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

  • leexgx - Friday, June 08, 2012 - link

    use an usa vpn loads of free ones Reply
  • Tujan - Friday, June 08, 2012 - link

    This is yes "nand",. What would be the complexity of simply creating a curcuit board,that fits regular DDR3 ,and places it into the PCI-e slot. Put a battery onto the board,with perhaps a simplified voltage regulator. Then this saves the state of the RAM when the board shuts off. Would be serous situation for such curcuit boards. Ho-hum save the state of the memory,where no change equals,saved state. Strobe etc,. Even the ideal of having RAM on the curcuit board w/o the saving is a serious relationship to performance 'in session' on a computer of course.

    Fail to understand reasons vendors would ask so much for such a PCI-e board. When I see a memory curcuit on a MB for example,a fraction of a whole MB,that would just as well be able to fit onto a removabl PCI-e board. For a PCI slot.
    Reply
  • jabber - Friday, June 08, 2012 - link

    Gigabyte did this about 7 years ago.

    http://www.anandtech.com/show/1742
    Reply
  • jabber - Friday, June 08, 2012 - link

    Just not through the PCI-e slot. Reply
  • Einy0 - Friday, June 08, 2012 - link

    Thanks for the trip down memory lane!!! I used to day dream for hours about how I would use one of those. Reply
  • Stahn Aileron - Friday, June 08, 2012 - link

    In one word: Capacity. Next issue would be power efficieny since you would always be feeding it power in some form (be it main power or battery power. And that battery will only last so long.) The power issue is relative minor point though.

    The other main power would be volatility. RAM drives are only useful when you absolutely, positively need high-speed, low latency read/write performance (like forcing cache to DRAM instead of the storage system.) As soon as you power them off, you lose all the data stored on them. Battery back-up systems can only go so far to retain your data. This type of storage is too risky for permanent data storage. Any loss of power to the RAM equates to losing all your data. Unlike non-volatile systems (HDDs, SSDs), you're not recovering that data either.

    You're not gonna see RAM drive tech in the consumer space unless they can makes non-volatile RAM. Right now, it's mainly an enterprise thing. Even then, with the uptake of 64-bit software during the past decade or so in that market, there's very little need for RAM drives since a 64-bit OS will give you direct access to practically any and all RAM you have installed in a system these days. You don't need a RAM Drive workaround to access more RAM (32-bit OSes have and inherent 4GiB memory space limitation without workarounds.) I can only see RAM drives being used in the consumer/professional space if some software used explicitly required cache/scratch space on a drive. Something like Photoshop scratch space would be better served on a RAM drive, perhaps.

    Past that, it's cost. Just the RAM itself is about $10/GB these days (give or take.) Fully assembled SSDs using a common interface (SATA) are averaging between $1 & $2 per GB.
    Reply
  • Shadowmaster625 - Friday, June 08, 2012 - link

    I have a bricked Sandcrap drive that tells me all that RAISE crap is pretty useless so they may as well just use that NAND for more capacity.

    Hell, they should just advertise it as a 1TB drive. Once it is bricked, who can ever tell the difference?
    Reply
  • DigitalFreak - Friday, June 08, 2012 - link

    U mad bro? Reply
  • Belard - Monday, June 11, 2012 - link

    Sandforce has become the dominate player in the market. If their controllers were pure crap, then intel wouldn't have touched them. Notice how long intel's G2 drives were THE #1 drives to get, not just in performance but in reliability.

    I admit, I'm a bit confused that intel didn't continue to use their own controller in their top in drive (Their 320 series are like a "G3" and perform slightly better but cheaper than the G2s).

    Also, what sandcrap drive did you get? OCZ makes about 4 different versions of any particular size. Even 6 months ago, you can pick up a 120GB OCZ for $95, but also spend $250... the cheap drive had a much higher failure rate, include DOA. Its performance was crap, becoming slower than a HD after a while.

    Was talking with friends who are looking to upgrade soon. They are going over the various drive brands and pricing. I said, "I don't care... intel 320 or 520. Reliability counts. Saving $50 in exchange for BSOD / performance loss / lack of support isn't worth it".

    I don't know about other brands, but OCZ has no tools for their drives, other than a firmware upgrader. That's it. Intel has a tool-kit, it tells you everything about the SSD, optimization, config, diagnostics and more.

    I'm open to buy a drive from someone else, I'm NOT an intel fan. But I want quality over fandom first.
    Reply
  • ImSpartacus - Friday, June 08, 2012 - link

    Knowing this was an SSD review, I assumed Anand wrote it. After I read the intro piece, I was CONVINCED that it was Anand. But lo and behold, when I glanced at the top of the next page, I did not see the name I was expected.

    Bravo, Mr. Vättö, bravo.
    Reply

Log in

Don't have an account? Sign up now