Used vs. New Performance: Revisited

Nearly all good SSDs perform le sweet when brand new. None of the blocks have any data in them, each write is performed at full speed, all is bueno. Over time, your drive gets written to, all blocks get occupied with data (both valid and invalid) and now every time you write to the SSD its controller has to do that painful read modify write and cleaning.

In the Anthology I simulated this worst used case by first filling the drive with data, deleting the partition, then installing the OS and running my benchmarks. This worked very well because it filled every single flash block with data. The OS installation and actual testing added a few sprinkles of randomness that helped make the scenario even more strenuous, which I liked.

The problem here is that if a drive properly supports TRIM, the act of formatting the drive will erase all of the wonderful used data I purposefully filled the drive with. My “used” case on a drive supporting TRIM will now just be like testing a drive in a brand new state.

To prove this point I provide you with an example of what happens when you take a drive supporting TRIM, fill it with data and then format the drive:

SuperTalent UltraDrive GX 1711 4KB Random Write IOPS
Clean Drive 13.1 MB/s
Used Drive 6.93 MB/s
Used Drive After TRIM 12.9 MB/s

 

Oh look, performance doesn’t really change. The cleaning process takes longer now but other than that, the performance is the same.

So, I need a new way to test. It’s a shame because I’m particularly attached to the old way I tested, mostly because it provides a very stressful situation for the drives to deal with. After all, I don’t want to fool anyone into thinking a drive is faster than it is.

Once TRIM is enabled on all drives, the way I will test is by filling a drive after it’s been graced with an OS. I will fill it with both valid and invalid data, delete the invalid data and measure performance. This will measure how well the drive performs closer to capacity as well as how well it can TRIM data.

Unfortunately, no drives properly support TRIM yet. The beta Indilinx firmware with TRIM support works well, unless you put your system to sleep. Then there’s a chance you might lose your data. Woops. There’s also the problem with Intel’s Matrix Storage Manager not passing TRIM to your drives. All of this will get fixed before the end of the year, but it’s just a bit too early to get TRIM happy.

What we get today is the first stage of migrating the way we test. In order to simulate a real user environment I take a freshly secure erased drive, install Windows 7 x64 on it (no cloning, full install this time), then install drivers/apps, then fill the remaining space on the drive and delete it. This fills the drive with invalid data that the drive must keep track of and juggle, much like what you'd see by simply using your system.

I’m using the latest IMSM driver so TRIM doesn’t get passed to the drives; I’m such a jerk to these poor SSDs.

I’ll start look at both new and used performance on the coming pages. Once TRIM gets here in full force I’ll just start using it and we won't have to worry about looking at new vs. used performance.

The Test

CPU Intel Core i7 965 running at 3.2GHz (Turbo & EIST Disabled)
Motherboard: Intel DX58SO (Intel X58)
Chipset: Intel X58
Chipset Drivers: Intel 9.1.1.1015 + Intel IMSM 8.9
Memory: Qimonda DDR3-1066 4 x 1GB (7-7-7-20)
Video Card: eVGA GeForce GTX 285
Video Drivers: NVIDIA ForceWare 190.38 64-bit
Desktop Resolution: 1920 x 1200
OS: Windows 7 x64
Tying it All Together: SSD Performance Degradation Intel's X25-M 34nm vs 50nm: Not as Straight Forward As You'd Think
Comments Locked

295 Comments

View All Comments

  • Anand Lal Shimpi - Monday, August 31, 2009 - link

    The tables the drive needs to operate are also stored in a small amount of flash on the drive. The start of the circular logic happens in firmware which points to the initial flash locations, which then tells the controller how to map LBAs to flash pages.

    Take care,
    Anand
  • Bakkone - Monday, August 31, 2009 - link

    Any gossip about the new SATA?
  • Zaitsev - Monday, August 31, 2009 - link

    Thanks for the great article, Anand! It's been quite entertaining thus far.
  • cosmotic - Monday, August 31, 2009 - link

    The page about sizes (GB, GiB, spare areas, etc) is very confusing. It sounds very much like you are confusing the 'missing' space when converting from GB to GiB with the space the drive is using for its spare area.

    Is it the case that the drive has 80GiB internally, uses 5.5GiB for spare, and reports it's size as 80GB to the OS leaving the OS to say 74.5GiB as usable?
  • Anand Lal Shimpi - Monday, August 31, 2009 - link

    I tried to keep it simply by not introducing the Gibibyte but I see that I failed there :)

    You are correct, the drive has 80GiB internally, uses 5.5GiB for spare and reports that it has 156,301,488 sectors (or 74.5GiB) of user addressable space.

    Take care,
    Anand
  • sprockkets - Tuesday, September 1, 2009 - link

    Weird. So what you are saying is, the drive has 80Gib capacity, but then reports it has 80GB to the OS, advertised as having an 80GB capacity, which the OS then says the capacity is 74.5GiB?
  • sprockkets - Tuesday, September 1, 2009 - link

    As a quick followup, this whole SI vs binary thing needs to be clarified using the proper terms, as people like Microsoft and others have been saying GB when it really is GiB (or was the GiB term invented later?)

    For those who want a quick way to convert:

    http://converter.50webs.com">http://converter.50webs.com
  • ilkhan - Monday, August 31, 2009 - link

    so they are artifically bringing the capacity down, because the drive has the full advertised capacity and is getting the "normal" real capacity. :argh:
  • Vozer - Monday, August 31, 2009 - link

    I tried looking for the answer, but haven't found it anywhere so here it is: There are 10 flash memory blocks on both Intel 160GB and 80GB X25-M G2, right? (and 20 blocks with the G1).

    So, is the 80GB version actually a 160GB with some bad blocks or do they actually produce two different kind of flash memory block to use on their drives?
  • Anand Lal Shimpi - Monday, August 31, 2009 - link

    While I haven't cracked open the 80GB G2 I have here, I don't believe the drives are binned for capacity. The 80GB model should have 10 x 8GB NAND flash devices on it, while the 160GB model should have 10 x 16GB NAND flash devices.

    Take care,
    Ananad

Log in

Don't have an account? Sign up now