AnandTech Storage Bench - The Destroyer

The Destroyer is an extremely long test replicating the access patterns of very IO-intensive desktop usage. A detailed breakdown can be found in this article. Like real-world usage, the drives do get the occasional break that allows for some background garbage collection and flushing caches, but those idle times are limited to 25ms so that it doesn't take all week to run the test. These AnandTech Storage Bench (ATSB) tests do not involve running the actual applications that generated the workloads, so the scores are relatively insensitive to changes in CPU performance and RAM from our new testbed, but the jump to a newer version of Windows and the newer storage drivers can have an impact.

We quantify performance on this test by reporting the drive's average data throughput, the average latency of the I/O operations, and the total energy used by the drive over the course of the test.

ATSB - The Destroyer (Data Rate)

The Crucial BX300 is tied for second-fastest average data rate on The Destroyer among SATA drives. The BX300's performance falls between the Samsung 850 EVO and 850 PRO, and matches the Intel 545s that uses a newer generation of 3D NAND and a newer SSD controller.

ATSB - The Destroyer (Average Latency)ATSB - The Destroyer (99th Percentile Latency)

The BX300's latency during The Destroyer is best in class, with both average and 99th percentile latencies at the top of the chart.

ATSB - The Destroyer (Average Read Latency)ATSB - The Destroyer (Average Write Latency)

Breaking the average latency score down by read and write operations, we find the BX300 in second place for each subscore, but with a different drive in first place each time: the 850 PRO is what beats the BX300's average read latency, and the Crucial MX200 beats the BX300's average write latency.

ATSB - The Destroyer (99th Percentile Read Latency)ATSB - The Destroyer (99th Percentile Write Latency)

The Crucial BX300 does a great job keeping read latency low throughout the destroyer, with the lowest 99th percentile read latency out of this bunch of drives. By contrast, the 99th percentile write latency only ranks third, behind the Intel 545s and Samsung 850 PRO. The MX300's 99th percentile write latency is moderately worse than the BX300's, but its 99th percentile read latency is almost twice as high.

ATSB - The Destroyer (Power)

The BX300 further improves on the power efficiency of the MX300, but not enough to match the Intel 545s that benefits both from a newer Silicon Motion controller and from newer 64L 3D NAND.

Introduction AnandTech Storage Bench - Heavy
Comments Locked

90 Comments

View All Comments

  • lilmoe - Tuesday, August 29, 2017 - link

    Question. This is provably unlikely, but is binning layers possible?
  • lilmoe - Tuesday, August 29, 2017 - link

    Probably*
  • Billy Tallis - Wednesday, September 6, 2017 - link

    3D NAND is not really built one layer at a time. The first stage of building the memory array is to make a tall stack of alternating materials, and then vertical strings of memory cells are formed through that stack by etching deep but narrow holes and filling them with the remaining components. That high aspect ratio etching step is one of the main limiting factors in scaling layer count. If you push the layer count too far, you end up with memory cells in layers near the top of the stack having significantly different properties from the ones near the bottom of the stack.

    It's relatively unlikely to have an individual layer somewhere in the middle of the stack be dead/defective across that entire layer. It's more common to see an entire vertical column fail, which involves a much smaller number of memory cells.
  • Radio-Zone - Wednesday, August 30, 2017 - link

    Thanks for the information!!!
  • Ej24 - Wednesday, August 30, 2017 - link

    Congratulations Micron you're almost back to where you were 2 years ago in performance with the m550, Mx100 and mx200. I've always been a huge fan of crucial SSD's. Great bang for the buck for MLC drives. But the last year or so it's been hard to keep praising crucial.
  • m16 - Sunday, September 3, 2017 - link

    It's an interesting move, but all in all, due to the shortage, any SATA drive will do for anyone that is looking for a switch to SSD on the desktop, while power might be the top issue for laptops.

    There's the RAM caching on some of their drives which is very good all in all, especially for computers that have AMD CPUs, that can't use Intel's caching technology to speed things up.
  • keta - Wednesday, September 6, 2017 - link

    Over two-and-a-half years ago (January 2015), I bought a 256GB MX100 for $95. That worked out to $0.371/GB, or a little less than what the BX300 is going for today ($0.375).

    I would be willing to pay the same rate if it meant better performance, but using the ATSB Heavy stats in Bench, it seems that my old MX100 outperforms the BX300 in both data rate and latency. Are the 2015 ATSB Heavy stats comparable to the 2017 stats? Is it really the case that SATA SSD price/performance is worse than it was 2.5 years ago?
  • Billy Tallis - Wednesday, September 6, 2017 - link

    The average data rate and latency stats for the ATSB tests should be comparable between the 2015 and 2017 test suites. The workload didn't change, but the OS version and motherboard did. Next month or maybe late this month, I'll pull the MX100 from my gaming machine and put it through the 2017 test suite.
  • keta - Wednesday, September 6, 2017 - link

    Thanks! I'd be super interested in a 'long-view' piece that puts some of the older flagship SSDs (X-25M, Vertex 2, MX100) through the present-day latency/consistency analysis that AT has developed. And maybe throw in that old WD Scorpio as well, not just to see how far we've come from spinning drives, but also to put the differences between SSDs in perspective!
  • Lolimaster - Thursday, August 9, 2018 - link

    And now in Peru you can find the BX300 120GB for $35 xD.

Log in

Don't have an account? Sign up now