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)

When the Heavy test is run on an empty Intel SSD 660p, the test is able to operate almost entirely within the large SLC cache and the average data rate is competitive with many high-end NVMe SSDs. When the drive is full and the SLC cache is small, the low performance of the QLC NAND shows through with an average data rate that is slower than the 600p or Crucial MX500, but still far faster than a mechanical hard drive.

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

The average and 99th percentile latency scores of the 660p on the empty-drive test run are clearly high-end; the use of a four-channel controller doesn't seem to be holding back the performance of the SLC cache. The full-drive latency scores are an order of magnitude higher and worse than other SSDs of comparable capacity, but not worse than some of the slowest low-capacity TLC drives we've tested.

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

The average read latency of the Intel 660p on the Heavy test is about 2.5x higher for the full-drive test run than when the test is run on a freshly-erased drive. Neither score is unprecedented for a NVMe drive, and it's not quite the largest disparity we've seen between full and empty performance. The average write latency is where the 660p suffers most from being full, with latency that's about 60% higher than the already-slow 600p.

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

The 99th percentile read latency scores from the 660p are fine for a low-end NVMe drive, and close to high-end for the empty-drive test run that is mostly using the SLC cache. The 99th percentile write latency is similarly great when using the SLC cache, but almost 20 times worse when the drive is full. This is pretty bad in comparison to other current-generation NVMe drives or mainstream SATA drives, but is actually slightly better than the Intel 600p's best case for 99th percentile write latency.

ATSB - Heavy (Power)

The Intel SSD 660p shows above average power efficiency on the Heavy test, by NVMe standards. Even the full-drive test run energy usage is lower than several high-end drives.

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

86 Comments

View All Comments

  • eastcoast_pete - Tuesday, August 07, 2018 - link

    Firstly, thanks for calling me one of the "idiots salivating over elusive real world endurance rating numbers". I guess it takes one to know one, or think you found one. Second, I am quite aware of the need to have a sufficient sample size to make any inference to the real world. And third, I asked the question because this is new NAND tech (QLC), and I believe it doesn't hurt to put the test sample that the manufacturer sends through its paces for a while, because if that shows any sign of performance deterioration after a week or so of intense use, it doesn't bode well for the maturity of the tech and/or the in-house QC.
    And, your last comment about your 80 GB near first gen drive shows your own ignorance. Most/maybe all of those early SSDs were SLC NAND, and came with large overprovisioning, and yes, they are very hard to kill. This new QLC technology is, well, new, so yes I would like to see some stress testing done, just to see if the assumption that it's all just fine holds, at least for the drive the manufacturer provided.
    Reply
  • Oxford Guy - Tuesday, August 07, 2018 - link

    If a product ships with a defect that is shared by all of its kind then only one unit is needed to expose it. Reply
  • mapesdhs - Wednesday, August 08, 2018 - link

    Proof by negation, good point. :) Reply
  • Spunjji - Wednesday, August 08, 2018 - link

    That's a big if, though. If say 80% of them do and Anandtech gets the one that doesn't, then...

    2nd gen OCZ Sandforce drives were well reviewed when they first came out.
    Reply
  • Oxford Guy - Friday, August 10, 2018 - link

    "2nd gen OCZ Sandforce drives were well reviewed when they first came out."

    That's because OCZ pulled a bait and switch, switching from 32-bit NAND, which the controller was designed for, to 64-bit NAND. The 240 GB model with 64-bit NAND, in particular, had terrible bricking problems.

    Beyond that, there should have been pressure on Sandforce's decision to brick SSDs "to protect their firmware IP" rather than putting users' data first. Even prior to the severe reliability problems being exposed, that should have been looked at. But, there is generally so much passivity and deference in the tech press.
    Reply
  • Oxford Guy - Friday, August 10, 2018 - link

    This example shows why it's important for the tech press to not merely evaluate the stuff they're given but go out and get products later, after the initial review cycle. It's very interesting to see the stealth downgrades that happen.

    The Lenovo S-10 netbook was praised by reviewers for having a matte screen. The matte screen, though, was replaced by a cheaper-to-make glossy later. Did Lenovo call the machine with a glossy screen the S-11? Nope!

    Sapphire, I just discovered, got lots of reviewer hype for its vapor chamber Vega cooler, only to replace the models with those. The difference? The ones with the vapor chamber are, so conveniently, "limited edition". Yet, people have found that the messaging about the difference has been far from clear, not just on Sapphire's website but also on some review sites. It's very convenient to pull this kind of bait and switch. Send reviewers a better product then sell customers something that seems exactly the same but which is clearly inferior.
    Reply
  • Oxford Guy - Tuesday, August 07, 2018 - link

    People trusted Samsung with the 840 and then, oops...

    The real rule is verify then trust.
    Reply
  • mapesdhs - Wednesday, August 08, 2018 - link

    One thing about the 840 EVO issue which was a real pain was trying to find out if the same thing affected the standard 840. In the end my conclusion was yes, but few sites bothered to mention it. Oddly enough, of the many SSDs I have, one of the very few that did die was a standard 840. I never bought an 840 EVO because of the reports that came out, but I have a fair few 840 Pros and a heck of a lot of OCZs. Reply
  • Spunjji - Wednesday, August 08, 2018 - link

    It was pretty obvious that the 840 was affected because it used the same NAND as the 840 Evo, just without the caching mode. It was also pretty obvious that Samsung didn't care because it was "old" so they never properly fixed it. Reply
  • OwCH - Wednesday, August 08, 2018 - link

    Ryan, I love that you will. It is not easy for the user to find real world data on these things and it is, at least to me, information that I want before making the decision to buy a drive.

    Looking forward to it!

    Thanks!
    Reply

Log in

Don't have an account? Sign up now