The Corsair MP400 1TB QLC NVMe SSD: A Quick Review

Following up from our recent look at 8TB QLC SSDs, today we’re taking a look at the 1TB Corsair MP400. This is a QLC NVMe SSD using the Phison E12 controller, which puts it a step up from earlier QLC SSDs that used four-channel Silicon Motion controllers. Unlike last week’s review of 8TB SSDs, this time we’re dealing with a much more affordable capacity of 1TB. At 8TB, many of the downsides of QLC NAND can be overcome by the sheer volume of flash memory, but this 1TB drive falls toward the low end of the QLC SSD capacity range and faces real competition from entry-level drives using TLC NAND.

The MP400 is Corsair’s answer to Sabrent’s Rocket Q and other similar SSDs that have adopted the combination of the Phison E12S controller and QLC NAND. Compared to the Sabrent Rocket Q, Corsair’s specifications for the MP400 are a bit more optimistic on performance and a bit lower on the write endurance rating, but we expect the real-world differences between these drives at the same capacity to be insignificant given the near-identical hardware.


Corsair MP400 1TB (QLC) and the Corsair Force MP510 (TLC)

Sabrent’s Rocket Q product line covers capacities from 500GB to 8TB. Corsair drops the 500GB option, which is very reasonable: we consider 1TB to be the bare minimum for a QLC drive to make sense. That’s especially true of these drives that use an 8-channel Phison E12S controller, half of which goes unused on a 500GB QLC model. Mushkin’s recently announced ALPHA series goes even further and will only offer 4TB and 8TB options.

Corsair MP400 Specifications
Capacity 1 TB 2 TB 4 TB 8 TB
Form Factor M.2 2280 PCIe 3 x4
Controller Phison E12S
NAND Flash Micron 1Tbit 96L 3D QLC
Sequential Read (MB/s) 3480
Sequential Write (MB/s) 1880 3000
Random Read IOPS (4kB) 190k 380k 610k
Random Write IOPS (4kB) 470k 560k 710k
Power Consumption 4.0 W 5.5 W 6.5 W 6.5 W
Warranty 5 years
Write Endurance 200 TB
1.04 DWPD
400 TB
0.52 DWPD
800 TB
0.26 DWPD
1600 TB
0.13 DWPD
Current Retail Prices $114.99
(11¢/GB)
$244.99
(12¢/GB)
$662.00
(17¢/GB)
$1498.00
(19¢/GB)
 

The 1TB capacity point is currently the volume spot in the consumer SSD market for QLC, with the most competition and the best prices on a per-GB basis. QLC SSDs have made multi-TB SSDs more affordable, but 2TB and larger drives still tend to carry a premium. In the entry-level NVMe market segment, there’s overlap at 1TB between DRAMless TLC designs and QLC with DRAM designs, two markedly different strategies for cutting costs. There are thankfully only a handful of DRAMless QLC NVMe drives that combine both weaknesses. There are also a few relatively budget-oriented TLC SSDs with DRAM that hit low price points using cheaper 4-channel controllers.


Corsair MP400 1TB (QLC, Top) and the Corsair Force MP510 (TLC, Bottom)

Each of these approaches to an entry-level NVMe SSD (QLC+DRAM vs TLC without DRAM) comes with its own typical weaknesses, and some advantages. DRAMless SSDs will suffer under workloads with heavy random IO, but where they do offer decent performance they tend to have very good power efficiency – not having to power any external DRAM chips helps. QLC SSDs suffer most during sustained writes, and are very heavily reliant on their SLC caches. Smaller drives have smaller SLC caches, so it will be much easier to overflow that write cache on this 1TB MP400 than on the larger variants. Most QLC and TLC drives tend to use SLC caches, but QLC drives also tend to use the largest SLC cache sizes possible, which exacerbates the performance problems once the cache is full – there’s little or no empty flash left that could be written to directly as QLC, and until the drive can catch a break, further writes will require compacting data from the SLC cache into QLC blocks to free up space.

Most drives using 4-channel controllers have notably limited throughput. SK hynix was first to market with a 4-channel drive that could saturate PCIe 3 x4 (with TLC NAND), and that Gold P31 is priced more like a high-end drive. Silicon Motion has introduced a 4-channel Gen4 controller that is also more than fast enough for a Gen3 x4 interface, but it also is not yet cheap enough for entry-level drives. So for now, the 8-channel Phison E12 controller is the best option for high-capacity QLC SSDs to improve performance.

Gallery: Corsair MP400 1TB

This review has two main points of comparison for our 1TB Corsair MP400 sample: the 8TB Sabrent Rocket Q we recently reviewed is the most similar, and lets us see how this Phison E12+QLC design scales down to smaller capacities. We also have results for several other 1TB entry-level SSDs, including DRAMless TLC models from Mushkin and Toshiba/Kioxia, and earlier QLC NVMe drives from Intel and Crucial. Unfortunately, we were unable to secure the Western Digital WD Blue SN550 in time for this review; it generally seems to be the best DRAMless TLC drive on the market, and would offer the toughest competition against QLC designs at this 1TB capacity point.

Read on for more analysis.

AnandTech 2018 Consumer SSD Testbed
CPU Intel Xeon E3 1240 v5
Motherboard ASRock Fatal1ty E3V5 Performance Gaming/OC
Chipset Intel C232
Memory 4x 8GB G.SKILL Ripjaws DDR4-2400 CL15
Graphics AMD Radeon HD 5450, 1920×1200@60Hz
Software Windows 10 x64, version 1709
Linux kernel version 4.14, fio version 3.6
Spectre/Meltdown microcode and OS patches current as of May 2018

This test starts with a freshly-erased drive and fills it with 128kB sequential writes at queue depth 32, recording the write speed for each 1GB segment. This test is not representative of any ordinary client/consumer usage pattern, but it does allow us to observe transitions in the drive’s behavior as it fills up. This can allow us to estimate the size of any SLC write cache, and get a sense for how much performance remains on the rare occasions where real-world usage keeps writing data after filling the cache.

The Corsair MP400 opts for the largest possible SLC cache size, allowing for a quarter of the drive’s advertised capacity to be written to the cache before performance plummets. This is the same strategy used by the Sabrent Rocket Q and probably all other QLC drives using Phison controllers. The Intel and Crucial QLC drives based on Silicon Motion’s SM2263 controller have somewhat smaller variable-sized SLC caches, while the Samsung QLC SATA drives use the same small SLC cache sizes as their TLC counterparts.

Sustained 128kB Sequential Write (Power Efficiency)
Average Throughput for last 16 GB Overall Average Throughput

Overall drive fill performance for the Corsair MP400 is marginally faster than for the other 1TB QLC drives we’ve tested, but the DRAMless TLC drives and the larger Sabrent Rocket Q are considerably faster. However, all of the budget NVMe drives are clearly much slower for sustained writes than the mainstream and high-end TLC drives.

The random read latency from the Corsair MP400 is quite similar to what we saw from the 8TB Sabrent Rocket Q, especially for medium to large working sets. The 1TB MP400 doesn’t exhibit the same unsteady performance for small working sets as the 8TB Rocket Q, but instead only shows poor performance for the absolute smallest working set size tested.

The performance drop-off when performing random reads across the entire drive is expected and normal, because the Crucial P1 is the only QLC drive in this bunch to include the full 1GB per 1TB of DRAM. Most low-end DRAMless TLC drives will show an even earlier drop in performance, and many of the more mainstream TLC drives that have switched to a lower DRAM ratio will also show the same drop that the Rocket Q and MP400 show.

The Destroyer is an extremely long test replicating the access patterns of very IO-intensive desktop usage. A detailed breakdown can be found in this article. Like real-world usage, the drives do get the occasional break that allows for some background garbage collection and flushing caches, but those idle times are limited to 25ms so that it doesn’t take all week to run the test. These AnandTech Storage Bench (ATSB) tests do not involve running the actual applications that generated the workloads, so the scores are relatively insensitive to changes in CPU performance and RAM from our new testbed, but the jump to a newer version of Windows and the newer storage drivers can have an impact.

We quantify performance on this test by reporting the drive’s average data throughput, the average latency of the I/O operations, and the total energy used by the drive over the course of the test.

ATSB The Destroyer
Average Data Rate
Average Latency Average Read Latency Average Write Latency
99th Percentile Latency 99th Percentile Read Latency 99th Percentile Write Latency
Energy Usage

The Corsair MP400 is faster on The Destroyer than the other 1TB QLC drives that are based on 4-channel controllers, but it’s also generally slower than the DRAMless TLC drives. The MP400 and other QLC drives also require far more energy than the fairly efficient DRAMless TLC competition.

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
Average Data Rate
Average Latency Average Read Latency Average Write Latency
99th Percentile Latency 99th Percentile Read Latency 99th Percentile Write Latency
Energy Usage

On the Heavy test, the Corsair MP400 and other QLC drives offer superior peak performance compared to the DRAMless TLC drives, but that situation is reversed when the test is run on a full drive. The MP400 in particular doesn’t seem to be as good as the other QLC drives at maintaining decent read latency when full, but this test is very write-intensive so the MP400’s overall performance on the full-drive test run is still better than the other QLC drives.

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.

ATSB Light
Average Data Rate
Average Latency Average Read Latency Average Write Latency
99th Percentile Latency 99th Percentile Read Latency 99th Percentile Write Latency
Energy Usage

The Light test is short enough to fit entirely within the SLC cache of the 1TB Corsair MP400 when the test is run on an empty drive. That allows the MP400 to outperform the 8TB Sabrent Rocket Q, which is burdened with extra overhead of managing so much flash. The DRAMless TLC drives cannot match the peak performance of the QLC drives that have DRAM. When the test is run on a full drive, the performance of the QLC drives as usual suffers greatly, but the Corsair MP400 remains faster than at least some of the DRAMless TLC drives.

Our burst IO tests run at a queue depth of one and the amount of data transferred is limited to ensure that SLC write buffers don’t fill up and controllers don’t overheat. In between each burst there’s enough idle time to keep the drive averaging a 20% duty cycle, allowing for some buffered writes and deferred garbage collection to be completed. The random read and write tests use 4kB operations and the sequential tests use 128kB operations. All the burst tests are confined to a 16GB portion of the drive, so DRAMless SSDs are not disadvantaged as much as they are for larger tests.

QD1 Burst IO Performance
Random Read Random Write
Sequential Read Sequential Write

The aggressive SLC caching strategy used by the Corsair MP400 and most other QLC NVMe SSDs allows them to provide best-case random IO performance that is competitive with many high-end PCIe 3.0 drives. However, despite the 8-channel controller, the burst sequential IO performance of the Corsiar MP400 is still fairly low by NVMe standards. The Sabrent Rocket Q 8TB’s results indicate that at least some of the higher-capacity MP400 models should also be able to provide better burst sequential write speeds by virtue of having larger and faster SLC caches.

Our sustained IO tests measure performance on queue depths up to 32, but the scores reported here are only the averages for the low queue depths (1,2,4) that are most representative of real-world consumer workloads. Each queue depth is tested for up to one minute or 32GB, and the tests are confined to a 64GB span of the drive.

Sustained IO Performance
Random Read Random Write
Sequential Read Sequential Write

On the longer synthetic IO tests, the Corsair MP400’s best results are for random writes, where its SLC cache is sufficient to keep it competitive against high-end PCIe 3 drives. The sequential write and random read performance scores are both constrained to the entry-level NVMe performance ranges, but are competitive for that market segment. The sequential read performance is relatively poor even for entry-level NVMe drives, though still significantly better than Samsung’s QLC SATA alternative.

Sustained IO Performance
Random Read Random Write
Sequential Read Sequential Write

With QLC NAND and an aging 8-channel controller, it’s no surprise that the Corsair MP400’s power efficiency scores are generally unimpressive, especially compared to what the 4-channel NVMe drives score when they are performing well. However, the only particularly poor efficiency score from the MP400 is for the sequential read test that it did not perform well on.

Performance at a glance
Random Read Random Write
Sequential Read Sequential Write

Plotting power and performance against our entire library of benchmark results shows that—for better or for worse—the Corsair MP400 doesn’t stand out from the crowd or break new ground. The random read performance stays entirely within the range of SATA drives. Random and sequential writes make some use of PCIe performance, but don’t come close to saturating the PCIe 3 x4 interface. The sequential read performance does almost make it to 3GB/s at higher queue depths, but it isn’t able to fully saturate the PCIe interface the way the 8TB Sabrent Rocket Q can.

Random Read
Random Write
Sequential Read
Sequential Write

Digging into how performance and power scale with increasing queue depths reveals no particular surprises for the Corsair MP400. The biggest discrepancies with the 8TB Sabrent Rocket Q are for random reads and sequential writes: more flash allows the 8TB drive to continue scaling up random read performance after the 1TB MP400 is starting to reach saturation, and the larger SLC cache for the 8TB drive allows higher and more consistent sequential write performance.

Our tests of mixed read/write IO vary the workload from pure reads to pure writes at 10% increments. Each mix is tested for up to 1 minute or 32GB of data transferred. The mixed random IO test uses a queue depth of 4 while the mixed sequential IO test uses a queue depth of 1. The tests are confined to a 64GB span of the drive, and the drive is given up to one minute of idle time in between each mix tested.

Mixed IO Performance
Mixed Random IO Mixed Sequential IO

The QLC NVMe drives like the Corsair MP400 have a clear advantage over the DRAMless TLC drives for mixed read/write workloads. This is particularly pronounced for the mixed random IO test, where the DRAMless TLC drives are even slower than the QLC SATA drive. On the mixed sequential IO test, those DRAMless TLC drives can compete with some of the slower QLC NVMe drives, but the 8-channel Phison E12 controller used in the Corsair MP400 and Sabrent Rocket Q helps them stay ahead as the faster budget NVMe strategy.

Mixed IO Efficiency
Mixed Random IO Mixed Sequential IO

The budget NVMe drives all have worse power efficiency during the mixed IO tests than any of the high-end options, but the Corsair MP400 has some of the best efficiency scores within the budget NVMe segment. The 8TB Sabrent Rocket Q trails behind the 1TB MP400 because of the extra power draw of so many NAND dies.

Mixed Random IO
Mixed Sequential IO

The Corsair MP400’s performance curves through the mixed random and sequential IO tests generally resemble what we saw for the Sabrent Rocket Q. On the mixed sequential IO test, the 8TB Rocket Q generally maintained a clear performance lead over the 1TB MP400 (at the cost of much higher power draw), but their performance scaling across the random IO test is very similar. The overall shape of the performance curves for these QLC drives has a lot more in common with mainstream TLC drives than it does with the entry-level DRAMless TLC drives; the QLC drives are slower than mainstream TLC drives, but not as obviously limited as the DRAMless drives.

SATA SSDs are tested with SATA link power management disabled to measure their active idle power draw, and with it enabled for the deeper idle power consumption score and the idle wake-up latency test. Our testbed, like any ordinary desktop system, cannot trigger the deepest DevSleep idle state.

Idle power management for NVMe SSDs is far more complicated than for SATA SSDs. NVMe SSDs can support several different idle power states, and through the Autonomous Power State Transition (APST) feature the operating system can set a drive’s policy for when to drop down to a lower power state. There is typically a tradeoff in that lower-power states take longer to enter and wake up from, so the choice about what power states to use may differ for desktop and notebooks, and depending on which NVMe driver is in use. Additionally, there are multiple degrees of PCIe link power savings possible through Active State Power Management (APSM).

We report three idle power measurements. Active idle is representative of a typical desktop, where none of the advanced PCIe link or NVMe power saving features are enabled and the drive is immediately ready to process new commands. Our Desktop Idle number represents what can usually be expected from a desktop system that is configured to enable SATA link power management, PCIe ASPM and NVMe APST, but where the lowest PCIe L1.2 link power states are not available. The Laptop Idle number represents the maximum power savings possible with all the NVMe and PCIe power management features in use—usually the default for a battery-powered system but rarely achievable on a desktop even after changing BIOS and OS settings. Since we don’t have a way to enable SATA DevSleep on any of our testbeds, SATA drives are omitted from the Laptop Idle charts.

Idle Power Consumption - No PMIdle Power Consumption - DesktopIdle Power Consumption - Laptop

Idle Wake-Up Latency

The Corsair MP400 identifies itself as having the same idle power management capabilities as the Sabrent Rocket Q, and significantly lower maximum power draw in its active power states than the very pessimistic figures our 8TB Rocket Q sample provides to the OS.

The active and desktop idle power values we measured for the MP400 are a bit lower than for the Rocket Q 8TB, which is to be expected given the lower part count on the 1TB MP400. Waking up from the intermediate desktop idle state is extremely quick, but waking from the deepest sleep state is just a bit on the slow side.

The Corsair MP400 has proved to be a competent budget NVMe SSD in its 1TB version. The recent crop of drives like the Corsair MP400 and Sabrent Rocket has raised the bar for consumer QLC SSDs. That being said, the a 1TB QLC drive is relatively low capacity for the controller, and there are performance compromises that go along with that (compared to the 8TB relatives we looked at last week). At mainstream capacities they can compete against many budget TLC SSDs, and at the higher capacities where there are few or no budget TLC options, many of the benefits of QLC NAND come into play.

The MP400 sits on the boundary between a good TLC drive and an entry level QLC drive. It performs as expected, and the key arbiter in going for this drive is going to be in the cost.

When Does QLC Make Sense? An Overview

Based on our testing, QLC drive capacities below 1TB (such as 500 GB), we recommend avoiding QLC SSDs. These smaller capacities are where DRAMless TLC SSDs are clearly the better value, and more mainstream TLC drives with DRAM are often on sale for entry-level prices as well. Above 1TB, the DRAMless TLC options are few and far between, and we don’t expect any of them to handle heavier workloads as easily as 2+TB QLC drives with DRAM do.

At the 1TB capacity point we’re focused on today, the conclusion is not as clear. The Corsair MP400 generally outperformed the low-end TLC drives we have to compare against, though our collection is missing a few of the best-performing budget TLC options on the market today. It is pretty clear that DRAMless TLC SSDs have the edge in power efficiency.

For general purpose consumer desktop usage, both QLC and TLC entry-level NVMe drives offer better performance than SATA SSDs, and with little or no price premium. Which kind of entry-level NVMe drive is the better really comes down to day to day pricing.

Budget NVMe Consumer SSD Price Comparison
December 11, 2020
  PCIe
DRAM
NAND 500GB 1TB 2TB 4TB 8TB
NVMe PCIe 3.0
ADATA XPG SX8100 3.0 x4
Yes
TLC
8ch
$59.99 (12¢/GB) $94.99
(9¢/GB)
$229.99 (11¢/GB) $499.99 (12¢/GB)
ADATA Swordfish 3.0 x4
No
TLC
4ch
$54.99 (11¢/GB) $94.99
(9¢/GB)
$189.99 (9¢/GB)
Corsair MP400 3.0 x4
Yes
QLC
8ch
$114.99 (11¢/GB) $244.99 (12¢/GB) $662.00 (17¢/GB) $1498.00 (19¢/GB)
Inland Platinum 3.0 x4
Yes
QLC
8ch
$94.99
(9¢/GB)
$193.99 (10¢/GB) $499.99 (12¢/GB)
Intel 660p 3.0 x4
Yes
QLC
4ch
$59.99 (12¢/GB) $109.99 (11¢/GB) $209.99 (10¢/GB)
Intel 665p 3.0 x4
Yes
QLC
4ch
$109.99 (11¢/GB) $239.99 (12¢/GB)
Kingston A2000 3.0 x4
Yes
TLC
4ch
$53.99 (11¢/GB) $102.99 (10¢/GB)
Mushkin ALPHA 3.0 x4
Yes
QLC
8ch
$599.99 (15¢/GB) $1299.99 (16¢/GB)
Mushkin Helix-L 3.0 x4
No
TLC
4ch
$54.99 (11¢/GB) $89.99
(9¢/GB)
Sabrent Rocket Q 3.0 x4
Yes
QLC
8ch
$64.99 (13¢/GB) $109.98 (11¢/GB) $219.98 (11¢/GB) $599.98 (15¢/GB) $1299.99 (16¢/GB)
WD Blue SN550 3.0 x4
No
TLC
8ch
$53.99 (11¢/GB) $104.99 (10¢/GB) $247.99 (12¢/GB)
NVMe PCIe 4.0
Sabrent Rocket Q 4.0 4.0 x4
Yes
QLC
8ch
$149.98 (15¢/GB) $319.99 (16¢/GB) $689.98 (17¢/GB)
Addlink S92 4.0 x4
Yes
QLC
8ch
$145.88 (15¢/GB) $277.88 (14¢/GB) $649.99 (16¢/GB)
SATA
Samsung 870 QVO SATA
Yes
QLC $89.99
(9¢/GB)
$199.99 (10¢/GB) $419.99 (10¢/GB) $861.27 (11¢/GB)

The handful of multi-TB QLC drives using the Phison E12S controller are competing not just on price, but on the vendor’s ability to keep the drive in stock. From day to day, we’re seeing the best-priced models quickly end up backordered, so there’s clearly demand for these massive SSDs but the prices should drift downward a bit as these drives become more widely available from multiple brands. The Corsair MP400 hasn’t been on the market for as long as the Sabrent Rocket Q, so the latter currently has it beat on pricing and availability. Microcenter’s Inland Platinum QLC drive seems to still be the cheapest Phison E12S+QLC drive on the market, with especially attractive pricing for the 4TB model.

Even though the proliferation of new QLC alternatives has broadened the scope of the entry-level NVMe market segment, these drives are still almost always overshadowed by the best deals in the more mainstream NVMe market segment that is dominated by drives with TLC and DRAM and 8-channel controllers. Right now with holiday pricing, it is very easy to score a drive that doesn’t have any of the acute weaknesses of DRAMless or QLC models, without paying a premium. The best example is ADATA’s XPG SX8100, a TLC drive with Realtek’s 8-channel controller with DRAM. The SX8100 is one of the few TLC models with a 4TB option so it competes against high-capacity QLC models, and beats many of them on price at all capacity points.

Our next look into consumer QLC SSDs will be Sabrent’s Rocket Q4, the successor to the Rocket Q that adopts the Phison E16 PCIe 4.0 controller. Even though the newer Phison E18 Gen4 controller is starting to ship in high-end SSDs, The E18 is probably overkill for QLC models, and it’s certainly more expensive. The E16 controller may stick around for a while to offer a more affordable path toward better QLC performance.

Next Review: SSD Benchmark Suite Update for PCIe Gen 4

This review marks the end of our current generation of SSD testing equipment and procedures. Our new overhauled test suite designed for PCIe Gen4 SSDs will be launching soon, along with a new section in Bench for the new test results. The existing SSD18 results will remain available with no further updates. Many recent drives we have already reviewed will be re-tested on our new SSD test suite and their results will be added to the new SSD21 section as they are completed.