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

The Intel 600p's steady state random write performance is reasonably fast, especially for a TLC SSD. The 600p is faster than all of the SATA SSDs in this collection. The Intel 750 and Samsung 960s are in an entirely different league, but the OCZ RD400 is only slightly ahead of the 600p.

Steady-State 4KB Random Write Consistency

Despite a decently high average performance, the 600p has a very low consistency score, indicating that even after reaching steady state, the performance varies widely and the average does not tell the whole story.

IOPS over time
25% Over-Provisioning

Very early in the test, the 600p begins showing cyclic drops in performance due to garbage collection. Several minutes into the hour-long test, the drive runs out of spare area and reaches steady state.

Steady-State IOPS over time
25% Over-Provisioning

In its steady state, the 600p spends most of the time tracing out a sawtooth curve of performance that has a reasonable average but is constantly dropping down to very low performance levels. Oddly, there are also brief moments of unhindered performance where the drive spikes to exceptionally high performance of up to 100k IOPS, but these are short and infrequent enough to have little impact on the average performance. It would appear that the 600p occasionally frees up some SLC cache, which then immediately gets used up and kicks off another round of garbage collection.

With extra overprovisioning, the 600p's garbage collection cycles don't drag performance down as far, making the periodicity less obvious.

Introduction AnandTech Storage Bench - The Destroyer


View All Comments

  • Billy Tallis - Tuesday, November 22, 2016 - link

    The old firmware. The testbed has been too busy with PCIe SSDs lately for me to have a chance to put the November MX300 update through its paces. Reply
  • seanmac2 - Wednesday, November 23, 2016 - link

    I would never intentionally buy this product but it bothers me anyway because laptops advertise things like "512 GB PCIe SSD" and I'm left wondering if I'll get this or something sweet like a Samsung 950/951/960. Reply
  • ddriver - Wednesday, November 23, 2016 - link

    You get what you pay for. The 600p will likely go into budget products, which won't be CPU powerhouses which may be limited by the sdd performance. Most applications, even prosumer grade software, shows like 1-2$ improvement from going sata to nvme, and this particular product, although technically nvme is more in the sata ballpark. Reply
  • Flying Aardvark - Friday, November 25, 2016 - link

    That's why Intel products cost more than others. You do get what you pay for. Intel SSDs have the industry's best reliability, which matters most when your drive fails prematurely. Unlikely if using M.2 you'll see any real world difference between the 600P and anything else.
    The true step up is the heavy duty Intel 750 stuff with heatsink and zero throttling concerns under heavy, sustained load.
  • Meteor2 - Wednesday, November 23, 2016 - link

    A suggestion: you could link to the previous reviews of devices the first time you mention them, e.g. the 850 Evo. Would save hunting around for them/encourage more page views a people read those reviews before coming back. Reply
  • Meteor2 - Wednesday, November 23, 2016 - link

    So where's this drive falling down compared to the other NVMe drives? Is it the TLC NAND, the construction of the dies, the controller, or something else? Reply
  • DominionSeraph - Wednesday, November 23, 2016 - link

    "1750MB/s sequential read", and not a single test showing if it could actually reach 1750MB/s sequential read in any real life tasks.
    Great job there.
  • beginner99 - Wednesday, November 23, 2016 - link

    WTF is this? It's another useless TLC crap drive. Intel, your ruining your reputation and brand with crap like this. I don't see why I should buy this over a MX300 or similar crappy TLC entry level ssd that is even cheaper. Reply
  • Flying Aardvark - Friday, November 25, 2016 - link

    Everything is going to be 3D TLC soon except the truly next-level stuff like the Intel 750. 3D TLC is not planar TLC. Reply
  • creed3020 - Wednesday, November 23, 2016 - link

    Billy, when are these results going to be included in Bench? I was hoping to compare to my Crucial MX100 but cannot find these Intel drives under SSD2015. Reply

Log in

Don't have an account? Sign up now