Along with the move to a new platform, we decided to make a change in one of the benchmarks. There’s a relatively new benchmark called Anvil Storage Utilities that is in beta but close to production. It’s a very powerful tool that measures performance through a variety of tests which can be customized. Since some of the tests more or less duplicate what we get from other benchmarks we use already, we decided to use the IOPS (Input/Output Operations Per Second) testing on 4kb file sizes at a queue depth of 1, 4, 8, 16, 32, 64 and 128. IOPS performance is something SSD makers tout quite a bit but we generally don’t do a lot of IOPS testing because frankly a lot of users can’t relate to IOPS metrics as well and it tends to be more meaningful to the enterprise/server crowd. Still, it is another performance indicator with relevance and while some drives post good MB/s numbers, their IOPS scores aren’t always commensurate which this test will prove out.
Benchmark Results: The Anvil SSD Benchmark showed that with 100% compression (incompressible data) the ADATA SX8000 512GB PCIe NVMe SSD scored 8,921.46 points with stock Windows NVMe Driver and Windows write-cache buffer flushing disabled on the drive.
Benchmark Results: With the compression at 46% to help mimic real world applications better we found the overall score remained basically the same at 8,910.95 points.
Benchmark Results: We used Anvil to check the 4K Random Read performance and found we we topped out at 188,900 IOPS, which is actually over the drives rated maximum 4K Random Read IOPS of up to 160K. The QD1 and QD4 4K Random Read performance wasn’t anything special, but both were better than the level of performance seen from the Intel SSD 600P PCIe NVMe 512GB drive.
Benchmark Results: When it came to 4K Random Write performance, the ADATA XPS SX8000 512GB drive topped out at 187,400 IOPS at QD16 and that is well over the drives rated 140k IOPS for maximum 4K Random Write performance. Not bad 4K Random Read IOPS and this drive falls in the middle of the pack.