I am trying to set up a series of performance tests to run on 4 vms on a single host. Using various settings I have been able to get CPU and RAM to perform consistently across all vms, but not disk. We are using a test that writes out a 50,000 line log file and deletes it, but the time it takes to do this is never consistent. Each VM has IOPS limited to 600 in config and is using a thick vmdk. The disk can be slow, it just has to be consistent. What can I do to ensure that all 4 of them perform the same way every time?
↧