Random Access Performance

Our first batch of synthetic tests looks at 4K random IO. We test the drive at various queue depths ranging from 1 to 128. Besides random read and random write, we also test a mixed workload that randomly issues a read or write access request with equal probability.

Throughout this review we will present two sets of data—the first with the old firmware that has been shipping on retail drives for many months and the updated firmware, released on May 21.



Random IO performance is pretty much the same between both firmware versions.

To provide some context, the charts below compare these results with other drives. We report a combined and weighted score that should cover real-life consumer workloads very well. Accordingly, the weighting factors were chosen to represent these mostly low queue depth loads.

Sequential Throughput

Next, we test sequential throughput with a large block size of 512 KB. As before, a third data point is provided for a mixed workload that randomly issues a read or write access request with equal probability.



While the majority of results are identical between both firmware versions, sequential QD1 mixed sees a huge 400% improvement. Surely this rarely tested value can't have much of an effect on actual performance? Read on.

Using the same weighted scheme as for random IO, the charts below provide comparison data against other drives in the test group.