Random Read Performance

The random read test requests 4kB blocks and tests queue depths ranging from 1 to 32. The queue depth is doubled every three minutes, for a total test duration of 18 minutes. The test spans the entire drive, which is filled before the test starts. The primary score we report is an average of performances at queue depths 1, 2 and 4, as client usage typically consists mostly of low queue depth operations.

Iometer - 4KB Random Read

The X400's random read performance is almost as good as the Samsung 850 EVO and much better than the other planar TLC drives. This is a significant accomplishment, as random reads are often the slowest operation for TLC drives and hard to improve with caching.

Iometer - 4KB Random Read (Power)

The X400's mid-range random read performance is achieved with relatively low power consumption, making it surprisingly efficient for a TLC drive.

At the highest queue depths the X400 can't quite reach the limits of the fastest drives, but overall the scaling of both performance and power usage are reasonable for a mid-range SATA drive.

Random Write Performance

The random write test writes 4kB blocks and tests queue depths ranging from 1 to 32. The queue depth is doubled every three minutes, for a total test duration of 18 minutes. The test is limited to a 16GB portion of the drive, and the drive is empty save for the 16GB test file. The primary score we report is an average of performances at queue depths 1, 2 and 4, as client usage typically consists mostly of low queue depth operations.

Iometer - 4KB Random Write

The X400's low queue depth random write speeds fall in the middle of the gap between the slowest MLC drive and the rest of the planar TLC drives.

Iometer - 4KB Random Write (Power)

The X400's power consumption is low, but with performance well behind any MLC drive the efficiency is only better than the other planar TLC drives.

The SanDisk X400's random write speeds show almost no scaling with increased queue depths, behavior that is typical of low-end TLC drives. The QD1 performance is as good as any SATA drive and while the OCZ Trion 150 hits great speeds at QD16 and QD32, the SanDisk X400 is clearly faster for the more realistic lower queue depths.

AnandTech Storage Bench - Light Sequential Performance
Comments Locked

41 Comments

View All Comments

  • Michael Bay - Saturday, May 7, 2016 - link

    There`s 3.1 down there somewhere too.
    I`d like to have the source on your percentages though.
  • Madpacket - Wednesday, May 11, 2016 - link

    Looks like the 1TB Mushkin Reactor (MKNSSDRE1TB) is still the best value drive to beat. Nice to see TLC drives other than Evo's getting better though.
  • hojnikb - Thursday, June 23, 2016 - link

    there is also reactor LT, if you want 512GB.
  • justkar4u - Wednesday, May 11, 2016 - link

    @anandtech : Seriously ? You are trying to compare apples to oranges to grapes. You are comparing 3D NAND products with 2D NAND, MLC with TLC type products. Sandisk X400 should be compared with OCZ Trion and Crucial BX series. As you can see X400 is better than Crucial MX in some cases ! Samsung, OCZ vector, crucial MX should not even be there in comparison. With that said, clearly X400 is the winner in TLC segment.
  • nobozos - Thursday, May 12, 2016 - link

    It would sure be nice if you could include a graph in some (all?) of your charts that normalizes for cost. Raw performance is nice, but performance/$ is also very useful.
  • Andre74 - Friday, May 27, 2016 - link

    What's the deal with referring to "Power" both as W·h, and as W (but commenting on efficiency)?

    Efficiency would be energy consumed per byte read, for example. Effectiveness could be bytes read per second. Measuring power usage during operation tells you nothing of either efficiency or effectiveness, unless it's calculated as total energy.
  • BimmerInd - Wednesday, June 1, 2016 - link

    "The Reactor is about $25 cheaper but only has a 3-year warranty and less than half the write endurance rating." Is this because of n-cache technique? MLC, TLC factors - Does it not make Mushkin a little better one?

    Endurance Rating
    Mushkin Enhanced Reactor 1TB - 144TB
    SanDisk X400 1TB - 320TB
    Moreover SanDisk X400 is recommended for OEM unlike Mushkin which is targeted at consumer? Does it make a difference?
  • hojnikb - Thursday, June 23, 2016 - link

    Thats just manufacturer rating. I'm sure unless Mushkin uses the crappiest MLC out there, that it will outlive sandisk x400 in terms of real world endurance.
  • BimmerInd - Friday, June 24, 2016 - link

    It says it uses Micron's NAND same as in Crucial's BX100. So which one should I choose?
  • runasroot - Thursday, January 12, 2017 - link

    I have a question: I know it states that it is 1024gb but is it a true 1024 or is it like something 960gb? I'm cloning a desktop with clonezilla and I need a 1tb ssd that is larger that 960GB to clone from disk to disk. <a href="https://wander.io">Wander</a>

Log in

Don't have an account? Sign up now