Performance Consistency

Performance consistency tells us a lot about the architecture of these SSDs and how they handle internal defragmentation. The reason we do not have consistent IO latency with SSDs 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 dropdown selections 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.

SanDisk Ultra II 240GB
25% Over-Provisioning

The IO consistency of the Ultra II is not too good. At steady-state it averages about 2,500 IOPS, whereas MX100 and 840 EVO manage around 4,000-5,000. However, what is positive is the fact that it takes about 200 seconds before the performance starts to drop, which is mostly due to the fact that the Ultra II does not provide as many IOPS in the first place.

Since we are dealing with a value client drive, I would not consider the IO consistency to be a big issue because it is very unlikely that the drive will be used in a workload that is even remotely comparable to our performance consistency benchmark, but nevertheless it is always interesting to dive into the architecture of the drive. While the Ultra II is not the fastest SSD, it is still relatively consistent, which is ultimately the key to a smooth user experience.

SanDisk Ultra II 240GB
25% Over-Provisioning


SanDisk Ultra II 240GB
25% Over-Provisioning


TRIM Validation

To test TRIM, I filled the Ultra II with sequential 128KB data and proceeded with a 30-minute random 4KB write (QD32) workload to put the drive into steady-state. After that I TRIM'ed the drive by issuing a quick format in Windows and ran HD Tach to produce the graph below.

And TRIM works as it should.

The Introduction, The Drive & The Test AnandTech Storage Bench 2013


View All Comments

  • Death666Angel - Saturday, September 17, 2016 - link

    That's mostly because the MX100 has been outdated for a while. Crucial/Micron has the MX200 and now MX300 and even a BX100. As long as the MX100 had been in play, it was a great value. But the MX200 and BX100 didn't replace it adequately. I hope the 300 does better. Reply
  • danjw - Tuesday, September 16, 2014 - link

    So, basically Sandisk and Micron are both a generation behind Samsung in performance and Micron is a generation behind in features as well. With the 850 Pro offering a 10 year warranty and winning hands down on performance, Sandisk and Micron can for the scraps of the value market.

    That said, I do hope others, including Toshiba, can get their act together and actually compete with Samsung. I just don't see it happening quite yet.
  • Kristian Vättö - Tuesday, September 16, 2014 - link

    SanDisk offers a 10-year warranty on the Extreme Pro as well and it is close to the 850 Pro in performance while being generally cheaper, so I wouldn't say Samsung is a generation ahead. Micron is a different story, but their focus has never been on the high performance niche.

    Toshiba's SSD business is more or less OEM only and there are no signs of that being about to change. Their branded side is very small and there is no marketing push behind it, so while Toshiba will remain strong in the OEM side I don't see them having any major role in the retail business.
  • ZeDestructor - Tuesday, September 16, 2014 - link

    Is there any chance you could get a Crucial/Micron M550DC in for review? From a review I read a while back at, it seemed like a pretty fast drive, up there with the intel DC S3x00 dsrives. Reply
  • Kristian Vättö - Wednesday, September 17, 2014 - link

    We reviewed the M500DC when it was launched:
  • Wixman666 - Wednesday, September 17, 2014 - link

    I believe he meand that they are a generation behind as far as TLC SSDs go. Since Toshiba bought OCZ, they'll use that brand to push their retail business. Reply
  • MrSpadge - Wednesday, September 17, 2014 - link

    That is a very short-sighted view. The 850 Pro is almost twice as expensive as these value drives. If the performance of those value drives is enough (and for many people it will be) than paying twice as much for no real-world benefit is a pretty bad proposition.

    Sure, 10 years of warrenty sound nice.. but is a small 850 Pro still worth anything in 5+ years? And a shorter warrenty doesn't mean the other drives are guaranteed to fail shortly after that either.
  • hojnikb - Tuesday, September 16, 2014 - link

    Wow, i never though nand dies are actually larger than 128Gbit. I always figered that spare area, bad blocks and ECC stuff comes from GB to GiB conversion (which works out to be ~7%).

    So does real die capacity differ with other manufacturers aswell ?
  • hojnikb - Tuesday, September 16, 2014 - link

    I wonder if ULTRA II will exhibit the same issues with reading cold files as EVO. It seems that both 840 and EVO are losing on read performance with old files. And since this seems to be limited to TLC drives there might just be a slight chance, that ultra ii could potentially be affected aswell ?
    Any comments on that ?
  • iLovefloss - Wednesday, September 17, 2014 - link

    I thought it was confirmed that issue was limited to the 840 EVO only with the original 840 and the 840 Pro showing no signs of issues. Honestly, it seems more like a controller issue than NAND issue. Reply

Log in

Don't have an account? Sign up now