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 average data rate of the Plextor M9Pe on The Destroyer is a clear step forward from Plextor's previous TLC-base NVMe SSD (the M8Se), but there are plenty of other recent TLC-based drives that perform much better, and the M8Pe with planar MLC is still faster than the M9Pe.

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

The average latency of the 512GB M9Pe matches that of the Intel SSD 760p, but without a 1TB 760p to compare against the 1TB M9Pe's average latency looks quite poor. The 99th percentile latencies of both M9Pe capacities are also worse than they should be, but don't stand out quite as much from the relevant competition.

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

The average write latency scores from the M9Pe rank a bit better than the average read latency scores, but in both cases the M9Pe is clearly slower than the top tier drives from Samsung and Western Digital.

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

The 99th percentile read and write latency scores from the M9Pe are an improvement over the planar TLC-based M8Se, but the scores still aren't great. The 512GB model has trouble staying ahead of the Crucial MX500 and MyDigitalSSD SBX.

ATSB - The Destroyer (Power)

Energy consumption from the M9Pe during The Destroyer is on the high side, but not as bad as the M8Se was. The Samsung 970 EVO's energy consumption is also a bit higher than the M9Pe. The WD Black impresses the most, with higher performance than the Samsung drives while using half the energy.

Introduction AnandTech Storage Bench - Heavy
POST A COMMENT

16 Comments

View All Comments

  • Yuriman - Thursday, May 24, 2018 - link

    Looks like that heatspreader does it a lot of good. Reply
  • peevee - Tuesday, May 29, 2018 - link

    But the price of it? I understand it for $4 on 256GB model. But why the same thing is closer to $40 on 1T? Reply
  • romrunning - Thursday, May 24, 2018 - link

    Regarding the testing platform: "The Windows 10 version will still be 1709, because Microsoft has not yet fixed all the new bugs introduced in the NVMe driver in Windows 10 version 1803."

    If you're referring to the issues with Intel 600p drives in the April Update (version 1803), Microsoft released a new patch (KB4100403) that "Addresses an issue with power regression on systems with NVMe devices from certain vendors."

    So it sounds like you should be able to update Windows to 1803 as long as you include that patch.
    Reply
  • Billy Tallis - Thursday, May 24, 2018 - link

    That's not the only problem that's been reported with 1803's NVMe driver. I don't trust that they've even found all the new bugs yet, let alone patched them all. And I actually started running the new tests almost a month ago, to try to minimize the interruption to our review schedule. Reply
  • Drazick - Thursday, May 24, 2018 - link

    Are you sure it is Microsoft's issue and not the firmware of those drives? Reply
  • Billy Tallis - Thursday, May 24, 2018 - link

    In the absence of a proper changelog from Microsoft, I assume the new issues are mostly their fault. At the very least, they're responsible for upsetting whatever fragile balance of bugs the SSD manufacturers have achieved by testing against previous versions of Windows 10. I want to freeze my testbed software configuration for at least a year, and there's sufficient reason to consider 1803 as still being essentially beta-quality and thus a bad choice for the 2018 SSD test suite. Reply
  • GeorgeH - Thursday, May 24, 2018 - link

    FWIW that's very reasonable. It's utterly foolish to update to any Windows 10 version until at least 6 months after release (unless your time is worthless and you'd like to do free QA for Microsoft, of course). Reply
  • lmcd - Thursday, May 24, 2018 - link

    Not even close to true. In fact, it's because I value my time that I upgraded to 1803 immediately. 1803 adds the "Windows Hypervisor Platform" to its features, which (as a primary effect) allows Docker for Windows and a buggy-but-usable Xamarin variant of AVD to run side-by-side (along with other Hyper-V images). It's possible we even see VirtualBox run on this excellent feature, though I don't know if it's on their roadmap yet. Reply
  • smilingcrow - Friday, May 25, 2018 - link

    Which is an irrelevant feature for most home users so your post is myopic. Reply
  • Death666Angel - Friday, May 25, 2018 - link

    If you are running normal consumer grade hardware, I don't think that is the case. Reply

Log in

Don't have an account? Sign up now