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 performance of the ADATA drives on The Destroyer is about as expected given how the other SM2262 drives behave: The average data rates are significantly lower than most of the other recent high-end SSDs. The SX8200 and GAMMIX S11 with 64L 3D TLC and a newer controller perform about as well as the older SX8000 with 32L MLC and the slower SM2260 controller, while the older TLC-based GAMMIX S10 sits at the bottom of the chart. It is interesting that the Intel 760p with very similar hardware shows much greater variation in performance between capacities than the SX8200. Whatever customizations Intel has made to the SM2262 platform are helping their 512GB model but hurting the 256GB model.

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

The SX8200 and GAMMIX S11 can't match the latency of the MLC-based SX8000 on The Destroyer, with a small disadvantage in average latency and much worse 99th percentile latency. Compared to the previous-generation TLC drive, things are greatly improved to the point that the 240GB SX8200 has lower latency than the 512GB GAMMIX S10.

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

Differences in drive capacity seem to have a much bigger effect on the SX8200's average write latency than the average read latency. However, it's on the read side that the latency of the SX8200 stands out as clearly worse than other current competitors like the Samsung 970 EVO. The poor write latency of the TLC-based GAMMIX S10 has been thoroughly addressed by the new drives, with a factor of four improvement.

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

The older SM2260 SSDs with MLC or TLC have much better 99th percentile read latencies than the newer ADATA drives with the SM2262 controller. Average latency for the TLC-based drives is vastly better with the newer generation, but some consistency has been sacrificed. The 99th percentile write latency hasn't changed much, and the MLC-based SX8000 still has a clear advantage there despite using  the older controller and NAND.

ATSB - The Destroyer (Power)

The SX8200 and GAMMIX S11 use a bit more energy than their predecessors to complete The Destroyer, but this isn't too surprising–it's often necessary to sacrifice some efficiency to get better performance, and The Destroyer is quite a bit more intense than the workloads that the newer ADATA drives are optimized for.

Introduction AnandTech Storage Bench - Heavy
Comments Locked

19 Comments

View All Comments

  • Pewzor - Tuesday, May 14, 2019 - link

    FuzeDrive (aka Virtual SSD) is used by Dell EMC data center, people saying you lose FuzeDrive you lose everything is just full of it. FuzeDrive is just Virtual SSD (by Enmotus) rebranded for AMD use.
    It works like Intel Rapid Storage except VSSD is data center proven.
    There's a very little chance for total catastrophic failure to happen, which could happen to IRST as well.
    You will lose your data when multiple drives fail at the same time, which is true even for raid 1 and raid 5.
    VSSD/FuzeDrive when it pushes data across different devices it creates a mirror in (duplicates in shadow file), and the duplicates are not purged until after the data is verified to complete copying to the new destination drive.
    Only time this happens is when file is copied the destination drive fails the instant the copy is verified then the source device fails and breaks the shadow image.
    Technically even a 3 drive raid 5 array could fail catastrophically if all 3 drives failed.
  • eddieobscurant - Thursday, July 26, 2018 - link

    I think the drives deserved an award.
  • Samus - Thursday, July 26, 2018 - link

    Double sided :(

    Would be good for a notebook considering the power profile and price. The 980 EVO is just dangerous in a mobile device so I've been sticking to the WD Black, which is still pretty expensive.
  • wolve - Thursday, July 26, 2018 - link

    FYI this SSD is on sale for $100 on Rakuten. Got it a few weeks ago when they had a similar deal.
    https://www.rakuten.com/shop/adata/product/ASX8200...
  • SanX - Saturday, July 28, 2018 - link

    This drive was completely destroyed by the Destroyer still the author and the crowd sing the Dithyrambs to it.
  • gglaw - Saturday, August 11, 2018 - link

    the vast majority of home users could not even emulate the Destroyer tests if they tried and it has no bearing on the actual user experience. It is there mostly for academic purposes - did you even read the details of what the Destroyer test runs? For even an advanced home techie, this drive's price/performance is most likely the best that currently exists, especially when it goes on sale for $95 for the ~500GB model. That's not much higher than a budget SATA drive for identical performance to a 970 EVO or WD Black for home use. It's been on sale for $95-$100 3X now that I'm aware of, not only should the author give it a positive review, for the segment it addresses I feel it should be even given Editor's Choice. And yes I have 2 of these so not just making up opinions based on reading tests that I don't understand. There is absolutely no visible difference between this, the 960 EVO and 970 EVO which I have all running in the same LAN room.
  • Wolfclaw - Tuesday, July 31, 2018 - link

    Based on review, I purchased the 240GB SX8200 for new Ryzen build, it came yesterday, now just waiting for the motherboard ... running out of patience :(
  • Wolfclaw - Saturday, August 4, 2018 - link

    OK, got one for my x470 and it is fast, would I notice the difference to say a Samsung, I doubt it. 4 seconds form boot to W10 desktop, I have a large Outlook data footprint and it opens and is ready a lot quicker than my old SSD, Visual Studio is extremely responsive with it.
  • a_pete - Friday, August 31, 2018 - link

    I think there's an issue in the power consumption information for the Optane 800p.

    It's being listed here (and on other charts) as using 0.8W while active, but on the review page it was actually using 3.5W active. This is messing up all the Power efficiency charts.

    Thanks!

Log in

Don't have an account? Sign up now