AnandTech Storage Bench - The Destroyer

Our AnandTech Storage Bench tests are traces (recordings) of real-world IO patterns that are replayed onto the drives under test. The Destroyer is the longest and most difficult phase of our consumer SSD test suite. For more details, please see the overview of our 2021 Consumer SSD Benchmark Suite.

ATSB The Destroyer
Average Data Rate
Average Latency Average Read Latency Average Write Latency
99th Percentile Latency 99th Percentile Read Latency 99th Percentile Write Latency
Energy Usage

For SATA drives, the Samsung 870 EVOs turn in class-leading scores on almost all of the performance metrics. But these improvements are all marginal at best; the SATA interface bottleneck almost completely levels the playing field. The small improvements to read latency brought by the 870 EVO pale in comparison to what is achieved by even entry-level NVMe SSDs.

In stark contrast to the performance numbers, the 870 EVOs turn out to be the most power-hungry TLC drives in this bunch: they sacrifice some of the efficiency improvements the 860 EVO provided, even though drives like the SK hynix Gold S31 have been able to deliver significant improvement on this.

AnandTech Storage Bench - Heavy

The ATSB Heavy test is much shorter overall than The Destroyer, but is still fairly write-intensive. We run this test twice: first on a mostly-empty drive, and again on a completely full drive to show the worst-case performance.

ATSB Heavy
Average Data Rate
Average Latency Average Read Latency Average Write Latency
99th Percentile Latency 99th Percentile Read Latency 99th Percentile Write Latency
Energy Usage

The scores for the Heavy test paint much the same picture as for The Destroyer. The full-drive test runs additionally show that the worst-case performance of the mainstream SATA SSDs is still superior to many entry-level NVMe SSDs, even though the NVMe SSDs significantly outperform SATA for any more normal workload.

AnandTech Storage Bench - Light

The ATSB Light test represents ordinary everyday usage that doesn't put much strain on a SSD. Low queue depths, short bursts of IO and a short overall test duration mean this should be easy for any SSD. But running it a second time on a full drive shows how even storage-light workloads can be affected by SSD performance degradation.

ATSB Light
Average Data Rate
Average Latency Average Read Latency Average Write Latency
99th Percentile Latency 99th Percentile Read Latency 99th Percentile Write Latency
Energy Usage

On the Light test, the measurable but imperceptible performance advantages of the 870 EVOs over other SATA drives have basically disappeared. The read latency scores on the full-drive test runs may be a tiny bit better than the 860 EVO, but the only scores that have clearly shifted with this new generation are the energy consumption figures that have creeped up.

PCMark 10 Storage Benchmarks

The PCMark 10 Storage benchmarks are IO trace based tests similar to our own ATSB tests. For more details, please see the overview of our 2021 Consumer SSD Benchmark Suite.

PCMark 10 Storage Traces
Full System Drive Overall Score Average Bandwidth Average Latency
Quick System Drive Overall Score Average Bandwidth Average Latency
Data Drive Overall Score Average Bandwidth Average Latency

The Full System Drive test from the PCMark 10 Storage suite shows a much wider spread of performance scores among SATA drives than our ATSB traces, but also a much smaller advantage for the NVMe drives. Judging by this test, the 870 EVO offers a small but real improvement to performance compared to earlier SATA drives. The 4TB 870 QVO also scores quite well since it benefits from the same controller and has enough SLC cache to almost match the performance of the 4TB 870 EVO.

The subset of tests included in the Quick System Drive and Data Drive benchmarks show a more level playing field among SATA SSDs, and a greater advantage for NVMe drives. Since we run these tests before the Full System Drive test, each drive is closer to its fresh out-of-the-box state, which helps these tests get closer to showing the theoretical peak performance of a drive.

Introduction Synthetic Tests: Basic IO Patterns
Comments Locked

136 Comments

View All Comments

  • Kamen Rider Blade - Thursday, February 18, 2021 - link

    That's why I buy & use SATA BackPlanes =D
  • Cooperdale - Saturday, February 20, 2021 - link

    My motherboard has SATA Express support. Not a SATA upgrade as much as a kind-of-hybrid between SATA and NVMe. But yes I see what you mean. It failed miserably though.
  • Juraj_SK - Wednesday, February 17, 2021 - link

    I think SATA is dead. Even with a newer version it's still a terrible interface for drives. Not only it doesn't provide power (so you need a separate cable from the PSU), but the drive itself needs a box and the whole thing takes a lot of space (often wasted inside - you could literally cut some SSD in half and it would still work :D).
    Whereas NVMe is chip only, super small, power included. No wasted cables or materials and it's connected with PCIe just like everything else.
  • eek2121 - Wednesday, February 17, 2021 - link

    NVME is limited by surface area, so I wouldn’t count SATA as being dead yet. A SATA drive will always be able to hold more data than an NVME drive.
  • DanNeely - Wednesday, February 17, 2021 - link

    Except at the silly fringe that doesn't matter though. A sata drive packing more flash than can fit into an m.2 is going to be crazy expensive for a consumer model; and in the enterprise market taking several times longer than an m.2 drive to fill (think initial fill or raid rebuilds) is a major liability.
  • eek2121 - Wednesday, February 17, 2021 - link

    It isn’t a silly fringe thing. There are legitimate needs for bulk storage. One of my clients has a database that is 44TB in size.
  • Guspaz - Wednesday, February 17, 2021 - link

    Except for enterprise use there are already pcie-based connection standards for 2.5” drives. SATA isn’t needed for that.
  • schujj07 - Wednesday, February 17, 2021 - link

    If you have a 44TB DB that would be placed on a physical SAN typically. The only other possibility is the entire DB is a physical appliance. Either way the server will have multiple 2.5" drive bays. Depending on the age of the server, those slots will either be SATA/SAS, SATA/SAS/NVMe, or strictly NVMe. Either way both SAS and NVMe have drives larger than 15TB. Outside of one company (and that is a 3.5" SSD), the largest Enterprise grade SATA SSD are 7.68TB now. Sure you can purchase older ones on SATA that are larger, but with the rapid adoption of NVMe there isn't any reason to go SATA unless absolutely required. Also when it comes to cost, SATA Enterprise SSD isn't much cheaper than Enterprise NVMe, SAS is still overpriced though.
  • CaedenV - Wednesday, February 17, 2021 - link

    "It isn't a silly fringe thing" and then proceeds to put forward an extremely fringe case.
    Just how many people have a 44TB DB laying around their house? This is consumer equipment. Don't put a 44TB DB on consumer equipment!
  • stancilmor - Thursday, February 18, 2021 - link

    44TB? That is small potatoes. I’m dealing with storage requirements in double digits of PB annually. Certainly not consumer level when just drives cost in the millions.

    For home use I rely on the hot plug feature of SATA. For the hot plug feature I’ll be switching to USB C, USB 4 or thunderbolt 3 or 4. I still don’t have an M.2 Drive, but likely the next system upgrade will include an M.2 for the OS. SATA is getting to be too slow.

    As for the Samsung drives. I recently upgraded an aging laptop’s mechanical drive with the EVO 870 simply, because the 860 had too long of a shipping time.

    I also almost exclusively use Samsung drives in upgrades, because of how well the Samsung data migration tool works. I have tried Acronis and use clonezilla, both have created unusable clones on occasion. Samsung’s Data Migration just works, even on a running system.

Log in

Don't have an account? Sign up now