Single page Print

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 VX500's sequential read speeds are strong, hovering in the 500-550 MBps range at both queue depths. That's nipping at the heels of the 850 EVO 1TB, which has both a size and technology advantage (V-NAND) over the VX500. But before we can break out the champagne, the drive's paltry sequential write speeds ruin our fun. Plenty of cheaper drives beat the VX500's writes, including OCZ's own Trion 150. The VX500 is straight-up MLC flash with a pseudo-SLC mode and no obvious DRAM cache, so perhaps these results were to be expected. Cost-cutting comes at a price.



The results are inverted on the random side. The VX500 is a bit slow to respond on random reads, but we're still talking sub-millisecond response times here. We've often seen drives perform relatively poorly in this test before they go on to deliver solid real-world numbers, so we'll refrain from angry tirades for the moment. Random write response times are perfectly acceptable, if unremarkable.