Utilization metrics

The appliance gathers utilization data for certain resources on metrics such as CPU usage, memory, power consumption, temperature, and health. This data is displayed in the Utilization panel for the resource, and in utilization graphs in the Utilization view for the resource.

Capacity

Capacity amount is calculated in tebibyte (TiB) of space on storage systems. The average value displayed for each metric is rounded off to the nearest whole number.

Metric

Description

Total capacity

The total disk space available on the storage systems

NOTE:

If there are failed components the total capacity of the storage system might not add up to the sum of allocated and free capacities of the storage system.

Allocated capacity

Total disk space allocated to storage systems

Free capacity

Total disk space that is still available for allocation

CPU

Server hardware CPU utilization statistics are gathered from the historical data stored on an iLO every five minutes.

Interconnect CPU utilization statistics are fetched from the interconnect every 60 seconds when you open the interconnects page.

Interconnect CPU trend graph displays the CPU utilization trend for last five minutes. The graph is updated every 60 seconds while the interconnect screen is open.

You can see the CPU utilization data for a component under CPU on the Utilization panel.

For interconnects:
  • If CPU utilization > 70%, a warning alert is displayed.
  • If CPU utilization > 90%, a critical alert is displayed.

Statistics for all CPUs are displayed in one graph.

Metric

Description

CPU utilization

CPU utilization is expressed as a percentage.

A high percentage indicates that processes running on the device are consuming a considerable amount of CPU resources. If the percentage appears frozen at or near 100%, a process might not be responding.

CPU speed

Not available for interconnects

The average CPU frequency, in GHz.

Health

HPE OneView administrators can periodically check the health of the interconnect. To check the health of an interconnect, select the Hardware menu in the Interconnects screen.

A health attribute indicates if the system is functioning fine or displays warnings on faulty interconnects to take suitable action.
  • If the interconnect health is in a degraded state, a warning alert is displayed.

  • If the interconnect health is in a failed state, a critical alert is displayed.

Memory

Memory utilization displays the current usage and the memory threshold configured by the system for that resource.

The memory threshold is configured automatically by the system during the interconnect configuration process. If the memory threshold set is surpassed, an alert is generated. Subsequent threshold alerts are suppressed if the usage is still beyond or equal to threshold configured. A new alert is regenerated only after the current utilization falls below the threshold and crosses it again. The appliance displays these alerts in the notification banner and in the Activity sidebar.

You can see the memory utilization data for a component under Memory on the Utilization panel.

Power

Power capacity is the calibrated maximum power that a device can consume. The power utilization metrics refresh every five minutes while the panel is open.

You can see the power utilization data for a component under Power on the Utilization panel.

Use this data to determine how much power your facility is consuming and the resources that are consuming it. The appliance reports alerts for devices that exceed their power capacity. Alerts are not shown for interconnects.

Metric

Description

Allocated power

(For Interconnects only)

The amount of power allocated to the resource.

Average power

The average amount of power the resource is consuming.

Peak power

The peak amount of power consumed by the resource.

Low power

The lowest amount of power consumed by the resource.

Temperature

Temperature utilization graphs display the ambient/inlet air temperature of your data center. The air temperature is detected by sensors embedded on the front of enclosures and other hardware devices.

The operating threshold is 10°C to 35°C (50°F to 95°F). When the device reaches a threshold, it generates temperature alerts. The appliance displays these alerts in the notification banner and in the Activity sidebar. Alerts are not shown for interconnects.

You can see the temperature utilization data for a component under Temperature on the Utilization panel.

NOTE:

The temperature is displayed in degrees Celsius or Fahrenheit, depending upon the locale setting of your browser.

For interconnects, the metrics display only the present ambient temperature and there is no utilization graph.

Custom

You can create custom utilization graphs by selecting two metrics for a particular resource. The two metrics you select are displayed on a single graph. The custom metrics that are available depend on the resource you are viewing.

Only for interconnects, the CPU utilization metrics show a graph trend for last five minutes utilization.

The other attributes such as temperature, power, and memory display the present or current value.

Resource

Metrics

Enclosures
Average power

The average power consumption of the enclosure over the time interval, in watts

Peak power

The peak power consumption of the enclosure over the time interval, in watts

Temperature

The temperature of the enclosure over the time interval in Celsius or Fahrenheit (depending on your browser locale settings)

Server Hardware
CPU utilization

The percentage of CPU utilization by the device over the time interval

CPU speed

The speed of the device CPU over the time interval, in GHz

Average power

The average power consumption of the device over the time interval, in watts

Peak power

The peak power consumption of the device over the time period, in watts

Power cap

The user-defined power cap, displayed as a gray band that covers the values the cap restricts

Temperature

The temperature of the device over the time interval, in degrees Celsius or Fahrenheit (depending on your browser locale settings)

More information