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 1TB Samsung 860 QVO does not handle The Destroyer very well, with an average data rate that is slightly slower than the DRAMless TLC drive. By comparison, the NVMe QLC drives from Intel and Micron are only slightly slower than the 860 EVO and MX500.

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

The QLC drives in general stand out more when looking at latency metrics than throughput, and especially when looking at 99th percentile latencies. The 1TB 860 QVO comes in last place for both average and 99th percentile latency, and all three QLC drives have worse 99th percentile latency than the DRAMless TLC drive.

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

The average read and write latencies of the 860 QVO are both only slightly worse than the DRAMless TLC SSD. The NVMe QLC drives are slightly faster than the mainstream SATA drives for read latency but fall behind in average write latency.

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

The 860 QVO actually doesn't come in last place for 99th percentile write latency, and in fact scores far better than the DRAMless TLC drive. However, the QLC drives are all still far worse off than the mainstream TLC SATA drives.

ATSB - The Destroyer (Power)

With low performance dragging out the test to a far longer duration, it's no surprise that the QLC drives all use much more energy over the course of The Destroyer than most SATA drives. The DRAMless Toshiba TR200 is an impressive exception that manages to be very efficient despite its low overall performance.

SLC Cache Sizes & Energy Consumption AnandTech Storage Bench - Heavy
Comments Locked

109 Comments

View All Comments

  • R0H1T - Wednesday, November 28, 2018 - link

    >moozooh
    QVO is the first SATA QLC drive, so yeah first of it's kind unless we're being pedantic. As for the price ~ it should & will likely come down soon enough.

    >Right now there is exactly zero reason to choose it over the EVO.

    The 500GB EVO costs about $130 US where I'm from, there's very little incentive for me to buy it given the "inflated" price.
  • moozooh - Wednesday, November 28, 2018 - link

    > "QVO is the first SATA QLC drive, so yeah first of it's kind unless we're being pedantic."
    The fact that it's the first or the only doesn't matter to anyone who's buying things based on anything resembling a performance/price ratio. It's the first to be inferior to an already existing product. Who would be the early adopter of something that's clearly worse than something else that costs more or less the same?

    > the price ~ it should & will likely come down soon enough
    So why didn't Samsung recommend a lower price to begin with, considering how badly this products needs it? I'm sure they follow the market close enough to see this series competes with their own EVO (and loses hands-down).

    > The 500GB EVO costs about $130 US where I'm from, there's very little incentive for me to buy it given the "inflated" price.
    Yet this makes the QVO more attractive for you, especially considering it doesn't even feature a 500 GB model? I don't understand your argument. The point is this drive needs to be much, much cheaper than the EVO to be attractive at all. The downsides of the QLC NAND are numerous and significant; they need to be offset using the price. It's also clear this is where the multi-bit madness should end, because QLC is already encroaching onto the HDD territory in certain aspects (except the price, sadly) and scenarios. If PLC were a thing, I'd most likely stay away from it even if it were cheaper than hard drives. That's just asking for trouble, like those glass platters in IBM's Deskstar 75GXP (one of the most disastrous HDD series of all time).
  • R0H1T - Wednesday, November 28, 2018 - link

    >The fact that it's the first or the only doesn't matter to anyone who's buying things based on anything resembling a performance/price ratio.

    The fact is you quoted me when I said first of a kind, which holds true for this drive, end of!

    >So why didn't Samsung recommend a lower price to begin with, considering how badly this products needs it?

    I dunno, how about you ask Samsung why didn't they sell the 860 EVO for $130 at launch?

    >Yet this makes the QVO more attractive for you, especially considering it doesn't even feature a 500 GB model?

    Yes because the QVO model, when it launches here, should be cheaper ($/GB) than the EVO drives. It's not like I can't afford $130 drive, but the 1TB or 2TB would be better VFM for me, considering I'm looking to replace some HDDs permanently. The EVOs would probably still be 40~60% more expensive.
  • moozooh - Wednesday, November 28, 2018 - link

    > The fact is you quoted me when I said first of a kind, which holds true for this drive, end of!
    Once again, the fact that I'm pointing out is that it is a non-argument. Early adopter premium only exists for something that such an early adopter would want to have NO MATTER THE COST. Such as a new feature or better performance with existing features. Here, the cost is the ONLY thing an early adopter would want about it and the only potential advantage, period. Why do you not see how you're not making sense? "One of a kind" is an idiotic argument to use for the product that's intended to be cheaper, not better.

    > I dunno, how about you ask Samsung why didn't they sell the 860 EVO for $130 at launch?
    They launched the 860 EVO at the same time with the 860 Pro with a significant enough difference in MSRP that one didn't cannibalize the other, and the EVO was also fast enough to overtake most of the competition widely available at that price point. So the pricing made sense at the time, not so much here.

    > The EVOs would probably still be 40~60% more expensive.
    Hopefully so, but Samsung's lack of aggression and insight in undercutting their own existing product is disappointing. They are well aware of the going price of the EVO.
  • R0H1T - Wednesday, November 28, 2018 - link

    >moozooh

    We're forgetting arguably the most important thing ~ yields. There were some (unconfirmed) reports that QLC yields were below par, so it's quite possible that these products being priced so close to TLC drives is a result of that.
  • moozooh - Wednesday, November 28, 2018 - link

    I don't really think yields are important. It's not an attribute for customer to base their decisions on, it's not something that can be tested or seen, and needn't be either—it's the manufacturer's problem. After all, customers aren't altruists and aren't out there to help Samsung or any other vendor do their business—what they need to care about is that the products they buy are priced fairly. Samsung won't convince anyone to overpay for QLC because the yields are too low to justify a fair price.

    Two possible ways to handle this launch better would be either to bite the bullet and suggest a sensible MSRP from the get go or stabilize the technology before coming out with the product and selling it at a healthy margin. Either way there won't be many people buying this until it's sufficiently cheap so the difference isn't as big as it might feel.
  • FullmetalTitan - Thursday, November 29, 2018 - link

    'Yields don't matter to initial consumer product pricing' is a pretty spicy take.
    It doesn't matter whether the consumers want to be altruistic (definitely not the correct usage here), this is the price if you want high density SSD storage in a single unit, like it or not. You clearly don't, so kindly shut up and move on.
  • Manch - Wednesday, November 28, 2018 - link

    If the 500GB EVO is double the going price in your area, what makes you think the 860 QVO won't be?

    Me thinks, you've dug a hole. Stop digging LOL
  • R0H1T - Wednesday, November 28, 2018 - link

    >double the going price

    Double the what? Do you know the price 860 EVO debuted in every country of the world, now can you guess the price QVO would retail for?

    How about you stop assuming $130 US (1TB) is the normal EVO price everywhere around the world? Then stop reaching.
  • s.yu - Saturday, December 1, 2018 - link

    If you're knowingly buying from an expensive source, you're buying it wrong. If you insist on buying it wrong, then stop wasting other people's time with your BS.
    Time to hit eBay, nowadays Taobao may help.

Log in

Don't have an account? Sign up now