Mixed Random Read/Write Performance

Mixed read/write tests are also a new addition to our test suite. In real world applications a significant portion of workloads are mixed, meaning that there are both read and write IOs. Our Storage Bench benchmarks already illustrate mixed workloads by being based on actual real world IO traces, but until now we haven't had a proper synthetic way to measure mixed performance. 

The benchmark is divided into two tests. The first one tests mixed performance with 4KB random IOs at six different read/write distributions starting at 100% reads and adding 20% of writes in each phase. Because we are dealing with a mixed workload that contains reads, the drive is first filled with 128KB sequential data to ensure valid results. Similarly, because the IO pattern is random, I've limited the LBA span to 16GB to ensure that the results aren't affected by IO consistency. The queue depth of the 4KB random test is three.

Again, for the sake of readability, I provide both an average based bar graph as well as a line graph with the full data on it. The bar graph represents an average of all six read/write distribution data rates for quick comparison, whereas the line graph includes a separate data point for each tested distribution. 

Iometer - Mixed 4KB Random Read/Write

Quite surprisingly the SM951 and Samsung drives in general don't do very well with mixed data.

Samsung SM951 512GB

The reason lies in the fact that the performance of Samsung drives plummets when the share of writes is increased. At 80/20 read/write, the Samsung drives manage to do pretty well, but after that the performance declines to about 40MB/s. What's odd is that the performance is also bad with 100% writes, whereas with other drives we usually see a spike here. I'm guessing there's some garbage collection going on here that causes the performance degradation. 

Mixed Sequential Read/Write Performance

The sequential mixed workload tests are also tested with a full drive, but I've not limited the LBA range as that's not needed with sequential data patterns. The queue depth for the tests is one.

Iometer - Mixed 128KB Sequential Read/Write

With 128KB sequential data, however, the SM951 is the king of the hill. There's a clear difference between PCIe and SATA based drives, although it's worthy to note that the difference is mostly due to PCIe drives having much higher throughput at 100% reads and writes (i.e. the infamous bathtub curve). 

Samsung SM951 512GB
Sequential Performance ATTO & AS-SSD
Comments Locked

128 Comments

View All Comments

  • Kristian Vättö - Sunday, March 1, 2015 - link

    The 840 EVO issue takes weeks, even months to show up, so testing it is not something that we can really incorporate in our test suite.

    The read speed depends on the test you use and its specifications. The figures are always "up to" and tend to be based on high queue depth 128KB sequential read performance. You may want to try multiple benchmarking apps, but especially ATTO tends to show high performance since it tests multiple IO sizes.

    And yes, we run the SSD as a secondary drive to eliminate any OS overhead.
  • MFinn3333 - Saturday, February 28, 2015 - link

    Is there any way you can review the Fujitsu FSX 240GB? It's an old drive but it is the only consumer level drive that I am aware of that uses entirely SLC?
  • Kristian Vättö - Sunday, March 1, 2015 - link

    At least for now it's not in the review queue, but I will keep it in mind in case I have excess time.
  • kenshinco - Monday, March 2, 2015 - link

    How can we get the sm951 to runs up to the rated speed? The rated speed for 512gb is 2.15gbs/1550mbs read/write, but i got only 1560mbs/1570mbs read/write. I got temp monitor never pass 75 when testing.
  • Kristian Vättö - Monday, March 2, 2015 - link

    I was able to achieve 2250MB/s with 128KB sequential read (QD32) on an empty drive, which is how the read performance has been rated. That's not a realistic bench, though, because in reality you will never be reading from an empty drive.
  • Gonemad - Thursday, March 5, 2015 - link

    No word on Novachips 8TB SSD yet?

    http://www.theregister.co.uk/2015/03/05/eight_tera...
  • CallsignVega - Friday, March 6, 2015 - link

    I just purchased the SM951 from the UK (512GB for $450). They are out there, you just have to know where to look.
  • vegipiniata - Wednesday, March 11, 2015 - link

    I got one SM951 512GB for 340£
    They were gone later that day.
    Have Z97 Extreme9 and can't set it as the boot drive though :(
    Bios 1.3 from DEC 2014
    any chance it's the BIOS fault (too old)?
  • Stas - Friday, March 13, 2015 - link

    There we go. Finally an incentive to upgrade from 2500k to a new platform. Once mobos with M.2 and NVM hit the market in Summer/Fall, I will be retiring the faithful rig.
  • Edgar_in_Indy - Friday, March 13, 2015 - link

    The 2500k is too good to retire!

    When I upgraded my main system a few weeks ago, I recycled my old 2500k and the board for use in a living room HTPC build that can handle 4K video files and do some gaming, all while running Windows Media Center with 5 ATSC tuners.

Log in

Don't have an account? Sign up now