Final Words

The 850 Pro and EVO are undoubtedly the best SATA 6Gbps SSDs on the market. The Pro has been holding the performance crown for the past year and it's starting to look like no SATA drive can dethrone it, whereas the EVO provides very competitive performance at a much more affordable price point. From a performance standpoint, the 2TB models leave the Pro and EVO lines unchanged as the performance matches with the 1TB models already on the market. That's hardly a surprise given that the 1TB models saturate the SATA 6Gbps interface and AHCI presents its own limitations, so the 2TB SKUs are solely a capacity bump. There are minor performance differences in steady-state 4KB random write and random read benchmarks that favor the 1TB models, but to be honest that's merely an architectural observation (the internal SRAM caches in the controller may need upgrading to extract better performance out of +1TB of NAND) because the impact on actual user performance is in the order of a few percent. 

I'm very glad to see improved power efficiency in the 2TB models. A part of that is explained by the move from LPDDR2 to LPDDR3, but it's also possible that the MHX is manufactured using a more power efficient process node. Depending on the benchmark the power savings can be anywhere from 5% to close to 20%, so it's not a marginal gain especially because higher capacity SSDs usually consume more power due to the additional NAND. The 850 EVO in particular wasn't very power efficient before, but the new 2TB is mostly on par with the 1TB-class drives we have tested. It's no challenger to the BX100 though, but TLC is inherently less power efficient and the SM2246EN controller is also less powerful by being a single-core design while the MHX consists of three processor cores. 

At $800, the 2TB 850 EVO is very reasonably priced. The average going price for a 1TB-class value SSD is about $350-$380 with an occasional sale bringing the price closer to $300, so the 2TB EVO carries a small premium, but at $0.40 per gigabyte it's not overpriced by any means. The $1000 2TB Pro on the other hand has a much tinier niche because unless you have a The Destroyer level workload there won't be any difference in performance. Even under such an intensive IO workload the Pro only has a ~10% advantage, but the Pro is overall a little (~5-10%) more power efficient, so if you need a 2TB SSD and value every extra minute of battery life high, the $200 premium might be justifiable. The Pro also carries twice the endurance (300TB vs 150TB) and warranty (10 vs 5 years), but I don't consider those two having much value given that 150TB already translates to 82GB a day for five years and in five years time a SATA 6Gbps drive will most likely be obsolete anyway.

Since the 850 Pro and EVO are the first 2TB client SSDs on the market so they face no competition. They receive a strong recommendation from us for those who need/want a 2TB SSD. Both have excellent performance like the 1TB models we had already tested and the increased power efficiency is a welcome addition for mobile users. Out of the two the EVO is better value for the vast majority, but the 2TB Pro is there for those who want the added endurance and the most impressive SATA SSD in the market. 

Idle Power Consumption, ATTO & AS-SSD
Comments Locked

66 Comments

View All Comments

  • leexgx - Thursday, July 23, 2015 - link

    the bug is related to the incorrect Qued trim support on the Samsung drives

    the samsung drives says they support Qued Trim support but they failed to implement it correctly when they added SATA 3.2 in the latest firmware updates, the Old firmware did not have Qued trim bug because the SSD did not advertise support for it, other SSDs that advertise Qued support it have been patched or don't have the buggy support to start off with (accept the m500)
  • editorsorgtfo - Thursday, July 23, 2015 - link

    Can you corroborate this? Nothing in the patch hints at a vendor issue.
  • leexgx - Thursday, July 23, 2015 - link

    i guess this is relating to RAID , there is a failed implementation of advertised Queued Trim support in the samsung 840 and 850 evo/pro drives (the drive says it supports it but it does not support it correctly so TRIM commands are issued incorrectly as to why there is a black list for all 840* and 850* drives)

    your post seems to be related to RAID and kernel issue (but the issue did not happen on Intel drives that they changed to) they rebuilt there intel SSD setups the same as the samsung ones

    they did the same auto restore only the drives changed they had 0 problems once they changed to intel/"other whatever it was" SSDs that also supported Qued TRIM even thought they was not using it the RAID bit probably was (was a bit ago when i looked at it)
  • sustainednotburst - Friday, July 24, 2015 - link

    Algolia stated Queued Trim is disabled on their systems, so its not related to Queued Trim.
  • leexgx - Saturday, July 25, 2015 - link

    the problem with samsung drives and Qued trim is till there (not just fake qued trim they failed to implement they also failed to implement the 3.2 spec and the advertised features that samsung is exposing)
  • Gigaplex - Thursday, July 23, 2015 - link

    Those two links show separate bugs. The algolia reported bug was a kernel issue. The second bug which vFunct was probably referring to is a firmware bug where the SSD advertises queued TRIM support but does not handle it correctly. The kernel works around this by blacklisting queued TRIM from known-bad drives. Windows doesn't support queued TRIM at all which is why you don't see the issue there yet.
  • jann5s - Thursday, July 23, 2015 - link

    @AT: please do some data retention measurements with SSD drives! I'm so curious to see if the myth is true and to what extent!
  • Shadowmaster625 - Thursday, July 23, 2015 - link

    With 2 whole gigabytes of DRAM, why are random writes not saturating the SATA bus?
  • Kristian Vättö - Thursday, July 23, 2015 - link

    The extra DRAM is needed for the NAND mapping table, it's not used to cache any more host IOs.
  • KaarlisK - Thursday, July 23, 2015 - link

    Where did TRIM validation go? (The initial approach, which checked whether TRIM restored performance on a filled drive).
    Considering that controllers have had problems with TRIM not restoring performance, even if this is a minor revision, it still seems an important aspect to test.

Log in

Don't have an account? Sign up now