Sign in with
Sign up | Sign in

Hard Drives And SSDs: Capacity Vs. Performance

Crucial's m4 SSD Tested At 64, 128, 256, And 512 GB
By

Before we dive into SSD performance, you’re probably asking why performance improves as capacity goes up, right? After all, that’s certainly not the case with hard drives. In a mechanical drive, capacity is determined by the form-factor, number of platters, and areal density. Often, however, hard drives have a lower shipping capacity than what you would get if you added up the drive's relevant specs.

For example, a 160 GB Barracuda 7200.12 uses a single 500 GB platter. However, Seagate only uses the outer-most sectors, because this allows for higher performance. So whether you buy a dual-platter 1 TB drive or the 160 GB Barracuda 7200.12, you’re getting a maximum outside-diameter data rate of 125 MB/s.

Of course, SSDs are different. Instead of a spinning magnetic media, you have solid-state memory packages attached to a piece of controller logic. Those NAND-based devices communicate over multiple channels, and it's up to the SSD vendor to populate them in a way that yields the desired capacity, performance level, and cost.

Intel's own proprietary controller is a 10-channel design, for instance. In our example on the previous page, the 80 GB X25-M achieves 70 MB/s because all 10 of its channels are populated. The 40 GB X25-V employs the same controller, but a shift down to five channels correspondingly cuts write speed to 35 MB/s.

The Marvell 88SS9174 controller used by Crucial in its m4 SSDs is an eight-channel design. All of the m4s fully populate the controller's available channels, and yet there are still significant spec sheet-level differences between the four family members. This is because simply exploiting every channel isn't enough to saturate them. The number of packages residing on each channel matter. The number of memory dies in each package matter. The density of each die matters. And the firmware-level modifications a company like Crucial implements to help control performance scaling up and down the stack matter.

Crucial m4
64 GB
128 GB
256 GB
512 GB
Channels Used
8
8
8
8
Memory Packages
8
16
16
16
Memory Packages Per Channel
1
2
2
2
Die Density
32 Gb
32 Gb64 Gb64 Gb
Dies Per Package2
2
2
4
Dies Per Channel
1
4
4
8


As you can see, all four SSDs look quite similar from the top. We've clearly labeled a memory package on the 64 GB model, in case you're not familiar with the terminology in the chart above. 

25 nm, 8 GB (64 Gb), 167 square millimeters25 nm, 8 GB (64 Gb), 167 square millimeters

Within each one of those packages, you can have one, two, or four physical NAND flash dies. The shot above is an 8 GB (64 Gb) die manufactured on IMFT's 25 nm process. It measures about 167 square millimeters on its own.

Standardized interfaces like ONFi ensure that any compatible NAND device employs the same pin-out, a unified command set, improved data integrity, and a host of other benefits. When a controller vendor like Marvell or SandForce incorporates support for those interface standards, it allows drive partners to switch between NAND chips manufactured by several possible suppliers without worrying about some sort of compatibility issue. It just so happens that all four Crucial m4 drives employ 25 nm ONFi 2.2-compliant NAND manufactured by Micron (hardly a surprise there, right?).

See how the 128, 256, and 512 all have 16 NAND packages (eight up front and eight around back)? Similar though they look, they're not all the same. The 128 GB model has two 4 GB die per package, the 256 GB has two 8 GB dies per package, and the 512 GB has four 8 GB dies per package. That’s how SSD manufacturers end up with higher-capacity SSDs, even though the number of chips you see stays the same.

Ask a Category Expert

Create a new thread in the Reviews comments forum about this subject

Example: Notebook, Android, SSD hard drive

Display all 37 comments.
This thread is closed for comments
  • 5 Hide
    wintermint , August 3, 2011 5:11 AM
    I've been recommending the Crucial m4 128gb to people, and after seeing this.. I'm glad I did :]
  • 6 Hide
    sceen311 , August 3, 2011 5:22 AM
    it'd be nice if they threw a 7200 rpm hardrive on the bench... We don't all have laptops ya know.
  • 7 Hide
    compton , August 3, 2011 5:25 AM
    I'm glad this was done. It's rare that you get the chance to stack all the capacity points up (as in never). I bought an Intel 510 120GB and a M4 64GB and my own testing showed that you'd never know the difference besides the capacity (in day to day use, besides lower max write MB/S). I kinda like keeping my system drive to a bare minimum -- just Win7 no swap or hibernate, Office, a few other apps, and then I keep my Steam folder on a separate drive. Simple. I will say that if you are building a new system, cut whatever you have to in order to fit at least a 64GB SSD -- the M4 is excellent at any capacity. I'd rather have to go down to an i3 from a 2500k than from a SSD to a HDD. I get tired of people saying "it's not worth it" and "they're not much faster than a 7200rpm". Those people must be doing it wrong.
  • 6 Hide
    beenthere , August 3, 2011 6:01 AM
    Now if they could only make these SSDs reliable, we could all enjoy some performance improvement. Intel, Micron, OCZ and Corsair to name a few have all had reliability/compatibility/firmware issues of some sort resulting in loss of data, which for me is simply unacceptable.
  • -1 Hide
    Anonymous , August 3, 2011 6:17 AM
    Last month I got a 64GB for my laptop and a 128GB m4 for my desktop. So far no issues, and the speed is great. Glad I got the 128GB and not the 256GB.
  • -1 Hide
    Anonymous , August 3, 2011 6:37 AM
    PCMark 7 Storage tests are just pathetic, they have messed some of them up on purpose it seems just to shrink the difference between systems containing SSD and the ones containing HDD only, useless bench from start to "finish"...
  • -1 Hide
    ubercake , August 3, 2011 9:38 AM
    These things are still too expensive.
  • 1 Hide
    mroanhaus , August 3, 2011 11:40 AM
    I picked up the 64 GB M4 two weeks ago on Newegg for under $90. I am so glad I bought it, the thing makes boot times lightning fast. I have Win7 64-bit, Photoshop, 3DS Max, Google Chrome, and a few little monitoring and Bitcoin mining apps on there and I STILL have 21 GB to spare. Don't buy the 128 GB unless you really need it, throwing Steam and other massive apps will be much better suited on a secondary HDD. SSDs are simply amazing and well worth the money spent, even if you're a cheapass like me they're still affordable. The time saved from having to wait around while booting your computer makes SSDs worth the money imo
  • -2 Hide
    burnley14 , August 3, 2011 12:59 PM
    Quote:
    See how they all hover pretty close to the same price per gigabyte, while sequential write and random write performance trend upward? Those are the spoils available to folks willing to spend more on higher capacities.


    This is true, but in 6 months when the whole lineup is outdated and the next generation of drives blows these ones away, those that spent more are going to have spent the extra money without much purpose.
  • 1 Hide
    cknobman , August 3, 2011 1:29 PM
    burnley14This is true, but in 6 months when the whole lineup is outdated and the next generation of drives blows these ones away, those that spent more are going to have spent the extra money without much purpose.


    Well going by your logic why should anyone ever spend money on anything in technology??? Guess its always a waste huh?

    Failed logic.
  • 1 Hide
    jerreddredd , August 3, 2011 1:30 PM
    the Reviews on Newegg have been really positive. no DOA or failures. the only issue i have seen is that some laptops have issues with the M4. this is probably a MB Bios issue or driver issue. I have a 256GB Phoenix Pro and my sees how quickly levels load and thinks he needs an SSD too. I am building his new system soon and the M4 is a strong contender for his build. The Vertex3 seems to have a lot of issues right now, which was the other SSD consideration.
  • -1 Hide
    burnley14 , August 3, 2011 2:39 PM
    cknobmanWell going by your logic why should anyone ever spend money on anything in technology??? Guess its always a waste huh? Failed logic.


    No, not failed logic at all. Go ahead and buy a SSD today, I already have, but why spend 8x as much money on a larger drive to get marginally better performance when everyone knows a better product will be out so soon? My logic would be that for the price of a single large drive, you could buy a smaller drive in this generation, the next, and the one following that for the same amount of money. And odds are that capacities will increase at the same price level in the future as well. Your performance would be substantially greater than just having today's single large drive while spending the same amount of money.
  • 1 Hide
    brenro , August 3, 2011 3:03 PM
    burnley14No, not failed logic at all. Go ahead and buy a SSD today, I already have, but why spend 8x as much money on a larger drive to get marginally better performance when everyone knows a better product will be out so soon? My logic would be that for the price of a single large drive, you could buy a smaller drive in this generation, the next, and the one following that for the same amount of money. And odds are that capacities will increase at the same price level in the future as well. Your performance would be substantially greater than just having today's single large drive while spending the same amount of money.




    The same could be said of every single computer upgrade you could ever do. CPU's, graphics cards, motherboards? By your logic I could never upgrade because something better will soon come out.
  • 3 Hide
    dgingeri , August 3, 2011 3:14 PM
    I have an outstanding question regarding SSDs that I've been trying to find for a while now: how does raid performance compare at the same capacity. In other words, I'd like to see the comparison between 4X64GB, 2X128GB, and a single 256GB to see which performs better for the money spent.

    I'm currently running a 2X120GB Vertex 2 setup, and I can tell you for certain that it massively outperforms a single 240GB Vertex 2. That was pretty plain with that generation of drives. It's not so clear with this generation, though. Also, since TRIM isn't an option for a raid config, how much performance is sacrificed after it gets used for a while? I haven't lost much at all with my dual Vertex 2 raid after over a year, but it is also only half used. I haven't run out of unused cells yet to see a difference.

    Since nobody else has written an article on such things, I would think such a thing would attract readers.
  • 0 Hide
    jacobdrj , August 3, 2011 3:16 PM
    brenroThe same could be said of every single computer upgrade you could ever do. CPU's, graphics cards, motherboards? By your logic I could never upgrade because something better will soon come out.

    Yeah. At this point, even a mid-grade SSD has balanced my PC out so much to the point that an upgrade will only happen if my computer dies in a lightning storm... A C2Q with an Agility 2 60gb and a RAID of 500GB Samsung drives with 8 gb of DDR2 RAM and Windows 7 x64 will last me a long long time...
  • 0 Hide
    stevelord , August 3, 2011 3:24 PM
    I run a few 128s and 256s at work. So far so good. Although a coworker had the freezing bug and had to update firmware. Beware of this. It is fairly common and allover Crucial's forums.
  • 0 Hide
    JohnnyLucky , August 3, 2011 3:25 PM
    I'm looking at the article page with the response time graphs. A human blink of an eye takes between 300ms and 400ms. It would seem then that average and maximum response times would appear to be instantaneous to a human being. What would a gamer or an enthusiast be doing with a ssd for the difference between 64GB and a 512GB ssd response times to be noticeable?
  • 2 Hide
    cadder , August 3, 2011 3:41 PM
    1. The recommended 128GB size has a lot of negative feedback on newegg, specifically freezing periodically.

    http://www.newegg.com/Product/Product.aspx?Item=N82E16820148442

    2. I wish Toms would come up with some real world benchmarks for testing SSD's. How long does it take for the computer to boot? How long does it take to load Excel? How long does it take to load Crysis? Things like that. I've seen tests other places that showed how fast a computer would boot, and the difference between the slowest hard drive and the fastest SSD wasn't all that much. I would like to see real world tests of these drives. While the artificial benchmarks show big differences, I'm betting in the real world the differences are very small.
  • 1 Hide
    X-Nemesis , August 3, 2011 4:48 PM
    Something tells me that over 90% of the users out there wouldn't notice a difference between a sata 6 ssd and a sata 3 ssd. Eventually all that will be available will be sata 6 but for now, buy a sata 3 last gen model for cheaper price.
  • 0 Hide
    jacobdrj , August 3, 2011 4:57 PM
    X-NemesisSomething tells me that over 90% of the users out there wouldn't notice a difference between a sata 6 ssd and a sata 3 ssd. Eventually all that will be available will be sata 6 but for now, buy a sata 3 last gen model for cheaper price.

    The problem is, while the last gen models are cheaper, they are not THAT MUCH cheaper... It has got to get to $1/GB... It really just has to...
Display more comments