Performance Consistency

Our performance consistency test explores the extent to which a drive can reliably sustain performance during a long-duration random write test. Specifications for consumer drives typically list peak performance numbers only attainable in ideal conditions. The performance in a worst-case scenario can be drastically different as over the course of a long test drives can run out of spare area, have to start performing garbage collection, and sometimes even reach power or thermal limits.

In addition to an overall decline in performance, a long test can show patterns in how performance varies on shorter timescales. Some drives will exhibit very little variance in performance from second to second, while others will show massive drops in performance during each garbage collection cycle but otherwise maintain good performance, and others show constantly wide variance. If a drive periodically slows to hard drive levels of performance, it may feel slow to use even if its overall average performance is very high.

To maximally stress the drive's controller and force it to perform garbage collection and wear leveling, this test conducts 4kB random writes with a queue depth of 32. The drive is filled before the start of the test, and the test duration is one hour. Any spare area will be exhausted early in the test and by the end of the hour even the largest drives with the most overprovisioning will have reached a steady state. We use the last 400 seconds of the test to score the drive both on steady-state average writes per second and on its performance divided by the standard deviation.

Steady-State 4KB Random Write Performance

No consumer SATA drive sustains better random write IOPS than the Vector 180, while the VX500 is slower than most MLC drives.

Steady-State 4KB Random Write Consistency

The Barefoot 3 controller wasn't great for consistency in spite of its high overall performance, so the Vector 180 and VX500 end up with relatively similar scores, and both have lots of room for improvement.

IOPS over time
Default
25% Over-Provisioning

The VX500 goes through two distinct performance phases before reaching steady-state. During those early phases it maintains relatively good minimum performance, in stark contrast to the severe stuttering the Vector 180 showed throughout this test, especially for the larger capacities.

With extra manual overprovisioning, the VX500 goes through several more phase transitions but always maintains decent performance.

Steady-State IOPS over time
Default
25% Over-Provisioning

The steady state write performance of the VX500 is confined mostly to a band around 3k-5k IOPS with frequent outliers up to about twice that speed. With extra overprovisioning, the steady state is clearly better than that of the Phison-based PNY CS2211 but not as fast or consistent as the flagship MLC drives from Samsung and SanDisk.

Introduction AnandTech Storage Bench - The Destroyer
Comments Locked

29 Comments

View All Comments

  • Chaitanya - Tuesday, September 13, 2016 - link

    How is the after sales service of these drives since Toshiba take over? I have heard some horror stories of RMA with OCZ in past.
  • JebSpringfield - Tuesday, September 13, 2016 - link

    I bought one OCZ drive a year after Toshiba took over. The SSD failed after one month, and they replaced it with a better model (I had to pay for the shipping), after another month or so, the new drive also failed. I contacted them again but this time I said I was not going to pay for shipping. They agreed, and sent me their top of the line model which has 5 year warranty and it's been working fine (knock on wood) for a bit longer than a year.

    Sorry but I don't remember the models.
  • Meegul - Tuesday, September 13, 2016 - link

    While that doesn't speak to the quality of the drives, at least the customer service stepped up. The old OCZ days were just fraught with stories about the customer service affectively being MIA.
  • StevoLincolnite - Tuesday, September 13, 2016 - link

    ...I'm still running a 64Gb OCZ Vertex 2 from 6-7 years ago... I WANT IT TO DIE SO I CAN UPGRADE.
  • gammaray - Wednesday, September 14, 2016 - link

    both my ocz vertex III and Agility III are still running fine lol. Meanwhile i bought an assorted battery of other SSDs, Main rig running Sandisk Extreme Pro.
  • creed3020 - Wednesday, September 14, 2016 - link

    Likewise! I have that same drive as my boot drive for my HTPC. Its definitely slower than it once was but thankfully it keeps on chugging. My next gen HTPC will include a newer, bigger boot drive. Not sure what will happen to the SATA II drive when I rebuild...
  • Bullwinkle J Moose - Monday, October 3, 2016 - link

    A Vertex 2 is Super Easy to Kill
    Just follow OCZ recommendations on upgrading the firmware
    (NO, I am NOT joking)
    B.T.W.,
    Anandtech really needs to update their testing procedure for SSD's
    The original Vertex could copy and paste a 2GB file (to and from the same drive) at a blistering rate of 3.6 - 3.7 MB/sec
    A Samsung 840 Pro can copy/paste the same file at 56.8 MB/sec
    A Samsung 850 Pro can copy/paste the same file at 113.7 MB/sec
    YES, AN 850 PRO IS TWICE AS FAST AS AN 840 PRO!
    Disclaimer:
    ALL tests made with XP-SP2 on SATA2 Ports using IDE protocol
    Your results will vary depending on O.S. / Port Type and Protocol
    Hardware and O.S. were kept identical to that used when testing the Vertex 1 & 2 which are no longer available for testing on newer hardware
  • ocztaec - Thursday, September 15, 2016 - link

    Hi JebSpringfield,
    As this is my first post on this article please allow me to identify myself as a Toshiba America Electronic Components (TAEC) representative. Thank you for your comment and great to hear the current replacement drive is working well for you. We greatly appreciate both your business and support.
  • fanofanand - Wednesday, September 14, 2016 - link

    I won't be taking the risk. They refused to honor their warranty when my OCZ DDR2 sticks failed. Lifetime warranty my azz.....
  • ocztaec - Thursday, September 15, 2016 - link

    Hi fanofanand,
    Thank you for your comment and your business. I'm sorry to hear that you had issues in the past. We understand how you feel and hope that one day we will have the opportunity to demonstrate the reliability of our current Toshiba products. Thanks again for your feedback.

Log in

Don't have an account? Sign up now