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

Random read performance remains unchanged but the Vector 150 wasn't supposed to bring any improvements to that anyway.

Desktop Iometer - 4KB Random Write

Random write speeds at queue depth of 3 take a hit, though I'm thinking this might be due to the new smaller process node NAND. When the queue depth is increased to 32, the performance is on-par with the original Vector thanks to parallelism.

Desktop Iometer - 4KB Random Write (QD=32)

 

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

No surprises here either. Sequential performance has remained mostly the same for the last year or so and we won't see another bump until M.2 and other PCIe-based designs get more popular.

Desktop Iometer - 128KB Sequential Write

 

AS-SSD Incompressible Sequential Read/Write 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

Incompressible Sequential Write Performance

 

AnandTech Storage Bench 2013 Performance vs Transfer Size
Comments Locked

59 Comments

View All Comments

  • ssdpro - Thursday, November 7, 2013 - link

    Looks pretty good. I like that it is certified for 50GB/day - much higher than the original which makes me think the nand is better. Price will need to get down to 120 or so though, that 1GB/$1 is critical.
  • Solid State Brain - Thursday, November 7, 2013 - link

    OCZ indeed have managed fooling people that these drives are much better than the old ones.
    Any drive with 3k P/E writes MLC NAND from 128 GB and up, write endurance wise should be able to support at the very least 50 GB of writes per day for 5 years, even taking into account a rather high write amplification of 4.5-5.

    It's all mostly about how much manufacturers are willing to risk cannibalizing their enterprise lineup. I don't think OCZ has much left to lose at this point.
  • Guspaz - Thursday, November 7, 2013 - link

    When a company with a reputation for terrible reliability has their review sample fail, that's a pretty good sign that their reliability is still terrible.
  • romrunning - Thursday, November 7, 2013 - link

    Fool me once, shame on you. Fool me twice... or 3 times... or 4 times...
  • geniekid - Thursday, November 7, 2013 - link

    Fool me once, strike one. Fool me twice, strike...three.
  • Guspaz - Thursday, November 7, 2013 - link

    Sadly, this was the experience of a friend who made the mistake of buying an OCZ drive. It failed, so he RMA'd it. The replacement failed. So he RMA'd that. THAT replacement failed... Eventually he gave up and bought an Intel drive, which... didn't fail.
  • Samus - Friday, November 8, 2013 - link

    My last OCZ drive that failed was RMA'ed and the replacement eBayed. Learned my lesson. That was a few years ago, but at the time, NO other drives were failing in OCZ fashion.

    Kingston SSDNOW, Crucial C300, Intel X25-M/320, Samsung 700-series...they weren't as fast, but they also rarely failed.
  • deeps6x - Friday, November 8, 2013 - link

    Yep, NEVER AGAIN for me.

    Much cheaper EVO looks like the bang for the buck winner still. Every six months there is something significantly better for less cost anyway. Why pay premium prices for such a short amount of time at the 'top'? Buy the best 'bang for the buck' products as much as possible.
  • djscrew - Saturday, November 9, 2013 - link

    my 2nd gen OCZ Revodrive 128 gb has been going strong for 3 yrs
  • Senti - Thursday, November 7, 2013 - link

    Buying OCZ SSD is suicide. Even with impressive hardware it's just not worth the problems. I can tell as the user of quite a premium drive from them: Revodrive 3. No TRIM support, drivers only for Win7 (and not even planned for anything else), horrible boot times (due to its bios insisting on showing some useless information, you can even press Space to reduce this time that proves that it would be easy to improve the situation if the company was willing to improve things as users asked).

Log in

Don't have an account? Sign up now