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.

Iometer - 4KB Random Write, 8GB LBA Space, QD=3

Peak performance on the 120GB Vertex 3 is just as impressive as the 240GB pre-production sample as well as the m4 we just tested. Write incompressible data and you'll see the downside to having fewer active die, the 120GB drive now delivers 84% of the performance of the 240GB drive. In 3Gbps mode the 240 and 120GB drives are identical.

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:

Iometer - 4KB Random Write, 8GB LBA Space, QD=32

At high queue depths the gap between the 120 and 240GB Vertex 3s grows a little bit when we're looking at incompressible data.

Iometer - 4KB Random Read, QD=3

Random read performance is what suffered the most with the transition from 240GB to 120GB. The 120GB Vertex 3 is slower than the 120GB Corsair Force F120 (SF-1200, similar to the Vertex 2) in our random read test. The Vertex 3 is actually about the same speed as the old Indilinx based Nova V128 here. I'm curious to see how this plays out in our real world tests.

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.

Iometer - 128KB Sequential Write

Highly compressible sequential write speed is identical to the 240GB drive, but use incompressible data and the picture changes dramatically. The 120GB has far fewer NAND die to write to in parallel and in this case manages 76% of the performance of the 240GB drive.

Iometer - 128KB Sequential Read

Sequential read speed is also lower than the 240GB drive. Compared to the SF-1200 drives there's still a big improvement as long as you've got a 6Gbps controller.

The Vertex 3 120GB AnandTech Storage Bench 2011
POST A COMMENT

154 Comments

View All Comments

  • daidaloss - Thursday, April 14, 2011 - link

    @faster
    I second your petition to Anand to put the Revo2 on the charts, so us, real power user, would have an idea how do SSDs compare with PCI raid cards.

    Also, sure would be interesting to see how do SSD compare to ram drives like the HyperDrive5. Supposedly this thing boots up in 4 seconds. Should be interesting to compare such a system with a modern SSD.
    Reply
  • soltys - Thursday, April 14, 2011 - link

    Looking at past few articles, I was wondering - what exactly do SSDs do, that random writes are significantly faster than random reads (and looking at the tables above, 2x - 3x faster) ?

    Even considering magic firmware + spare space + caching - sooner or later R-E-M-W will have to be performed. And random patterns, with random data should emphasize that.

    Any insights or pointers ?
    Reply
  • Norrin - Friday, April 15, 2011 - link

    Hi Anand,

    I have the vertex 3 installed in a 2011 macbook pro.
    I'm having a horrible problem where the OS locks up for about 10 seconds every 30 minutes or so.

    What was the problem that cause OCZ to delay their March 3rd launch day??

    What changes were made (firmware version numbers)? How can the firmware on a vertex 3 be checked and where can the latest version be downloaded and installed?

    I suspect the problem I'm seeing is the same which delayed their launch. Maybe they have a firmware update available now which can be installed in the disk I currently have....

    Thanks so much!
    Reply
  • jammmet - Tuesday, April 19, 2011 - link

    I am experiencing exactly the same issue - did you find a workaround? Also, do you also have a spinning HD in your machine too? Reply
  • typofonic - Monday, April 18, 2011 - link

    Wouldn't a Vertex 3 120 GB be a really bad choice for a boot drive when it has such a low random read performance, compared to the older Force F120/Vertex, even if I have a new SATA3 MacBook Pro?

    I can imagine that launching applications, booting the system etc. would be much slower with this compared to a Vertex 2/Corsair Force F120. Yes, the sequential performance is much better, but wouldn't the older drives seem snappier in normal everyday use?

    Even if the Vertex 3 120GB cost the same as a Vertex 2/Force F120, wouldn't the older drives still be a much better choice for normal use, because of their high random read/write? Can't decide if I should go for the Vertex 3 or the Force F120/Vertex 2.

    Anybody who knows more about this?
    Reply
  • rgbxyz - Wednesday, April 20, 2011 - link

    I own a 120 GB Vertex. I've been thinking about adding another one. However, it will not be an OCZ. With the word coming, that it seems. and I stress, seems, that OCZ can not once again be trusted. And this time around it's an even bigger issue.

    From the just released report: "OCZ has parlayed investor and market excitement for solid state drives (SSDs) into an amazing story. From a low of $1.79 last summer, OCZ's stock has steadily climbed more than 350% on a feel good tale told by its CEO. But there is a much darker and sinister side that has been well hidden. It is our opinion that OCZ has misrepresented its SSD growth and has financial irregularities that are nearly impossible to reconcile. We believe that some form of a restatement may be required and that the auditors tick and tie review has some substantial inconsistencies. As such, we have sent our findings to the Securities and Exchange Commission asking for clarification on the multiple sets of numbers that we have uncovered. We believe OCZ's Board has the fiduciary responsibility to form a special committee to examine these discrepancies." The bottom line for those curious where this short-seller sees the stock: "If OCZ trades in-line with the comp group, a generous assumption given OCZ's limited asset value, differentiation, and minimal profitability, a reasonable price target would be between $2.58 and $4.98 per share."

    http://www.scribd.com/doc/53435574/OCZ-The-Master-...
    Reply
  • la taupe - Friday, April 22, 2011 - link

    http://www.scribd.com/doc/53435574/OCZ-The-Master-... Reply
  • geroj - Saturday, April 23, 2011 - link

    it would be interesting to see if 2 120gb ssd-s in raid0 would be better choice over a 240gb vertex3 or intel 510 (performance and costwise).

    im thinking of putting 2x120gb crucial c300 in raid0, it would cost 2/3rd of a 240gb vertex3 but a thorough test would be nice before deciding.

    2x64gb in raid0 is also enough for me (and as i see for a lot of us) but what about the performance?
    Reply
  • ekerazha - Wednesday, April 27, 2011 - link

    New "Vertex 3 Max IOPS" series released.

    120 GB
    Read IOPS: 20.000 -> 35.000
    Write IOPS: 60.000 -> 75.000

    240 GB
    Read IOPS: 40.000 -> 55.000
    Write IOPS: 60.000 -> 65.000
    Max Write: 520 MB/s -> 500 MB/s (decrease)
    Reply
  • sor - Friday, April 29, 2011 - link

    Yeah, what the hell is this all about? Anand mentioned in his review that there was supposed to be some sort of firmware cap on iops according to sandforce, but that his test vertex3 didn't have it, and that OCZ promised that performance of the shipping drive would be identical. Turns out apparently that they had TWO versions they were going to ship, and everyone was apparently led to believe that the test review one was the same performer that everyone has been jumping on as fast as they can ship. I think we've been duped. Reply

Log in

Don't have an account? Sign up now