The performance data collection subsystem for vSphere collects performance data on a variety of inventory items and their devices. Data counters define individual performance metrics. Performance metrics are organized into logical groups based on the object or object device. Statistics for one or more metrics can be displayed in a chart.

Metric Groups

Metric group


Cluster Services

Performance statistics for clusters configured by using VMware DRS (distributed resource scheduler), VMware HA (high availability), or both.


CPU utilization per host, virtual machine, resource pool, or compute resource.

Storage Pods and Datastores

Statistics for datastore utilization


Disk utilization per host, virtual machine, or datastore. Disk metrics include I/O performance (such as latency and read/write speeds), and utilization metrics for storage as a finite resource.

Management Agent

Memory swap statistics per COS.


Memory utilization per host, virtual machine, resource pool, or compute resource. The value obtained is one of the following:

For virtual machines, memory refers to guest physical memory. Guest physical memory is the amount of physical memory presented as a virtual-hardware component to the virtual machine, at creation time, and made available when the virtual machine is running.

For hosts, memory refers to machine memory. Machine memory is the RAM that is installed in the hardware that comprises the host system.


Network utilization for both physical and virtual network interface controllers (NICs) and other network devices, such as the virtual switches (vSwitch) that support connectivity among all components (hosts, virtual machines, VMkernel, and so on).


Energy usage statistics per host.

Storage Adapter

Data traffic statistics per HBA.

Storage Path

Data traffic statistics per path.


Overall system availability, such as system heartbeat and uptime. These counters are available directly from hosts and from vCenter Server.

Virtual Machine Operations

Virtual machine power and provisioning operations in a cluster or datacenter.