Conclusion

The Crucial P1 SSD doesn't leave us particularly excited about the near-term prospects for QLC NAND in the consumer SSD market. The P1 is a decent entry-level NVMe SSD for less intensive workloads, but the wide gap between its best and its worst performance means the P1 comes with more caveats than most of its competition.

The Crucial P1 relies very heavily on its SLC cache to provide high performance, and that cache shrinks as the drive fills up. When the drive is full, a very write-heavy workload can overflow the cache and severely impact write speeds and even read performance to some extent. However when the drive isn't close to full, it is nearly impossible to fill the SLC cache with a realistic workload, and the Crucial P1 performs at least as well as any other entry-level NVMe drive, and sometimes rivals high-end NVMe drives. Compared to the Intel 660p, the SLC cache on the Crucial P1 seems to be more write-oriented and is not as good at accelerating read operations. It seems like the P1 may be a bit quicker to evict data from the cache and compact it into QLC blocks.

Overall the Crucial P1 is primarily aimed at consumer machines, and that definitely seems like the segment it's best suited for. A typical consumer use case would involve most of the large data on the drive coming from things like movies and video games that are rarely modified, as opposed to workstation workloads that generate massive files that constantly change. This is helpful to the P1 because it reduces the actual amount of writing the drive needs to do, though it does mean that the drive's variable-size SLC cache could end up quite small. On balance, even that small cache should be adequate given the limited amount of data that does change with most consumer workloads; though to be sure, overflowing the SLC cache is something that would be far more noticeable on the P1 than most TLC-based SSDs. But it is still not something that will happen to most consumers often enough to worry about.

That leaves the Crucial P1 as usually being very fast, and definitely faster overall than any SATA SSD. The use of QLC NAND doesn't cripple the drive, and is a detail that most consumers don't have to care about. Even at its worst, the P1 is still faster and more efficient than a mechanical hard drive. NVMe SSDs should aspire to more than that, but this will probably be true even of QLC SATA drives as long as they also avoid the low capacity points where high performance is impossible.

NVMe SSD Price Comparison
  240-280GB 480-512GB 960GB-1TB 2TB
Crucial P1   $109.99 (22¢/GB) $219.99 (22¢/GB) Coming Soon
Intel 660p   $99.99 (20¢/GB) $189.99 (19¢/GB) $349.99 (17¢/GB)
MyDigitalSSD SBX $54.99 (21¢/GB) $94.99 (19¢/GB) $219.99 (21¢/GB)  
Kingston A1000 $56.99 (24¢/GB) $97.99 (20¢/GB) $219.99 (23¢/GB)  
MyDigitalSSD BPX Pro $74.99 (31¢/GB) $129.99 (27¢/GB) $259.99 (27¢/GB) $519.99 (27¢/GB)
ADATA XPG SX8200 $62.99 (26¢/GB) $107.99 (22¢/GB) $214.99 (22¢/GB)  
HP EX920 $73.99 (29¢/GB) $119.99 (23¢/GB) $199.99 (20¢/GB)  
WD Black (2018) $85.99 (34¢/GB) $138.46 (28¢/GB) $259.75 (26¢/GB)  
Samsung 970 EVO $87.90 (35¢/GB) $147.99 (30¢/GB) $227.99 (23¢/GB) $577.95 (29¢/GB)
SATA Drives:        
Crucial MX500 $52.99 (21¢/GB) $84.95 (17¢/GB) $154.99 (15¢/GB) $328.99 (16¢/GB)
Samsung 860 EVO $57.99 (23¢/GB) $82.99 (17¢/GB) $162.99 (16¢/GB) $347.99 (17¢/GB)

The downsides of QLC NAND are pretty easy to accept if they come with a significant price cut, but that is not yet the case for the Crucial P1 or the Intel SSD 660p. The Crucial P1 is 22 cents per GB and the Intel 660p is 19 cents per GB, so Micron obviously needs to drop their prices at least a little bit to be at all competitive. Meanwhile, mainstream SATA SSDs are about 16–17 cents per GB for 512GB and larger capacities, and there are some high-performance TLC-based NVMe SSDs in the 20-22 cents per GB range.

Ultimately if you are going to pay extra for a NVMe SSD instead of a SATA drive, at current prices there are far more compelling options than the Crucial P1 and Intel 660p. We're accustomed to seeing entry-level NVMe SSDs get undercut by more popular high-performance drives as prices in general trend downward, and the two QLC drives we have so far on the consumer market are continuing that pattern. When QLC comes to the SATA SSD market, prices will need to be at or below 13 cents per GB to avoid repeating this problem.

Power Management
Comments Locked

66 Comments

View All Comments

  • DigitalFreak - Thursday, November 8, 2018 - link

    At this rate, by the time they get to H(ex)LC you'll only be able to write 1GB per day to your drive or risk having it fail.
  • PeachNCream - Thursday, November 8, 2018 - link

    Please don't give them any ideas! The last thing we need is NAND that generously handles a few dozen P/E cycles before dying. We've already gone from millions of P/E cycles to a few hundred in the last 15 years and data retention has dropped from over a decade to under six months. Sure you can get a lot more capacity for the price, but NAND needs to be replaced with something more durable sooner rather than later. (And no, I'm not advocating for Optane either, just something that lasts longer and has room for density improvements - don't care what that something is.)
  • MrCommunistGen - Thursday, November 8, 2018 - link

    I was expecting the extra DRAM to provide a more meaningful advantage over the Intel 660p... I guess it makes sense that Intel left it off to save on BOM.
  • Ratman6161 - Thursday, November 8, 2018 - link

    This could be a very good standard desktop drive if 1) the price is right and 2) you can accept that the 1 TB drive is really only good for up to 900 GB. You would just partition the drive such that there is 100 GB free (or make sure you always just keep that much space free) so you always have the maximum SLC cach available. For the price to be right, it has to be lower. Taking the prices from the article, the 1 TB P1 is only $8 cheaper than a 970 EVO. Now if they could get the price down to the same territory as the current MX 500 they might have something.
  • Billy Tallis - Thursday, November 8, 2018 - link

    Leaving 10% of the drive unpartitioned won't be enough to get the maximum size SLC cache, because 1GB of SLC cache requires 4GB of QLC to be used as SLC. However, 10% manual overprovisioning would definitely reduce the already small chances of overflowing the SLC cache.
  • mczak - Thursday, November 8, 2018 - link

    On that note, wouldn't it actually make sense to use a MLC cache instead of a SLC cache for these SSDs using QLC flash (and by MLC of course I mean using 2 bits per cell)? I'd assume you should still be able to get very decent write speeds with that, and it would effectively only need half as much flash for the same cache size.
  • Billy Tallis - Thursday, November 8, 2018 - link

    Cache size isn't really a big enough problem for a 2bpc MLC write cache to be worthwhile. Using SLC for the write cache has several advantages: highest performance/lowest latency, single-pass reads and writes (important for Crucial's power loss immunity features), and your SLC cache can use flash blocks that are too worn out to still reliably store multiple bits per cell. A slower write cache with twice the capacity would only make sense if consumer workloads regularly overflowed the existing write cache. Almost all of the instances where our benchmarks overflow SLC caches are a consequence of our tests giving the drive less idle time than real-world usage, rather than being tests representing use cases where the cache would be expected to overflow even in the real world.
  • idri - Thursday, November 8, 2018 - link

    Why don't you guys include the Samsung 970 PRO 1TB in your charts for comparison? It's one of the most sought after SSDs on the market for HEDT systems and for sure it would be useful to have your tests results for this one too. Thanks.
  • Billy Tallis - Thursday, November 8, 2018 - link

    A.) Samsung didn't send me a 970 PRO. B.) The 970 PRO is pretty far outside the range of what could be considered competition for an entry-level NVMe SSD. It's a drive you buy for bragging rights, not for real-world performance benefits. The Optane SSD is in that same category, and I don't think the graphs for this kind of review need to be cluttered up with too many of those.
  • PeachNCream - Thursday, November 8, 2018 - link

    Not to be obtuse, but by price the 970 PRO is well within the range of competition for the P1 given that the 1TB 970 retails for $228 on Amazon right now and the MSRP for the 1TB P1 $220. Buyers looking for a product will most certainly consider the $8 difference and factor that into their decision to move up from an entry-level product to a "bragging rights" option given the insignificant difference in cost. Your first point is valid. I would have stopped there since its reasonable to say, "Physically impossible, don't have one there pal."

Log in

Don't have an account? Sign up now