Random Read/Write Speed

The four corners of SSD performance are as follows: random read, random write, sequential read and sequential write speed. Random accesses are generally small in size, while sequential accesses tend to be larger and thus we have the four Iometer tests we use in all of our reviews.

Our first test writes 4KB in a completely random pattern over an 8GB space of the drive to simulate the sort of random access that you'd see on an OS drive (even this is more stressful than a normal desktop user would see). I perform three concurrent IOs and run the test for 3 minutes. The results reported are in average MB/s over the entire time. We use both standard pseudo randomly generated data for each write as well as fully random data to show you both the maximum and minimum performance offered by SandForce based drives in these tests. The average performance of SF drives will likely be somewhere in between the two values for each drive you see in the graphs. For an understanding of why this matters, read our original SandForce article.

Desktop Iometer - 4KB Random Read (4K Aligned)

The 60GB drive is nearly enough to saturate the 525's 4KB random read performance. We don't see a ton of scaling here beyond the 60GB capacity.

Desktop Iometer - 4KB Random Write (4K Aligned) - 8GB LBA Space

With easily compressible data, nearly all of the 525 capacities perform alike since very little data is actually being written - we're just effectively updating the indirection table in addition to a small number of NAND writes. Flip the switch and look at incompressible data and you'll see a clear relationship between the number of active die on board and random IO performance. None of these drives are bad by any means, but they don't all perform at the level of the 240GB model.

Many of you have asked for random write performance at higher queue depths. What I have below is our 4KB random write test performed at a queue depth of 32 instead of 3. While the vast majority of desktop usage models experience queue depths of 0 - 5, higher depths are possible in heavy I/O (and multi-user) workloads:

Desktop Iometer - 4KB Random Write (8GB LBA Space QD=32)

There's some scaling with queue depth, but when you're this constrained by the number of die you can write to there's just not that much more parallelism to extract.

Sequential Read/Write Speed

To measure sequential performance I ran a 1 minute long 128KB sequential test over the entire span of the drive at a queue depth of 1. The results reported are in average MB/s over the entire test length.

Desktop Iometer - 128KB Sequential Read (4K Aligned)

Even the smallest 30GB 525 can read at almost 300MB/s in low queue depth sequential workloads, that's very quick. To put that in perspective, the 30GB 525 is 30% faster in sequential reads than Intel's 2nd generation, high-end 160GB SSD. The old Intel SSD 310 also gets a sound beating by the new 525.

Desktop Iometer - 128KB Sequential Write (4K Aligned)

Sequential write performance once again comes down to the natur eof the data you're writing to the drive. Incompressible data, which will likely make up a good portion of what you write sequentially to a decent sized 525 sees performance that's almost directly proportional to capacity. Looking at Intel's performance historically though, only the 30GB model gets really slow here. The 60GB drive is at least as fast as the old X25-M G2, while the 120 and larger capacities deliver downright solid performance.

AS-SSD Incompressible Sequential Performance

The AS-SSD sequential benchmark uses incompressible data for all of its transfers. The result is a pretty big reduction in sequential write speed on SandForce based controllers.

Incompressible Sequential Read Performance - AS-SSD

Incompressible Sequential Write Performance - AS-SSD

The AS-SSD data mimics what we've seen already in IOmeter, although we do get the benefit of seeing what higher queue depths do to incompressible performance on the 525.

Introduction Performance vs. Transfer Size
POST A COMMENT

26 Comments

View All Comments

  • PolarisOrbit - Monday, February 04, 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. Reply
  • Denithor - Monday, February 04, 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.
    Reply
  • AndrewDobie - Monday, February 04, 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
    Reply
  • philipma1957 - Monday, February 04, 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.
    Reply
  • Kristian Vättö - Monday, February 04, 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.
    Reply
  • DanNeely - Monday, February 04, 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. Reply
  • ssj3gohan - Monday, February 04, 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.
    Reply
  • Anand Lal Shimpi - Monday, February 04, 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
    Reply
  • RU482 - Monday, February 04, 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.
    Reply
  • extide - Monday, February 04, 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.
    Reply

Log in

Don't have an account? Sign up now