Whole-Drive Fill: Testing SLC Cache Size

This test starts with a freshly-erased drive and fills it with 128kB sequential writes at queue depth 32, recording the write speed for each 1GB segment. This test is not representative of any ordinary client/consumer usage pattern, but it does allow us to observe transitions in the drive's behavior as it fills up. This can allow us to estimate the size of any SLC write cache, and get a sense for how much performance remains on the rare occasions where real-world usage keeps writing data after filling the cache. Samsung's official specifications are:

Samsung 860 QVO Secondary Specifications
Capacity 1 TB 2 TB 4 TB
SLC Cache
Size
Min 6 GB 6 GB 6 GB
Max 42 GB 78 GB 78 GB
Sequential
Write
SLC Cache 520 MB/s
QLC 80 MB/s 160 MB/s 160 MB/s

Our results show the following:

The Samsung 860 QVOs run out of SLC cache right on schedule, at 42 GB for the 1TB model and 78 GB for the 4TB. After that, they are both slow and very steady for the rest of the test.

Sustained 128kB Sequential Write (Power Efficiency)
Average Throughput for last 16 GB Overall Average Throughput

The 1TB 860 QVO falls below the sequential write speed of a 1TB hard drive once the SLC cache runs out, but the 4TB model is able to sustain twice the write speed and remains ahead of not just the hard drive's speed, but also some of the slower TLC drives.

BAPCo SYSmark 2018

BAPCo's SYSmark 2018 is an application-based benchmark that uses real-world applications to replay usage patterns of business users, with subscores for productivity, creativity and responsiveness. Scores represnt overall system performance and are calibrated against a reference system that is defined to score 1000 in each of the scenarios. A score of, say, 2000, would imply that the system under test is twice as fast as the reference system.

SYSmark scores are based on total application response time as seen by the user, including not only storage latency but time spent by the processor. This means there's a limit to how much a storage improvement could possibly increase scores, because the SSD is only in use for a small fraction of the total test duration. This is a significant difference from our ATSB tests where only the storage portion of the workload is replicated and disk idle times are cut short to a maximum of 25ms.

AnandTech SYSmark SSD Testbed
CPU Intel Core i5-7400
Motherboard ASUS PRIME Z270-A
Chipset Intel Z270
Memory 2x 8GB Corsair Vengeance DDR4-2400 CL17
Case In Win C583
Power Supply Cooler Master G550M
OS Windows 10 64-bit, version 1803

Our SSD testing with SYSmark uses a different test system than the rest of our SSD tests. This machine is set up to measure total system power consumption rather than just the drive's power.

BAPCo SYSmark 2018 - Creativity

BAPCo SYSmark 2018 - Productivity

BAPCo SYSmark 2018 - Responsiveness

The 860 QVO isn't any slower for compute-heavy interactive tasks than the mainstream SATA SSDs, and even on the more I/O-bound Responsiveness test the 860 QVO is ahead of the DRAMless TLC drive and not far behind the Crucial MX500.

Energy Use

The SYSmark energy usage scores measure total system power consumption, excluding the display. Our SYSmark test system idles at around 26 W and peaks at over 60 W measured at the wall during the benchmark run. SATA SSDs seldom exceed 5 W and idle at a fraction of a watt, and the SSDs spend most of the test idle. This means the energy usage scores will inevitably be very close. A typical notebook system will tend to be better optimized for power efficiency than this desktop system, so the SSD would account for a much larger portion of the total and the score difference between SSDs would be more noticeable.

BAPCo SYSmark 2018 - Energy Consumption

The Samsung 860 QVO's energy usage during SYSmark is not a problem at all, with it using slightly less energy than the mainstream SATA TLC drives.

Introduction AnandTech Storage Bench - The Destroyer
POST A COMMENT

107 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.
    Reply
  • 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).
    Reply
  • 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.
    Reply
  • 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.
    Reply
  • 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.
    Reply
  • 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.
    Reply
  • 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.
    Reply
  • 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
    Reply
  • 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.
    Reply
  • 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.
    Reply

Log in

Don't have an account? Sign up now