The Intel SSD 660p SSD Review: QLC NAND Arrives For Consumer SSDs
by Billy Tallis on August 7, 2018 11:00 AM ESTSequential Read Performance
Our first test of sequential read performance uses short bursts of 128MB, issued as 128kB operations with no queuing. The test averages performance across eight bursts for a total of 1GB of data transferred from a drive containing 16GB of data. Between each burst the drive is given enough idle time to keep the overall duty cycle at 20%.
The burst sequential read performance of the Intel SSD 660p is lower than several of the fastest high-end drives, but is still pretty quick given the 4-channel controller used by the 660p. The read speed is only moderately impaired after filling the drive all the way.
Our test of sustained sequential reads uses queue depths from 1 to 32, with the performance and power scores computed as the average of QD1, QD2 and QD4. Each queue depth is tested for up to one minute or 32GB transferred, from a drive containing 64GB of data. This test is run twice: once with the drive prepared by sequentially writing the test data, and again after the random write test has mixed things up, causing fragmentation inside the SSD that isn't visible to the OS. These two scores represent the two extremes of how the drive would perform under real-world usage, where wear leveling and modifications to some existing data will create some internal fragmentation that degrades performance, but usually not to the extent shown here.
On the longer sequential read test that goes beyond QD1, the true high-end NVMe drives pull away from the 660p but it is still faster than most other low-end NVMe SSDs. Internal fragmentation is more of a problem for the 660p than the TLC drives, but this is not too surprising—the QLC NAND is likely using larger page and block sizes that add to the overhead of gathering data that has been dispersed by wear leveling during random writes.
 |
|||||||||
| Power Efficiency in MB/s/W | Average Power in W | ||||||||
The power efficiency of sequential reads from the 660p is competitive with many of the best TLC SSDs, and isn't too far behind even after filling the drive all the way.
 |
|||||||||
The 660p doesn't reach its maximum sequential read speed until around QD8, but it was already pretty quick at QD1 so the overall growth is relatively small.
Sequential Write Performance
Our test of sequential write burst performance is structured identically to the sequential read burst performance test save for the direction of the data transfer. Each burst writes 128MB as 128kB operations issued at QD1, for a total of 1GB of data written to a drive containing 16GB of data.
The burst sequential write test only hits the SLC write cache even when the Intel SSD 660p is completely full, so it performs comparably to many high-end NVMe drives.
Our test of sustained sequential writes is structured identically to our sustained sequential read test, save for the direction of the data transfers. Queue depths range from 1 to 32 and each queue depth is tested for up to one minute or 32GB, followed by up to one minute of idle time for the drive to cool off and perform garbage collection. The test is confined to a 64GB span of the drive.
Our usual test conditions of a mostly-empty drive mean that the 660p's score on the sustained sequential write test reflects only writes to the SLC cache at its largest configuration. When the drive is full and the SLC cache has shrunk to just 12GB, the test quickly fills that cache and performance drops to last place.
 |
|||||||||
| Power Efficiency in MB/s/W | Average Power in W | ||||||||
The power efficiency of the 660p when writing sequentially to the SLC cache is excellent, but it ends up slightly worse off than the 600p when the drive is full and the SLC cache is too small.
 |
|||||||||
The 660p reaches its maximum sequential write speed at QD2 and maintains it for the rest of the test, showing that the drive is largely keeping up with flushing the SLC write cache during the idle phases of the test.
Facebook
Twitter
RSS
86 Comments
View All Comments
mapesdhs - Wednesday, August 8, 2018 - link
If you have quite literally "valuable info" then don't use a consumer SSD at all. Heck, damn the speed, you're far better with even a used 840 Pro. That's why I obtained one for this build I did, along with an SM951 for a scratch video drive:http://www.sgidepot.co.uk/misc/charitypc1.html
BurntMyBacon - Wednesday, August 8, 2018 - link
First point of interest is always have a backup plan. If information is valuable, don't rely on any single copy of it.As to your question of endurance, I don't think most personal use cases are likely to have an issue. If you have a professional workload, get a professional drive. The 840 Pro that mapesdhs keeps evangelizing is actually a pretty good option, though a Pro series (MLC) nvme drive will provide better performance while still providing endurance is the same ballpark as the 840Pro.
As to whether it will refresh the cell if powered on, I would expect most Samsung drive will, though it is not known whether
BurntMyBacon - Wednesday, August 8, 2018 - link
As to whether it will refresh if powered on, I don't believe that Samsung flash required the refresh cycle once the moved to 3D NAND with a larger feature size. That said, since QLC halves the voltage swing (and corresponding charge) vs TLC, it is likely that Samsung will need to do something to prevent voltage drift. This may not necessarily require active refreshing, though. It is not known (by me) whether this is a requirement for other manufacturer's 3DQLC NAND either.BurntMyBacon - Wednesday, August 8, 2018 - link
I get why they don't want an edit feature, but would it really hurt if they added a time limited recall type edit feature for when you fat thumb a hot key that posts your unfinished message before you are done with it. Maybe give you five minutes after a post initiate the edit to catch typos or grammar issues. It wouldn't really be enough to alter a conversation as it is unlikely that others will have responded within this time frame.AbRASiON - Tuesday, August 7, 2018 - link
Considering the abysmal performance of this thing, I think you really need a $/GB chart on the page and it would be nice to put in a very fast, modern hard drive. Something huge and 7200RPM with a lot of cache on it.Just to put it in perspective, because as it stands, wow this thing looks terrible. I expect VERY cheap prices if they're gonna run like this.
Oxford Guy - Tuesday, August 7, 2018 - link
No matter how terrible QLC is it is going to succeed in the market because consumers respond well to big and cheap.So, I think one interesting question is going to be how much disguising there will be of products having QLC. Microcenter, for instance, is apparently selling a TLC Inland drive, calling it MLC.
piroroadkill - Wednesday, August 8, 2018 - link
That's how I want QLC drives to be compared - to the best hard drives people might actually buy today to store their games on, for example.I'd love a cheap and large 4TB drive for my games, but it has to be both much faster than the HDD setup I use for games (2× 2TB 3.5" Seagate Hybrid drives in RAID0) and not too far off the same price.
zodiacfml - Wednesday, August 8, 2018 - link
Impressive performance. Easily beats my SATA 850 EVO in performance and twice the capacity I bought last December for the same price.There should be no reason for notebook manufacturers to settle for HDD except the cheapest laptops.
mapesdhs - Wednesday, August 8, 2018 - link
Given the 850 EVO's strong reliability reputation though, I wouldn't be overly eager to recommend this new QLC model for anyone wanting a decent degree of confidence that their data is safe. But then, most consumers don't have backup strategies anyway. :DSpunjji - Wednesday, August 8, 2018 - link
If you want safe data, make regular backups. Anything else is a false sense of security!