Mixed Random Read/Write Performance

The mixed random I/O benchmark starts with a pure read test and gradually increases the proportion of writes, finishing with pure writes. The queue depth is 3 for the entire test and each subtest lasts for 3 minutes, for a total test duration of 18 minutes. As with the pure random write test, this test is restricted to a 16GB span of the drive, which is empty save for the 16GB test file.

Iometer - Mixed 4KB Random Read/Write

The mixed random I/O performance of the 4TB 850 EVO is much better than the other large 850 EVOs, putting te 4TB model close to the top of the chart.

Iometer - Mixed 4KB Random Read/Write (Power)

The 4TB 850 EVO also manages a large reduction in power usage as compared with the 1TB and 2TB 850 EVOs, making the 4TB much more efficient.

Unlike the other 850 EVOs, the 4TB never loses performance as the proportion of writes in the test workload increases. Meanwhile, the power draw is essentially constant until near the end of the test.

Mixed Sequential Read/Write Performance

The mixed sequential access test covers the entire span of the drive and uses a queue depth of one. It starts with a pure read test and gradually increases the proportion of writes, finishing with pure writes. Each subtest lasts for 3 minutes, for a total test duration of 18 minutes. The drive is filled before the test starts.

Iometer - Mixed 128KB Sequential Read/Write

The 4TB 850 EVO is essentially tied for the best mixed sequential read and write performance.

Iometer - Mixed 128KB Sequential Read/Write (Power)

The 4TB 850 EVO averages using slightly less power than the 2TB model, and it is one of the most efficient of the large drives.

The usual pattern is for performance on this test to resemble a bathtub curve, but the 2TB 850s and the 4TB 850 EVO don't lose as much of their performance during the first half of the test, leading them to bottom out much later than most other drives.

Sequential Performance ATTO, AS-SSD & Idle Power Consumption
Comments Locked

145 Comments

View All Comments

  • ddriver - Monday, July 11, 2016 - link

    That's a valid point, and even though majority of the people who buy consumer stuff are gonna use it on windows, it is still no excuse, it is not like samsung doesn't have the resources to dedicate to proper support.
  • Palorim12 - Tuesday, July 12, 2016 - link

    Linux is the only OS affected. Windows and Mac are fine. Disable Queued TRIM and Sequential TRIM will run. So NBD.
  • Kevin G - Monday, July 11, 2016 - link

    Samsung has horrible warranty support and they have had a few major issues with their SDDs (840 EVO performance degradation).
  • Samus - Monday, July 11, 2016 - link

    Yeah. I had two really sour back to back experiences with Samsung Storage support, one regarding the 840 EVO. After a month of back and fourth communication attempting different firmware updates as support requested, secure erase and reimage, and even trying the drive in another PC as support asked, it was obvious they were in denial of the well documented read performance problem. After RMA they shipped me back another 840 EVO that eventually (after a year) developed the same problems even with the latest firmware update. The problems always come up after a lot of writes like a game install. It wasn't worth the trouble. I would have been happy if they simply replaced the drive with an 850 EVO.
  • Palorim12 - Tuesday, July 12, 2016 - link

    The FW update that came out in April completely fixed the issue. I posted several updates on a 840 EVO and an 840 EVO m-sata on Overclock that are fine well over a year since the fix.
  • Palorim12 - Tuesday, July 12, 2016 - link

    And they also came out with a fix for the non-EVO 840 recently.
  • Impulses - Wednesday, July 13, 2016 - link

    Did they? That's news to me! To teh Google...
  • Impulses - Wednesday, July 13, 2016 - link

    Huh, go figure, they DID issue an 840 update towards the end of June (2016)... What the heck took so long? I think most people had rightfully assumed the 840 (non EVO) was abandoned, the EVO did come out like 6 months after it.

    Apparently the issue was also never quite as severe on the 840 non EVO? Did they ever commit to a fix and it got drowned out over time or did that update happen out of the blue? No AT Pipeline post about it either...

    http://www.pcper.com/reviews/Storage/Samsung-Magic...
  • Palorim12 - Thursday, July 14, 2016 - link

    I think its because in most cases, it took longer for the issue to appear in the 840. So it would take longer for them to see if a fix fully worked?
  • SetiroN - Monday, July 11, 2016 - link

    Why wouldn't you?
    When you're talking TBs, that difference translates in HUNDREDS of dollars that I have better use for when Sandisk's performance is already good enough.

    This drive only really makes sense in oddly demanding small laptops.

Log in

Don't have an account? Sign up now