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, as drives can run out of spare area and have to start performing garbage collection as well as 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

The X400's steady-state write performance is unimpressive but typical for planar TLC drives.

Steady-State 4KB Random Write Consistency

The consistency score of the X400 is good but not great, and it is again close to the OCZ Trion 150.

IOPS over time
Default
25% Over-Provisioning

The X400 does not display an initial burst of extreme performance and instead wobbles around 20k IOPS before dropping down to steady state. The X400 does not exhibit severe stalling at any stage of the test, whereas the previously reviewed Trion 150 handles the transition to steady state poorly.

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

In steady-state the X400's performance is not tightly regulated but doesn't have any outliers of significantly below-average performance. Extra overprovisioning does little to improve the worst-case performance but greatly increases the average and best-case write performance.

Introduction AnandTech Storage Bench - The Destroyer
Comments Locked

41 Comments

View All Comments

  • Margalus - Friday, May 6, 2016 - link

    It uses less power than some, and is priced lower. But it seems performance is severely lacking..
  • jabber - Friday, May 6, 2016 - link

    This just shows what a fantastic budget SSD the BX100 was. Crucial were stupid to dump it.
  • Mixal11 - Sunday, May 8, 2016 - link

    Exactly, for me it's v300 for low end desktop, BX100 for laptops (hard to get over time) and Sandisk Extreme Pro or 850 Pro for high end. I avoid TLC, because of experience with Dell Samsung 841oem. Who knows if I can read data from it after year or two. TLC drives are great to reduce ssd prices.
  • jabber - Sunday, May 8, 2016 - link

    Yeah everyone moaned about the V300's back in the day but they are perfect SSDs for putting in SATA II kit as they push 285+MBps all day long...plus they are the cheapest you can buy usually. Also I have bought dozens of them and not one has yet failed. They are a solid tough little SSD. I shall be sorry when they go.
  • jhh - Friday, May 6, 2016 - link

    I wonder if they have included any of the increased endurance technology from their Smart Storage (formerly part of Smart Modular) acquisition. The idea behind the technology was that most cells didn't need full current to program, and when programmed with less than full current, that the cell would allow more write/erase cycles.
  • Michael Bay - Friday, May 6, 2016 - link

    Goddamn it, one more terabyte.
    Just one.
  • Samus - Friday, May 6, 2016 - link

    I think if I were shopping for a TLC drive I'd stick with Sandisk too. I haven't had any issues with their Ultra II's, although many people have. I have, however, had two ADATA SP550's fail (a 120GB and 240GB) one during a power failure in a laptop (BSOD) which a secure erase recovered usability of the drive, and another within an hour of installation - cloning about 100GB of data to it killed it an no longer detects by BIOS.

    I have 5 or so other SP550's in the field running fine though, but none of them have suffered the "abuse" of the above cases.

    I have dozens of Mushkin drives out there, even ECO2's, all running incredibly well. I have a few ECO3 TLC drives in house about to go out, but I've been avoiding them because the ECO2 is still available.

    On a side note, I still have 840EVO's coming in at least bi-weekly with basically unusable performance. Samsung is hell to deal with for RMA (a stark contrast to, say, OCZ that actually sends you an advanced replacement!) and nothing I can do revives performance in these drives. Secure erase, fill and trim, etc, nothing works. Even after a fresh OS install they read at half the speed they write. It's crazy, slower than a 2.5" hard disk.
  • ladder_to_heaven - Friday, May 6, 2016 - link

    Win 8.1 - STILL? -

    For the love of god WHY?
  • Billy Tallis - Friday, May 6, 2016 - link

    Switching to Windows 10 would require re-testing a lot of drives, monopolizing the testbed for a month. It'll probably happen at some point this year, but I'll need to put together a second system for it (hopefully a Skylake system with working PCIe power management).
  • jabber - Saturday, May 7, 2016 - link

    Yeah no rush, after all 85% of 10's code is...8.1.

Log in

Don't have an account? Sign up now