AnandTech Storage Bench - Light

Our Light storage test has relatively more sequential accesses and lower queue depths than The Destroyer or the Heavy test, and it's by far the shortest test overall. It's based largely on applications that aren't highly dependent on storage performance, so this is a test more of application launch times and file load times. This test can be seen as the sum of all the little delays in daily usage, but with the idle times trimmed to 25ms it takes less than half an hour to run. Details of the Light test can be found here. As with the ATSB Heavy test, this test is run with the drive both freshly erased and empty, and after filling the drive with sequential writes.

ATSB - Light (Data Rate)

The peak performance of the Samsung 970 EVO on our Light test is record-setting, but that's only an improvement of 6% over the Samsung 960 PRO's average data rate—not a big enough difference to notice on such a light workload. When the test is run on a full drive, the 970 EVO loses more performance than most top drives, because it is one of the few TLC-based drives in that tier.

ATSB - Light (Average Latency)ATSB - Light (99th Percentile Latency)

The average and 99th percentile latencies from the 970 EVO on the Light test are some of the best we've measured, still represent tiny improvements over Samsung's previous high-end SSDs.

ATSB - Light (Average Read Latency)ATSB - Light (Average Write Latency)

The Samsung 970 EVO leads over other flash-based SSDs for both average read and write latency, but the differences are just a few microseconds and thus completely imperceptible.

ATSB - Light (99th Percentile Read Latency)ATSB - Light (99th Percentile Write Latency)

The Samsung 970 EVO is the first drive to keep its 99th percentile write latency below 100µs whether or not the Light test is run on a full drive, showing that the 4-6GB static SLC cache is still quite useful even when the dynamically sized portion of the cache is unavailable. The 99th percentile read latency shows that Samsung has improved their full-drive QoS over the 960 EVO, but for the 500GB model in particular they still have room for improvement.

ATSB - Light (Power)

The energy usage of the Samsung 970 EVO is slightly higher than the PM981, putting the 970 EVO in last place for efficiency among flash-based SSDs. The energy usage of the 970 EVO doesn't show much variation between running the test on a full vs empty drive, despite the large performance differences between those scenarios.

AnandTech Storage Bench - Heavy Random Performance
Comments Locked

68 Comments

View All Comments

  • jjj - Wednesday, April 25, 2018 - link

    The conclusion was shocking, nowadays when nobody has ethics and they just try to sell and sell and sell. What you did there is like telling people that a 500$ GPU is nuts and really, I have zero expectations for anyone to say something like that anymore. Today is all about manipulating people into being stupid and buying a politician or a product.
    You should make your own site, would be the only honest hardware review site on the planet. People are getting worse and worse in managing their money and parents, schools, the press are not doing anything about it.

    Congrats and thanks, I've missed seeing some sanity in a review.
  • peevee - Monday, April 30, 2018 - link

    Yep. Now if only they would start including any real-life test. Recoding a large video. Compilation of a software package. Decompressing a zip archive. I suspect they don't do it because they need to sell ads from large-margin manufacturers like Samsung.
  • hansmuff - Wednesday, May 2, 2018 - link

    If only you'd read the article properly and see what the Destroyer etc tests actually ARE.. they're explained in great detail. Follow the links. All of those things ARE IN THERE.
  • Urbanos - Sunday, May 6, 2018 - link

    Its annoying that your charts seem to have little consistency, from chart to chart one can't easily follow the comparison part for part. Older Anandtech articles never had this problem.
  • mapesdhs - Sunday, May 6, 2018 - link

    Billy, I think it would worth adding something in the article somewhere to explain why in several cases the 950 Pro still shows so strongly after all this time. I'm intrigued. I knew it could beat the 960 EVO, but even so, sometimes it's above the 970 and other unexpected newer models.

    Ian.
  • Stephan0711 - Thursday, May 10, 2018 - link

    960 pro 512 TB or 970 evo 500TB for desktop use / gaming? What do you guys think?
    Which benchmark represents this kind of usage?
  • ETHANH - Friday, May 11, 2018 - link

    My friend just got a 970 pro 1TB yesterday, after we tried it out. I like my HP EX920 better, similar performance, much cheaper prices.
  • Abad - Saturday, May 19, 2018 - link

    Hi Friends,
    My pocket allows for the 512GB only and I was waiting results from the 970 and the EX920 before I write this: Toshiba RD400 512GB is the one to go for. If you factor in: price, performance and warranty, its unbeatable. To see 2016 MLC technology competing with Q2 2018 tech and winning must ring bells. Its no rocket science. The RD400 uses the more expensive and faster MLC cells, but because it comes from 2016, it is selling same price as the cheaper and slower TLC cells used in today's SSDs. You can't have a safer bet, can you?
    But then, I heard some talk that OCZ SSDs go south but even that wont deter me from going for the RD400. What do you think?

Log in

Don't have an account? Sign up now