IOMeter — Sequential and random performance
IOMeter fuels much of our latest storage test suite, including our sequential and random I/O tests. These tests are run across the full capacity of the drive at two queue depths. The QD1 tests simulate a single thread, while the QD4 results emulate a more demanding desktop workload. For perspective, 87% of the requests in our old DriveBench 2.0 trace of real-world desktop activity have a queue depth of four or less. Clicking the buttons below the graphs switches between results charted at the different queue depths.
Our sequential tests use a relatively large 128KB block size.
The SU900's sequential read speeds are as quick as any SATA drive's can be, demonstrating a 25% improvement over Adata's older (and planar) MLC drive, the XPG SX930. The SU900's' sequential writes, however, seem to suffer in the same way that the SU800's did.
At that time, Adata's explanation was that the drive's pseudo-SLC cache hadn't recovered in time to be of any use during IOMeter's scripted write testing. The resulting disappointing numbers reflected the raw write speed of the NAND. On the upside, those raw numbers are better for the SU900's 3D MLC than they were for the SU800's 3D TLC.
The SU900 will have plenty of opportunities in our test suite to make up for its sequential write results, so let's move on to random response times.
The drive's read response times are right in the middle of the pack. Write response times are a bit lackluster, but we've seen worse before.
Thus far, the SU900 has displayed blazing fast reads, but it's suffered a setback in its sequential write performance. Let's see how it fares under more complex workloads.