Performance vs. Transfer Size

ATTO does a good job of showing us how sequential performance varies with transfer size. Most controllers optimize for commonly seen transfer sizes and neglect the rest. The optimization around 4KB, 8KB and 128KB transfers makes sense given that's what most workloads are bound by, but it's always important to understand how a drive performs across the entire gamut.

In the initial 525 review I compared the SSD to other drives including the 520:

As you can see there's little difference between the 525 and the 520. SandForce also does a good job of performing well across all transfer sizes, which seems to be less common in some of the newer controllers.

ATTO uses easily compressible data so if we toss all of the 525 capacities into the mix we end up with a bunch of curves that nearly overlap one another:

The 30GB model's peak write speed is capped noticeably lower than the rest as it only has a total of four NAND die to stripe across, but the rest are bound by the speed at which the DuraWrite engine can do its job.

Random & Sequential Performance Performance Consistency
Comments Locked

26 Comments

View All Comments

  • PolarisOrbit - Monday, February 4, 2013 - link

    The comparison table on the first page indicates a 90GB drive and then it's never mentioned again in the rest of the article.
  • Denithor - Monday, February 4, 2013 - link

    Addressed in the first paragraph:

    "At the time we only presented performance for a single 240GB drive, however Intel decided to break the mold and send us nearly every capacity in the 525 lineup."

    I would imagine that the 90GB model is the one they didn't provide.
  • AndrewDobie - Monday, February 4, 2013 - link

    Love my job, since I've been bringing in $5600… I sit at home, music playing while I work in front of my new iMac that I got now that I'm making it online.(Click Home information)
    http://goo.gl/nY29F
  • philipma1957 - Monday, February 4, 2013 - link

    first what mobo can I buy that will run at sata III speeds.

    I have 3 mobos with msata's all 3 use sata II speed's.

    I have an intel h77 itx

    an asrock z77 itx

    an asus z77 matx

    second question when will the crucial m500 480gb drop?

    third question which has nothing to do with msata just sata. when does sata IV come out.

    I get a bit bored with ssd reviews since speed is pretty much capped at 550 read write.

    iops are not going to go to 550 read write at random 4k.

    so sata 4 would mean all new speeds to droll over.

    a bigger msata like the crucial m500 would be nice.

    and an itx board that used msata at sata III would be nice.

    not knocking intel but ssd's seem to have become more of the same.

    As Jimmy Fallon would say bigger harder faster stronger.
    oh one last thing the 5 year warranty is nice.
  • Kristian Vättö - Monday, February 4, 2013 - link

    Crucial M500 is Q2'13, that's all we know for now. I'm very interested in the drive as well, hopefully we can get samples soon.

    SATA Express is the future of SATA, we likely won't see SATA IV (12Gbps) for a few years (if we'll ever even see it). We may see some SATAe based SSDs/mobos H2'13 but I haven't heard any specific time frame.
  • DanNeely - Monday, February 4, 2013 - link

    That's disappointing; I was hoping they'd be available by 13Q2 to go along with the Haswell launch since there will be an uptick of enthusiast system building then. Based on prior history my Haswell box will last at least until Skylake launches; and probably until the tick following it four years from now.
  • ssj3gohan - Monday, February 4, 2013 - link

    ... because I just care that much :D

    But seriously, Anandtech. Let's talk logic here. Intel has specification sheets with detailed power consumption numbers. It says for the entire SSD 525 series: 250mW idle typical, 300mW under mobilemark 2007.

    How can you look at your own power consumption numbers and say 'well, close enough, let's just publish it even though it's 100% too high and clearly not correct'?

    Here's how to fix your SSD power consumption errors: measure power consumption going directly into the drive on all rails and use it in a system that has device initiated power management features enabled (DIPM), that is: basically all operating systems nowadays.
  • Anand Lal Shimpi - Monday, February 4, 2013 - link

    As I mentioned in the review, the mSATA adapter we test with only supplies 5V to the drive. To address this going forward I need to modify a board with a native mSATA connector and measure 3.3V on the board itself. The results here at least allow you to compare the various capacities of the 525.

    MobileMark 2007 is mostly an idle test, which is why none of our loaded numbers have ever come close to any spec sheet that reports it. This is the same reason we don't use it in our notebook reviews.

    We will be switching to DIPM-only testing in our 2013 storage suite update, which will unfortunately break backwards comparability with our older results.

    Take care,
    Anand
  • RU482 - Monday, February 4, 2013 - link

    Anand,
    What mSATA adapter board are you using?
    Just a thought, you should be able to lift a lead on the 5-to-3.3V regulator on the board and measure the output current with a multi-meter.
  • extide - Monday, February 4, 2013 - link

    Also note that those mSATA to SATA converters use a little linear regulator(like a 7833) to convert the 5v to 3.3v. Linear regulators are very in-efficient, as they essentially turn the "extra" voltage into heat by using a network of resistors.

    If you are simply measuring the power into the adapter then you are not getting a very good look at the actually mSATA device power draw.

    HOWEVER, if someone else is using the adapter in their system they will also be utilizing that same linear regulator, and thus see the same power usage as they show in the article here.

Log in

Don't have an account? Sign up now