Performance Consistency

We've been looking at performance consistency since the Intel SSD DC S3700 review in late 2012 and it has become one of the cornerstones of our SSD reviews. Back in the days many SSD vendors were only focusing on high peak performance, which unfortunately came at the cost of sustained performance. In other words, the drives would push high IOPS in certain synthetic scenarios to provide nice marketing numbers, but as soon as you pushed the drive for more than a few minutes you could easily run into hiccups caused by poor performance consistency.

Once we started exploring IO consistency, nearly all SSD manufacturers made a move to improve consistency and for the 2015 suite, I haven't made any significant changes to the methodology we use to test IO consistency. The biggest change is the move from VDBench to Iometer 1.1.0 as the benchmarking software and I've also extended the test from 2000 seconds to a full hour to ensure that all drives hit steady-state during the test.

For better readability, I now provide bar graphs with the first one being an average IOPS of the last 400 seconds and the second graph displaying the standard deviation during the same period. Average IOPS provides a quick look into overall performance, but it can easily hide bad consistency, so looking at standard deviation is necessary for a complete look into consistency.

I'm still providing the same scatter graphs too, of course. However, I decided to dump the logarithmic graphs and go linear-only since logarithmic graphs aren't as accurate and can be hard to interpret for those who aren't familiar with them. I provide two graphs: one that includes the whole duration of the test and another that focuses on the last 400 seconds of the test to get a better scope into steady-state performance.

Steady-State 4KB Random Write Performance

Steady-state performance isn't mind blowing, although it's a little unfair to compare the 256GB SM951-NVMe against a 512GB SM951-AHCI because available NAND throughput can play a major role in steady-state performance with a properly designed controller and firmware.

Steady-State 4KB Random Write Consistency

The mediocre steady-state performance is replaced by outstanding consistency, though. During the last 400 seconds, the SM951-NVMe has standard deviation of only 1.12, whereas the next drives are in the order of hundreds with many drives surpassing 1,000.

Samsung SM951 NVMe

As there's practically no variation in performance, the graph is just a straight line after the initial cliff. There are zero up and down swings, which is something I've yet to see even in an enterprise SSD. Samsung has always done well in IO consistency, but in all honesty the SM951-NVMe sets a new bar for consistency. On the downside, I would rather take some variation with higher performance because especially for client workloads such level of consistency isn't really needed, but increased performance can always help with intensive IO workloads. Nevertheless, I'm very happy with the direction Samsung is taking because we still see some controller vendors not paying enough attention to consistency, but it's clearly a high priority for Samsung.

Unfortunately I couldn't run any tests with added over-provisioning because the hdparm commands I use for limiting the capacity do not work with NVMe drives. There are similar commands for NVMe drives too, but for now there is no publicly available utility for issuing those commands.

Samsung SM951 NVMe
Thermal Throttling Revisited AnandTech Storage Bench - The Destroyer
Comments Locked


View All Comments

  • Notmyusualid - Sunday, June 28, 2015 - link

    I'm SO with you on that statement. My 840 Evos have been awful. TLC is not for me, and I don't care what benchies you throw at me, I won't buy TLC nand now from anybody.
  • Notmyusualid - Sunday, June 28, 2015 - link

    Sorry, just noticed this is MLC and not TLC. Well, still going to be buyer-beware due to my last experience of slow down, firmware revisions etc with Samsung...
  • Impulses - Tuesday, July 21, 2015 - link

    There's not one SSD OEM that hasn't suffered some sorta critical firmware bug, and many have suffered thru more of it than Samsung and/or hardware defects...

    Crucial had some bricked drives, as did Intel using their own controller, never mind their Sandforce drive which had broken encryption, I'm more concerned about how they react and respond.

    Samsung wasn't brilliant at it from what I've seen, but they did keep re issuing updates so at least they stuck with it. The fact that they ignored the non EVO (which few seem to bring up) seems the most egregious error to me.

    The newest iteration of 3D TLC is quite a different animal anyway... I've had two Intel drives, two 128GB 830s, bought a 500GB 840 EVO as a gift, just bought a 1TB 850 EVO, and I'll probably get a 256GB SM951. /shrug
  • Romney4President - Friday, June 26, 2015 - link

    What the heck...? No Encryption... :/ Can anyone shed some light on this? If I remember right other manufactures coming out with NVMe will be supporting hardware based encryption. This is a deal breaker to me. Also do you think later this year we'll see a Samsung version with encryption?
  • Perk5 - Monday, June 29, 2015 - link

    Can this SM951nvme be used at full speed with asrockextreme6 z97 mobo, which has ultra m.2 slot. also the ahci model of sm951 has been sucessfully used as boot drive at full speed by many users having this mobo. And are there any drawbacks of the asrock mobo ?
  • boe - Tuesday, June 30, 2015 - link

    Just bring on those 10TB and 32TB SSD drives. I need them like yesterday.
  • JKJK - Sunday, July 12, 2015 - link

    It seems that there is a firmware update that makes the drive handle fua more effectively:
  • Impulses - Tuesday, July 21, 2015 - link

    They got a second drive with updated firmware, no word about an actual update, being mostly OEM drives they might've not even built in a way to update the firmware...
  • JoKO4184 - Monday, July 20, 2015 - link

    So, if both the AHCI and NVMe have the same hardware, do you guys reckon we'd be able to flash the NVMe firmware onto the AHCI? Or at least if Samsung feels generous enough to provide the upgrade for all AHCI owners?
  • caelumtech - Thursday, August 27, 2015 - link

    If the two variants are so similar, what prevents them from being "flash" compatible? Could an intrepid hacker Download the firmware from the NVME device and overwrite the flash of the AHCI version?

Log in

Don't have an account? Sign up now