AnandTech Storage Bench - Heavy

Our Heavy storage benchmark is proportionally more write-heavy than The Destroyer, but much shorter overall. The total writes in the Heavy test aren't enough to fill the drive, so performance never drops down to steady state. This test is far more representative of a power user's day to day usage, and is heavily influenced by the drive's peak performance. The Heavy workload test details can be found here. This test is run twice, once on a freshly erased drive and once after filling the drive with sequential writes.

ATSB - Heavy (Data Rate)

The Silicon Motion NVMe drives provide excellent overall performance when the Heavy test is run on an empty drive, but at the cost of much worse full-drive performance. This effect is not as strong for the 1TB models as for the 2TB HP EX950, which has also regressed overall from the performance of the pre-production firmware. The very slight gains the 1TB SM2262EN drives make over the HP EX920 in empty-drive performance do not come close to justifying the sacrifice in full-drive performance, especially since the SM2262 was already subpar in this respect.

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

The average and 99th percentile latency scores from the SM2262EN drives are unrivaled when the Heavy test is run on an empty drive, but when the drives are full the average latency scores regress to low-end NVMe levels and the 99th percentile latency scores end up comparable to mainstream SATA drives.

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

The best-case average read latency scores from the SM2262EN drives when the Heavy test is run on an empty drive are unchanged from the earlier SM2262 drives and remain among the best from any flash-based SSD. The empty-drive average write latencies are significantly faster than the older drives and are comparable to what Samsung's latest 970 EVO Plus provides. But as with the other metrics, performance on a full drive is not competitive with other high-end SSDs.

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

The 99th percentile read and write latency scores repeat the same story as above. Silicon Motion has optimized these drives for extremely good performance when they don't have much data to keep track of and can operate almost entirely from their SLC caches, but at great cost to worst-case behavior.

ATSB - Heavy (Power)

The ADATA SX8200 Pro again turns in much better power consumption scores than the HP EX950 or other SMI-based NVMe drives, but at its best it is still a bit more power-hungry than the WD Black and Toshiba's XG6. Due to the extreme performance drops when operating with a full drive, the SM2262EN drives all require much more energy to complete those test runs. That disparity in full vs empty energy efficiency is only matched by the QLC based drives like the Crucial P1 that also use a Silicon Motion controller and prioritize SLC cache performance.

AnandTech Storage Bench - The Destroyer AnandTech Storage Bench - Light
POST A COMMENT

43 Comments

View All Comments

  • eddieobscurant - Wednesday, February 6, 2019 - link

    Nice review , as always although I disagree with your conclusion. Peak performance is what most people want. Reply
  • Billy Tallis - Wednesday, February 6, 2019 - link

    My reviews are intended to advise consumers who are buying SSDs to increase their productivity, not people who are trying to set a high score on Crystal Disk Mark.

    People who care about real-world productivity rather than CDM scores should recognize that imperceptible improvements to peak performance are probably not worth the sacrifice of significant regressions in performance on niche heavy workloads. For a lot of users, both SM2262 and SM2262EN drives are fast enough. Beyond those lighter use cases, I think it will be more common to find the SM2262EN coming up short in a meaningful way than to find it providing a tangible performance advantage over SM2262.
    Reply
  • mapesdhs - Thursday, February 7, 2019 - link

    I can't help wondering how some of the old favourites would behave in these comparisons, the 950 EVO/Pro, 960s, etc. Have things really moved on that much? Reply
  • Billy Tallis - Thursday, February 7, 2019 - link

    We have at least partial test results in Bench for most of the old drives that aren't worth including in every review: https://www.anandtech.com/bench/product/2219?vs=23... Reply
  • eddieobscurant - Thursday, February 7, 2019 - link

    It's not about crystal disk mark score. It's about almost no one of the everyday user, playing games, surfing the web and using microsoft office, will come near your "light" test, let alone "heavy" or "torture".

    Most of them need high random reads for their computer to feel snappy and responsive, and a big enough a slc cache to accommodate a full bluray of writes.
    Reply
  • Billy Tallis - Thursday, February 7, 2019 - link

    "Most of them need high random reads for their computer to feel snappy and responsive,"

    They already have that. Further increases to random read performance won't make the system feel any more responsive during light workloads, as demonstrated by SYSmark. High-end NVMe SSDs are already way past the point of diminishing returns for peak random read speeds, especially for lighter workloads where a few GB of DRAM used by the OS for caching is enough to almost completely decouple storage performance from application responsiveness.
    Reply
  • eddieobscurant - Friday, February 8, 2019 - link

    So, you're saying that optane doesn't feel more responsive to you, or that the high random reads of optane isn't responsible for feeling more responsive than a high end nvme ssd ? Reply
  • Dark_wizzie - Wednesday, February 6, 2019 - link

    Why does perf drop on 2tb model? Reply
  • Dark_wizzie - Thursday, February 7, 2019 - link

    For low qd random reads, sorry. Reply
  • Dark_wizzie - Thursday, February 7, 2019 - link

    And... serves me right for commenting before finishing the last page of the article. >.>
    oh well.
    Reply

Log in

Don't have an account? Sign up now