The First Terabyte Hard Drive Reviewed

mikemuch writes "ExtremeTech has a review and benchmarks of the Hitachi Deskstar 7K1000 1TB Hard Drive, which ushers in the terabyte age. It performs well on HDTach and PCMark benchmarks, though not as speedily as professional-grade drives. It could be just the ticket for digital media junkies. 'One of the first issues to note is that you may not see an actual one terabyte capacity on your system. First, the formatted capacity is always less than the raw space available on the drive. Directory information and formatting data always take up some space. Second, the hard drive industry's definition of a megabyte differs from the rest of the PC business. One megabyte of hard drive space is 1,000,000 bytes: 10^6 bytes. Operating systems calculate one megabyte as 2^20 bytes, or 1,048,576 bytes. Once installed and set up, Hitachi's 1TB hard drive offers up an actual formatted capacity of about 935GB, as measured by the OS. That's still a lot of space, by anyone's definition.'" Update: 05/17 21:52 GMT by Z : Adding '^s' missing from article.

Comments

Now I need faster broadband

[Anonymous Coward]

So that I can fill this new drive with pr0n ;)

Re:Now I need faster broadband

[lord_sarpedon]

No, it just means you'll get to consolidate what you already have ;)

New New Math?

[WrongSizeGlass]

One megabyte of hard drive space is 1,000,000 bytes: 106 bytes. Operating systems calculate one megabyte as 220 bytes, or 1,048,576 bytes. That was from TFA (not just the summary). I asked my calculator about that but it just got a headache.

Re:106 bytes and 220 bytes, ???

[Roger W Moore]

They mean that superscript tags don't work when submitting stories to slashdot. If should read 10^6 and 2^20.

Why is this still a discussion?

[Grelli]

Don't complain about the fact a megabyte isn't what you thought it was. Complain about the fact the industry still uses it for labels. But don't try and make the megabyte a mebibyte.

http://en.wikipedia.org/wiki/Binary_prefix vs http://en.wikipedia.org/wiki/Si_prefix

Re:Why is this still a discussion?

[jdgeorge]

Don't complain about the fact a megabyte isn't what you thought it was. Complain about the fact the industry still uses it for labels. But don't try and make the megabyte a mebibyte.

What!?! Next thing you'll be telling me is that a kilometer isn't 1024 meters long. Please, stop this madness before it spreads!

Re:Why is this still a discussion?

[Mattintosh]

The difference between the two numbers is due to this:

Manufacturers have an interest in you paying more and getting less, while computers do not. Manufacturers who are successful and have the cash to spend can then lobby international standards bodies to skew "standards" in their favor, regardless of historical context and practical day-to-day usage patterns (both technical and linguistic).

Don't side with "the man" on /. unless you enjoy tar + feathers, not even if it means bucking the "standard".

Re:Why is this still a discussion?

[blhack]

We could just simplify the process and start calculating drive space in libraries of congress * elephants of pressure per square postage stamp.

Re:Why is this still a discussion?

[SEMW]

Don't try to invent a new notation to make-up for corporate marketing corrupting established and well-understood notation. I would point out the "mega" was an established and well-understood prefix for 10^6 well before the computer industry (sans hard drive makers) started to use it mean 2^20.

Re:Why is this still a discussion?

[dgatwood]

They are still wrong. The fundamental organization of computers is base 2. Ever try to design a processor that uses 1000 byte pages? Good freaking luck.

The purpose of SI units being in base 10 is because the number system that we use to measure things is ALSO in base 10. Therefore, the unit fits comfortably within mathematics associated with the relative fields. However, A base-10 numbering scheme basically does not exist in the computing world; obscure BCD hardware notwithstanding, all occurrences of base ten in computing are entirely a fiction created by the machine to try to make things more understandable to people used to base 10.

More to the point memory and storage are inherently organized in units of powers of two. Memory will ALWAYS be organized in power-of-two increments as long as computer operate based on the binary system. Why? Because this makes it possible to express divisions of memory in terms of bit boundaries. A power-of-10 memory organization would require computationally heavy division or multiplication operations throughout the memory management code, while a power-of-2 memory organization requires an extremely lightweight bit shift. For this reason, as long as we have binary-based computers, we are stuck with power-of-two units of RAM.

Similarly, a hard drive block will ALWAYS be evenly divisible by the size of a memory page or vice versa. If this were not the case, the complexity of writing an operating system would be beyond insane. Paging and memory mapping of files alone would be enough to make the engineers commit seppuku. Therefore, as long as RAM is organized into groupings based on powers of two, hard drives will always be physically laid out in blocks whose length is a power of two.

Because the fundamental organization of data in a computer is, by nature, organized into power-of-two units, describing storage in power-of-ten units makes no sense, as it will almost always be a crude approximation. There are probably exactly zero hard drives with an exact decimal gigabyte capacity. The fundamental storage in hard drives is a 512 byte block, and 512 does not divide evenly into most multiple-of-ten values. Sure, you could create a 512 decimal gigabyte drive, I suppose, but for the most part, the values just don't divide evenly by 512. Therefore, using a multiple of a power-of-ten number to describe the amount of storage will almost always be a very crude approximation, while using a multiple of a power-of-two number can be (and usually is) an exact value.

In other words, the idiots in charge of making up the SI units should have been taken out and beaten for "Gibibyte". There is one natural unit in computers, and that is the base-2-derived gigabyte. All base-10 units are inherently inaccurate, and thus a poor fit for computing. They should be summarily rejected by the industry, as they simply do not make any sense in the context of storage. Honestly, they don't make a lot of sense for networking, either for the same reason, but I'm willing to overlook that... for now....

Re:Zonk

[nine-times]

It was probably originally typed as:

One megabyte of hard drive space is 1,000,000 bytes: 10⁶ bytes. Operating systems calculate one megabyte as 2²⁰ bytes, or 1,048,576 bytes.

And then the tags got stripped somehow.

Re:Zonk

[OrangeTide]

It's not a race Zonk, you can hit the preview button once in a while.

From this day forward all badly formed posts shall be known as Zonks.

First review? ummm... Anandtech, March 19th....

[Fallen Kell]

Initial review March 19th:

http://www.anandtech.com/storage/showdoc.aspx?i=29 49

Follow-up RAID performance April 19th:

http://www.anandtech.com/storage/showdoc.aspx?i=29 49

Follow-up to the follow-up April 23rd:

http://www.anandtech.com/storage/showdoc.aspx?i=29 74

WOW, 1TB

[Anon-Admin]

I remember when I paid $150 for a 10meg MFM drive! (poke c800:50 ;)
I remember paying $1000 for my first 1gig drive!
I remember paying $500 for my first 1TB of drive space (6x300gb drives ok 1.8TB unformatted)
I remember paying $350 for my second 1.1TB of drive space (4x320gb Just last week)

I can not wait to get to my first 6TB system! I may have said, many years ago, that I would never fill 1gig, but I know I can fill 6TB It should not take me more than a couple of months.

Man how things have changed!

Then 8mhz, 640k ram and 10megs.
Now 2.4Ghz dual core, 2gig ram, 1.1TB HD

I wonder what we will say in another 16 years.

Re:WOW, 1TB

[Chandon Seldon]

What will you store on your 10 TB drive that will take up all the space?

High quality 1080p video. Animated textures for video games. A massive sample database for a voice synthesizer.

I'm not actually sure what you would do with a 10,000 TB hard disk - but 10 TB is well within the "use it up with some video" range.

Megabyte/Terabyte

[Bobb Sledd]

We can only guess what Zonk meant to say. But I'll try to make some sense.

First, hard drive manufacturers have always calculated drive space differently than the rest of the entire computing world. It allows them to say that a drive is bigger than it really truly is. They've been able to do it for years, and lawsuits have been lost and won on this very issue. But essentially, their use of the metric words "kilo," "mega," and "giga" are the literal meanings of "1000," "1,000,000" and "1,000,000,000" instead of the computing world's 1024 multiplier.

Therefore, a "kilobyte" to them is 1,000 bytes (as opposed to 1,024 bytes in real life), and a "megabyte" is "1,000,000" bytes (as opposed to 1,048,576 bytes [1024 x 1024]), and a "gigabyte" is 1,000,000,000 bytes (instead of 1,073,741,824 [1024 x 1024 x 1024] bytes in real life).

The real difference in a terabyte? Divide 1,000,000,000,000 by 1024/1024/1024 and you get 931.32 gigabytes. That's a theoretical limit, mind you, and there is overhead for cluster size, partition info, FAT tables, etc., so you really don't even get that.

Doesn't that byte?

Re:Ahh Slashdot

[croddy]

eh, you're not missing anything anyway. TFA is just one of those meager gear review sites with 20 words per page spread out onto 8 pages all mostly covered with a bunch of empty rectangles.

what is the DEAL with all those empty rectangles anyway?

I look forward to more write-ups like this

[Anonymous Coward]

Perhaps the next story on Bill Gates or windows might consist mostly of a paragraph explaining that Microsoft is a company.

SI prefixes are powers of thousand.

[Zarhan]

Cue the ensuing Mebi/Gibi/Tebi vs. SI notation fights.

While it's takes a while to get used to it, I actually prefer the Bi-units now. 4,3GiB or 4,7GB is already a huge difference when talking about DVD capacity. At terabyte, it gets enormous.

Linux already uses those units.

Only place where I still see a purpose for using binary units in computing is memory - address bus is still addressed exactly with n lines so memory capacity will be 2^n. For all other cases, it's not needed. Yes, the hard drives have 512 to 4096 byte sectors, but who cares when were talking about trillions of them?

See http://en.wikipedia.org/wiki/Binary_prefix for more.

Re:Zonk

[elguap0]

He totally Schruted that summary.

New drive storage metrics needed

[PeeAitchPee]

In other news, Seagate announced that its upcoming line of hard drives will be measured using the new LoC (Library of Congress) storage units to avoid confusion. The advanced ST-54883432, weighing in at a monstrous .00000000000017 LoC, goes on sale June 14th.

Re:SUP tag missing - 10^6 and 2^20

[trentblase]

Not much, ^{with you?}

Re:Damn...

[crabpeople]

I think I have files older than you...

Screw the hitachi!

[AbRASiON]

The Hitach is a 1000mb drive with 5x200gb platters.
The Seagate (due soon) is a 1000mb drive with 4x250gb platters and (iirc) 32mb of cache.

The increased platter density will slightly increase performance and theoretically decrease cost, it'll slightly reduce heat and also power use too.

On top of this Seagate offer a 5 year warranty on all drives (Hitachi may also, sorry not sure) and Seagate used to be one of the quietest available to boot. (although I hear the 7200.10's suck for noise, apparently some kind of patent issue with using low acoustic mode - hope that's sorted?)

Anyhow, what this does mean for us end users is you'll see 2 platter, 500gb drives which weigh less, cost less, run faster and cost substantially less than the 1000mb models, also the glorious 750gb will become a 3 platter model instead of a 4 platter (my personal 'limit' is 3playtters - after that I find it too prone to noise / heat / failure rate)

I'd say we'll see 80$ (rebate) 500gb drives within 3 months and we'll see the 750's at 169$ or something soon(ish)

Re:Zonk

[Anonymous Coward]

This is still not really correct: One megabyte of hard drive space is 1,000,000 bytes: 10^6 bytes. Operating systems calculate one megabyte as 2^20 bytes, or 1,048,576 bytes.

It should read: Hard disk manufacturing company marketing departments define one megabyte of hard drive space as 1,000,000 bytes: 10^6 bytes. Fucking reality calculates one megabyte as 2^20 bytes, or 1,048,576 bytes.