Performance Consistency

Performance consistency tells us a lot about the architecture of these SSDs and how they handle internal defragmentation. The reason we don’t have consistent IO latency with SSD is because inevitably all controllers have to do some amount of defragmentation or garbage collection in order to continue operating at high speeds. When and how an SSD decides to run its defrag or cleanup routines directly impacts the user experience as inconsistent performance results in application slowdowns.

To test IO consistency, we fill a secure erased SSD with sequential data to ensure that all user accessible LBAs have data associated with them. Next we kick off a 4KB random write workload across all LBAs at a queue depth of 32 using incompressible data. The test is run for just over half an hour and we record instantaneous IOPS every second.

We are also testing drives with added over-provisioning by limiting the LBA range. This gives us a look into the drive’s behavior with varying levels of empty space, which is frankly a more realistic approach for client workloads.

Each of the three graphs has its own purpose. The first one is of the whole duration of the test in log scale. The second and third one zoom into the beginning of steady-state operation (t=1400s) but on different scales: the second one uses log scale for easy comparison whereas the third one uses linear scale for better visualization of differences between drives. Click the buttons below each graph to switch the source data.

For more detailed description of the test and why performance consistency matters, read our original Intel SSD DC S3700 article.

  Samsung SSD 850 Pro Samsung SSD 840 Pro SanDisk Extreme Pro Intel SSD 730 OCZ Vector 150
7% Over-Provisioning - - -
12% Over-Provisioning
25% Over-Provisioning

Wow, this is awesome. Even with the default 7% over-provisioning, the 850 Pro is pushing almost as many IOPS as the Extreme Pro with its 12% over-provisioning. When the over-provisioning is increased to the same 12% level, the 850 Pro is a leader without a doubt. Only the Vector 150 can come close, although it is nowhere hear as constant as the IOPS is ranging between 10K and 30K, whereas the 850 Pro can maintain a steady line.

When compared with the 840 Pro, the upgrade is tremendous. IO consistency was always the weak point of the 840 Pro, so it is great to see that Samsung has paid a great effort to fix that in the 850 Pro. A part of the performance increase obviously comes from the usage of V-NAND because with shorter program and erase latencies, the steady-state performance increases as the garbage collection takes less time and there are more empty blocks available.

Some of you may wonder the odd capacities at 25% over-provisioning but the reason is that I noticed an error in the old ones. Basically, the old 25% numbers were in gibibytes (i.e. 1024^3 bytes) whereas the other capacities have always been in gigabytes (1000^3 bytes). I decided to unify the capacities and now they are all reported in gigabytes. The actual testing or over-provisioning levels have not changes -- it is simply a matter of how the capacities are represented.

  Samsung SSD 850 Pro Samsung SSD 840 Pro SanDisk Extreme Pro Intel SSD 730 OCZ Vector 150
7% Over-Provisioning - - -
12% Over-Provisioning
25% Over-Provisioning

 

  Samsung SSD 850 Pro Samsung SSD 840 Pro SanDisk Extreme Pro Intel SSD 730 OCZ Vector 150
7% Over-Provisioning - - -
12% Over-Provisioning
25% Over-Provisioning

 

RAPID 2.0: Support For More RAM & Updated Caching Algorithm AnandTech Storage Bench 2013
Comments Locked

160 Comments

View All Comments

  • Pastuch - Wednesday, July 2, 2014 - link

    When will we see Vnand in smart phones? This 16gb Nexus 5 is brutal! Always out of space.
  • ajlueke - Wednesday, July 2, 2014 - link

    Page 1, "Scaling below 20nm was seemed", I believe you intended "Scaling below 20nm was seen".
  • Automaticman - Wednesday, July 2, 2014 - link

    Can current EVO 840 users upgrade to Magician 4.4 and get the benefits of RAPID 2.0 (assuming they have >16GB DRAM)?
  • bsd228 - Wednesday, July 2, 2014 - link

    just as RAPID support was extended to the 840 PRO, I would expect this to support the 840 pro/evo soon, if not right off the bat.
  • Automaticman - Sunday, July 6, 2014 - link

    Well, I was certainly able to upgrade to Magician 4.4, and it did take a couple reboots while it was re-activating RAPID. I am going to guess and say yes it seems to be the new version of RAPID, but I don't see anywhere that it actually says RAPID 2.0 or any indication of how much memory it has available.
  • sirvival - Wednesday, July 2, 2014 - link

    Ah ok.
    When I select the 470 in Bench there is no slumber so I got confused.

    Since power cosumption is a big thing in Mobile could you do the following:
    Bench the impact on the Battery of a Laptop due to a fast drive.
    E.g. drive A is fast but has the downside that it draws more under load as drive B which is slower. But since its done faster it returns to idle faster.
    I mean impact on real world scenarios.
    Or how much power was used for bench x etc. and have a average per hour or something like that.
  • sirvival - Wednesday, July 2, 2014 - link

    damn this was to be a reply to
    http://www.anandtech.com/comments/8216/samsung-ssd...
    sorry
  • Nickat - Thursday, July 3, 2014 - link

    Thank you so much. You explained everything so well.
  • Stokkolm - Thursday, July 3, 2014 - link

    Newegg still has them for preorder at the more expensive price, hopefully they drop those before the release date.
  • skarthikeyan - Monday, July 7, 2014 - link

    Hi, How come random read is 106.8MB/sec and random write is 292.4MB/sec for the SSD 850 Pro 256 GB? Aren't writes supposed to be slower than reads?

Log in

Don't have an account? Sign up now