The SSD Relapse: Understanding and Choosing the Best SSD
by Anand Lal Shimpi on August 30, 2009 12:00 AM EST- Posted in
- Storage
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 |
295 Comments
View All Comments
Anand Lal Shimpi - Monday, August 31, 2009 - link
Intel insists it's not an artificial cap and I tend to believe the source that fed me that information.That being said, if it's not an artificial cap it's either:
1) Designed that way and can't be changed without a new controller
2) A bug and can be fixed with firmware
3) A bug and can't be fixed without a new controller
Or some combination of those items. We'll see :)
Take care,
Anand
Adul - Monday, August 31, 2009 - link
Another fine article anand :). Keep up the good work.CurseTheSky - Monday, August 31, 2009 - link
This is absolutely the best article I've read in a very long time - not just from Anandtech - from anywhere.I've been collecting information and comparing benchmarks / testimonials for over a month, trying to help myself decide between Intel, Indilinx, and Samsung-based drives. While it was easy to see that one of the three trails the pack, it was difficult to decide if the Intel G2 or Indilinx drives were the best bang for the buck.
This article made it all apparent: The Intel G2 drives have better random read / write performance, but worse sequential write performance. Regardless, both drives are perfectly acceptable for every day use, and the real world difference would be hardly noticeable. Now if only the Intel drives would come back in stock, close to MSRP.
Thank you for taking the time to write the article.
deputc26 - Monday, August 31, 2009 - link
been waiting months for this one.therealnickdanger - Monday, August 31, 2009 - link
Ditto! Thanks Anand! Now the big question... Intel G2 or Vertex Turbo? :) It's nice to have options!Hank Scorpion - Monday, August 31, 2009 - link
Anand,YOU ARE A LEGEND!!! go and get some good sleep, thanks for answering and allaying my fears... i appreciate all your hard work!!!!
256GB OCZ Vertex is on the top of my list as soon as a validated Windows 7 TRIM firmware that doesnt need any work by me is organized....
once a firmware is organised then my new machine is born.... MUHAHAHAHAHAHA
AbRASiON - Monday, August 31, 2009 - link
Vertex Turbo is a complete rip off, Anand clearly held back saying it from offending the guy at OCZ.Now the other OCZ models however, could be a different story.
MikeZZZZ - Monday, August 31, 2009 - link
I too love my Vertex. Running these things in RAID0 will blow your mind. I'm just waiting for some affordable enterprise-class drives for our servers.Mike
http://solidstatedrivehome.com">http://solidstatedrivehome.com
JPS - Monday, August 31, 2009 - link
I loved the first draft of the Anthology and this is a great follow-up. I have been running a Vertex in workstation and laptop for months know and continue to be amazed at the difference when I boot up a comparable system still running standard HDDs.gigahertz20 - Monday, August 31, 2009 - link
Another great article from Anand, now where can I get my Intel X-25M G2 :)