Advanced Synthetic Tests

Our benchmark suite includes a variety of tests that are less about replicating any real-world IO patterns, and more about exposing the inner workings of a drive with narrowly-focused tests. Many of these tests will show exaggerated differences between drives, and for the most part that should not be taken as a sign that one drive will be drastically faster for real-world usage. These tests are about satisfying curiosity, and are not good measures of overall drive performance. For more details, please see the overview of our 2021 Consumer SSD Benchmark Suite.

Whole-Drive Sequential Fill

Pass 1
Pass 2

Some of our other tests have shown a few signs that the 870 EVO's write performance can drop when the SLC cache runs out, but this straightforward sequential write pass over the entire drive doesn't reveal any such behavior. The 870 EVO's sequential write performance is extremely consistent, even on the second write pass.

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

Due to the excellent performance consistency, the Samsung 870 EVOs edge out the other SATA drives with marginally higher average sequential write speeds. The entry-level NVMe drives end up much worse off than the mainstream SATA drives once their caches run out, but the more mainstream NVMe drive blows them all away.


Working Set Size

As expected, the Samsung 870 EVO's random read performance shows basically no variation across a range of working set sizes, and that read performance is at least a little bit faster than any of the other SATA drives or the entry-level NVMe drives.


Performance vs Block Sizes

Random Read
Random Write
Sequential Read
Sequential Write

There are no particular surprises in how the Samsung 870 EVO handles IOs of different block sizes. Unlike some drives, it has no trouble with sub-4kB IOs. It offers moderate improvements over the 860 EVO for mid-sized random reads (up to about 128kB). The one negative is that for writes we again see more inconsistency from the 870 EVO than the 860 EVO when testing an 80% full drive. The simple whole-drive sequential write test may not have been able to reveal any SLC caching troubles, but it does seem clear that the caching behavior has some performance regressions for more complicated workloads on a drive that's more well-used—though it's still unlikely to matter for any typical real-world consumer workload.

Synthetic Tests: Basic IO Patterns Mixed IO Performance and Idle Power Management


View All Comments

  • Wereweeb - Wednesday, February 17, 2021 - link

    They made a major update. No one cares about SATA Express. That you don't even know about it only goes to show that no one cares, there's no need or use for it.

    SATA is plenty enough for Hard Drives, and SSD's are going to keep using M.2, U.3, and other PCIe ports. There's no need for a port that isn't going to be used by anyone.

    If anything, they could theoretically run spinning rust off an x1 PCIe 3.0 (Or even 2.0) connector, but that's also not really needed.

    If you want consumer motherboards to have U.3 connectors, then say that. And I'd agree. I never like bare PCB's where they're not necessary.
  • Lord of the Bored - Wednesday, February 17, 2021 - link

    I ABSOLUTELY want U.2 connectors on motherboards, and U.2 drives priced for mass-market sales.

    It won't happen, because the manufacturers want a hard line drawn between home-use and business-use hardware so they can price-gouge for business hardware. Mass-market U.2 drives would ruin their pricing strategy.
  • Wereweeb - Thursday, February 18, 2021 - link

    They don't really need to, consumer SSD's are already shit for most enterprise applications, and will be plain garbage when it's all just QLC. Reply
  • Billy Tallis - Thursday, February 18, 2021 - link

    Consumer U.2 drives wouldn't ruin the enterprise SSD market, because the form factor is a much less important difference than the fact that consumer SSDs have SLC caching and enterprise SSDs don't.

    Consumer U.2 drives would fail because the market is simply too small. The number of consumers who can actually afford and want 3+ NVMe SSDs in their desktop (and aren't already on a HEDT system) is too small to justify bringing a new category of products to market.
  • Spunjji - Friday, February 19, 2021 - link

    Changing the SATA standard in a way that wrecks backwards compatibility would be pointless - U.2 is already an alternative standard that does that.

    It's dead. It's a silly way to access flash devices.
  • Gigaplex - Wednesday, February 17, 2021 - link

    Or they'd just switch to using SAS in those devices. Reply
  • flyingpants265 - Thursday, February 18, 2021 - link

    The suggestion for hard drives was to double the amount of heads/platters per drive to get costs down even further, I think this decreases reliability too but reduces overhead costs for datacenters because it's fewer drives.

    8 tb, 10 TB and 12 TB drives are more expensive per gb than the two terabyte drives.... Prices haven't gone down since 2010. I should be able to walk in and get a 8tb drive for $89. The markets really crapped out.
  • Spunjji - Friday, February 19, 2021 - link

    HDD prices never really recovered after the 2011 floods in Thailand. By the time the impact was over, SSDs were eating their lunch, and the incentive to keep dropping prices went away forever. Reply
  • npz - Wednesday, February 17, 2021 - link

    From the way you're stating it. I assume you're not aware of U.2 nvme drives which uses the same 2.5 in. form factor and is connected to pcie and still uses cables, and fills up the drive at higher capacities and also comes in 12mm and 15mm thickness for heat dissipation? Because fast nvne drives are also hot with very little surface area in the m.2 for factor Reply
  • 29a - Wednesday, February 17, 2021 - link

    He doesn't seem to know what he's talking about. Reply

Log in

Don't have an account? Sign up now