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

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

Iometer - 4KB Random Read, QD=3

Faster than a Vertex 3 Pro & The Test Sequential Read/Write Speed
POST A COMMENT

85 Comments

View All Comments

  • Figaro56 - Tuesday, March 01, 2011 - link

    Excuse me, but I'm confused. Why would a person rather get a refurb? For the warranty?

    What do you think a refurb part is any way? It's someone's used part that is not only used, but it also had a mfg defect. Are you kidding me?!
    Reply
  • Figaro56 - Tuesday, March 01, 2011 - link

    If you think a refurb in some way has more value go for it. I have never had a problem buying used from someone, just stay away from bad used parts venues like Ebay or Craigslist. Reply
  • Figaro56 - Tuesday, March 01, 2011 - link

    I got my C300 256GB as an early adopter when they finally fixed their infamous firmware issue. That's cost you pay for being an "early adopter enthusiast." Reply
  • zebrax2 - Thursday, February 24, 2011 - link

    Games i believe are sequential in nature Reply
  • sticks435 - Thursday, February 24, 2011 - link

    This is correct. They are sequential reads. I really wish they Anand would have shown the PC Vantage gaming scores. Hopefully the full review will them them, along with the test bench 2010 on the Sandy bridge platform, since the new bench is only 2 workloads and gaming is a very specific type of workload. Reply
  • B3an - Friday, February 25, 2011 - link

    I'd also like to see more real world and basic tests. Normal everyday things. As mentioned, Win7 start times, Photoshop tests, game loading times and so on... Reply
  • Figaro56 - Friday, February 25, 2011 - link

    I own a Crucial RealSSD C300 256GB myself. After reading this review I have come to the same conclusion. Yes there is a margin of performance improvement with the Vertex 3, but not so great as to make you crazy enough to sell your C300 for $100 and jump on the OCZ Vertex 3 test group. I would wait awhile to see how this Vertex 3 with it's questionable new 25nm NAND holds up in the real world. I was never a fan of their new idea of data compression from the get go either. I still view this as a grand experiment at our expense. It's smart to stick with what works even if next month it will be come 2nd best. Reply
  • Figaro56 - Friday, February 25, 2011 - link

    See my post below dated Friday, February 25, 2011, it was intended as a reply to your post. I don't know why it didn't stack in here as a reply. Reply
  • Figaro56 - Friday, February 25, 2011 - link

    RE: What about load times? by Figaro56 on Friday, February 25, 2011
    I own a Crucial RealSSD C300 256GB myself. After reading this review I have come to the same conclusion. Yes there is a margin of performance improvement with the Vertex 3, but not so great as to make you crazy enough to sell your C300 for $100 and jump on the OCZ Vertex 3 test group. I would wait awhile to see how this Vertex 3 with it's questionable new 25nm NAND holds up in the real world. I was never a fan of their new idea of data compression from the get go either. I still view this as a grand experiment at our expense. It's smart to stick with what works even if next month it will be come 2nd best.
    Reply
  • jimhsu - Friday, February 25, 2011 - link

    Actually with the whole OCZ mess, questionable firmware policies, and completely unknown lifespan or reliability, I'm not sure I even want to buy the Vertex 3 at half its current price, despite the performance figures here. In this case I think the C300 is actually worth more -- at least the drive has been mostly debugged and the firmware vetted, unlike this. Reply

Log in

Don't have an account? Sign up now