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)

As with The Destroyer, Samsung's SATA SSDs were still on top before the Samsung 860 PRO arrived. The 860 PRO brings only modest improvements to the average data rates on the Heavy test, and the 512GB models is slightly faster than the 4TB model. The only real outlier here is the Crucial MX300, for its poor performance when the drive is full.

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

The Samsung MLC SSDs and the SanDisk Ultra 3D offer the best average and 99th percentile scores among the SATA drives, but even the current models from Intel and Crucial are close enough to be indistinguishable without benchmarking tools.

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

Most of the drives show small differences in average read latency between the full and empty drive test runs, but it's the write latencies that account for the bulk of the delays experienced during this test. The Samsung 860 PROs are among the several drives that show virtually no difference in average write latency when the drive is full.

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

The 99th percentile read and write latency scores show that most of these SATA SSDs are equally competent at keeping latency under control. As usual, the Crucial MX300's full drive results stand out as particularly bad, and the BX300 is revealed to have a problem with high latency writes whether or not it is full.

ATSB - Heavy (Power)

The 860 PRO mostly eliminates the gap in power efficiency relative to the modern competitors. The 4TB model requires slightly more power than the 512GB, but is still a substantial improvement over the multi-TB 850s.

AnandTech Storage Bench - The Destroyer AnandTech Storage Bench - Light
Comments Locked

64 Comments

View All Comments

  • MayDayComputers - Wednesday, January 24, 2018 - link

    It wakes up in 8 milliseconds. The graph is in nanoseconds.
  • MayDayComputers - Wednesday, January 24, 2018 - link

    Yikes. Actually I was off, it wakes up in 8 nanoseconds, not milliseconds. Even at 8 milliseconds, you would never notice. This is 1000x faster than that.

    “A microsecond is equal to 1000 nanoseconds or 1/1,000 milliseconds. ” -source Wikipedia
  • stux - Saturday, February 17, 2018 - link

    Actually a million times faster.
  • letmepicyou - Wednesday, January 24, 2018 - link

    So...tests were done a while back that showed that 2x 850 EVOs in RAID 0 outperformed a single 850 Pro. The allure of putting 2 500gb EVOs in RAID for $300 and getting better performance than a single PRO 1TB for $450 was a no-brainer IMO, and boy does it scoot. My question is, what do RAID numbers look for the new 860's? Will it still make sense to RAID the EVO's? Or will the 860 series price/perf/space metric slant more towards the single PRO drive?
  • BurntMyBacon - Wednesday, January 24, 2018 - link

    Given that the 860 Pro struggles to distance itself from its EVO counterpart in a straight up comparison, I think its safe to say 2x860EVO will outperform 1x860PRO in the same metrics that 2x850EVO outperforms 1x850PRO. Also, MSRP shows 2x860EVO 500GB costing $340 vs $480 for the 1TB 860PRO. Your price/perf/space metric will not be slanting towards the PRO drive.
  • Luckz - Monday, May 14, 2018 - link

    SATA SSD RAID0 only makes sense if you need 'left to right copying' and can't do NVMe (which is much faster).
  • Roen - Monday, January 29, 2018 - link

    I'd like to see what Enterprise SATA / SAS SSDs the author has in mind that is a better balance of specs and price, especially price.

    The cheapest Seagate Nytro SAS SSD I've found with 1700 / 850 Sustained R/W is > $1500.
  • peevee - Tuesday, January 30, 2018 - link

    There is absolutely no point paying twice as much compared to other drives.
  • JokerzWild - Sunday, February 11, 2018 - link

    Good review, but it seems like there’s a “missing link” in the data presented. You mention in the Introduction that you are using a 512GB 850 PRO from, “the original generation using 32L 3D NAND and LPDDR2 DRAM, rather than the updated model with 48L 3D NAND and LPDDR3.” You also say that you are using the test results from the 2TB 850 Pro review, which I believe still used Samsung’s 2nd-generation (32L) 3D MLC NAND with LPDDR3 in the controller rather than their 3rd-generation (48L) product. I can’t tell which version of the 500GB 850 EVO is being presented for this review, but I suspect it is V1 as well based on its power usage compared to the 4TB 850 EVO (which was offered in V2 only) numbers. In your recent reviews of other current SSDs (e.g. the SanDisk Ultra 3D and the Crucial MX500) it also appears that you are using the 32L/LPDDR2 versions (which I’ll call V1) rather than the 48L/LPDDR3 (V2) iterations of the 850 PRO and EVO.

    Would you please add the data for 850 EVO/PRO V2s to your test results? Alternatively, it would be interesting to see an article that looks at the progress of Samsung’s NAND and controllers in V1 (32L/LPDDR2) and V2 (48L/LPDDR3) of the 850 EVOs and PROs along with the 860s (64L/LPDDR4), preferably in the 1TB configuration since that configuration seems to yield the highest overall performance (at least in the 850s) and is a popular choice. I’ve seen a couple of articles that compared V1 and V2 of the 850 EVO, and it appeared that both performance and power consumption improved in V2. I have yet to seen any comparison of V1 and V2 of the 850 PRO. I seem to also recall reading that Samsung was claiming a 30% reduction in power consumption was one of the benefits in switching from its 2nd-generation to its 3rd-generation NAND, which would wipe out most of the power management gains claimed for the 860 PRO. The changes between V1 and V2 of the 850s appear just as significant as the changes between 850 V2s and the 860s (1 generation DRAM, +16L each), so why not add this data to the mix? Using V1 of the 850s probably overstates the differences between a recent 850 EVO/PRO and an 860 EVO/PRO. Presenting data on V2 of the 850s would also give users of 850 V2s a better idea of what they may be missing. It would also help bargain hunters who want that last little bit of performance from a top performing SATA drive decide if it’s better to buy a marked down 850 or a new 860 for their use cases.
  • Lady Fitzgerald - Tuesday, March 13, 2018 - link

    SATA will be around for a long time, most likely well past 5 years from now. It's plenty fast for storage. Not everyone needs blazing speed for storing music, videos, documents, pictures, etc.

Log in

Don't have an account? Sign up now