past - technology has improved a lot since then, you can have 2 to 6 independent heads per platter face without going in each other's way. This means tremendously lower latencies, as there are multiple heads available at each 1/head count platter revolutions.
Larger platters means higher sequential speed, and a larger percent of the capacity would be in the fast area. Larger form factor means more room for platters - 10 are feasible. Which means at the same storage density of those 10TB HE drives, you can have a 40 TB drive that can easily push 5-6 GB per second transfers at lower PRM. Naturally such a drive would require multi-lane PCI-E and a good 4-8 GB cache/ram. With good caching policies this will annihilate SSD in pretty much every area at a better price safe for applications for vibration heavy environments.
It is entirely doable, but not done for a number of reasons, and no, complexity is not one of them.
Also, independent heads offer a boost in redundancy - such a drive can lose components, which are vital to current HDD implementations, while still retaining some or even full operation, albeit at reduced throughput. Head and/or platter parallelism and other advantages on top of that.
So you suggest a 10 platter design with independent heads. So basically 20 actuators. And the "brain power" to control all of them. So you have 20 actuators, a much bigger motor, higher inertia and stresses (due to increased weight - an increase in surface usually brings an exponential increase in volume and weight). That's an increase in power consumption, BoM, noise and research needed to put it all together in a world where SSDs are already getting close to the price per GB of spinning disks. Any reason I'd choose a slow and sensitive "spinner" and not the much faster and more resilient SSD at the same price? Also, remember Samsung already has 16TB 2.5" SSDs. Absolutely 0 reason to go for a clunky, mechanically complex 5.25" device that's extremely susceptible to any mechanical shock and that doesn't fit most devices out there (moving to 2.5" can't be done fast enough).
So I will urge you to quote a paper that actually researched this implementation with concrete details and not just submit lots of speculation, no facts, just a load of "probably" without argumentation because you seem to like the idea.
I suggest an arrangement with 4 stacks of platters (square formation) and the heads positioned in the center of the stack. Then the heads could quickly spin from one stack to another to access the data there. With a bit of software optimization you wouldn't even tell the difference. Much better for archiving than SMR. Also you can use just one bigger motor that can decouple from any stack independently to reduce load instead of 4 smaller ones. Also the design is scalable: in a box the size of a standard NAS you can fit 10-20 times the data,
It is entirely doable, but not done for a number of reasons, and no, complexity is not one of them. It actually reduces complexity by reducing the number of parts, especially moving ones.
And since I just explained you in a few words how it would work this is clearly not speculation, assumption, etc. It's fact. I also have some "spinning sphere" research.
"So you suggest a 10 platter design with independent heads. So basically 20 actuators. And the "brain power" to control all of them."
10 platters - 20 faces, optimal config of 4 heads per face - that's actually 80 actuators. 2 heads per face makes for 40. Each of those heads can access different areas of the platter individually, capable of 70-150 MB/sec transfers. The brainpower will not be as much, neither in terms of silicon area nor power consumption.
"That's an increase in power consumption, BoM, noise and research needed to put it all together"
It will still be more efficient, cheaper and substantially faster than the n number of regular HDDs needed to match its capacity. The concept is basically numerous worker heads sharing the same hardware. You sill will only have one motor, one case, one power sully, one "brain", one cache buffer.
"Also, remember Samsung already has 16TB 2.5" SSDs."
And it costs a set of good kidneys, and is still flash memory with a finite PE cycle count. Nor is it capable of the kind of concurrent throughput I am talking about.
35% larger platters, motor and case, more platters, let's be generous and say that alone will cost 50% more than a regular size HDD. The actuators - when mass produced will be pretty cheap, there is not much to them, it is basically some steel profiles, some copper wire and a magnet. Add in the 4-8 GB of ram and the 50$ of components needed to drive the whole thing and transfer data back and forth the PCI-E buss - the BOM will roughly come at twice that of a regular HDD, at 4 times the capacity, at least 30 times the throughput and tangibly lower latency. All in all, due to the sharing of the mechanics, it will use less power, generate less heat and noise and cost less than the number of HDDs needed to match the capacity alone. And hey, fast large SSDs are not exactly known for their stellar power consumption either.
Maybe but do you have any concrete research or only speculations and assumptions?
Also you make several glaring mistakes: "It will still be more efficient, cheaper and substantially faster than the n number of regular HDDs needed to match its capacity." How exactly is a drive that needs countless months of research and testing less complex than a few of the "good ol' drives" of today? How exactly is 80 independent actuators less complex than the tech found in any run of the mill $50 drive of today?
"The actuators - when mass produced will be pretty cheap, there is not much to them, it is basically some steel profiles, some copper wire and a magnet." I don't think you know what the actuator is. You are describing the *actuator arm*. That arm doesn't just do stuff, it needs the actuator. That's a motor to actuate the arm. That's 80 little motors that should move 80 little arms all over the platters at great speed and precision.
"and is still flash memory with a finite PE cycle count" You are forgetting that hard drives suffer from more mechanical failures than SSD suffer from PE cycles limitation. You will now have 80 little motors and one big motor (and I mean BIG, it has to spin 20 heavy platters) that will suffer wear and tear.
I think it's a lot simpler to create chips with 3D stacking. 512 or 1024 dies stacked together shouldn't cost that much. Also you can achieve low power consumption by using new fabrication techniques and materials. I would say at least 60-80% lower power usage. This way in 2 years we could have a 32-64TB SSD that consumes less power than the 5.25" hard drive motor alone.
Really missing an edit button here. 80 actuators that work independently also eat up a lot of energy, along with that big spindle in the middle. One that takes ages to exit standby because of inertia alone. So having 10 10TB drives means that you can have 9 in standby and still access your data. One 10TB drive is "always on".
And in the end you still end un with niche technology that could either work only in enterprise (no problems there since you can use unusual form factors even now - thick 2,5" or 3.5" drives, different connectors, etc.) or in full size desktops. Which, as you may have noticed, are fading away. Because most people would rather have reasonable capacities in a really small package than have enormous capacities in a big package.
And those actuators need to be positioned all around the platters in order to ensure the arms don't intersect. This means a 5.25" platter will need an enclosure that's wider than a standard optical unit. Look at an open HDD (random pic http://www.hardwaresecrets.com/wp-content/uploads/... and you'll see that there's no way to put 4 arms without increasing the size on all sides. Making a drive that doesn't fit in any computer case. Or you drop the size of the platter and you have to adjust the speculated numbers.
And a hard drive, no matter how many actuators you cram inside cannot keep up with solid state memory speed wise.
If the spinning disk industry had a trump card like this they would have used it. But most likely it's not feasible. I agree with you that profit is the end game but they see their market share shrinking and still don't come up with this.
A 10 platter drive with 4 actuators/heads per platter face is doable in the form factor of those older CD/CDRW/DVD/DVDRW drives - the longer ones.
The actuators snugly fit in the four corners, and although numerous, they are individually much lighter than the actuator of a regular HDD, therefore they need much smaller coils. They will only use power when the workloads demands it, otherwise they are parked and use no power whatsoever. The extra power they'd use while in operation offers a very good return in performance, since you have numerous heads working but spinning only one set of platters.
And no, contrary to your "expert" opinion, there are no "motors" in HDD actuators, you demonstrate profound cluelessness in the subject.
NVMe SSDs already exceed the power consumption of mechanical HDDs, I seriously doubt power consumption will go down as you add more DIEs. Semiconductor production will never become cheaper than platter production, as it is an immensely more complex, time consuming and environment unfriendly process, and is soon bound to run into a brick wall, which will prohibit any further scaling down of process node size.
The industry is not in the habit of aiming to provide the consumer with the best value for his money. An example - intel keeps cramming iGPUs into 400+ $ processors, even though hardly anyone, willing to pay that much for a CPU, would be willing to settle with their mediocre performance, and all that DIE area would be much better invested in twice the CPU cores. But such a product would offer too good valie, more than intel is willing to provide to consumers at this point, so it will keep wasting DIE area on lousy iGPUs, and the chips which are spared that utter waste will come at a significantly higher price.
Similar examples can be seen anywhere you look, provided that besides the ability to look you also have the ability to see ;) The product I speak of doesn't exist for the sole reason it is far better value than what the industry would like to offer. And no, it is not as easy as "kickstarting" your own foundry to make what the industry refuses to, even if you could gather the billions this will cost, you will run into patent trolling, because none of the big players who "own" the tech would be willing to allow you to humiliate them in such a manner, nor to extort and force them into providing better value than they are willing to.
So you don't know that a voice coil actuator *IS* a motor and that while the "copper wire" might be enough to make some shiny loops for you to chew on it's not enough to actually "actuate" but you claim to be a star hard disk designer...
I even gave you a damn picture http://www.hardwaresecrets.com/wp-content/uploads/... so you can understand the proportions involved because the actuator doesn't stay magically the same while still covering a 5" disk.
Somehow you find a way do dig yourself into a hole every time you comment on most articles. You just plaster suppositions, assumptions, maybes but show zero understanding of any of the things you talk about. The only thing that fits in a corner is you :).
I'm waiting for the next iteration: the truck tire sized hard disk.
Wow, you found a photo of a hard drive - you are a mastermind of the highest order. Good for you.
Now, consider the fact that this actuator from the photo is used to move a total of SIX arms, fused in a single assembly. Now consider that an independently operating head would require only one arm, in the case of a 35% wider platter let's say it will 35% heavier, thus 6 / 1.35 = 4.44 times lighter than the arm assembly of a regular HDD. Let's be generous here, and spare you the metal strain and round that to 4. 4 times lighter actuator arm would need a considerably smaller smaller magnet and a considerably smaller coil. And that's in the case of the rather modest count for only 3 platters. That disk from the article actually has 7. So 14 / 1.35 - that's a whooping 10+ times lighter.
Are you sill on the train of thought?
Now consider a 5.12 inch circle inside a square with a side of 5.25 inch, and the amount of room remaining free in its 4 corners. It goes without saying, the corner space of a 5.25 inch drive will be more than the corner space of a 3.5 inch drive, so what do you think, will you be able to fit a considerably smaller actuator in a larger area? Hint - the answer is yes. And we are thinking in 2D here, don't want to put too much strain on you ;)
Your idea that the actuator size will grow with the disk is a product of your complete failure to understand things in the context I present them, you just can't go out of that box. The actuator of a 5.25 inch drive following the traditional design would only be larger, because the arm assembly would be fused and it will be heavier than that of a 3.5 inch drive. But ultimately, the point you fail to grasp is that the actuator size is not a function of the platter size, but of the actuator arm weight, and a single arm with a relative mass of 1.35 will always be much lighter than 6, 8, 10, 12 or 14 arms with relative mass of 1 which would be in a single assembly respectively for drives with 3, 4, 5, 6 or 7 platters. Maybe now, after it has been explained to you in a matter fit for a toddler, you will finally get it?
And yes, I am well aware that anything, capable of converting some form of energy into motion qualifies as a motor, for example my foot, but still, I prefer to call it foot rather than motor. The same way it is only natural to refer to an actuator motor as an actuator, not a motor, because that's a vague generalization, and would also be confusing, since any layperson actually use "motor" in an entirely different context. And yes, you do strike me as a layperson.
So yes, obviously I do know that the actuator is a type of motor, and obviously, I never claimed to be star hard disk designer. You are resorting to making things up, which further goes to show your actual level of competence. Gonna refer you to your previous post:
"I don't think you know what the actuator is. You are describing the *actuator arm*. That arm doesn't just do stuff, it needs the actuator. That's a motor to actuate the arm."
Seems like you don't know what the actuator is. The HDD actuator is consisted of the magnet, the coil, the coil frame and the arm. So when I say actuator, it implies all of those. In fact, the very paragraph you responded to has listed the steel arm frame, magnet and coil, and yet somehow you interpret that as "talking about the arm". You might want to brush up on your reading and common sense skills :)
"Somehow you find a way do dig yourself into a hole every time you comment on most articles."
If imagining that makes you feel any better - go for it. It is only natural, narrow minded people always feel resentment for outside the box thinkers. Mainstream conformism never ceases to amaze me, especially the feeling of pride associated with it ;) Amazing the kind of things people take pride in nowadays, such as sexual orientation, skin color or being conceptually limited to only what has already been done and being totally ignorant of what could done considerably better.
CPU's don't scale because data is rarely independent. X depends on Y, Y depends on Z, so you can’t load X, Y and Z into different cores.
Actuators are motors that move something.
One actuator/read-write head assembly takes up around 1/6th of a 3.5” HDD enclosure. You want 80 actuators in a 5.25” enclosure…
HDD's have data tracks, like vinyl records, but far smaller. If you have 2 million tracks per inch then there is 5/10,000,000 of an inch between the centres of each track.
So your HDD read-write head needs to be in a very precise place to read each track. This means every actuator (the thing that moves the read head, steel arm frame, etc.) needs an extremely precise motor controller (the expensive/complicated silicon everyone keeps referring to).
Data tracks run in a spiral shape. When sequentially reading or writing, the read-write head constantly moves, which is fairly easy to control.
If you have four read-write heads per surface but only one data track they would have to jump to the next track every quarter revolution. Critically damping an actuator to move 5/10,000,000 of an inch 21,600 (4x 5400rpm) times each second reliably for 5 years would be an exciting engineering feat worthy of your billion dollar retainer. Making 80 read-write heads move so in a 5.25” package is Nobel Prize territory.
If you have one data track per read-write head, the latency will be the same as if there was only one read-write head. Latency is why HDD's suck so much. Yes you could increase sequential flow, but you might as well just have all four heads on each surface attached to the same actuator (with a complex mechanism to adjust for the different circumference of each track).
Then there is availability. Like others have said, metals expand at different rates when heated so the actuators for the read write heads need to be regularly recalibrated. For this 7 platter HDD (yes, I'm bringing you back on topic), there is only one actuator controlling the 14 read-write heads. Say this system has three 9's availability. Worst case it needs about 2 minutes each day to re-calibrating itself. With your 80 independent actuators your hard drive will be offline for around two hours every day (assuming your design is robust enough to recalibrate all 80 actuators without causing errors).
How are you going to synchronize data between your 80 write heads? Say you have a 3.5 inch disk. The data rate half an inch from the edge will be 28% slower. The data rate an inch from the edge will be 57% slower. How do you synchronise these data rates without adding excessive latency?
So cost. A significant materials cost in a HDD is the actuator. You want 80.
I respect your can do attitude, but innovations in HDDs require very complex simulations of materials, not the lazy management engineering that you, I and the other commenters have produced.
ddrive, There are some serious flaws in your thinking. Its pretty clear you don't have any decent real world experience in engineering or business.
Existing hard disk technology is bases on decades of research and development. Significant changes in design require a significant increase in investment. In order for this to be viable, manufacturers need to be assured of a return. If you think the great minds behind existing storage technologies haven't thought about the ideas you propose then you are mistaken. There are several technical issues with what you propose.
Firstly, larger (5.25") platters have several major disadvantages. While they will have a reasonably higher capacity, performance is negatively affected. Larger platters require more power, produce more noise and vibration and this need to operate at a lower RPM. This increases rotational latency which impacts performance. Furthermore the increase in the size and mass of the actuators will impact their operating precision, increasing seek times. Larger parts are also more heavily impacted by thermal stresses, which has an impact on the density you can achieve. These drives will also require more materials to construct, be more expensive to build and heavier, increasing things like shipping costs.
Secondly, having multiple actuators in a drive, while a novel idea, doesn't hold up so well in the real world (it has been tried, several times) There are several issues:
- They take up significant space. Assuming your maintain the existing form factor, this will shrink the usable storage area inside the drive. Unless you're going to invent a whole new form factor, this is not viable. (you can have a 3.5" platter with 2 actuators in a 5.25" form factor - this has been done commecially)
- They have a major impact on the cost of the drive. We're talking about a huge increase in the number of moving parts that have to be manufactured and assembled. Additional hardware required to drive the actuators has to be included. Complicated firmware has to be written. Optimizing access patterns for one set of actuators is difficult enough. Again, material costs increase significantly. Any hypothetical increase in performace is negated by the cost alone.
- Heat, power, vibration. More moving parts will have a negative impact on reliability of the drive. (Your argument of redundancy does not consider all potential failure modes.) These are also expensive problems to solve.
- The basic physics that hard drives deal with (and this is really the biggest issue with this idea) A read-write head has to deal with a lot of thermal stress. The platters, the actuators and the heads themselves undergo expansion and contraction significant enough for it to have an impact on performance. Hard disks deal with this by encoding "servo" data in the platters that are calibrated to the head assigned to it. Since the platters and the heads are not perfectly homogenous, this data varies from head to head and platter to platter. The issue is also compounded by the density of the platters (the smaller the tracks are, the greater the impact of expansion and contraction) This principle makes it impossible (or at least extremely difficult) to assign multiple heads to one platter. Of course you can mitigate this by trying to create heads that are all EXACTLY the same and platters that are perfectly homogenous, but this is extremely expensive. More moving parts further magnify this problem by creating a more thermally dynamic environment within the drive.
- Another physical aspect is that the actuators can interfere with each other. If they are moving independantly, they make microscopic changes in the density of the medium inside the drive, as well as vibration. This has a significant impact on the accuracy of tracking and increases seek times.
Yada yada yada, I've already addressed pretty much all of your points in other posts, save for the actuator "crosstalk", which is a valid issue, but nothing critical. It will only take a few seconds of profiling per assembly to measure it and create a dedicated profile for the particular HDD unit to compensate and normalize it. This is for EM interference, as for mechanical - since the actuators are independent, they will be individually lighter and influence the entire device to a much lesser extent than the single heavy fixed multi-head actuator of a regular HDD. As for actual actuator collisions - I've ran range of motion simulations, even SIX actuators per platter face are doable, but will add to the form factor. 4 are doable in standard 5.25" form factor. There are two ways to go about the actual actuator design, there is a cheaper one, which would be computationally intensive on the firmware, and a more expensive, which would require production of 2 to 3 slight shape variations - nothing much really.
5400 RPM 5.25 inch HDDs were possible 20 years ago. I am quite sure this is still technically possible today. Frankly, with independent multiple heads you don't need more, 5400 is ample. Low RPM and larger platter diameter are a problem only when you have a single actuator to service the device. Even only 2 heads per face at 5400 RPM will provide equal or better performance than 1 head at 10k RPM in every possible performance metric.
The firmware is not that much of a challenge either, nor its implementation, which should take no less than 6 months for a SINGLE decent firmware developer - everything from scratch, nor will it require any exotic, custom MCU design, I reckon a stock Cortex R7 would suffice.
It would be really amusing to see you try and apply your claims in the real world. You've made so many exaggerated comments without a shred of evidence supporting your claims. Your claim of "a few seconds of profiling" in particular is evidence that you are talking out of your ass. You can make claims of how an ideal system would work, but things are different in practice. You are not talking about a static system, but a dynamic one. Components are not perfect, the have flaws and tolerances. These kind of things compound with complexity which is essentially what you are proposing.
If you really think your claim isn't absurd post some hard data on what such a system would cost and how much power it would use.
How about also explaining how on earth you are miraculously going to end up with lighter actuators? (If you could just magically have lighter actuators, why wouldn't current drives embrace the idea to save material costs? What's the trade off?)
How are you going to address the added complexity of assembly? The fact that your production costs are going to increase significantly? The cost of more expensive materials?
What about the servo data? Are you going to write servo tracks for each head?
How are you planning on dealing with heat? Turbulence? Vibration? You haven't addressed any of these points?
Do you really think one firmware programmer is going to be able to develop a decent solution in 6 months? You're aware the industry has billion dollar companies that have spent decades analyzing real world applications to optimize firmware for drives in various applications?
Your claims are preposterous. How about a little substantiation? You speak of "simulations" involving configurations of 4 actuators, how about a technical drawing?
You talk about this stuff as if you snap your fingers and it just happens. Do you actually have any industry experience or are you just making stuff up?
All these points are pretty moot as your entire argument is predicated upon a hypothetical performance increase your system would have, despite the fact that this is flawed thinking. Your over complicated hypothetical unit will get trounced by an entry level disk in terms of unit cost and bang for buck.
Gimme a billion dollars and legal protection from patent trolling and I will show you.
You ask for hard data - that would require at least operational prototypes. I refer you to the previous point. I could provide you with simulation data, but you will have to pay me to develop that, it will cost you 500k, you will have your results within a year.
No magic - it is simple and obvious, and quite astonishing you still don't get it - current HDDs combine the arms for all platters in a single assembly, thus logically, it is much heavier than the individual arms on their own. n>1 count of arms will always be heavier than 1 arm. DO'H
HDDs are assembled by robots, robots don't care whether they do something once per HDD or 100 times per HDD.
The actuator synchronization markers are on the platters, they can be used by any number of actuators.
Heat conduction, vacuum, not gonna be an issue - wasn't 20 years ago, won't be today.
Yes I do, and I did not say 6 moths, I said less than 6 months. The billion dollar companies are full of slackers.
Range of motion simulations are children's play. If you can't set up a disk with 4 moving arms around it and check if they can move along along the disk radius without touching in any configuration, you have no business questioning my competence.
I have 20 years of experience in software, electronics and mechanical engineering. I haven't been in "the industry" though, I am more of a "custom shop" guy.
There is nothing hypothetical - if a single head can do X, then N heads can do N * X. The challenges are there, but I don't see anything that would qualify as an obstacle, nor have you nor any of the naysayers provided any factual evidence of such. You keep asking about "evidence" that it is possible, but each component of that system already exists and has decades of mature tech behind it, there is no reason why it shouldn't work, if anything, you should be providing evidence why it shouldn't work, and I mean tangible facts, not that drivel. You present a number of points you believe are going to be problematic, but not even a word on why would they be problematic. Where is your shred of evidence? Being conceptually limited to only what has been done so far does not speak in favor of your competence. If everyone was like you, we'd still be living in caves and wearing animal hides for clothes. You sound like a mainstream evangelist, you probably believe in ridiculous pipe-dreams like manned missions to Mars or asteroid mining, and yet have such a problem with a concept which has all its requirements already met technologically.
@ddriver - there are a few people in the HDD industry that's replying your thread. You have no simulation data because you are asking people to pay you to develop it. You are asking for arbitrary amount of money (1 billion dollars) to 'show' us how you do it. Even kickstarters won't give you that amount of money, much less HDD companies.
Your simple hypothesis that "if a single head can do X, then N heads can do N * X", even with something non mechanical like CPU cores, you know having double or quadruple the number of cores do not mean 2x or 4x the performance, having more heads per surface won't solve the problem, made worse by today's high densities in terms of track spacing and variation between head sizes and performance makes it impossible to do what you think you could do.
What makes you think the data written by one head can be read by another head? To allow for these variations so the heads can read data written by their counterparts, you have to make track spacing much wider and make the heads to perform at lower than what they are capable of, negating your so called increase in capacity. In the end, your 5.25" platter may have similar capacity to a 3.5" platter or worse, you'll find that it just doesn't work.
Even Steve Job's reality distortion field don't work all the time.
"What makes you think the data written by one head can be read by another head? "
What makes you think it can't?
"Your simple hypothesis that "if a single head can do X, then N heads can do N * X", even with something non mechanical like CPU cores, you know having double or quadruple the number of cores do not mean 2x or 4x the performance"
CPU cores share resources, not all workloads are CPU time bound, you are obviously quite ignorant to even make that comparison. In CPU intensive tasks, minimizing the strain on the functionality shared by the cores, test results actually show close to perfect scaling, but you are obviously not aware of that either. Multiple heads can actually scale better than 100% - since they will decrease latency and eliminate a lot of the seek times. For example, a single head reading from one location on disk and writing to another would have to travel back and forth, so its throughput will be split between the two tasks, and moving between the two will be a substantial overhead. Two independent heads can do 2 tasks at their full throughput and they won't have to waste ANY time seeking.
With multiple heads, even if the head count is higher, individual heads and their arms are much lighter, so even if the vibrations they produce are higher in frequency, they will be lower in amplitude than the vibrations produced by the heavy arm assembly of a traditional HDD. Naturally, and for someone with a shred of competence it should go without saying, but since you lack it, actuator drivers can use ease in and ease out to reduce vibrations to non-existent, something a drive with multiple heads can afford to a much larger extent than a traditional HDD actuator, which can't afford to lose precious time since it is the only one servicing the device. So your point about increasing track spacing entirely wrong, and such a device will inevitably end up producing much less vibrations, much less noise, and may even allow denser tracks than a traditional HDD.
The 1 billion is an approximation with a safe margin, if it makes you feel any better, I can give you a less (or more) arbitrary number, for example 987563, is that better? I have done range of motion simulation, which as I already said is trivial, the 500k I asked for a product simulation involves all the mechanics, electronics and firmware. This is a significant investment of effort, it is quite silly of you to think I have made such just to have them lying around ;)
Your belief that the "industry knows best" is ridiculous. You obviously have no knowledge in any of the fields involved in product design. Just to give you an example - yesterday a washing machine died - a whirlpool unit, from a company with long history of making such products. The culprit - the ceramic capacitor they used in lieu of a transformer to implement the PSU for the electronics. They used a capacitor rated at 240V for a product designed to operate on 230V line - practically no safe margin, resulting in a ticking timebomb, ruining an otherwise still operational device. A 400V capacitor with the same capacitance costs a mere 29 cents, only 6 cents more than the one rated for 240V, but would have lasted until some more significant component of the machine has died, and yet they did not use one. The industry knows best? Yeah right, and I don't say the engineers didn't knew all this, it is likely they did it on purpose, and they have likely calculated the capacitor to die just about the time the warranty runs out, because the industry, even if it does know best, doesn't care for the best, it cares only about profit.
Finally, you obviously have no idea of the extend of my knowledge and skill set, you demonstrated profound lack of technical knowledge, profound inability to understand simple logic and common sense, and on several occasions you failed miserably at trying to sound smart - something you'd realize had you actually been as smart as you try to pretend to be.
And that example with the washing machine is just one of the many cases I've seen the industry spew out lousy products, and anyone with a decent amount of knowledge in the area would notice that too.
Almost 10 years ago, I built my own smart oven, with the ability to automatically control the position of the top and bottom heating elements, which were on their own compound and could be activated in different patterns. It could also operate on hot air alone using an additional heater, and could program a temperature curve to follow with time, remote control and remove observation via a webcam. The industry has only just began selling smart ovens, and they come with nowhere nearly the set of features my own design had a decade ago.
So pardon be by not be impressed with what the industry does and how it does it, in many aspects I know things can be done better, and in some - as long as I had the resources, I've already done better.
RainDaemon's points are valid while ddriver's are mostly hypothetical. ddriver obviously have no idea the amount of code groups of firmware engineers have to write to not only control the actuator arms, but to interface with SATA or whatever interface you now have, to do many other background stuffs that you have no idea of and simply calling them slackers show how idealistic or out of touch you are. And quoting less than 6 months, just seals it.
weissPC, give it up. The guy knows sh*t about engineering (motors, circuits, firmware, interfaces, you name it) or business. He just thought it was a cool idea and now won't back out because he went too far with the crap. I gave him the benefit of the doubt and asked him to support his claims with real data, not some more "quotes from ddriver" and he failed so every single time.
He just came up with some bullsh*t figures that he can't substantiate and every time someone proves him wrong he just hides inside his "reality blurring machine" and thinks that only he has facts and everyone else has suppositions, assumptions, speculation, maybes. I asked him for any paper to support his claim. He managed to write a full page of crap but no actual link to what I asked.
So basically the only argument used to support his claims is "because I say so". He's a troll on Anandtech for at least some years. Don't waste too much time, you won't get anything good. He's had years to show that and failed.
@close, spot on, couldn't have said it better. Better spend my time of more productive stuff. If he's that good, let him produce a real product to prove us wrong.
You forget that 5.2" platters existed - and they go extinct for the reason I explained above. The Quantum Bigfoot drive (a 5.25" one) was universally remember for it's very slow speed (~ 4000 RPM and very high seek time), rather than it's capacity.
Earlier, 8 inch disks had the same fate - they where abandoned in favor of 5.25" disks.
There is a reason the industry standardized on cheap 3.5" for raw capacity and 2.5" for performance; however, recent 4 TB 2.5" disks are challenging that (consider that you can fit 2x2.5" disks in the same space as 1x3.5" disk).
For the multiple head counts: did you ever ask why current multi-platter, multi-head disk read from a single platter at a time, rather that striping on multiple platters? The reason is simple: with high platter density, each head must be place independently, with dedicated actuator. This will greatly increase disk cost and weight, giving only minor benefits. Please consider that such disks existed - and they got extinct for a reason.
There is a trade off, as you see, most HDDs are 3.5 inch devices, so obviosly, smaller is not better, there is a sweet spot. 5.25 inch HDDs will run at lower RPM, but using higher head count, they can easily and vastly outperform a traditional 3.5 inch HDD even if it spins faster. Today such components can be mass manufactured at a very low cost, and chips are advanced enough to be able to run the much more sophisticated firmware which a drive with multiple independent heads would require. Both of those were not technologically possible in the past, but today they are.
I think the market and the HDD manufacturers possibly know what they are doing and the physics involved. If it was a good idea and there was a market for it we would have them.
If they can make money on selling you straw, why should they bother selling you wheat? They don't care about making hard drives, all they care about is profit, making hard drives is just the means to attain profit. Their priority is making as much profit as possible by selling you as little value as possible - thus maximizing the profit margin.
@ddriver: "Their priority is making as much profit as possible by selling you as little value as possible - thus maximizing the profit margin."
Accept that the HDD market is a competitive market with more than one player. To get your money, they have to at least convince their target market that they are a better value than their competitors. Case in point is the Helium tech HGST is using to get a leg up on the competition. It is MORE expensive to build than the competition, so clearly not beneficial to their margins. It does, however, provide an advantage for its cost.
Given that SSDs are (apparently) threatening to make HDDs irrelevant due to superior performance and approaching capacities, I'd say the HDD manufacturers aren't in a position to hold back anyways. If they could "have a 40 TB drive that can easily push 5-6 GB per second transfers" as you posted above, I'm pretty sure they would have done it as soon as they could have to squash any reason to pursue SSD tech which looses them a lot more than they could possibly gain by holding out on us. The 5.25" form factor is a pretty well known quantity. Sure we could do better than they did with the bigfoot drives, but the tolerances will still necessarily be looser than the smaller drives.
On the other hand, if you a better understanding of it than the current HDD manufacturers and are convinced that it can be done to great effect, then by all means, launch a kickstarter and start pushing these puppies out. I'd love to see the look on their faces if such an event were to occur.
"Accept that the HDD market is a competitive market with more than one player."
Seems like this has become significantly less true the last several years. Today they are practically 4 - WD, Seagate, HGST and Toshiba. And they don't seem to be in a competitive spree, as the HDD technology is almost on hold, very low priority, barely any improvements, usually minor stuff, nothing ground breaking (just look at HGST - now basically the same thing, but we're gonna fill it with helium), and it is not like there's no headroom for improvement. 4 manufacturers on a planet with 7 billion people, enough business for everyone, no need to shift paradigms, better keep on price fixing and have a sweet time milking the market.
" "On the other hand, if you a better understanding of it than the current HDD manufacturers and are convinced that it can be done to great effect, then by all means, launch a kickstarter"
That activates my hilarity unit, a HDD factory, capable of producing most components in-house will cost at least a billion. That's a little too much for kickstarter, don't you think?
That's like saying sport cars are competing with cargo trucks. There is no competition between the two at this point. If the tech I want to see is produced - then yes, HDDs would actually be able to compete. But today those are entirely different market segments.
I have the feeling that ddriver is in love with the idea that harddrives should be 5.25 in size because it gives the impression of more 'value' and speed. I mean, 5.25 drive is bigger than a 3.5 drive, right? Well why doesn't somebody come up with a 5.25 sized drive that has like 15 SSD's inside, and has a built-in RAID10 controller inside interfacing externally with PCIe 16x?
@ddriver You cannot expect innovation and advance, especially of the type you'd like to see, in a market directed by top-down government regulation. Competition is what motivates R&D which in turn creates new products, etc. What companies strive for is actually to provide the very best value they can for a price the market will bear. If a company tries to give the least value it can it will probably fail quickly--that sort of thinking doesn't work in a competitive market. Don't know if you've noticed, but in the last 20 years technology has sky-rocketed in terms of capability while the prices for that technology have never been as low as they are today, and economies o scale have never been greater. The onus has changed from profit-per-unit to profits-per-thousand-units sold.
BTW, I still remember my very own BigFoot...;) Slow as molasses and sort of noisy, IIRC, but I bought it for capacity and nothing else at the time. 5.25" is an interesting idea, no doubt. Where the mechanical drives have it all over SSDs is capacity, and my guess is that this trend will continue until SSD's develop to a point where the mechanicals can no longer offer substantially more capacity for substantially less money.
Congratulations on fundamentally misunderstanding capitalism. Their priority isn't to sell as little value as possible, their priority is to maximize the disparity between perceived value and cost to manufacture. When possible this means adding things that increase value significantly (such as a hypothetical technology that increases performance and decreases total cost of ownership), but due to being based on some sort of development that has most of its cost to the manufacturer in a form independent of units produced, such as R&D or manufacturing changes so that with large production runs, the value increase is maintained but the cost decreases, driving that disparity upwards.
Congrats on getting a serious pinko to defend capitalism by the way, it takes a serious level of wrong to do that.
problem is: - in the volume of one 3.5" HDD one can fit 4x 2.5" HDDs - capacity remains roughly the same (4x2TB vs 1x8TB) - power use & cost however go up - in a RAID these are way faster & more redundant than a single 3.5" drive (2-3 times the MB/s) - random i/o is vastly improved (up to 4 times) - given a filesystem capable of caching the index on a SSD/RAM - reliability is vastly improved (pseudo-/RAID) the same things apply to 5.25" vs 3.5" HDDs...
They should just make them 10" so you can put your HDD next to your record player in your short bus. These guys are in the business to make money and they spend tons in R&D you think possibly they have done some research on these inanely obvious? I bet that they have and that they have and its some conspiracy and they have the prototypes in the corner next to the late 70's model car that got 50 mpg on tap water.
Most 10'000 rpm drives are 2.5 inch...Large platter with high RPM doesn't work. On the other hand if you want speed, you should ignore HDDs anyway. Even if you have a 50TB HDD, it would magically get 10 times the speed. So it will take forever to fill or extract data from. HDDs are slowly dying off. It will probably take at least another if not 2 decades. first flash and then non-volatile RAM types will replace it completely.
Next Gen Intel Processor (Kaby Lake 200-Series Chipset) will have support for Intel Optane SSD which use a non-volatile memory type. Eg. will make even high-end PCIe NVMe drives look like toys.
Quick question: why would you go for standard sizes like 5.25"? That's the platter size, not the disk size, so you can still go with 3.5" platters in a larger enclosure in order to cram in more independent heads or just to stack more platters in. Or why 5.25? Maybe the best compromise is a 4.2" platter. Any research on this or are you just assuming and speculating without facts?
Also, because you assume people sticking with 3.5" is anything more than compatibility and reduced manufacturing costs that go beyond just the simple HDD unit I will say that most cars run on gasoline now so electric sucks, most LAN connections top out at 100Mbps so gigabit is no good, etc.
You should really research causality and correlation.
Funny, you consider 5-6 GB/sec and quadruple capacity "minor benefit". At the risk of repeating myself, those things were attempted way before their time, using immature technology. That's why they failed. Actually, independent head and actuators, when mass produced, will have a negligible impact or both cost and weight. All it takes is vastly improved firmware capable of operating them independently.
Take wireless power - that dude Tesla did it more than a 100 years ago, and someone like you might say "it got extinct" but in reality, it was simply a century ahead of its time. As you see, now wireless power is a big and growing thing.
You seem to harbor a misconception that the industry is interested in innovation and improvement - on the contrary, the industry is only interest in making money, and having an easy time doing that. Thus they keep milking existing tech for as long as possible, keep things simple, because too good of a new product would kill their existing business. And they stay away from innovations until it is unavoidable and badly necessary, not to the users, but to the industry. It is really not that such hard drives are too complex or technically impossible, it is just that they'd be way better than what the industry would like to offer the consumer. They can't afford that, because next thing you know, the consumer is transformed from a paying tool to a progressing person with high standards of expectations.
@ddriver: "... they stay away from innovations until it is unavoidable and badly necessary, not to the users, but to the industry."
Agreed. However, I would argue that it is unavoidable and badly needed immediately if not sooner. The industry has been loosing an increasingly large portion of sales to SSDs. If they have any innovations that could make the move to SSDs less appealing, they would do well to use them.
Back in the days where those disks "failed", there weren't any chips capable of running such a device at high rpm. Since then technology has improved tremendously, both in terms of mechanics, manufacturing, but most notably - chip performance.
Calling this a failure is like calling space exploration a failure, just because 200 years ago someone tried to do it with an oversized kite and failed miserly.
Of course you are going to fail if you get ahead of yourself and try to accomplish something you don't have the technology for. But that doesn't mean an "ultimate failure" - it just means "everything in its time". Today technology is finally up to the task, but the industry still prefers having its sweet time milking the old tech, made so much easier by the advances in technology. Why should they bother to make such a giant leap, when as long as the consumer has no other choice he is going to buy the existing product line.
The previous issues with large-diameter platters were not electronic, they were mechanical. A larger platter spinning faster is much more vulnerable to instability, and needs to be mechanically stronger (thus thicker and less volume efficient, and harder to spin up/down).
The actual mechanism of HDDs is very mature. In the last decade, the only evolution has been in head technology (GMR) and orientation (PMR). Helium filling has allowed closer platter spacing, but will not allow larger platter sizing.
"The previous issues with large-diameter platters were not electronic, they were mechanical."
Because the electronics at the time were so inferior they didn't even conceive independent multiple heads per platter face. Thus they didn't even run into the electronic problems, only faced the mechanical. As I said at least a few times already - lower PRM would not be an issue with independent heads. Two heads at 5k will give you equal or better performance than one head at 10k, and extra redundancy. And it will end up being more energy efficient as well.
It's been done before. One of the big barriers was the different rates of heat expansion for the different servos. At current densities it would be a lot of work for very little benefit, particularly since lower speeds means higher latencies, which absolutely kills performance.
LOL, servos - enough said. This thing is a relic. Voice coil actuators won't have such a problem. 4 heads per platter face seems like the sweet spot, although even six are still possible without getting in each other's way.
Two heads at 5k RPM would be just as fast, and often faster than one head at 10k RPM. Two heads will offer the same throughput at lower RPM, saving on energy. Now if you have concurrent access, one head will have to move back and forth between the two locations, wasting more time on access than actually reading data. 2 hears can do that without the access, as they can simultaneously access the platter at different positions at the same time.
-- Because the electronics at the time were so inferior they didn't even conceive independent multiple heads per platter face.
mainframe and mini drives, even those with removable disk packs, had multiple independent head sets for decades. as to RPM, remember these devices had 14 inch diameter platters. given the laws of physics, I'd wager that angular velocity for most of such a platter is at least what we have today.
They had multiple heads, those failed. The mechanics of multiple heads are such that it is almost as cheap to buy 2 drives than 1 drive with 2 sets of heads. And having all the heads independent costs even more and presents massive mechanical issues.
Agreed, the problems with larger platters are mechanical and electrical, not electronic. Larger platters also require much more power to get spun up and maintain that rpm. More power means more heat. Both are "bad" in the long run. Larger platters also mean that the heads will need to move farther to cover the platter, which means longer actuator arms, which mean more mass. More mass, more power to move. F=ma. And slower. as it's going to a lot more power to stop the head at the desired point on the disk, or settle times will just be that much longer. Lose-lose.
Now, I could get behind a SSD in a 5.25 form factor to allow space for more memory in the case. However, that is such a niche market as to be not be viable. But it might be a way to dump previous gen flash in higher capacity drives while current/next gen flash bump on die capacity and go to smaller form factors.
Problem with larger form factor SSD's is the cost of the flash.Samsung already fits 2TB into a 7mm tall 2.5" drive, and it costs $800+ If you moved even to a 3.5" drive, so you could fit even more flash, it would be getting into the $2000 range! In the consumer market there is very little room for even an $800 SSD, much less ones significantly more expensive. What about enterprize, you say? Well, they are moving towards all PCIe flash, and there are already options out there with multiple terrabytes (3-4+) costing several thousands of dollars.
We will probably never see SSD's larger than 2.5" -- at least ones that are larger, in order to hold more flash. I think OCZ made some 3.5" ssd's a long time ago, but they were nothing more than the guts of a 2.5" drive in a bigger case. Pointless.
"Lots of speculation, no facts, just a load of "probably" without argumentation." – ddriver, I am confused. Are you talking about your first post or shodanshok's. The statement seems to apply to both equally.
The context is quite clear, if you really don't get it, you are definitely not as smart as you think you are.
The arguments presented by shodanshok don't apply, the product he claims to be proof of failure has nothing to do with the product I speak of.
I never used "probably" - the tech I speak of will work, it is sound and mature tech, it just has never been applied on such a scale due to corporate politics. shodanshok didn't provide a valid reason why it shouldn't work, thus his opinion is speculations based on his misconception.
Nah, I just know what is technically possible and have higher standards of expectations, which I agree is atypical in a world, mostly inhabited by consumer hoes whose "demands" are dictated by the industry. It is you who is a hopeless dreamer if you believe you are making any sort of point with such posts.
A typical 1/2 platter 500 GB desktop drive used to cost less than 10€ to build a few years ago (price from OEM including VAT 17€ around 2011, before the flood). Adding platter doesn't make things significantly more expensive, but all the things you are asking for do. They'd rather procude more standard drives and let you plug several of them into one 5.25" slot.
That they're charging 100's of $/€ for the bigger drives is an entirely different question - it's not only the production cost. If they stopped R&D they could probably sell the biggest drives for 50$ and still refinance the factory. But not much else.
ZERO speculation. Lots of actual facts. 5.25" drives would have lower MTBF, lower vibration tolerance, lower RPM, much worse seek performance, much lower random performance, and at best the same sequential performance.
Anyone familiar with the history of magnetic media will readily agree as would anyone within the industry.
Larger platters mean more vibration issues, longer armatures, all requiring greater spacing. Longer armatures also mean less precision, resulting in greater alignment issues for tracks, more mass, resulting in slower seaking, etc. There is a reason that 15k RPM drives use a fraction of the available area for actual recording.
Or there is the simple fact that NO ONE CARES ABOUT SEQUENTIAL SPEEDS! NO ONE. NOT A SINGLE PERSON. The limit is never sequential performance and 5.25" doesn't have the possibility of helping with anything else.
No offense, but if 5.25" drives were a good idea, one of the multi-billion dollar drive manufactures would have jumped on it. They obviously know some things you don't.
The last company to try mainstream 5.25" drives was Quantum, and look where they are...
And the real giveaway that going largest is a bad idea is that going smaller is/has been the trend for quite some time. Outside of data centers, most modern servers ship with 2.5" bays/backplane for SSD's and 2.5" SAS drives. And in data centers, no racks are designed for 5.25" formats and when you consider the huge power consumption increase those drives will have over even 3.5" drives (which use twice as much power as their 2.5" equals) while the entire industry is trying to be greener, even IF the drives doubled capacity while keeping performance the same (doubtful but not impossible) the fact that the drives occupy nearly twice as much physical space at a higher power envelope negates any benefits outside of any potential initial cost savings.
5.25" form factor is long dead and it isn't coming back. The world is going leaner, not bulkier.
More importantly the whole infrastructure is build around the current format so if you where to increase the size you would make it impossible to upgrade existing drives without replacing the racks for the new infrastructure, and besides that bigger drives also take up more space giving you room for much less space per rack.
On the manufacturers side they would have to first figure out how to best make the drives 5.25 and that takes up quite a bit of r&d and sure there would be more capacity per drive but it probably won't warrant the cost to start making them or the barrier to start implementing them.
+1. Hard drives are not a growth market. Therefore, you won't see large amounts of capital investment flowing into these divisions. It'll be about containing costs and managing the decline.
I was with StorageReview.com as moderator, user, and often technical editor for years and am now an engineer 50 ft. from a class 10 cleanroom, and I'll tell you guys: Listen to shodanshok. He knows what he is talking about.
I'll pass ;) love your legit credentials thou LOL, also, he might know what he is talking about, but he obviously has no idea what I am talking about, so his responses are intrinsically misplaced and do not apply.
As usual, the bulk of AT visitors aren't particularly big on "outside the box".
@ddriver - SSD was the "outside the box" solution. If you want speed, go for SSD, if you want capacity go for HDD. Doubling the number of read heads on a disk surface still won't get you near the seek nor read speeds of a SSD. That's why even the WD Raptors are quite irrelevant now. Let each focus on their niche.
Your "outside the box" ideas doesn't make engineering sense.
"Look up Quantum Bigfoot. I'm sure history won't repeat itself."
What I am talking about has absolutely nothing to do with that product. I am not talking simply larger plates, I am talking advanced HDD implementation on top of larger plate size. The Bigfoot was big, but ultimately, it was a traditional HDD design, thus even though it offered superior capacity, its access time and sequential performance were compromised because it had a single actuator to service larger area at lower RPM.
Independent multiple heads per platter face will result in dramatically reduced access time and tremendously increased sequential performance even at lower RPM. Independent multiple heads will easily beat even 2.5" 10k RPM drives in terms of latency, and vastly outperform them in terms of throughput. 4 heads per face, 10 platters - that's 80 heads, each capable of a good average 150 mb/sec, as already mentioned, such drive will have an easy time sustaining 5-6 gigabytes per second at below 4 milliseconds access time. Large enough cache buffer of cheap RAM will mask the latency almost entirely, as random frequent accesses will not be written on the media unless the drive is to shut down.
Mechanical storage has barely seen any actual design improvements, the same design has been used for decades, only using occasional technological improvements to scale it down in size, whereas what I talk about is a significant scale up in terms of design. 100% doable, unfortunately too good for the lousy, greedy and lazy industry to go for it.
@ddriver - have you noticed that two 3.5" drive can fit into the foot print of a single 5.25" drive? You want double the capacity? Get two 3.5" drives. You want double the transfer speed? Get two 3.5" drives and RAID 0 them.
HDD design is not as simple as a armchair critic envision them to be and is complicated enough as-is, without unnecessarily adding more complicated features that is good to have but in the end will compromise reliability or cost of the end product.
5.25" platter will have much more mechanical flutter towards the edge of the disk it will be difficult to fly the heads there and not crash the heads into the disk surface since the heads are already flying much much closer to the disk than they did back in the Quantum Bigfoot years (there is an exception to this general rule, but that's another story).
Adding another actuator arm to allow multiple heads access on the same platter will double the probability of heads failure making the drive unusable, in addition of consuming drive real estate and cost because you'd need two voice coil motors in two different locations. You can't place VCMs in the same location and have them move two actuator arms independently because they use magnetic fields to function and they will interfere with each other. It's no use having two heads on one surface for backup purposes because a significant portion of head failures is due to the head crashing into the surface of the disk and scraping the surface, having a second head is no much use when you have another head scraping the magnetic materials off the disk and making it unreadable no matter how many heads you have to read the surface.
I have one of the later ~19GB Bigfoot drives... it's been running for years, still works, still in my system as a data drive. Sure it was never the fastest thing, but on the same token it was an unusual technology so it appealed to me. But the Quantum Bigfoot that is not what we're talking about, those are consumer drives. Think something more like Seagate's Elite 5.25" SCSI line. ST446452W for example. Full-height 5.25" 47GB 5400 RPM drives. Sure they were massive in size, but at the time there were probably unmatched in capacity. I bought several used ones off ebay years ago (for really cheap) and they came in hot-swap trays so I expect they must of been in some enterprise storage system. I've had a RAID5 with three of them running 24/7 for probably 10+ years, and who knows how long they were used before that. Probably the most reliable drives I've seen. The sound of them spinning up is awesome... something along the lines of the Time Machine from the 1960 movie. They're awesome.
I have no idea if there would be a market for such a drive now, but it's an intriguing idea, and I'd love to see what could be done in a 5.25" form factor with modern technology.
"I think the fact that you are still using a bigfoot is probably NOT something you should brag about. It's not helping your case..."
Point is that the Bigfoot is a bad example of a 5.25" as it is a consumer drive, not an enterprise drive, which is the only place a modern 5.25" drive would make sense. But even the later Bigfoot drives at least (can't speak for the whole line, especially the early ones) are not bad drives if put to use in an intelligent manner (i.e. NOT as an OS drive) and this one at least has lasted a long time. Dismiss if you like, but the two examples I posted have proven to me that the form factor can make sense depending on the intended goal or use of the drive. These weren't supposed to be speed demons.
To think of the amount of 3D-flash that can be put to that 5.25 unit.. Too bad the market would be constricted to pedestal servers and workstations (with a future interconnect for speed), as the current racks would have to be redesigned.
The fastest mechanical drives are in fact using "2.5 inch" platters (because smaller = faster) inside a 3.5 inch enclosure for stability and protection.
But let's see... Let's assume that the outer track of a 5.3 inch drive moves at half the speed (m/s) compared to 3.5 inch, to keep the centripetal force constant (probably not directly limiting, but to keep vibrations and stability in check). We can also check that the fastest 2.5'' drives are 15000RPM and the fastest 3.5'' (that actually use big platters) are 7200RPM. So yes, the RPM seems to go down by the square of the platter diameter. Both approaches result in an RPM of 2000RPM or so.
You need two arms reading simultaneously to reach the same sustained speed, and four arms to reach the same rotational access speed. Bigger platters means bigger arms with more mass and more distance to cover, but that can be overcome by more powerful, precise and expensive hardware so I'll just ignore that.
Why not just build more arms in the smaller drives we already have? Simply a bigger platter without more arms just gives worse performance in every way. Why not just put more smaller drives in the same physical space as your proposed bigger one? A big drive needs proportionally more space for just rigidity and to keep everything together. 2.5 inch drives are leading the storage density over 3.5 inch drives, bigger drives would logically be even worse.
It's been done. Aside from the pre-3.5" drives, there was the Quantum Bigfoot. Which had performance problems due to it's size, and attempts to improve performance pushed their price out into the upper-high end of the hard drive market at speeds comparable to slowest 3.5" drives. And hard drive technology hasn't changed a lot since then. Oh, the heads are smaller, the density is better, the platters spin faster, sure. But it's all evolutionary, not revolutionary. You'll hit the same problems now that you did back then.
5.25" 1/2 height drives occupy approx 4x the volume as 3.5" disk drives.
Spouting off about a 30TB 5.25" drive that would "tremendously boost ... capacity" when you can put 40TB worth of existing much more reliable 3.5" drives in the same number of cubic inches is sufficient reason by itself to not consider a niche product. Data centers are driven by cost, power and reliabilty. None of those would be better on a per byte basis compared with 3.5" drives. Cramming more actuators increases costs, decreases reliability and has been tried in the past and discarded for those and additional reasons.
Ignoring the sound technical reasons why bigger spinning platters is not a good idea or the substantial increase in cost involved in using more heads and actuators the reality is that 5.25" drives do NOT give you an increase in storage per cubic inch.
There is a reason 14" disk packs have gone the way of the dodo bird and so have 8" and 5.25" disk drives.
Consumer products will likely see a complete disappearance of rotating magnetic media within the next couple of years. Flash is now cheaper than rotating media drives for smaller capacities and larger capacity drives just aren't needed by most consumers. SSD covers all the bases, cheap, reliable, fast, for consumers.
Only data centers and a few power user applications will need the higher capacity magnetic media drives and they are driven so strongly by costs that they aren't going to give the SLIGHTEST consideration to more expensive, less reliable, bulky 5.25" drives.
You can look at the calculations as made in the slide reproduced in the article. I have no reason to doubt HGST's calculation.
In general, datacenter customers care a lot about saving on space (i.e, they want to cram more terabytes per rack) and power (i.e, they want to have the lowest possible watt / TB) - because, for the 24x7 operation, the rack ownership/rental cost and cooling costs as well as power bills will be much more than what the member drives themselves cost.
You state that "helium drives offer the best performance to power ratio and watts per TB metric amongst all the drives in their capacity class". Now in the article you cite for that, the RAID 5 volume Resync consumed 1096Wh (10h 24m 22s X 105.42 W) for the Seagate Enterprise Capacity 3.5" HDD v4 6 TB, and 1198Wh (12h 34m 20s X 95.36 W) for the HGST Ultrastar He6 6 TB. That's a 9% power consumption _increase_. That seems to be a contradiction?
And you don't have a reason to doubt HGST's claim of a 65% power _decrease_ between a 6TB air drive and a 10TB He drive? I'm sure they found some power hogging ancient 6TB drive that can validate those numbers, but you seem to think this is actually a valid comparison with current state of the art hardware, in contradiction to your own measurements?
Sorry, this looks like publicity space bought by HGST, no more.
This is a pipeline story. It's just news, albeit much better thought out reporting than most news outlets, technology a focused or otherwise. I don't know why you're complaining. Your expectations are unreasonable. Plus, computing is more deserve these days. They didn't have as many device categories in the past, such as smartphone and tablets. Laptops would have probably received more attention back then.
+1 because the trickle down to consumer gear is much more relevant, just as F1 technology making it into your next sports car and then to the next compact car generations later.
Laptops - and now (or soon) even phones - have become more refined and more commoditized. Therefore reviewing them all serves little purpose, especially with so many other parties reviewing them. Let AT's thorough reviews be reserved for significant and notable products - even though a few purchase-worthy ones will get left out.
Am I the only one slightly concerned that helium based storage is sees as the solution to increasing HDD densities while the world's helium reserves are shrinking into oblivion with no hope of recovery? Don't most estimates say we might have helium for another 20 years or so, and then we're pretty much completely out? I get that 20 years is an eternity in tech terms, but it's still pretty short sighted and dumb. Increasing helium usage is not the way to go, no matter your goal.
You aren't the only one. But you are misinformed. This uses a fraction of the helium used in balloons or medical devices. Did you think HelioSeal drives contained gigantic voids with no drive parts in them?
-- I get that 20 years is an eternity in tech terms
Years???? a calendar quarter is forever in capitalist's terms. they care only about socializing cost and privatizing profit. so what if there's no X resource for their kids? they'll be dead and gone by then.
Anyone actually find out if they are really using Hydrogen instead of Helium? Hydrogen is better choice for this application for all reasons... but... marketing..
@okashira - it's not marketing, it safety really, Helium is an inert gas and is much much safer (and cheaper too) to use in a manufacturing environment. If the seal in a batch of He drives fail in a datacenter, you may have a relatively harmless gas plus failed drives, but if you have a batch of leaking hidrogen drives, you not only get failed drives, the safety implications are much more severe.
Those are enterprise hard-drives, very few people will be able to afford those drives. The helium vs air pricing trend graph is for the least a marketing tool at this point: ramping up large-scale productions of those drives will only be possible when the old technology will be replaced, it's still a few decades from now, and by then SSDs will have flooded the market once their size and price per Gb become democratized. Anyway this graph is pure science fiction at this point.
We’ve updated our terms. By continuing to use the site and/or by logging into your account, you agree to the Site’s updated Terms of Use and Privacy Policy.
Facebook
Twitter
RSS
113 Comments
Back to Article
ddriver - Wednesday, December 2, 2015 - link
What I want to see is 5.25 inch form factor HDDs. It will be a tremendously boost not only to capacity, but also to sequential performance as well. Larger head count, independently operating heads, increased cache size - 512 mb at least with in memory defragmentation for small random writes, and integrated nano UPS, capable of supporting the drive until all cache is hard stored in case of a power failure.This will make possible 30-50TB HDDs, capable of sustaining 1+ GB/sec transfers on workloads which are well distributed over the platters.
shodanshok - Wednesday, December 2, 2015 - link
While 5.25" platters seem a good idea, this is probably not true.5.25" platter would be much vibration-prone, with resulting lower RPM (< 4000, probably).
Moreover, a bigger platter size implied bigger/heavier actuator and heads, with lower precision and consequently lower platter density.
Platters with multiple, concurrent heads were tried in the past, but with current high platter density they are probably not feasible.
On the other hand, I +1 the idea of power-protected write caches (which _are_ already available on selected enterprise-class disk).
ddriver - Wednesday, December 2, 2015 - link
Lots of speculation, no facts, just a load of "probably" without argumentation. The difference in radius is ~35%, the difference in surface area is over 100%. Independently operating heads and actuators, even if 35% larger, will actually be lighter than current approach where they are stuck together. Tried in the past - technology has improved a lot since then, you can have 2 to 6 independent heads per platter face without going in each other's way. This means tremendously lower latencies, as there are multiple heads available at each 1/head count platter revolutions.Larger platters means higher sequential speed, and a larger percent of the capacity would be in the fast area. Larger form factor means more room for platters - 10 are feasible. Which means at the same storage density of those 10TB HE drives, you can have a 40 TB drive that can easily push 5-6 GB per second transfers at lower PRM. Naturally such a drive would require multi-lane PCI-E and a good 4-8 GB cache/ram. With good caching policies this will annihilate SSD in pretty much every area at a better price safe for applications for vibration heavy environments.
It is entirely doable, but not done for a number of reasons, and no, complexity is not one of them.
ddriver - Wednesday, December 2, 2015 - link
Also, independent heads offer a boost in redundancy - such a drive can lose components, which are vital to current HDD implementations, while still retaining some or even full operation, albeit at reduced throughput. Head and/or platter parallelism and other advantages on top of that.close - Thursday, December 3, 2015 - link
So you suggest a 10 platter design with independent heads. So basically 20 actuators. And the "brain power" to control all of them. So you have 20 actuators, a much bigger motor, higher inertia and stresses (due to increased weight - an increase in surface usually brings an exponential increase in volume and weight). That's an increase in power consumption, BoM, noise and research needed to put it all together in a world where SSDs are already getting close to the price per GB of spinning disks. Any reason I'd choose a slow and sensitive "spinner" and not the much faster and more resilient SSD at the same price?Also, remember Samsung already has 16TB 2.5" SSDs. Absolutely 0 reason to go for a clunky, mechanically complex 5.25" device that's extremely susceptible to any mechanical shock and that doesn't fit most devices out there (moving to 2.5" can't be done fast enough).
So I will urge you to quote a paper that actually researched this implementation with concrete details and not just submit lots of speculation, no facts, just a load of "probably" without argumentation because you seem to like the idea.
I suggest an arrangement with 4 stacks of platters (square formation) and the heads positioned in the center of the stack. Then the heads could quickly spin from one stack to another to access the data there. With a bit of software optimization you wouldn't even tell the difference. Much better for archiving than SMR. Also you can use just one bigger motor that can decouple from any stack independently to reduce load instead of 4 smaller ones. Also the design is scalable: in a box the size of a standard NAS you can fit 10-20 times the data,
It is entirely doable, but not done for a number of reasons, and no, complexity is not one of them. It actually reduces complexity by reducing the number of parts, especially moving ones.
And since I just explained you in a few words how it would work this is clearly not speculation, assumption, etc. It's fact.
I also have some "spinning sphere" research.
ddriver - Thursday, December 3, 2015 - link
"So you suggest a 10 platter design with independent heads. So basically 20 actuators. And the "brain power" to control all of them."10 platters - 20 faces, optimal config of 4 heads per face - that's actually 80 actuators. 2 heads per face makes for 40. Each of those heads can access different areas of the platter individually, capable of 70-150 MB/sec transfers. The brainpower will not be as much, neither in terms of silicon area nor power consumption.
"That's an increase in power consumption, BoM, noise and research needed to put it all together"
It will still be more efficient, cheaper and substantially faster than the n number of regular HDDs needed to match its capacity. The concept is basically numerous worker heads sharing the same hardware. You sill will only have one motor, one case, one power sully, one "brain", one cache buffer.
"Also, remember Samsung already has 16TB 2.5" SSDs."
And it costs a set of good kidneys, and is still flash memory with a finite PE cycle count. Nor is it capable of the kind of concurrent throughput I am talking about.
35% larger platters, motor and case, more platters, let's be generous and say that alone will cost 50% more than a regular size HDD. The actuators - when mass produced will be pretty cheap, there is not much to them, it is basically some steel profiles, some copper wire and a magnet. Add in the 4-8 GB of ram and the 50$ of components needed to drive the whole thing and transfer data back and forth the PCI-E buss - the BOM will roughly come at twice that of a regular HDD, at 4 times the capacity, at least 30 times the throughput and tangibly lower latency. All in all, due to the sharing of the mechanics, it will use less power, generate less heat and noise and cost less than the number of HDDs needed to match the capacity alone. And hey, fast large SSDs are not exactly known for their stellar power consumption either.
close - Thursday, December 3, 2015 - link
Maybe but do you have any concrete research or only speculations and assumptions?Also you make several glaring mistakes:
"It will still be more efficient, cheaper and substantially faster than the n number of regular HDDs needed to match its capacity."
How exactly is a drive that needs countless months of research and testing less complex than a few of the "good ol' drives" of today? How exactly is 80 independent actuators less complex than the tech found in any run of the mill $50 drive of today?
"The actuators - when mass produced will be pretty cheap, there is not much to them, it is basically some steel profiles, some copper wire and a magnet."
I don't think you know what the actuator is. You are describing the *actuator arm*. That arm doesn't just do stuff, it needs the actuator. That's a motor to actuate the arm. That's 80 little motors that should move 80 little arms all over the platters at great speed and precision.
"and is still flash memory with a finite PE cycle count"
You are forgetting that hard drives suffer from more mechanical failures than SSD suffer from PE cycles limitation. You will now have 80 little motors and one big motor (and I mean BIG, it has to spin 20 heavy platters) that will suffer wear and tear.
I think it's a lot simpler to create chips with 3D stacking. 512 or 1024 dies stacked together shouldn't cost that much. Also you can achieve low power consumption by using new fabrication techniques and materials. I would say at least 60-80% lower power usage. This way in 2 years we could have a 32-64TB SSD that consumes less power than the 5.25" hard drive motor alone.
close - Thursday, December 3, 2015 - link
Really missing an edit button here. 80 actuators that work independently also eat up a lot of energy, along with that big spindle in the middle. One that takes ages to exit standby because of inertia alone. So having 10 10TB drives means that you can have 9 in standby and still access your data. One 10TB drive is "always on".And in the end you still end un with niche technology that could either work only in enterprise (no problems there since you can use unusual form factors even now - thick 2,5" or 3.5" drives, different connectors, etc.) or in full size desktops. Which, as you may have noticed, are fading away. Because most people would rather have reasonable capacities in a really small package than have enormous capacities in a big package.
And those actuators need to be positioned all around the platters in order to ensure the arms don't intersect. This means a 5.25" platter will need an enclosure that's wider than a standard optical unit. Look at an open HDD (random pic http://www.hardwaresecrets.com/wp-content/uploads/... and you'll see that there's no way to put 4 arms without increasing the size on all sides. Making a drive that doesn't fit in any computer case. Or you drop the size of the platter and you have to adjust the speculated numbers.
And a hard drive, no matter how many actuators you cram inside cannot keep up with solid state memory speed wise.
If the spinning disk industry had a trump card like this they would have used it. But most likely it's not feasible. I agree with you that profit is the end game but they see their market share shrinking and still don't come up with this.
ddriver - Thursday, December 3, 2015 - link
A 10 platter drive with 4 actuators/heads per platter face is doable in the form factor of those older CD/CDRW/DVD/DVDRW drives - the longer ones.The actuators snugly fit in the four corners, and although numerous, they are individually much lighter than the actuator of a regular HDD, therefore they need much smaller coils. They will only use power when the workloads demands it, otherwise they are parked and use no power whatsoever. The extra power they'd use while in operation offers a very good return in performance, since you have numerous heads working but spinning only one set of platters.
And no, contrary to your "expert" opinion, there are no "motors" in HDD actuators, you demonstrate profound cluelessness in the subject.
NVMe SSDs already exceed the power consumption of mechanical HDDs, I seriously doubt power consumption will go down as you add more DIEs. Semiconductor production will never become cheaper than platter production, as it is an immensely more complex, time consuming and environment unfriendly process, and is soon bound to run into a brick wall, which will prohibit any further scaling down of process node size.
The industry is not in the habit of aiming to provide the consumer with the best value for his money. An example - intel keeps cramming iGPUs into 400+ $ processors, even though hardly anyone, willing to pay that much for a CPU, would be willing to settle with their mediocre performance, and all that DIE area would be much better invested in twice the CPU cores. But such a product would offer too good valie, more than intel is willing to provide to consumers at this point, so it will keep wasting DIE area on lousy iGPUs, and the chips which are spared that utter waste will come at a significantly higher price.
Similar examples can be seen anywhere you look, provided that besides the ability to look you also have the ability to see ;) The product I speak of doesn't exist for the sole reason it is far better value than what the industry would like to offer. And no, it is not as easy as "kickstarting" your own foundry to make what the industry refuses to, even if you could gather the billions this will cost, you will run into patent trolling, because none of the big players who "own" the tech would be willing to allow you to humiliate them in such a manner, nor to extort and force them into providing better value than they are willing to.
Capisce?
close - Friday, December 4, 2015 - link
So you don't know that a voice coil actuator *IS* a motor and that while the "copper wire" might be enough to make some shiny loops for you to chew on it's not enough to actually "actuate" but you claim to be a star hard disk designer...I even gave you a damn picture http://www.hardwaresecrets.com/wp-content/uploads/... so you can understand the proportions involved because the actuator doesn't stay magically the same while still covering a 5" disk.
Somehow you find a way do dig yourself into a hole every time you comment on most articles. You just plaster suppositions, assumptions, maybes but show zero understanding of any of the things you talk about. The only thing that fits in a corner is you :).
I'm waiting for the next iteration: the truck tire sized hard disk.
ddriver - Saturday, December 5, 2015 - link
Wow, you found a photo of a hard drive - you are a mastermind of the highest order. Good for you.Now, consider the fact that this actuator from the photo is used to move a total of SIX arms, fused in a single assembly. Now consider that an independently operating head would require only one arm, in the case of a 35% wider platter let's say it will 35% heavier, thus 6 / 1.35 = 4.44 times lighter than the arm assembly of a regular HDD. Let's be generous here, and spare you the metal strain and round that to 4. 4 times lighter actuator arm would need a considerably smaller smaller magnet and a considerably smaller coil. And that's in the case of the rather modest count for only 3 platters. That disk from the article actually has 7. So 14 / 1.35 - that's a whooping 10+ times lighter.
Are you sill on the train of thought?
Now consider a 5.12 inch circle inside a square with a side of 5.25 inch, and the amount of room remaining free in its 4 corners. It goes without saying, the corner space of a 5.25 inch drive will be more than the corner space of a 3.5 inch drive, so what do you think, will you be able to fit a considerably smaller actuator in a larger area? Hint - the answer is yes. And we are thinking in 2D here, don't want to put too much strain on you ;)
Your idea that the actuator size will grow with the disk is a product of your complete failure to understand things in the context I present them, you just can't go out of that box. The actuator of a 5.25 inch drive following the traditional design would only be larger, because the arm assembly would be fused and it will be heavier than that of a 3.5 inch drive. But ultimately, the point you fail to grasp is that the actuator size is not a function of the platter size, but of the actuator arm weight, and a single arm with a relative mass of 1.35 will always be much lighter than 6, 8, 10, 12 or 14 arms with relative mass of 1 which would be in a single assembly respectively for drives with 3, 4, 5, 6 or 7 platters. Maybe now, after it has been explained to you in a matter fit for a toddler, you will finally get it?
And yes, I am well aware that anything, capable of converting some form of energy into motion qualifies as a motor, for example my foot, but still, I prefer to call it foot rather than motor. The same way it is only natural to refer to an actuator motor as an actuator, not a motor, because that's a vague generalization, and would also be confusing, since any layperson actually use "motor" in an entirely different context. And yes, you do strike me as a layperson.
So yes, obviously I do know that the actuator is a type of motor, and obviously, I never claimed to be star hard disk designer. You are resorting to making things up, which further goes to show your actual level of competence. Gonna refer you to your previous post:
"I don't think you know what the actuator is. You are describing the *actuator arm*. That arm doesn't just do stuff, it needs the actuator. That's a motor to actuate the arm."
Seems like you don't know what the actuator is. The HDD actuator is consisted of the magnet, the coil, the coil frame and the arm. So when I say actuator, it implies all of those. In fact, the very paragraph you responded to has listed the steel arm frame, magnet and coil, and yet somehow you interpret that as "talking about the arm". You might want to brush up on your reading and common sense skills :)
"Somehow you find a way do dig yourself into a hole every time you comment on most articles."
If imagining that makes you feel any better - go for it. It is only natural, narrow minded people always feel resentment for outside the box thinkers. Mainstream conformism never ceases to amaze me, especially the feeling of pride associated with it ;) Amazing the kind of things people take pride in nowadays, such as sexual orientation, skin color or being conceptually limited to only what has already been done and being totally ignorant of what could done considerably better.
This Guy - Monday, December 7, 2015 - link
MateCPU's don't scale because data is rarely independent. X depends on Y, Y depends on Z, so you can’t load X, Y and Z into different cores.
Actuators are motors that move something.
One actuator/read-write head assembly takes up around 1/6th of a 3.5” HDD enclosure. You want 80 actuators in a 5.25” enclosure…
HDD's have data tracks, like vinyl records, but far smaller. If you have 2 million tracks per inch then there is 5/10,000,000 of an inch between the centres of each track.
So your HDD read-write head needs to be in a very precise place to read each track. This means every actuator (the thing that moves the read head, steel arm frame, etc.) needs an extremely precise motor controller (the expensive/complicated silicon everyone keeps referring to).
Data tracks run in a spiral shape. When sequentially reading or writing, the read-write head constantly moves, which is fairly easy to control.
If you have four read-write heads per surface but only one data track they would have to jump to the next track every quarter revolution. Critically damping an actuator to move 5/10,000,000 of an inch 21,600 (4x 5400rpm) times each second reliably for 5 years would be an exciting engineering feat worthy of your billion dollar retainer. Making 80 read-write heads move so in a 5.25” package is Nobel Prize territory.
If you have one data track per read-write head, the latency will be the same as if there was only one read-write head. Latency is why HDD's suck so much. Yes you could increase sequential flow, but you might as well just have all four heads on each surface attached to the same actuator (with a complex mechanism to adjust for the different circumference of each track).
Then there is availability. Like others have said, metals expand at different rates when heated so the actuators for the read write heads need to be regularly recalibrated. For this 7 platter HDD (yes, I'm bringing you back on topic), there is only one actuator controlling the 14 read-write heads. Say this system has three 9's availability. Worst case it needs about 2 minutes each day to re-calibrating itself. With your 80 independent actuators your hard drive will be offline for around two hours every day (assuming your design is robust enough to recalibrate all 80 actuators without causing errors).
How are you going to synchronize data between your 80 write heads? Say you have a 3.5 inch disk. The data rate half an inch from the edge will be 28% slower. The data rate an inch from the edge will be 57% slower. How do you synchronise these data rates without adding excessive latency?
So cost. A significant materials cost in a HDD is the actuator. You want 80.
I respect your can do attitude, but innovations in HDDs require very complex simulations of materials, not the lazy management engineering that you, I and the other commenters have produced.
RainDaemon - Thursday, December 3, 2015 - link
ddrive, There are some serious flaws in your thinking. Its pretty clear you don't have any decent real world experience in engineering or business.Existing hard disk technology is bases on decades of research and development. Significant changes in design require a significant increase in investment. In order for this to be viable, manufacturers need to be assured of a return. If you think the great minds behind existing storage technologies haven't thought about the ideas you propose then you are mistaken. There are several technical issues with what you propose.
Firstly, larger (5.25") platters have several major disadvantages. While they will have a reasonably higher capacity, performance is negatively affected. Larger platters require more power, produce more noise and vibration and this need to operate at a lower RPM. This increases rotational latency which impacts performance. Furthermore the increase in the size and mass of the actuators will impact their operating precision, increasing seek times. Larger parts are also more heavily impacted by thermal stresses, which has an impact on the density you can achieve. These drives will also require more materials to construct, be more expensive to build and heavier, increasing things like shipping costs.
Secondly, having multiple actuators in a drive, while a novel idea, doesn't hold up so well in the real world (it has been tried, several times) There are several issues:
- They take up significant space. Assuming your maintain the existing form factor, this will shrink the usable storage area inside the drive. Unless you're going to invent a whole new form factor, this is not viable. (you can have a 3.5" platter with 2 actuators in a 5.25" form factor - this has been done commecially)
- They have a major impact on the cost of the drive. We're talking about a huge increase in the number of moving parts that have to be manufactured and assembled. Additional hardware required to drive the actuators has to be included. Complicated firmware has to be written. Optimizing access patterns for one set of actuators is difficult enough. Again, material costs increase significantly. Any hypothetical increase in performace is negated by the cost alone.
- Heat, power, vibration. More moving parts will have a negative impact on reliability of the drive. (Your argument of redundancy does not consider all potential failure modes.) These are also expensive problems to solve.
- The basic physics that hard drives deal with (and this is really the biggest issue with this idea) A read-write head has to deal with a lot of thermal stress. The platters, the actuators and the heads themselves undergo expansion and contraction significant enough for it to have an impact on performance. Hard disks deal with this by encoding "servo" data in the platters that are calibrated to the head assigned to it. Since the platters and the heads are not perfectly homogenous, this data varies from head to head and platter to platter. The issue is also compounded by the density of the platters (the smaller the tracks are, the greater the impact of expansion and contraction) This principle makes it impossible (or at least extremely difficult) to assign multiple heads to one platter. Of course you can mitigate this by trying to create heads that are all EXACTLY the same and platters that are perfectly homogenous, but this is extremely expensive. More moving parts further magnify this problem by creating a more thermally dynamic environment within the drive.
- Another physical aspect is that the actuators can interfere with each other. If they are moving independantly, they make microscopic changes in the density of the medium inside the drive, as well as vibration. This has a significant impact on the accuracy of tracking and increases seek times.
ddriver - Thursday, December 3, 2015 - link
Yada yada yada, I've already addressed pretty much all of your points in other posts, save for the actuator "crosstalk", which is a valid issue, but nothing critical. It will only take a few seconds of profiling per assembly to measure it and create a dedicated profile for the particular HDD unit to compensate and normalize it. This is for EM interference, as for mechanical - since the actuators are independent, they will be individually lighter and influence the entire device to a much lesser extent than the single heavy fixed multi-head actuator of a regular HDD. As for actual actuator collisions - I've ran range of motion simulations, even SIX actuators per platter face are doable, but will add to the form factor. 4 are doable in standard 5.25" form factor. There are two ways to go about the actual actuator design, there is a cheaper one, which would be computationally intensive on the firmware, and a more expensive, which would require production of 2 to 3 slight shape variations - nothing much really.5400 RPM 5.25 inch HDDs were possible 20 years ago. I am quite sure this is still technically possible today. Frankly, with independent multiple heads you don't need more, 5400 is ample. Low RPM and larger platter diameter are a problem only when you have a single actuator to service the device. Even only 2 heads per face at 5400 RPM will provide equal or better performance than 1 head at 10k RPM in every possible performance metric.
The firmware is not that much of a challenge either, nor its implementation, which should take no less than 6 months for a SINGLE decent firmware developer - everything from scratch, nor will it require any exotic, custom MCU design, I reckon a stock Cortex R7 would suffice.
RainDaemon - Thursday, December 3, 2015 - link
It would be really amusing to see you try and apply your claims in the real world. You've made so many exaggerated comments without a shred of evidence supporting your claims. Your claim of "a few seconds of profiling" in particular is evidence that you are talking out of your ass. You can make claims of how an ideal system would work, but things are different in practice. You are not talking about a static system, but a dynamic one. Components are not perfect, the have flaws and tolerances. These kind of things compound with complexity which is essentially what you are proposing.If you really think your claim isn't absurd post some hard data on what such a system would cost and how much power it would use.
How about also explaining how on earth you are miraculously going to end up with lighter actuators? (If you could just magically have lighter actuators, why wouldn't current drives embrace the idea to save material costs? What's the trade off?)
How are you going to address the added complexity of assembly? The fact that your production costs are going to increase significantly? The cost of more expensive materials?
What about the servo data? Are you going to write servo tracks for each head?
How are you planning on dealing with heat? Turbulence? Vibration? You haven't addressed any of these points?
Do you really think one firmware programmer is going to be able to develop a decent solution in 6 months? You're aware the industry has billion dollar companies that have spent decades analyzing real world applications to optimize firmware for drives in various applications?
Your claims are preposterous. How about a little substantiation? You speak of "simulations" involving configurations of 4 actuators, how about a technical drawing?
You talk about this stuff as if you snap your fingers and it just happens. Do you actually have any industry experience or are you just making stuff up?
All these points are pretty moot as your entire argument is predicated upon a hypothetical performance increase your system would have, despite the fact that this is flawed thinking. Your over complicated hypothetical unit will get trounced by an entry level disk in terms of unit cost and bang for buck.
ddriver - Thursday, December 3, 2015 - link
Gimme a billion dollars and legal protection from patent trolling and I will show you.You ask for hard data - that would require at least operational prototypes. I refer you to the previous point. I could provide you with simulation data, but you will have to pay me to develop that, it will cost you 500k, you will have your results within a year.
No magic - it is simple and obvious, and quite astonishing you still don't get it - current HDDs combine the arms for all platters in a single assembly, thus logically, it is much heavier than the individual arms on their own. n>1 count of arms will always be heavier than 1 arm. DO'H
HDDs are assembled by robots, robots don't care whether they do something once per HDD or 100 times per HDD.
The actuator synchronization markers are on the platters, they can be used by any number of actuators.
Heat conduction, vacuum, not gonna be an issue - wasn't 20 years ago, won't be today.
Yes I do, and I did not say 6 moths, I said less than 6 months. The billion dollar companies are full of slackers.
Range of motion simulations are children's play. If you can't set up a disk with 4 moving arms around it and check if they can move along along the disk radius without touching in any configuration, you have no business questioning my competence.
I have 20 years of experience in software, electronics and mechanical engineering. I haven't been in "the industry" though, I am more of a "custom shop" guy.
There is nothing hypothetical - if a single head can do X, then N heads can do N * X. The challenges are there, but I don't see anything that would qualify as an obstacle, nor have you nor any of the naysayers provided any factual evidence of such. You keep asking about "evidence" that it is possible, but each component of that system already exists and has decades of mature tech behind it, there is no reason why it shouldn't work, if anything, you should be providing evidence why it shouldn't work, and I mean tangible facts, not that drivel. You present a number of points you believe are going to be problematic, but not even a word on why would they be problematic. Where is your shred of evidence? Being conceptually limited to only what has been done so far does not speak in favor of your competence. If everyone was like you, we'd still be living in caves and wearing animal hides for clothes. You sound like a mainstream evangelist, you probably believe in ridiculous pipe-dreams like manned missions to Mars or asteroid mining, and yet have such a problem with a concept which has all its requirements already met technologically.
weissPC - Friday, December 4, 2015 - link
@ddriver - there are a few people in the HDD industry that's replying your thread. You have no simulation data because you are asking people to pay you to develop it. You are asking for arbitrary amount of money (1 billion dollars) to 'show' us how you do it. Even kickstarters won't give you that amount of money, much less HDD companies.Your simple hypothesis that "if a single head can do X, then N heads can do N * X", even with something non mechanical like CPU cores, you know having double or quadruple the number of cores do not mean 2x or 4x the performance, having more heads per surface won't solve the problem, made worse by today's high densities in terms of track spacing and variation between head sizes and performance makes it impossible to do what you think you could do.
What makes you think the data written by one head can be read by another head? To allow for these variations so the heads can read data written by their counterparts, you have to make track spacing much wider and make the heads to perform at lower than what they are capable of, negating your so called increase in capacity. In the end, your 5.25" platter may have similar capacity to a 3.5" platter or worse, you'll find that it just doesn't work.
Even Steve Job's reality distortion field don't work all the time.
ddriver - Saturday, December 5, 2015 - link
"What makes you think the data written by one head can be read by another head? "What makes you think it can't?
"Your simple hypothesis that "if a single head can do X, then N heads can do N * X", even with something non mechanical like CPU cores, you know having double or quadruple the number of cores do not mean 2x or 4x the performance"
CPU cores share resources, not all workloads are CPU time bound, you are obviously quite ignorant to even make that comparison. In CPU intensive tasks, minimizing the strain on the functionality shared by the cores, test results actually show close to perfect scaling, but you are obviously not aware of that either. Multiple heads can actually scale better than 100% - since they will decrease latency and eliminate a lot of the seek times. For example, a single head reading from one location on disk and writing to another would have to travel back and forth, so its throughput will be split between the two tasks, and moving between the two will be a substantial overhead. Two independent heads can do 2 tasks at their full throughput and they won't have to waste ANY time seeking.
With multiple heads, even if the head count is higher, individual heads and their arms are much lighter, so even if the vibrations they produce are higher in frequency, they will be lower in amplitude than the vibrations produced by the heavy arm assembly of a traditional HDD. Naturally, and for someone with a shred of competence it should go without saying, but since you lack it, actuator drivers can use ease in and ease out to reduce vibrations to non-existent, something a drive with multiple heads can afford to a much larger extent than a traditional HDD actuator, which can't afford to lose precious time since it is the only one servicing the device. So your point about increasing track spacing entirely wrong, and such a device will inevitably end up producing much less vibrations, much less noise, and may even allow denser tracks than a traditional HDD.
The 1 billion is an approximation with a safe margin, if it makes you feel any better, I can give you a less (or more) arbitrary number, for example 987563, is that better? I have done range of motion simulation, which as I already said is trivial, the 500k I asked for a product simulation involves all the mechanics, electronics and firmware. This is a significant investment of effort, it is quite silly of you to think I have made such just to have them lying around ;)
Your belief that the "industry knows best" is ridiculous. You obviously have no knowledge in any of the fields involved in product design. Just to give you an example - yesterday a washing machine died - a whirlpool unit, from a company with long history of making such products. The culprit - the ceramic capacitor they used in lieu of a transformer to implement the PSU for the electronics. They used a capacitor rated at 240V for a product designed to operate on 230V line - practically no safe margin, resulting in a ticking timebomb, ruining an otherwise still operational device. A 400V capacitor with the same capacitance costs a mere 29 cents, only 6 cents more than the one rated for 240V, but would have lasted until some more significant component of the machine has died, and yet they did not use one. The industry knows best? Yeah right, and I don't say the engineers didn't knew all this, it is likely they did it on purpose, and they have likely calculated the capacitor to die just about the time the warranty runs out, because the industry, even if it does know best, doesn't care for the best, it cares only about profit.
Finally, you obviously have no idea of the extend of my knowledge and skill set, you demonstrated profound lack of technical knowledge, profound inability to understand simple logic and common sense, and on several occasions you failed miserably at trying to sound smart - something you'd realize had you actually been as smart as you try to pretend to be.
ddriver - Saturday, December 5, 2015 - link
And that example with the washing machine is just one of the many cases I've seen the industry spew out lousy products, and anyone with a decent amount of knowledge in the area would notice that too.Almost 10 years ago, I built my own smart oven, with the ability to automatically control the position of the top and bottom heating elements, which were on their own compound and could be activated in different patterns. It could also operate on hot air alone using an additional heater, and could program a temperature curve to follow with time, remote control and remove observation via a webcam. The industry has only just began selling smart ovens, and they come with nowhere nearly the set of features my own design had a decade ago.
So pardon be by not be impressed with what the industry does and how it does it, in many aspects I know things can be done better, and in some - as long as I had the resources, I've already done better.
weissPC - Friday, December 4, 2015 - link
RainDaemon's points are valid while ddriver's are mostly hypothetical. ddriver obviously have no idea the amount of code groups of firmware engineers have to write to not only control the actuator arms, but to interface with SATA or whatever interface you now have, to do many other background stuffs that you have no idea of and simply calling them slackers show how idealistic or out of touch you are. And quoting less than 6 months, just seals it.close - Monday, December 7, 2015 - link
weissPC, give it up. The guy knows sh*t about engineering (motors, circuits, firmware, interfaces, you name it) or business. He just thought it was a cool idea and now won't back out because he went too far with the crap. I gave him the benefit of the doubt and asked him to support his claims with real data, not some more "quotes from ddriver" and he failed so every single time.He just came up with some bullsh*t figures that he can't substantiate and every time someone proves him wrong he just hides inside his "reality blurring machine" and thinks that only he has facts and everyone else has suppositions, assumptions, speculation, maybes. I asked him for any paper to support his claim. He managed to write a full page of crap but no actual link to what I asked.
So basically the only argument used to support his claims is "because I say so". He's a troll on Anandtech for at least some years. Don't waste too much time, you won't get anything good. He's had years to show that and failed.
weissPC - Tuesday, December 8, 2015 - link
@close, spot on, couldn't have said it better. Better spend my time of more productive stuff. If he's that good, let him produce a real product to prove us wrong.shodanshok - Wednesday, December 2, 2015 - link
You forget that 5.2" platters existed - and they go extinct for the reason I explained above. The Quantum Bigfoot drive (a 5.25" one) was universally remember for it's very slow speed (~ 4000 RPM and very high seek time), rather than it's capacity.Earlier, 8 inch disks had the same fate - they where abandoned in favor of 5.25" disks.
There is a reason the industry standardized on cheap 3.5" for raw capacity and 2.5" for performance; however, recent 4 TB 2.5" disks are challenging that (consider that you can fit 2x2.5" disks in the same space as 1x3.5" disk).
For the multiple head counts: did you ever ask why current multi-platter, multi-head disk read from a single platter at a time, rather that striping on multiple platters? The reason is simple: with high platter density, each head must be place independently, with dedicated actuator. This will greatly increase disk cost and weight, giving only minor benefits. Please consider that such disks existed - and they got extinct for a reason.
jabber - Wednesday, December 2, 2015 - link
For spinning- smaller is better, not larger.ddriver - Wednesday, December 2, 2015 - link
There is a trade off, as you see, most HDDs are 3.5 inch devices, so obviosly, smaller is not better, there is a sweet spot. 5.25 inch HDDs will run at lower RPM, but using higher head count, they can easily and vastly outperform a traditional 3.5 inch HDD even if it spins faster. Today such components can be mass manufactured at a very low cost, and chips are advanced enough to be able to run the much more sophisticated firmware which a drive with multiple independent heads would require. Both of those were not technologically possible in the past, but today they are.jabber - Wednesday, December 2, 2015 - link
I think the market and the HDD manufacturers possibly know what they are doing and the physics involved. If it was a good idea and there was a market for it we would have them.ddriver - Wednesday, December 2, 2015 - link
If they can make money on selling you straw, why should they bother selling you wheat? They don't care about making hard drives, all they care about is profit, making hard drives is just the means to attain profit. Their priority is making as much profit as possible by selling you as little value as possible - thus maximizing the profit margin.BurntMyBacon - Wednesday, December 2, 2015 - link
@ddriver: "Their priority is making as much profit as possible by selling you as little value as possible - thus maximizing the profit margin."Accept that the HDD market is a competitive market with more than one player. To get your money, they have to at least convince their target market that they are a better value than their competitors. Case in point is the Helium tech HGST is using to get a leg up on the competition. It is MORE expensive to build than the competition, so clearly not beneficial to their margins. It does, however, provide an advantage for its cost.
Given that SSDs are (apparently) threatening to make HDDs irrelevant due to superior performance and approaching capacities, I'd say the HDD manufacturers aren't in a position to hold back anyways. If they could "have a 40 TB drive that can easily push 5-6 GB per second transfers" as you posted above, I'm pretty sure they would have done it as soon as they could have to squash any reason to pursue SSD tech which looses them a lot more than they could possibly gain by holding out on us. The 5.25" form factor is a pretty well known quantity. Sure we could do better than they did with the bigfoot drives, but the tolerances will still necessarily be looser than the smaller drives.
On the other hand, if you a better understanding of it than the current HDD manufacturers and are convinced that it can be done to great effect, then by all means, launch a kickstarter and start pushing these puppies out. I'd love to see the look on their faces if such an event were to occur.
ddriver - Wednesday, December 2, 2015 - link
"Accept that the HDD market is a competitive market with more than one player."Seems like this has become significantly less true the last several years. Today they are practically 4 - WD, Seagate, HGST and Toshiba. And they don't seem to be in a competitive spree, as the HDD technology is almost on hold, very low priority, barely any improvements, usually minor stuff, nothing ground breaking (just look at HGST - now basically the same thing, but we're gonna fill it with helium), and it is not like there's no headroom for improvement. 4 manufacturers on a planet with 7 billion people, enough business for everyone, no need to shift paradigms, better keep on price fixing and have a sweet time milking the market.
"
"On the other hand, if you a better understanding of it than the current HDD manufacturers and are convinced that it can be done to great effect, then by all means, launch a kickstarter"
That activates my hilarity unit, a HDD factory, capable of producing most components in-house will cost at least a billion. That's a little too much for kickstarter, don't you think?
xthetenth - Wednesday, December 2, 2015 - link
They're competing with SSDs. It's kind of blatantly obvious.ddriver - Wednesday, December 2, 2015 - link
That's like saying sport cars are competing with cargo trucks. There is no competition between the two at this point. If the tech I want to see is produced - then yes, HDDs would actually be able to compete. But today those are entirely different market segments.RanDum72 - Thursday, December 10, 2015 - link
I have the feeling that ddriver is in love with the idea that harddrives should be 5.25 in size because it gives the impression of more 'value' and speed. I mean, 5.25 drive is bigger than a 3.5 drive, right? Well why doesn't somebody come up with a 5.25 sized drive that has like 15 SSD's inside, and has a built-in RAID10 controller inside interfacing externally with PCIe 16x?nils_ - Wednesday, December 2, 2015 - link
HGST is owned by WD which makes it practically 3.extide - Wednesday, December 2, 2015 - link
Don't forget SamsungWaltC - Wednesday, December 2, 2015 - link
@ddriver You cannot expect innovation and advance, especially of the type you'd like to see, in a market directed by top-down government regulation. Competition is what motivates R&D which in turn creates new products, etc. What companies strive for is actually to provide the very best value they can for a price the market will bear. If a company tries to give the least value it can it will probably fail quickly--that sort of thinking doesn't work in a competitive market. Don't know if you've noticed, but in the last 20 years technology has sky-rocketed in terms of capability while the prices for that technology have never been as low as they are today, and economies o scale have never been greater. The onus has changed from profit-per-unit to profits-per-thousand-units sold.BTW, I still remember my very own BigFoot...;) Slow as molasses and sort of noisy, IIRC, but I bought it for capacity and nothing else at the time. 5.25" is an interesting idea, no doubt. Where the mechanical drives have it all over SSDs is capacity, and my guess is that this trend will continue until SSD's develop to a point where the mechanicals can no longer offer substantially more capacity for substantially less money.
xthetenth - Wednesday, December 2, 2015 - link
Congratulations on fundamentally misunderstanding capitalism. Their priority isn't to sell as little value as possible, their priority is to maximize the disparity between perceived value and cost to manufacture. When possible this means adding things that increase value significantly (such as a hypothetical technology that increases performance and decreases total cost of ownership), but due to being based on some sort of development that has most of its cost to the manufacturer in a form independent of units produced, such as R&D or manufacturing changes so that with large production runs, the value increase is maintained but the cost decreases, driving that disparity upwards.Congrats on getting a serious pinko to defend capitalism by the way, it takes a serious level of wrong to do that.
bernstein - Wednesday, December 2, 2015 - link
problem is:- in the volume of one 3.5" HDD one can fit 4x 2.5" HDDs
- capacity remains roughly the same (4x2TB vs 1x8TB) - power use & cost however go up
- in a RAID these are way faster & more redundant than a single 3.5" drive (2-3 times the MB/s)
- random i/o is vastly improved (up to 4 times) - given a filesystem capable of caching the index on a SSD/RAM
- reliability is vastly improved (pseudo-/RAID)
the same things apply to 5.25" vs 3.5" HDDs...
hpglow - Wednesday, December 2, 2015 - link
They should just make them 10" so you can put your HDD next to your record player in your short bus. These guys are in the business to make money and they spend tons in R&D you think possibly they have done some research on these inanely obvious? I bet that they have and that they have and its some conspiracy and they have the prototypes in the corner next to the late 70's model car that got 50 mpg on tap water.beginner99 - Thursday, December 3, 2015 - link
Most 10'000 rpm drives are 2.5 inch...Large platter with high RPM doesn't work. On the other hand if you want speed, you should ignore HDDs anyway. Even if you have a 50TB HDD, it would magically get 10 times the speed. So it will take forever to fill or extract data from. HDDs are slowly dying off. It will probably take at least another if not 2 decades. first flash and then non-volatile RAM types will replace it completely.Next Gen Intel Processor (Kaby Lake 200-Series Chipset) will have support for Intel Optane SSD which use a non-volatile memory type. Eg. will make even high-end PCIe NVMe drives look like toys.
Mugur - Thursday, December 3, 2015 - link
And most 15k rpm drives are still 3.5... 😄close - Thursday, December 3, 2015 - link
Quick question: why would you go for standard sizes like 5.25"? That's the platter size, not the disk size, so you can still go with 3.5" platters in a larger enclosure in order to cram in more independent heads or just to stack more platters in. Or why 5.25? Maybe the best compromise is a 4.2" platter. Any research on this or are you just assuming and speculating without facts?Also, because you assume people sticking with 3.5" is anything more than compatibility and reduced manufacturing costs that go beyond just the simple HDD unit I will say that most cars run on gasoline now so electric sucks, most LAN connections top out at 100Mbps so gigabit is no good, etc.
You should really research causality and correlation.
ddriver - Wednesday, December 2, 2015 - link
Funny, you consider 5-6 GB/sec and quadruple capacity "minor benefit". At the risk of repeating myself, those things were attempted way before their time, using immature technology. That's why they failed. Actually, independent head and actuators, when mass produced, will have a negligible impact or both cost and weight. All it takes is vastly improved firmware capable of operating them independently.Take wireless power - that dude Tesla did it more than a 100 years ago, and someone like you might say "it got extinct" but in reality, it was simply a century ahead of its time. As you see, now wireless power is a big and growing thing.
You seem to harbor a misconception that the industry is interested in innovation and improvement - on the contrary, the industry is only interest in making money, and having an easy time doing that. Thus they keep milking existing tech for as long as possible, keep things simple, because too good of a new product would kill their existing business. And they stay away from innovations until it is unavoidable and badly necessary, not to the users, but to the industry. It is really not that such hard drives are too complex or technically impossible, it is just that they'd be way better than what the industry would like to offer the consumer. They can't afford that, because next thing you know, the consumer is transformed from a paying tool to a progressing person with high standards of expectations.
FunBunny2 - Wednesday, December 2, 2015 - link
-- it is just that they'd be way better than what the industry would like to offer the consumer.IBM dumped the 33XX DASD for emulating CKD/VSAM files on 3.5 commodity drives. Why? cheap.
BurntMyBacon - Wednesday, December 2, 2015 - link
@ddriver: "... they stay away from innovations until it is unavoidable and badly necessary, not to the users, but to the industry."Agreed. However, I would argue that it is unavoidable and badly needed immediately if not sooner. The industry has been loosing an increasingly large portion of sales to SSDs. If they have any innovations that could make the move to SSDs less appealing, they would do well to use them.
ddriver - Wednesday, December 2, 2015 - link
Back in the days where those disks "failed", there weren't any chips capable of running such a device at high rpm. Since then technology has improved tremendously, both in terms of mechanics, manufacturing, but most notably - chip performance.Calling this a failure is like calling space exploration a failure, just because 200 years ago someone tried to do it with an oversized kite and failed miserly.
Of course you are going to fail if you get ahead of yourself and try to accomplish something you don't have the technology for. But that doesn't mean an "ultimate failure" - it just means "everything in its time". Today technology is finally up to the task, but the industry still prefers having its sweet time milking the old tech, made so much easier by the advances in technology. Why should they bother to make such a giant leap, when as long as the consumer has no other choice he is going to buy the existing product line.
edzieba - Wednesday, December 2, 2015 - link
The previous issues with large-diameter platters were not electronic, they were mechanical. A larger platter spinning faster is much more vulnerable to instability, and needs to be mechanically stronger (thus thicker and less volume efficient, and harder to spin up/down).The actual mechanism of HDDs is very mature. In the last decade, the only evolution has been in head technology (GMR) and orientation (PMR). Helium filling has allowed closer platter spacing, but will not allow larger platter sizing.
ddriver - Wednesday, December 2, 2015 - link
"The previous issues with large-diameter platters were not electronic, they were mechanical."Because the electronics at the time were so inferior they didn't even conceive independent multiple heads per platter face. Thus they didn't even run into the electronic problems, only faced the mechanical. As I said at least a few times already - lower PRM would not be an issue with independent heads. Two heads at 5k will give you equal or better performance than one head at 10k, and extra redundancy. And it will end up being more energy efficient as well.
NonSequitor - Wednesday, December 2, 2015 - link
http://www.tomshardware.com/news/seagate-hdd-hardd...It's been done before. One of the big barriers was the different rates of heat expansion for the different servos. At current densities it would be a lot of work for very little benefit, particularly since lower speeds means higher latencies, which absolutely kills performance.
ddriver - Wednesday, December 2, 2015 - link
LOL, servos - enough said. This thing is a relic. Voice coil actuators won't have such a problem. 4 heads per platter face seems like the sweet spot, although even six are still possible without getting in each other's way.Two heads at 5k RPM would be just as fast, and often faster than one head at 10k RPM. Two heads will offer the same throughput at lower RPM, saving on energy. Now if you have concurrent access, one head will have to move back and forth between the two locations, wasting more time on access than actually reading data. 2 hears can do that without the access, as they can simultaneously access the platter at different positions at the same time.
FunBunny2 - Wednesday, December 2, 2015 - link
-- Because the electronics at the time were so inferior they didn't even conceive independent multiple heads per platter face.mainframe and mini drives, even those with removable disk packs, had multiple independent head sets for decades. as to RPM, remember these devices had 14 inch diameter platters. given the laws of physics, I'd wager that angular velocity for most of such a platter is at least what we have today.
ats - Wednesday, December 2, 2015 - link
They had multiple heads, those failed. The mechanics of multiple heads are such that it is almost as cheap to buy 2 drives than 1 drive with 2 sets of heads. And having all the heads independent costs even more and presents massive mechanical issues.kb9fcc - Wednesday, December 2, 2015 - link
Agreed, the problems with larger platters are mechanical and electrical, not electronic. Larger platters also require much more power to get spun up and maintain that rpm. More power means more heat. Both are "bad" in the long run. Larger platters also mean that the heads will need to move farther to cover the platter, which means longer actuator arms, which mean more mass. More mass, more power to move. F=ma. And slower. as it's going to a lot more power to stop the head at the desired point on the disk, or settle times will just be that much longer. Lose-lose.Now, I could get behind a SSD in a 5.25 form factor to allow space for more memory in the case. However, that is such a niche market as to be not be viable. But it might be a way to dump previous gen flash in higher capacity drives while current/next gen flash bump on die capacity and go to smaller form factors.
extide - Wednesday, December 2, 2015 - link
Problem with larger form factor SSD's is the cost of the flash.Samsung already fits 2TB into a 7mm tall 2.5" drive, and it costs $800+ If you moved even to a 3.5" drive, so you could fit even more flash, it would be getting into the $2000 range! In the consumer market there is very little room for even an $800 SSD, much less ones significantly more expensive. What about enterprize, you say? Well, they are moving towards all PCIe flash, and there are already options out there with multiple terrabytes (3-4+) costing several thousands of dollars.We will probably never see SSD's larger than 2.5" -- at least ones that are larger, in order to hold more flash. I think OCZ made some 3.5" ssd's a long time ago, but they were nothing more than the guts of a 2.5" drive in a bigger case. Pointless.
smartthanyou - Wednesday, December 2, 2015 - link
"Lots of speculation, no facts, just a load of "probably" without argumentation." – ddriver, I am confused. Are you talking about your first post or shodanshok's. The statement seems to apply to both equally.ddriver - Wednesday, December 2, 2015 - link
The context is quite clear, if you really don't get it, you are definitely not as smart as you think you are.The arguments presented by shodanshok don't apply, the product he claims to be proof of failure has nothing to do with the product I speak of.
I never used "probably" - the tech I speak of will work, it is sound and mature tech, it just has never been applied on such a scale due to corporate politics. shodanshok didn't provide a valid reason why it shouldn't work, thus his opinion is speculations based on his misconception.
extide - Wednesday, December 2, 2015 - link
Lol man, you are in a dream world..ddriver - Wednesday, December 2, 2015 - link
Nah, I just know what is technically possible and have higher standards of expectations, which I agree is atypical in a world, mostly inhabited by consumer hoes whose "demands" are dictated by the industry. It is you who is a hopeless dreamer if you believe you are making any sort of point with such posts.DCide - Wednesday, December 2, 2015 - link
I suspect that ddriver (Discussion Driver?) is better at positing almost-good-sounding arguments than being right.MrSpadge - Wednesday, December 2, 2015 - link
A typical 1/2 platter 500 GB desktop drive used to cost less than 10€ to build a few years ago (price from OEM including VAT 17€ around 2011, before the flood). Adding platter doesn't make things significantly more expensive, but all the things you are asking for do. They'd rather procude more standard drives and let you plug several of them into one 5.25" slot.That they're charging 100's of $/€ for the bigger drives is an entirely different question - it's not only the production cost. If they stopped R&D they could probably sell the biggest drives for 50$ and still refinance the factory. But not much else.
ats - Wednesday, December 2, 2015 - link
ZERO speculation. Lots of actual facts. 5.25" drives would have lower MTBF, lower vibration tolerance, lower RPM, much worse seek performance, much lower random performance, and at best the same sequential performance.Anyone familiar with the history of magnetic media will readily agree as would anyone within the industry.
Larger platters mean more vibration issues, longer armatures, all requiring greater spacing. Longer armatures also mean less precision, resulting in greater alignment issues for tracks, more mass, resulting in slower seaking, etc. There is a reason that 15k RPM drives use a fraction of the available area for actual recording.
Or there is the simple fact that NO ONE CARES ABOUT SEQUENTIAL SPEEDS! NO ONE. NOT A SINGLE PERSON. The limit is never sequential performance and 5.25" doesn't have the possibility of helping with anything else.
Samus - Friday, December 4, 2015 - link
No offense, but if 5.25" drives were a good idea, one of the multi-billion dollar drive manufactures would have jumped on it. They obviously know some things you don't.The last company to try mainstream 5.25" drives was Quantum, and look where they are...
And the real giveaway that going largest is a bad idea is that going smaller is/has been the trend for quite some time. Outside of data centers, most modern servers ship with 2.5" bays/backplane for SSD's and 2.5" SAS drives. And in data centers, no racks are designed for 5.25" formats and when you consider the huge power consumption increase those drives will have over even 3.5" drives (which use twice as much power as their 2.5" equals) while the entire industry is trying to be greener, even IF the drives doubled capacity while keeping performance the same (doubtful but not impossible) the fact that the drives occupy nearly twice as much physical space at a higher power envelope negates any benefits outside of any potential initial cost savings.
5.25" form factor is long dead and it isn't coming back. The world is going leaner, not bulkier.
qlum - Wednesday, December 2, 2015 - link
More importantly the whole infrastructure is build around the current format so if you where to increase the size you would make it impossible to upgrade existing drives without replacing the racks for the new infrastructure, and besides that bigger drives also take up more space giving you room for much less space per rack.On the manufacturers side they would have to first figure out how to best make the drives 5.25 and that takes up quite a bit of r&d and sure there would be more capacity per drive but it probably won't warrant the cost to start making them or the barrier to start implementing them.
wiz329 - Wednesday, December 2, 2015 - link
+1. Hard drives are not a growth market. Therefore, you won't see large amounts of capital investment flowing into these divisions. It'll be about containing costs and managing the decline.Sivar - Wednesday, December 2, 2015 - link
I was with StorageReview.com as moderator, user, and often technical editor for years and am now an engineer 50 ft. from a class 10 cleanroom, and I'll tell you guys: Listen to shodanshok. He knows what he is talking about.ddriver - Wednesday, December 2, 2015 - link
I'll pass ;) love your legit credentials thou LOL, also, he might know what he is talking about, but he obviously has no idea what I am talking about, so his responses are intrinsically misplaced and do not apply.As usual, the bulk of AT visitors aren't particularly big on "outside the box".
weissPC - Thursday, December 3, 2015 - link
@ddriver - SSD was the "outside the box" solution. If you want speed, go for SSD, if you want capacity go for HDD. Doubling the number of read heads on a disk surface still won't get you near the seek nor read speeds of a SSD. That's why even the WD Raptors are quite irrelevant now. Let each focus on their niche.Your "outside the box" ideas doesn't make engineering sense.
jasonelmore - Wednesday, December 2, 2015 - link
"5.25" platter would be much vibration-prone, with resulting lower RPM (< 4000, probably)"yeah thats why 90% 2.5 laptop drives are lower RPM /sarcasm
There is more room to fit complex dampening technologies in that form factor.
The real reason you should have dismissed this idea is enterprise would never use it due to space.
The Enterprise Market pays the bills , and consumers get the leftovers
SunLord - Wednesday, December 2, 2015 - link
Hmm I wonder how many platters you could stack in a drive as tall as a 5.25" baymilli - Wednesday, December 2, 2015 - link
Look up Quantum Bigfoot. I'm sure history won't repeat itself.djgandy - Wednesday, December 2, 2015 - link
+1. I had one of these drives. It was so slow and the seek noise was awful.ddriver - Wednesday, December 2, 2015 - link
"Look up Quantum Bigfoot. I'm sure history won't repeat itself."What I am talking about has absolutely nothing to do with that product. I am not talking simply larger plates, I am talking advanced HDD implementation on top of larger plate size. The Bigfoot was big, but ultimately, it was a traditional HDD design, thus even though it offered superior capacity, its access time and sequential performance were compromised because it had a single actuator to service larger area at lower RPM.
Independent multiple heads per platter face will result in dramatically reduced access time and tremendously increased sequential performance even at lower RPM. Independent multiple heads will easily beat even 2.5" 10k RPM drives in terms of latency, and vastly outperform them in terms of throughput. 4 heads per face, 10 platters - that's 80 heads, each capable of a good average 150 mb/sec, as already mentioned, such drive will have an easy time sustaining 5-6 gigabytes per second at below 4 milliseconds access time. Large enough cache buffer of cheap RAM will mask the latency almost entirely, as random frequent accesses will not be written on the media unless the drive is to shut down.
Mechanical storage has barely seen any actual design improvements, the same design has been used for decades, only using occasional technological improvements to scale it down in size, whereas what I talk about is a significant scale up in terms of design. 100% doable, unfortunately too good for the lousy, greedy and lazy industry to go for it.
weissPC - Thursday, December 3, 2015 - link
@ddriver - have you noticed that two 3.5" drive can fit into the foot print of a single 5.25" drive? You want double the capacity? Get two 3.5" drives. You want double the transfer speed? Get two 3.5" drives and RAID 0 them.HDD design is not as simple as a armchair critic envision them to be and is complicated enough as-is, without unnecessarily adding more complicated features that is good to have but in the end will compromise reliability or cost of the end product.
5.25" platter will have much more mechanical flutter towards the edge of the disk it will be difficult to fly the heads there and not crash the heads into the disk surface since the heads are already flying much much closer to the disk than they did back in the Quantum Bigfoot years (there is an exception to this general rule, but that's another story).
Adding another actuator arm to allow multiple heads access on the same platter will double the probability of heads failure making the drive unusable, in addition of consuming drive real estate and cost because you'd need two voice coil motors in two different locations. You can't place VCMs in the same location and have them move two actuator arms independently because they use magnetic fields to function and they will interfere with each other. It's no use having two heads on one surface for backup purposes because a significant portion of head failures is due to the head crashing into the surface of the disk and scraping the surface, having a second head is no much use when you have another head scraping the magnetic materials off the disk and making it unreadable no matter how many heads you have to read the surface.
domboy - Wednesday, December 2, 2015 - link
I have one of the later ~19GB Bigfoot drives... it's been running for years, still works, still in my system as a data drive. Sure it was never the fastest thing, but on the same token it was an unusual technology so it appealed to me. But the Quantum Bigfoot that is not what we're talking about, those are consumer drives. Think something more like Seagate's Elite 5.25" SCSI line. ST446452W for example. Full-height 5.25" 47GB 5400 RPM drives. Sure they were massive in size, but at the time there were probably unmatched in capacity. I bought several used ones off ebay years ago (for really cheap) and they came in hot-swap trays so I expect they must of been in some enterprise storage system. I've had a RAID5 with three of them running 24/7 for probably 10+ years, and who knows how long they were used before that. Probably the most reliable drives I've seen. The sound of them spinning up is awesome... something along the lines of the Time Machine from the 1960 movie. They're awesome.I have no idea if there would be a market for such a drive now, but it's an intriguing idea, and I'd love to see what could be done in a 5.25" form factor with modern technology.
extide - Wednesday, December 2, 2015 - link
I think the fact that you are still using a bigfoot is probably NOT something you should brag about. It's not helping your case...domboy - Wednesday, December 2, 2015 - link
"I think the fact that you are still using a bigfoot is probably NOT something you should brag about. It's not helping your case..."Point is that the Bigfoot is a bad example of a 5.25" as it is a consumer drive, not an enterprise drive, which is the only place a modern 5.25" drive would make sense. But even the later Bigfoot drives at least (can't speak for the whole line, especially the early ones) are not bad drives if put to use in an intelligent manner (i.e. NOT as an OS drive) and this one at least has lasted a long time. Dismiss if you like, but the two examples I posted have proven to me that the form factor can make sense depending on the intended goal or use of the drive. These weren't supposed to be speed demons.
zodiacfml - Wednesday, December 2, 2015 - link
It is because that is where the current market/volume is, for reduction of costs and better margins.nandnandnand - Wednesday, December 2, 2015 - link
You won't get 5.25 inch form factor HDDs, stop talking about it.TeXWiller - Wednesday, December 2, 2015 - link
To think of the amount of 3D-flash that can be put to that 5.25 unit.. Too bad the market would be constricted to pedestal servers and workstations (with a future interconnect for speed), as the current racks would have to be redesigned.ajp_anton - Thursday, December 3, 2015 - link
The fastest mechanical drives are in fact using "2.5 inch" platters (because smaller = faster) inside a 3.5 inch enclosure for stability and protection.But let's see...
Let's assume that the outer track of a 5.3 inch drive moves at half the speed (m/s) compared to 3.5 inch, to keep the centripetal force constant (probably not directly limiting, but to keep vibrations and stability in check).
We can also check that the fastest 2.5'' drives are 15000RPM and the fastest 3.5'' (that actually use big platters) are 7200RPM. So yes, the RPM seems to go down by the square of the platter diameter.
Both approaches result in an RPM of 2000RPM or so.
You need two arms reading simultaneously to reach the same sustained speed, and four arms to reach the same rotational access speed.
Bigger platters means bigger arms with more mass and more distance to cover, but that can be overcome by more powerful, precise and expensive hardware so I'll just ignore that.
Why not just build more arms in the smaller drives we already have? Simply a bigger platter without more arms just gives worse performance in every way.
Why not just put more smaller drives in the same physical space as your proposed bigger one? A big drive needs proportionally more space for just rigidity and to keep everything together. 2.5 inch drives are leading the storage density over 3.5 inch drives, bigger drives would logically be even worse.
Lord of the Bored - Friday, December 4, 2015 - link
It's been done. Aside from the pre-3.5" drives, there was the Quantum Bigfoot. Which had performance problems due to it's size, and attempts to improve performance pushed their price out into the upper-high end of the hard drive market at speeds comparable to slowest 3.5" drives.And hard drive technology hasn't changed a lot since then. Oh, the heads are smaller, the density is better, the platters spin faster, sure. But it's all evolutionary, not revolutionary. You'll hit the same problems now that you did back then.
Two smaller drives is better than one big drive.
realityengine - Sunday, December 6, 2015 - link
5.25" 1/2 height drives occupy approx 4x the volume as 3.5" disk drives.Spouting off about a 30TB 5.25" drive that would "tremendously boost ... capacity" when you can put 40TB worth of existing much more reliable 3.5" drives in the same number of cubic inches is sufficient reason by itself to not consider a niche product. Data centers are driven by cost, power and reliabilty. None of those would be better on a per byte basis compared with 3.5" drives. Cramming more actuators increases costs, decreases reliability and has been tried in the past and discarded for those and additional reasons.
Ignoring the sound technical reasons why bigger spinning platters is not a good idea or the substantial increase in cost involved in using more heads and actuators the reality is that 5.25" drives do NOT give you an increase in storage per cubic inch.
There is a reason 14" disk packs have gone the way of the dodo bird and so have 8" and 5.25" disk drives.
Consumer products will likely see a complete disappearance of rotating magnetic media within the next couple of years. Flash is now cheaper than rotating media drives for smaller capacities and larger capacity drives just aren't needed by most consumers. SSD covers all the bases, cheap, reliable, fast, for consumers.
Only data centers and a few power user applications will need the higher capacity magnetic media drives and they are driven so strongly by costs that they aren't going to give the SLIGHTEST consideration to more expensive, less reliable, bulky 5.25" drives.
JanW1 - Wednesday, December 2, 2015 - link
"the TCO (total cost of ownership) metric is highly in favor of these drives"Do you have any own data to back this up (particularly on reliability), or are you just repeating HGST's com?
ganeshts - Wednesday, December 2, 2015 - link
You can look at the calculations as made in the slide reproduced in the article. I have no reason to doubt HGST's calculation.In general, datacenter customers care a lot about saving on space (i.e, they want to cram more terabytes per rack) and power (i.e, they want to have the lowest possible watt / TB) - because, for the 24x7 operation, the rack ownership/rental cost and cooling costs as well as power bills will be much more than what the member drives themselves cost.
JanW1 - Friday, December 4, 2015 - link
Surprising.You state that "helium drives offer the best performance to power ratio and watts per TB metric amongst all the drives in their capacity class". Now in the article you cite for that, the RAID 5 volume Resync consumed 1096Wh (10h 24m 22s X 105.42 W) for the Seagate Enterprise Capacity 3.5" HDD v4 6 TB, and 1198Wh (12h 34m 20s X 95.36 W) for the HGST Ultrastar He6 6 TB. That's a 9% power consumption _increase_. That seems to be a contradiction?
And you don't have a reason to doubt HGST's claim of a 65% power _decrease_ between a 6TB air drive and a 10TB He drive? I'm sure they found some power hogging ancient 6TB drive that can validate those numbers, but you seem to think this is actually a valid comparison with current state of the art hardware, in contradiction to your own measurements?
Sorry, this looks like publicity space bought by HGST, no more.
JanW1 - Friday, December 4, 2015 - link
Sorry, 35% power decrease claimed by HGST.boozed - Wednesday, December 2, 2015 - link
A sustained transfer rate of 249MB/s? REALLY?jabber - Wednesday, December 2, 2015 - link
Yeah but it's the access times that really count.extide - Wednesday, December 2, 2015 - link
Yeah as the data density goes up the sequential transfer rates go up as well. Of course that is strictly sequential access only.boozed - Wednesday, December 2, 2015 - link
Oh of course, I should have realised it was proportional to density.Hrel - Wednesday, December 2, 2015 - link
I miss the days when Anandtech was more about in depth technical reviews and less (not at all) about press releases.I can think of at least 7 laptops you guys should have done full reviews of by now, that have not even been mentioned.
I don't see anything even on here about the various Sony smartphones, certainly no full reviews.
It's so sad, bring back Anand!
Wardrop - Wednesday, December 2, 2015 - link
This is a pipeline story. It's just news, albeit much better thought out reporting than most news outlets, technology a focused or otherwise. I don't know why you're complaining. Your expectations are unreasonable. Plus, computing is more deserve these days. They didn't have as many device categories in the past, such as smartphone and tablets. Laptops would have probably received more attention back then.nandnandnand - Wednesday, December 2, 2015 - link
A 10 TB drive release is more important than some laptop.creed3020 - Wednesday, December 2, 2015 - link
+1 because the trickle down to consumer gear is much more relevant, just as F1 technology making it into your next sports car and then to the next compact car generations later.Kvaern2 - Wednesday, December 2, 2015 - link
Amen.DCide - Wednesday, December 2, 2015 - link
Laptops - and now (or soon) even phones - have become more refined and more commoditized. Therefore reviewing them all serves little purpose, especially with so many other parties reviewing them. Let AT's thorough reviews be reserved for significant and notable products - even though a few purchase-worthy ones will get left out.nandnandnand - Wednesday, December 2, 2015 - link
Now that a second 10 TB drive has been released, what comes next? 12 TB? 16 TB?SirMaster - Wednesday, December 2, 2015 - link
Probably 12TB by using SMR on this disk instead of PMR.Valantar - Wednesday, December 2, 2015 - link
Am I the only one slightly concerned that helium based storage is sees as the solution to increasing HDD densities while the world's helium reserves are shrinking into oblivion with no hope of recovery? Don't most estimates say we might have helium for another 20 years or so, and then we're pretty much completely out? I get that 20 years is an eternity in tech terms, but it's still pretty short sighted and dumb. Increasing helium usage is not the way to go, no matter your goal.DigitalFreak - Wednesday, December 2, 2015 - link
Blame the damned kids and their birthday parties!nandnandnand - Wednesday, December 2, 2015 - link
You aren't the only one. But you are misinformed. This uses a fraction of the helium used in balloons or medical devices. Did you think HelioSeal drives contained gigantic voids with no drive parts in them?FunBunny2 - Wednesday, December 2, 2015 - link
-- I get that 20 years is an eternity in tech termsYears???? a calendar quarter is forever in capitalist's terms. they care only about socializing cost and privatizing profit. so what if there's no X resource for their kids? they'll be dead and gone by then.
xthetenth - Wednesday, December 2, 2015 - link
Honestly I'd much rather that we put the helium into hard drives than birthday balloons. At least there's a chance we can reclaim it from hard drives.HotTorch451 - Wednesday, December 2, 2015 - link
We are not going to run out of helium anytime soon.http://www.forbes.com/sites/timworstall/2015/06/18...
jann5s - Wednesday, December 2, 2015 - link
+1, thank youRefuge - Wednesday, December 2, 2015 - link
This isn't even equivalent to a drop in the bucket.Most of the Helium consumed in the world is manufacturing and balloons.
Mikemk - Wednesday, December 2, 2015 - link
So when will we get a petabyte?robob4him - Wednesday, December 2, 2015 - link
I think I'm behind as this is the first time I've heard of helium-injected HDs.okashira - Wednesday, December 2, 2015 - link
Anyone actually find out if they are really using Hydrogen instead of Helium?Hydrogen is better choice for this application for all reasons... but... marketing..
FunBunny2 - Wednesday, December 2, 2015 - link
-- Hydrogen is better choice for this application for all reasonsyeah, Zeppelin proved that (not the dinosaur garage band).
okashira - Thursday, December 3, 2015 - link
Your post explains exactly why they have to market "Helium," instead of Hydrogen. And not because of your zeppelin reference. (hint: marketing)weissPC - Thursday, December 3, 2015 - link
@okashira - it's not marketing, it safety really, Helium is an inert gas and is much much safer (and cheaper too) to use in a manufacturing environment. If the seal in a batch of He drives fail in a datacenter, you may have a relatively harmless gas plus failed drives, but if you have a batch of leaking hidrogen drives, you not only get failed drives, the safety implications are much more severe.kpopat - Thursday, December 3, 2015 - link
Serious question...wont the helium leak at some point over a number of years?stevenrix - Friday, December 11, 2015 - link
Those are enterprise hard-drives, very few people will be able to afford those drives.The helium vs air pricing trend graph is for the least a marketing tool at this point: ramping up large-scale productions of those drives will only be possible when the old technology will be replaced, it's still a few decades from now, and by then SSDs will have flooded the market once their size and price per Gb become democratized. Anyway this graph is pure science fiction at this point.