Write Performance Isn’t Safe Either

Testing read performance is the easiest since I just fill the SSD with data once and can read off it multiple times. To achieve repeatable write performance however I have to secure erase the drive between each test. Not impossible, but annoying given that only certain motherboards allow me to drop the SATA ports into legacy mode which is necessary for the DOS based secure erase application to work. For that reason I’m only providing a small subset of my testbeds here to prove that write speed is also impacted:

Here the results are even more frustrating. Paired with a PCIe 1.0 slot, random write speed is virtually cut in half. The frustration comes from the fact that Intel’s native 3Gbps controller is faster than almost anything else here.

I say almost because we do have one exception. AMD’s 890GX delivers a staggering 180MB/s in random write performance, a full 31% faster than Intel’s X58. The random write speed makes me believe that with a bit of driver and/or BIOS work we can get random read performance up there as well.

Performance in the Real World

These differences are visible in the real world as well. I took four systems and copied a 10GB file from the C300 to itself and measured average write speed:

The real takeaway here is that sticking a 6Gbps controller behind a PCIe 1.0 slot wreaks havoc on performance.

Random Read Performance is Also Affected Final Words
Comments Locked

57 Comments

View All Comments

  • assassin37 - Thursday, March 25, 2010 - link

    why isnt the x-58 gigabyte native 6gbs board on the write benchmarks?
  • blacksun1234 - Thursday, March 25, 2010 - link

    I would like to see HD Tune & HD Tach Average Read speed with Crucial HDD for each chipset. With this benchmark, AMD SB850 can beat Marvell's solution a lot!
  • Nickel020 - Thursday, March 25, 2010 - link

    There's a small error on page 4, that's an X58A-UD3R you've got there, not an X58-UD3R.

    Also, there seem to be two different Marvell 6G controllers, the 88SE9123 and the 88SE9128, what's difference between these two?
  • Nickel020 - Thursday, March 25, 2010 - link

    Finished reading, very interesteing results :)

    I find it really strange that P55 performs so poorly, I wonder whether it also performs poorly when used with SATA 3G SSDs, seeing as I'm just about two migrate my Vertex 60GB RAID 0 from P45&ICH10R to P55.
    Would be great if you could look into that as well, better storage performance would be a major reason to buy S1366 instead of S1156.
  • Etern205 - Thursday, March 25, 2010 - link

    If it's possible, mind adding the Asus U3S6 to your test (in a updated article) since that card uses a PCIe x4 interface.
    Thank You! :)

    The card
    http://www.newegg.com/Product/Product.aspx?Item=N8...">http://www.newegg.com/Product/Product.a...&cm_...
  • nerdtalker - Thursday, March 25, 2010 - link

    That's an interesting card, since it appears from the photo to incorporate the 4x PCIe 1.0 PLX controller, or essentially the same on-motherboard solution ASUS was using.

    That seems like a much more interesting card to test.
  • 7Enigma - Thursday, March 25, 2010 - link

    Hi Anand,

    I have to admit that this particular article was a bit confusing for me. Probably because the test rigs are so similar in name I was going back and forth. My question is how does this article's results correlate to earlier boards (P45 for me in particular)? Am I understanding things correctly to assume that sticking a 6Gbps SATA card would actually be detrimental to performance in my rig if I was to get a new SSD in the coming months?

    Thanks for the informative article.
  • semo - Thursday, March 25, 2010 - link

    Hi Anand,

    On the 1st page, were you comparing Vertex LE performance on 890GX vs X58 or H55? And also do you have any comments on why it's random read is slower than the random write. AFAIK this is the only SSD with such characteristics.

    Thanks
  • Casper42 - Thursday, March 25, 2010 - link

    I noticed the same. Text says compared to X58 but both charts on page 1 say H55.
  • Exodite - Thursday, March 25, 2010 - link

    With the Thuban hexa-cores and 890X/FX boards in the pipeline AMD looks better and better for my next rig. After building a 790FX/PII 965BE rig for a friend, however, I were worried by the obviously poor disk performance even in comparison to my old P35/E6600 setup with an older HDD.

    I appreciate being kept up to date with this development as I see disk performance as the only major drawback of the platform at this point.

Log in

Don't have an account? Sign up now