VKernel recently published a new paper titled The Top 20 VMware Performance Metrics You Should Care About.
It’s a pretty interesting document not just because of the topic, but also because it goes straight to the point, solely focusing on the metrics that VKernel considers critical to reveal virtual machines performance issues. It provides a short description for each of them with, explaining why they are important, without trying to promote the VKernel products at all (not directly at least).
The 20 metrics are divided as follow:
CPU metrics
- cpu.extra.summation
- cpu.ready.summation
- cpu.usagemhz.average
Disk metrics
- disk.busResets.summation
- disk.commandsAborted.summation
- disk.totalLatency.average
- disk.queueLatency.average
- disk.read.average / disk.write.average
Memory metrics
- mem.active.average
- mem.consumed.average
- mem.overhead.average
- mem.swapin.average / mem.swapout.average / mem.swapped.average
- mem.vmmemctl.average
Network metrics
- net.received.average / net.transmitted.average / net.usage.average
Of course to have it you have to register.