Прочети на българскиWe re-ran the fio tests on the Proxmox host itself with explicit absolute paths to each storage pool. The reason is simple: the older benchmark results were run without an absolute --filename parameter, which could point different tests at the same target and make the comparison misleading.
Correct methodology
- fio 3.39
- 4 parallel jobs
- 60 seconds
- profile: randrw with 70% read
- parameters: bs=4k, iodepth=32, direct=1
- each test is pointed at a specific pool with an absolute path
Results per pool
- vps-start: 3825 read IOPS, 1642 write IOPS, average latency about 23.5 ms
- vps-power: 12.0k read IOPS, 5157 write IOPS, average latency about 7.45 ms
- vps-plus: 6810 read IOPS, 2926 write IOPS, average latency about 13.1 ms
- micron-mirror: 4614 read IOPS, 1981 write IOPS, average latency about 19.3 ms
What this shows
- the pools do not give the same result
- the differences between them are real and measurable
- the older, similar numbers were not proof of identical plans, but of a wrongly targeted test
- once the benchmark is pointed correctly, the picture is clear
These results are more useful than single synthetic numbers without context, because they show how the different storage pools behave under the same methodology.
If you are looking for a VPS for real applications and want to see the other technical topics too, have a look at the VPSStorages VPS plans.
For more background on the technology see what ZFS storage is and why it matters.