Performance Over Time and TRIM

Usually we use HD Tach to test TRIM performance but since SandForce drives do real-time compression, using HD Tach and compressible data would not give us a good idea of worst case performance. Instead, I filled the drive with incompressible data and proceeded to hammer it with incompressible 4KB random writes (QD32) for 60 minutes. Then I ran AS-SSD which uses incompressible data as well to see how the SX900 performs in worst case state. Finally I TRIMed the drive and ran AS-SSD again to test whether TRIM recovers the performance.

ADATA XPG SX900 - Resiliency - AS SSD Sequential Write Speed - 6Gbps
  Clean After Torture After TRIM
ADATA XPG SX900 128GB 175.4MB/s 35.4MB/s 146.8MB/s
ADATA S511 120GB 160.8MB/s 96.4MB/s 98.8MB/s

There is quite a big difference between the two ADATA drives when it comes to TRIM and post-torture performance. The S511 performs much better after torture but TRIM is not very effective. The SX900, on the other hand, is the complete opposite. Its performance is poor after torture but a single TRIM pass will almost restore the performance back to clean state, as after TRIM the performance is back to 84% of clean performance. The S511 is definitely an odd case because for example OCZ Vertex 3 behaves similarly with the SX900. However, the important part is that TRIM is able to restore the performance, which is what matters. Firmware is the apparent culprit once again, and it's unfortunate that the S511 hasn't been updated in quite some time.

Again, what I would like to emphasize that our torture scenario is an extreme case. In the real world, it's impossible to create a such scenario if you are using the SSD as a boot drive. That's because you will at least have Windows or some other easily compressible OS on the drive. Even if the drive was used as a storage drive, it's still fairly unlikely that you would fill it with incompressible data only, and what's more it is highly unlikely that a majority of your writes would be random in nature.

AnandTech Storage Bench 2011 - Light Workload Power Consumption
POST A COMMENT

58 Comments

View All Comments

  • vol7ron - Friday, June 08, 2012 - link

    If you're going to put Mushkin up there, you might as well put OWC there too. Their drives seem to perform fairly well and are priced "decent" Reply
  • Kristian Vättö - Friday, June 08, 2012 - link

    I only put Mushkin there because many have been asking for that since it appears to be one of the cheapest brands. OWC is not cheap, in fact even Vertex 3 is cheaper except the 480GB model. The table is endless if I start putting every brand there, plus checking the prices is PITA and already takes a decent amount of time. Reply
  • StevoLincolnite - Friday, June 08, 2012 - link

    Plus... Only 4.52% of the worlds population resides in the USA, so the prices are pretty much useless for the 95.48% of the Earths population that doesn't reside in the US. Reply
  • StevoLincolnite - Friday, June 08, 2012 - link

    To add to that, I don't mean to belittle your efforts, I just don't bother to look at the pricing on this site. Reply
  • jak3676 - Friday, June 08, 2012 - link

    % of world population is hardly a useful stat to toss out there - you could make a decent argument with % of SSD's sold by country/region, but lets face it 99.99% of the world population (to include the US) isn't buying SSDs.

    If he listed prices in Euro or CAD or Yen or anything else he'd just be favoring that market (which is probably smaller than the US market anyway). Even if he could list prices available by country for the top 10 markets, he'd just turn off all of us as people wouldn't want to scroll through 10x the number of charts.
    Reply
  • nathanddrews - Friday, June 08, 2012 - link

    4.52% of the world's population, but 22% of the world's GDP. That's why US prices matter. Reply
  • JarredWalton - Friday, June 08, 2012 - link

    And let's not forget that our site's primary readership *is* in the USA. I'm not sure of the breakdown, but I'd guess close to half of all our traffic is US based. Even if it's only 1/3 (Kristian for example is based in Finland), I doubt there's any other currency where our listing SSD prices in that denomination would prove more useful to our readers. Reply
  • Jaybus - Friday, June 08, 2012 - link

    Yes, but some two thirds of international trades are in US dollars and it is still the de facto exchange currency.

    Anyway, what difference does it make? The point is relative prices between drives from different manufacturers. I don't think the ratios would change for different currencies.
    Reply
  • djboxbaba - Saturday, June 09, 2012 - link

    You realize this is a US based website right? and that the majority of the readership is based in the US?

    Go to a website that caters to your country's currency if this is a problem for you.
    Reply
  • lyeoh - Tuesday, June 12, 2012 - link

    Useless? Speak for yourself, some of us in the 95.48% know how to do currency conversion.

    Are you also going to claim the USD prices of oil, gold, silver, CPUs, DRAMs, etc are useless to the rest of the world?

    There's plenty of stuff in the world that are priced in US dollars - as in the manufacturer's/producer's main selling price for the item is in US dollars. And the price in other countries is linked to that USD price. When the USD price goes up, their prices go up too.

    If the petrodollar loses its hold (its slipping a bit) then it might make sense to use some other currency. That'll be bad for the USA as the US Gov will no longer be able "tax" other countries just by creating more US dollars.
    Reply

Log in

Don't have an account? Sign up now