Samsung 860 QVO SSD Linux Benchmarks: 1TB SATA 3.0 SSD For $150 USD

[phoronix]

Phoronix: Samsung 860 QVO SSD Linux Benchmarks: 1TB SATA 3.0 SSD For $150 USD

After being announced a few weeks back, the Samsung 860 QVO series is beginning to ship as a new, lower-cost SATA 3.0 SSD offering. The Samsung 860 QVO series offers four bit per cell flash memory to usher in a new era of lower-cost solid-state storage with the now-shipping 1TB model costing just $150 USD while the 2TB version coming soon at $300 USD and $600 USD for a 4TB edition.

http://www.phoronix.com/vr.php?view=27304

[perd.un]

Interesting to see such a performant storage available at lower cost than ever. HDD industry has to pull a lot of effort to catch up.

[RussianNeuroMancer]

Write test benchmarks from other reviewers suggest that as soon as SLC-based write cache deplete QLC-based SSD have HDD-level performance.

[ThoreauHD]

Ghetto Fktrash. No thank you. TLC is bad enough.

[mulenmar]

Interesting, but given Samsung's track record of government bribing, self-immolating smartphones, and DDR4 price-fixing, I don't think I'll be giving then any more of my money.

[patrakov]

It says 5V 1.4A - that's quite a lot. Will likely overheat if used in a fanless PC, and will not work with a router through USB-to-SATA connector, either.

[milkylainen]

Write test benchmarks from other reviewers suggest that as soon as SLC-based write cache deplete QLC-based SSD have HDD-level performance.

You're absolutely right.
The drive is absolutely rubbish from a longevity standpoint, hard load usage and continuous write usages.
As a low load, desktop something drive... most normal users won't be able to tell the difference.
The small SLC-cache will paint a rosier picture than the QLC-backend if used lightly.

[commiethebeastie]

Your's tests are bullshit. This test don't take into account SLC cache.

[fuzz]

Would this be a good drive for read-oriented storage like large games?

[bug77]

Write test benchmarks from other reviewers suggest that as soon as SLC-based write cache deplete QLC-based SSD have HDD-level performance.

Only the transfer speeds slow down. HDDs could catch up to SSD's seek times if the SSD would stop for a coffee. And most of the time, it's the seek times you're after.

Also, yes, the tests don't care about the SLC cache, but you know what? Most tests are based on real workloads and real workloads don't care about SLC cache either.

At the same time, that Crucial drive looks suspiciously slow. It's as if it was tested while almost full (a known weakness in MX300). Or maybe it's a Linux thing?