Long-Term Performance Evaluation

A few of the benchmarks are repeated on the memory card after subjecting it to the extended usage simulation.

Sequential Access - fio Workload

Re-processing the fio workload in the used mode gives an idea of long-term performance consistency (whether there is appreciable degradation in performance as the amount of pre-existing data increases and / or the card is subject to wear and tear in terms of amount and type of NAND writes).

fio Sequential Workload [Used]
TOP: BOTTOM:

In the SD Express mode, the card's SLC cache has essentially run out by the time the workload starts for the used case. So, we do not see the ~375MBps level seen in the fresh pass. However, there is no drop to 30 MBps either, as the card is able to maintain a steady 75 MBps almost all through. In fact, the fio workload completed faster to fill up 90% of the card capacity in the used pass compared to the fresh pass. The reads are slightly slower in the used pass, but the relative variations are similar. In the UHS-I mode, the writes start slower in the used pass, but the consistency is better compared to the fresh pass - essentially similar to the SD Express case. Reads are consistent in both passes at around 70 MBps.

Performance Restoration - CrystalDiskMark

The traditional memory card use-case is to delete the files on it after the import process is completed. Some prefer to format the card either using the PC, or, through the options available in the camera menu. The first option is not a great one, given that flash-based storage devices run into bandwidth issues if garbage collection (processes such as TRIM) is not run regularly. Different memory cards have different ways to bring them to a fresh state. Silicon Motion specified that SD Express cards need to be formatted in NVMe mode in order to restore performance.

In order to test out the effectiveness of the performance restoration process, we run the default sequential workloads in CrystalDiskMark before and after the formatting. Note that this is at the end of all our benchmark runs, and the card is in a used state at the beginning of the process.

CrystalDiskMark [Used] Benchmarks
TOP: BOTTOM:

In the used pass, the reads drop from 890 MBps to 733 MBps, and writes from 418 MBps to 95 MBps for the sequential workloads in the SD Express case. Other access traces see similar drops. The UHS-I case also sees a similar drop in relative performance.

CrystalDiskMark [Refreshed] Benchmarks
TOP: BOTTOM:

Upon formatting in SD Express mode, the performance gets restored to around 878 MBps / 415 MBps). However, formatting in UHS-I mode has no effect, as the refreshed CrystalDiskMark numbers are very similar to the numbers seen in the used case.

Simulating Extended Usage Miscellaneous Aspects and Concluding Remarks
Comments Locked

43 Comments

View All Comments

Log in

Don't have an account? Sign up now