AnandTech 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.

ATSB - Light (Data Rate)

On the Light test, almost all NVMe SSDs have the opportunity to significantly outpace all SATA SSDs—when the test is run on an empty drive. When the drives are full, only some of the faster NVMe drives still need the extra bandwidth of PCI Express. The MyDigitalSSD SBX suffers more than most drives from being full, and the effect is more severe at lower capacities. The SBX is still faster than SATA drives in those difficult conditions.

ATSB - Light (Average Latency)ATSB - Light (99th Percentile Latency)

The full-drive test runs show significantly higher average and 99th percentile latency, especially for the smaller capacities of the SBX. The empty-drive test runs show latency that is much more in line with other NVMe drives and is generally much better than how the smaller Intel 760p drives behave.

ATSB - Light (Average Read Latency)ATSB - Light (Average Write Latency)Almost everything shows a fairly large disparity in average read latency between full and empty drive conditions for the Light test, so the MyDigitalSSD SBX doesn't stand out too much. The  full-drive average write latency scores for the SBX aren't the only poor results in the bunch, but they are still outliers compared to NVMe drives in general.

ATSB - Light (99th Percentile Read Latency)ATSB - Light (99th Percentile Write Latency)

The 99th percentile read and write scores for the MyDigitalSSD SBX show reasonable QoS for the empty-drive test runs, but some of the worst results we've measured for full drive performance. The Intel 760p's results are probably worse for real-world scenarios, because its empty drive latency is almost as bad as the full drive latency.

ATSB - Light (Power)

The three capacities of the MyDigitalSSD SBX all have about the same energy usage on the Light test. Their efficiency scores are great by NVMe standards, but mediocre by the standards of modern SATA drives. The SBX has reduced energy usage almost by half compared to the Phison E7 drives.

AnandTech Storage Bench - Heavy Random Performance
Comments Locked

46 Comments

View All Comments

  • peevee - Friday, May 4, 2018 - link

    What dgingeri said. Learn your stuff before commenting.
    Looks like it is a fraud on the part of manufacturer, or a fk-up on the AT side.
  • Billy Tallis - Friday, May 4, 2018 - link

    Literally everything in your comment is wrong.
  • MajGenRelativity - Tuesday, May 8, 2018 - link

    I don't see in your link where it says that drives can switch between NVMe and AHCI.
  • Lolimaster - Saturday, May 5, 2018 - link

    The thing is that unless you need to work with huge data (editing for example) buying an NVME SSD makes ZERO sense specially on a laptop with the added powerconsumption and heat vs a sata ssd that will be as fast for all of the usages of a non-prosumer.
  • Lolimaster - Saturday, May 5, 2018 - link

    It's nice that you see those 1-2-3GB/s on crystaldiskmark but it's totally wasted for 99% of your daily usage.
  • Lolimaster - Saturday, May 5, 2018 - link

    Want faster boot having alreayd an SSD? Enable fast boot on bios to skip some checks.

Log in

Don't have an account? Sign up now