There are plenty
of metrics provided
by VMware. Some of these are familiar
to anybody who’s ever monitored
a computer (CPU%, IOPS etc.).
So for a short list of 5 I’ve selected 5 metrics that are important and available in VMware environments.
To some extent I’ve cheated to make a list of 5, because for some I’m looking to get the same metric from different levels in the environment. Most of these I will cover in greater detail in the sections following this.
The amount of memory the VM has accessed in the last 20 seconds. If there isn’t space for all the active memory in the cluster, then performance will be sub optimal.
To some extent I’ve cheated to make a list of 5, because for some I’m looking to get the same metric from different levels in the environment. Most of these I will cover in greater detail in the sections following this.
CPU MHz
Why not %? Well because
we can’t compare the CPU% Used of a VM with the % of the Host or the Cluster. We want to judge the amount of processing power
an individual VM requires. That way when we want to move it to another cluster, or are considering the size of the existing
cluster, we have a comparable value to work with. I fully admit
it’s not perfect. The processing you can do with 1MHz today is greater than that of 10 years ago.
But it’s still better
than %.
Ready Time
It’s a measure of CPU contention. The bigger the number
the less happy your users are. But it doesn’t always mean you are short of CPU
power.
The amount of memory the VM has accessed in the last 20 seconds. If there isn’t space for all the active memory in the cluster, then performance will be sub optimal.
Ballooned Memory
Memory ballooning works
by “robbing Peter
to pay Paul”. When memory is in short
supply and/or over committed, pages of RAM
in a VM OS can
be filled by a “balloon”. These
pages are then not actually available
to the OS, and the space freed up and will be used by other
VMs that need the RAM resources. As memory demand goes down, VMware deflates
the VMs balloon and the RAM is again available to the VM. Again this is a sign of contention
for
resource and introduces additional overhead to the VMware hypervisor.
Host Disk Latency
Among the metrics that are provided for Hosts are the Disk Latency metrics.
Disk IO performance is still the
greatest performance challenge faced by most organizations I meet.
In my next blog on Monday I'll take a closer look at Ready Time.
Phil Bell
Consultant
No comments:
Post a Comment