The Crucial P1 1TB SSD Review: The Other Consumer QLC SSD
by Billy Tallis on November 8, 2018 9:00 AM ESTAnandTech 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.
As with the Heavy test, the Crucial P1 handles the Light test as well as most high-end drives when the test is run on an empty drive with plenty of free space in the SLC cache. When the test is run on a full drive, the P1's average data rate drops to just below that of the Crucial MX500 SATA SSD.
When the Light test is run on an empty Crucial P1, the average and 99th percentile latency scores are comparable to high-end NVMe SSDs because the test is operating entirely within the SLC cache. When that cache is shrunk by completely filling the drive, both latency scores are an order of magnitude worse. However, the 99th percentile latency is much better than what we saw from the Intel 660p when full.
The average read latency of the Crucial P1 stays reasonably below that of SATA SSDs even when the test is run on a full drive, but the average write latency ends up several times higher than the MX500 SATA drive. The Intel 660p and DRAMless Toshiba RC100 have similar average write latency when full.
The 99th percentile read and write latency scores tell a similar story to the average latencies, but the weaknesses of the Crucial P1 stand out more clearly. Even with a full drive, read latency on the Light test isn't a problem, but write latency can climb to tens of milliseconds.
Energy usage by the Crucial P1 is reasonably low (by NVMe standards) when the Light test is run on an empty drive. When the test is run on a full drive, the P1 uses substantially more energy than the Intel 660p and instead shows comparable efficiency to most high-performance NVMe SSD.
Facebook
Twitter
RSS
66 Comments
View All Comments
Billy Tallis - Thursday, November 8, 2018 - link
I think you were looking at the price for the 1TB 970 EVO. The 1TB 970 PRO is currently $392.99 on Amazon, closer to twice the price of the Crucial P1. I think it is occasionally reasonable to get something like the 970 EVO for a high-end system. Going past that to a 970 PRO isn't reasonable.PeachNCream - Thursday, November 8, 2018 - link
Whoops, you're correct! Please accept my apologies for that one.DigitalFreak - Friday, November 9, 2018 - link
Even then, the 970 EVO wipes the floor with the P1.Death666Angel - Thursday, November 8, 2018 - link
Who wants QLC NVME drives as the first widely available consumer QLC tech? Not me I tell you! :DI am fine with 3D TLC for my performance needs both from a performance and price point at the moment. 500GB is enough for many casual enthusiasts and 1TB isn't too expensive either. I'd really like 2.5" SATA and M.2 SATA QLC for my casual media storage needs.
Lolimaster - Friday, November 9, 2018 - link
QLC is such useless product except for manufactures, they give you a WORST product for basically the same price or more than a TLC.MX500/860 EVO 1TB for $160-180.
Lolimaster - Friday, November 9, 2018 - link
*Edit 155-160.piroroadkill - Friday, November 9, 2018 - link
QLC doesn't seem to make any sense in an M.2 PCIe NVMe format - it's just really slow compared to even a good SATA 6Gbps SSD. QLC seems to make sense in a 2.5" SATA format, with an enormous capacity. 1TB makes no sense for this shitty performance level. It needs to be there to replace larger drives. Actually, even that makes no sense for a home user - where long term retention is more important, and a hard disk is therefore more useful. QLC drives will probably come into their own at the ~4TB mark in Enterprise storage arrays as a mid-tier storage solution, with hard disks under, and MLC NAND above.crotach - Friday, November 9, 2018 - link
Oh dearThe_Assimilator - Friday, November 9, 2018 - link
Why the bloody bejesus do these manufacturers keep tying ever-slower NAND to ever-faster interfaces? If you want your bloody QLC NAND to be a success, Crucial, make a 2TB+ SATA SSD that costs less per gigabyte than any other SSD on the market, and watch them fly off the shelves. You already got this right with the Micron 1100 series that uses 3D TLC NAND, why can't you do it for QLC?The_Assimilator - Friday, November 9, 2018 - link
Ah, I see that Micron is touting their "5210 ION" series SSDs (using 3D QLC NAND) as "hard drive replacements", and they start at 2TB. Write speeds are not great, but I don't care and I doubt most consumers looking for high-capacity SSDs will either. Hopefully there will be stock of these in time for Black Friday!