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 from the new WD Black on The Destroyer is almost as fast as Samsung's TLC-based 960 EVO and their newer PM981 OEM drive. Where the original WD Black NVMe SSD was clearly a low-end NVMe drive and no faster than SATA SSDs on this test, the new WD Black is competitive at the high end.

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

The average latencies from the WD Black are competitive with Samsung's TLC drives, and the 99th percentile latencies are the fastest we've seen from any flash-based SSD for this capacity class.

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

The average read latencies from the WD Black on The Destroyer are as good as any flash-based SSD we've tested. Average write latencies are great but Samsung's top drives are still clearly faster.

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

The WD Black has the best 99th percentile read latency scores aside from Intel's Optane SSD 900P, but the 99th percentile write latency scores are only in the second tier of drives.

ATSB - The Destroyer (Power)

The load power consumption of the new WD Black is a huge improvement over the previous SSD to bear this name. The new model uses less than half as much energy over the course of The Destroyer, putting it in first place slightly ahead of the Toshiba XG5.

The Western Digital NVMe Architecture - NAND & Controller AnandTech Storage Bench - Heavy
POST A COMMENT

70 Comments

View All Comments

  • JWKauffman - Friday, April 6, 2018 - link

    I understand that, but if I were WD and positioning these drives as Samsung competitors, I'd want to have a driver tailored to my controller the same as Samsung does. Reply
  • Mr Perfect - Friday, April 6, 2018 - link

    On one hand I appreciate having a mechanical in the charts to see how these SSDs compare, since it's a great way to show the benefits of upgrading to one. On the other hand it makes the SSD results really hard to read, as they become disappearingly small. Hopefully one day we won't have to show people the difference. Reply
  • Billy Tallis - Friday, April 6, 2018 - link

    It's not something I plan to include in most reviews. I only added it for this one because the mechanical drive I happened to have on hand to benchmark was also a 1TB WD Black. On a lot of reviews, I leave out Optane drives for the same reasons. Reply
  • amar.znzi - Friday, April 6, 2018 - link

    > The new controller has a tri-core architecture (probably using Arm Cortex-R cores) fabricated in a 28nm process.
    Please don't speculate. Can you confirm with WD which Instruction Set Architecture is being used?
    Reply
  • Billy Tallis - Sunday, April 8, 2018 - link

    We asked repeatedly, and all we could get was that it isn't RISC-V. But every other NVMe controller used in consumer SSDs uses Cortex-R, and there's no reason to suspect WD is doing anything different. There aren't many alternatives. They designed this controller architecture to put as much of the important functionality on dedicated hardware as possible, so doing something unusual with the CPU cores doesn't present much opportunity for improving performance or efficiency. Reply
  • Klimax - Sunday, April 8, 2018 - link

    Maybe ARC. (Intel uses it for some of their MEs) Reply
  • amar.znzi - Saturday, April 14, 2018 - link

    Oh, it's not. WD has anounced that it intends to transition a large volume of it's products to RISC-V. Thanks, that answered my question. Reply
  • HStewart - Sunday, April 8, 2018 - link

    One question, I have is there any real advantage of using this model version cheaper model - in an USB-C Gen 2 case? Reply
  • SanX - Sunday, April 8, 2018 - link

    Which tasks will benefit from fast drives and which will not in real life ? Will Antivirus full clean go faster then 3-4 days currently? Or archieving? Or search for file with specific content? Having 10x read speed will loading Windows go 10x faster then with neanderthal mechanical Western Digital Gold hard drives or only by mere 10%? That what I like to see as tests not that semi-nonsence which resembles proverbial fake news of political media.

    Good would be to see the temperature map on a heavy load, the 10, 13 and even on some drives 20 Watts for such small formfactor is a lot.

    Also I still keep for history some old hard drives which don't giveup their life after 30 years. Will these new ones with guaranteed 5 years then disintegrate after 10?
    Reply
  • MajGenRelativity - Tuesday, April 10, 2018 - link

    Most people don't keep their hard drives for 30 years, as the interface connector is far obsolete by now. I'm not even certain that IDE/PATA goes back that far, and you'd most likely need a highly specialized product to even read/write to that drive. 10 years for an SSD is a reasonable lifespan, as you'd probably upgrade to something faster or denser after that time. Reply

Log in

Don't have an account? Sign up now