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 IOPS divided by 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. These results are for all drives 240GB and up.

Steady-State 4KB Random Write Performance

Steady-state performance is fairly good, although given that the SX930 employes 12% over-provisioning it's expected to perform better than drives with only 7%. 

Steady-State 4KB Random Write Consistency

Consistency, on the other hand, isn't that good. The good news is that the JMF670H is more consistent than the SM2246EN in the BX100, but there's a long way to achieve Samsung-level consistency. 

ADATA XPG SX930
Default
25% Over-Provisioning

As the SX930 isn't very consistent, we saw performance dropping below 1,000 IOPS. It seems that consistency is one of the areas that truly separate Samsung and Marvell drives from the rest because JMicron, Silicon Motion and Phison based drives all have trouble sustaining steady performance. Basically, the baseline performance is about 1,000 IOPS for all controllers with frequent peaks of +5,000 IOPS, whereas Samsung and Marvell drives have very little variation in performance. I suspect the controller design itself has something to do with this because Samsung and Marvell controllers are all multi-core, but JMicron and Silicon Motion rely on single-core designs for higher cost efficiency. 

ADATA XPG SX930
Default
25% Over-Provisioning
Introduction, The Drives & The Test AnandTech Storage Bench - The Destroyer
POST A COMMENT

67 Comments

View All Comments

  • sonny73n - Sunday, July 19, 2015 - link

    Oh really? Was it another firmware update for the 840EVO? When? I just threw my 840EVO out about 5 days ago after 2 firmware updates this year which did not fix the problem. The last update I had, Samsung had some kind of optimization in "Magician" (lmao) by moving all the old data to new blocks. Yeah ok, I had that 250GB EVO filled with about 190GB. It took like forever to finish and the optimization had to be run frequently in order to keep the 840EVO runs near advertised specs.
    "Vitriol" or whatever, I would take any SSD with JMicron controller over the 840EVO in a heart beat. At least I wouldn't feel like being cheated out of paying for something that it's clearly NOT!
    I'm thinking anyone that purchased the 840EVO should get together and file a class action lawsuit on Samsung for faulty advertising, consumer fraud or something like that.
    Reply
  • voicequal - Monday, July 20, 2015 - link

    Can you get a replacement under warranty? Reply
  • Oxford Guy - Sunday, July 19, 2015 - link

    "Samsung has made 1 slip-up that was fixed with a firmware update."

    False. The 840 and 840 EVO drives reportedly have a permanent TLC-caused flaw. The only thing Samsung has managed to do, last I heard (and that was two "fixed" later) is re-write the data over and over again to paper over the problem.

    The TLC is too weak to avoid voltage degradation so data needs to be rewritten to prevent massive slowdowns in read speed. I don't think Apple has ever bothered to release anything to fix the Samsung OEM drives they put their brand on either.
    Reply
  • Oxford Guy - Sunday, July 19, 2015 - link

    Interestingly, too, Apple decided to dump TLC, at least for its mobile line, sometime ago -- citing the inherent flaws. One could look at that move as being part of their feud with Samsung but I doubt that was the main motivation. Reply
  • zodiacfml - Sunday, July 19, 2015 - link

    that's what truly happened. it only worked good when it was new. Reply
  • jabber - Monday, July 20, 2015 - link

    Running SATA II? Buy the cheapest Kingston V300 as it will push 275MBps all day long.

    Running SATA III? Buy a BX100 and be done with it.
    Reply
  • Saiyan32 - Sunday, November 27, 2016 - link

    the firmware update really did the trick .. it has improved by a lot... I request anandtech to another review on this.... Reply

Log in

Don't have an account? Sign up now