Puffnstuff
Lifer
- Mar 9, 2005
- 16,048
- 4,807
- 136
Hard drives are the dinosaur of storage and will be extinct before too long just like betamax and vhs went away.
Maybe the first step towards 5.25" would be to take a page out of the Western Digital Raptor handbook and use a smaller platter (3.5") spinning a high rpm in larger enclosure (5.25"). The larger enclosure acting as heatsink.
The sometime after the transition of high rpm 3.5" platter in 5.25" enclosure, the move to 5.25" platters at slower rpm could made.
P.S. If anyone here doesn't remember the Western Digital Raptor, it was 3.5" drive that used 2.5" platters spinning @ 10,000 rpm. The larger than platter size enclosure acted as heatsink (see below for picture).
There's no reason to drop a high-RPM 3.5" HDD into a giant heatsink just to have a 5.25" drive - firstly, because the heat sinks aren't necessary in a well-ventilated system. Doubly so because nobody seems to make 15k 3.5" drives in capacities >600GB.
Hard drives are the dinosaur of storage and will be extinct before too long just like betamax and vhs went away.
I believe that's incorrect. It uses 8/10 encoding on the bits, so it's really only 600MB/sec, of which there is protocol overhead. I think that SSDs already maxed out SATA6G at 560MB/sec.However, with SATA 6 Gbps theorectically capable of 750 MB/s
I believe that's incorrect. It uses 8/10 encoding on the bits, so it's really only 600MB/sec, of which there is protocol overhead. I think that SSDs already maxed out SATA6G at 560MB/sec.
You guys are making me nostalgic for my old 50lb (that's what it felt like) CDC 5.25" Full Height 40MB beast.
When it spun up a small magnetic storm and large acoustic field surrounded the case. When it seeked, so did the desk. When it spun down, felt like something important had happened and the world could finally get some rest. If it had to taken out or system moved - had to engage the mechanical head lock or suffer the platter damage. After re-installing, disengaging the head lock drastically improved seek times.
Can get a refurb for only $314 (super cheap!!!). Won't mention the cost per MB back then. There was no cost per GB, because the Gigabyte hadn't been invented yet. :biggrin:
I believe that's incorrect. It uses 8/10 encoding on the bits, so it's really only 600MB/sec, of which there is protocol overhead. I think that SSDs already maxed out SATA6G at 560MB/sec.
Assuming WD Black 6TB (5 platters) transfer rates (~220 MB/s) scale linearly with rpm and increased platter count, here are some possibilities I came up with:
1. WD Black 12TB (10 platters @ 7200 rpm) = 440 MB/s
2. WD Black 6TB (5 platters @ 10,000 rpm) = 305 MB/s
3. WD Black 12TB (10 platters @ 10,000 rpm) = 611 MB/s
4. WD Black 6TB (5 platters @ 15,000 rpm) = 458 MB/s
5. WD Black 8.4TB (7 platters @ 15,000 rpm) = 641 MB/s
Uhm, you only read/write one platter at a time. Linear track density and RPM pretty much determine max transfer rate, it has nothing to do with number of platters (other than head-settling time and seek time).
Maybe the first step towards 5.25" would be to take a page out of the Western Digital Raptor handbook and use a smaller platter (3.5") spinning a high rpm in larger enclosure (5.25"). The larger enclosure acting as heatsink.
The sometime after the transition of high rpm 3.5" platter in 5.25" enclosure, the move to 5.25" platters at slower rpm could made.
P.S. If anyone here doesn't remember the Western Digital Raptor, it was 3.5" drive that used 2.5" platters spinning @ 10,000 rpm. The larger than platter size enclosure acted as heatsink (see below for picture).
Do you really think our memories are that short? Piffle. :awe:
The 3.5" enclosure on the Raptors was just heat sink - extra metal on the outside. Mechanically, they were boring, run-of-the-mill 2.5" server hard drives. You could even yank the drives out of the heat sink if you wanted, and you'd have a 12mm thick 2.5" SATA drive that pulled 12v. (Most 2.5" drives run on 5v.)
There's no reason to drop a high-RPM 3.5" HDD into a giant heatsink just to have a 5.25" drive - firstly, because the heat sinks aren't necessary in a well-ventilated system. Doubly so because nobody seems to make 15k 3.5" drives in capacities >600GB. At that point, you might as well just get an SSD. But if you really want to, you can buy one.
Platter Size
The size of the platters in the hard disk is the primary determinant of its overall physical dimensions, also generally called the drive's form factor; most drives are produced in one of the various standard hard disk form factors. Disks are sometimes referred to by a size specification; for example, someone will talk about having a "3.5-inch hard disk". When this terminology is used it usually refers to the disk's form factor, and normally, the form factor is named based on the platter size. The platter size of the disk is usually the same for all drives of a given form factor, though not always, especially with the newest drives, as we will see below. Every platter in any specific hard disk has the same diameter.
The first PCs used hard disks that had a nominal size of 5.25". Today, by far the most common hard disk platter size in the PC world is 3.5". Actually, the platters of a 5.25" drive are 5.12" in diameter, and those of a 3.5" drive are 3.74"; but habits are habits and the "approximate" names are what are commonly used. You will also notice that these numbers correspond to the common sizes for floppy disks because they were designed to be mounted into the same drive bays in the case. Laptop drives are usually smaller, due to laptop manufacturers' never-ending quest for "lighter and smaller". The platters on these drives are usually 2.5" in diameter or less; 2.5" is the standard form factor, but drives with 1.8" and even 1.0" platters are becoming more common in mobile equipment.
Traditionally, drives extend the platters to as much of the width of the physical drive package as possible, to maximize the amount of storage they can pack into the drive. However, as discussed in the section on hard disk historical trends, the trend overall is towards smaller platters. This might seem counter-intuitive; after all, larger platters mean there is more room to store data, so shouldn't it be more cost-effective for manufacturers to make platters as big as possible? There are several reasons why platters are shrinking, and they are primarily related to performance. The areal density of disks is increasing so quickly that the loss of capacity by going to smaller platters is viewed as not much of an issue--few people care when drives are doubling in size every year anyway!--while performance improvements continue to be at the top of nearly everyone's wish list. In fact, several hard disk manufacturers who were continuing to produce 5.25" drives for the "value segment" of the market as recently as 1999 have now discontinued them. (The very first hard disks were 24" in diameter, so you can see how far we have come in 40 or so years.)
Here are the main reasons why companies are going to smaller platters even for desktop units:
Enhanced Rigidity: The rigidity of a platter refers to how stiff it is. Stiff platters are more resistant to shock and vibration, and are better-suited for being mated with higher-speed spindles and other high-performance hardware. Reducing the hard disk platter's diameter by a factor of two approximately quadruples its rigidity.
Manufacturing Ease: The flatness and uniformity of a platter is critical to its quality; an ideal platter is perfectly flat and consistent. Imperfect platters lead to low manufacturing yield and the potential for data loss due to the heads contacting uneven spots on the surface of a platter. Smaller platters are easier to make than larger ones.
Mass Reduction: For performance reasons, hard disk spindles are increasing in speed. Smaller platters are easier to spin and require less-powerful motors. They are also faster to spin up to speed from a stopped position.
Power Conservation: The amount of power used by PCs is becoming more and more of a concern, especially for portable computing but even on the desktop. Smaller drives generally use less power than larger ones.
Noise and Heat Reduction: These benefits follow directly from the improvements enumerated above.
Improved Seek Performance: Reducing the size of the platters reduces the distance that the head actuator must move the heads side-to-side to perform random seeks; this improves seek time and makes random reads and writes faster. Of course, this is done at the cost of capacity; you could theoretically achieve the same performance improvement on a larger disk by only filling the inner cylinders of each platter. In fact, some demanding customers used to partition hard disks and use only a small portion of the disk, for exactly this reason: so that seeks would be faster. Using a smaller platter size is more efficient, simpler and less wasteful than this sort of "hack".
The trend towards smaller platter sizes in modern desktop and server drives began in earnest when some manufacturers "trimmed" the platters in their 10,000 RPM hard disk drives from 3.74" to 3" (while keeping them as standard 3.5" form factor drives on the outside for compatibility.) Seagate's Cheetah X15 15,000 RPM drive goes even further, dropping the platter size down to 2.5", again trading performance for capacity (it is "only" 18 GB, less than half the size of modern 3.5" platter-size drives.) This drive, despite having 2.5" platters, still uses the common 3.5" form factor for external mounting (to maintain compatibility with standard cases), muddying the "size" waters to some extent (it's a "3.5-inch drive" but it doesn't have 3.5" platters.)
The smallest hard disk platter size available on the market today is a miniscule 1" in diameter! IBM's amazing Microdrive has a single platter and is designed to fit into digital cameras, personal organizers, and other small equipment. The tiny size of the platters enables the Microdrive to run off battery power, spin down and back up again in less than a second, and withstand shock that would destroy a normal hard disk. The downside? It's "only" 340 MB. :^)
The thing is though, data is written to the edge of the platters first and the end of the drive is actually at the center. They do this because drive reading speeds are slowest towards the center of the disk.Improved Seek Performance: Reducing the size of the platters reduces the distance that the head actuator must move the heads side-to-side to perform random seeks; this improves seek time and makes random reads and writes faster. Of course, this is done at the cost of capacity; you could theoretically achieve the same performance improvement on a larger disk by only filling the inner cylinders of each platter. In fact, some demanding customers used to partition hard disks and use only a small portion of the disk, for exactly this reason: so that seeks would be faster. Using a smaller platter size is more efficient, simpler and less wasteful than this sort of "hack".
Some more information on platter size here.
The exact reason the reduction from 3.5" (3.74") @ 10,000 rpm to 3" @ 10,000 rpm occurred is still unclear to me. Was this primarily done for rigidity/cost or was it done for power and heat reduction?
All this is driven by server/enterprise tech. That's where the money is.Were the changes done primarily for server or workstation?
Nope.And is there anything about adding a 5.25" heatsink to a 3.5" drive (spinning at 10,000 rpm) that changes this for desktop/workstation?
Why not Hydrogen, Xenon, oxygen, nitrogen or some other sort of gas? I don't like the idea of using a limited resource like Helium.Regarding Helium, I found out it does more than just reduce friction, it also allows a closer hovering distance from the media (allowing more platters within the same Z-height):
http://forums.anandtech.com/showpost.php?p=37637679&postcount=14
With that mentioned, when we consider that the 5.25" form factor has a greater height than the 3.5" form factor (1.625" vs 1"), it might be that up 11 platters could be used when Helium is present and up to 8 platters without Helium present.
The thing is though, data is written to the edge of the platters first and the end of the drive is actually at the center. They do this because drive reading speeds are slowest towards the center of the disk.
Why not Hydrogen, Xenon, oxygen, nitrogen or some other sort of gas? I don't like the idea of using a limited resource like Helium.
Probably because it's intert. Of the noble gases, Helium is probably the easiest to obtain.