vRealize Operations Manager collects configuration, storage, disk space, CPU use, disk, memory, network, power, and summary metrics for cluster compute resources.

Cluster Compute Resource metrics include capacity and badge metrics. See definitions in:

Metrics marked with an asterisk (*) provide the most relevant data to use when you troubleshoot the clusters in your environment.

Configuration Metrics for Cluster Compute Resources

Configuration metrics provide information about configuration settings.

Metric

Description

Configuration|Failover Level

DAS configuration failover level.

Key: configuration|dasconfig|failoverLevel

Configuration|Active Admission Control Policy

DAS configuration active admission control policy.

Key: configuration|dasconfig|activeAdministrationControlPolicy

Configuration|CPU Failover Resources Percent

Percent CPU failover resources for DAS configuration admission control policy.

Key: configuration|dasconfig|adminissionControlPolicy|cpuFailoverResourcesPercent

Configuration|Memory Failover Resources Percent

Percent memory failover resources for DAS configuration admission control policy.

Key: configuration|dasconfig|adminissionControlPolicy|memoryFailoverResourcesPercent

Storage Metrics for Cluster Compute Resources

Storage metrics provide information about storage use.

Metric

Description

Storage|Total Usage

Total throughput rate in kilobytes per second.

Key: storage|usage_average

Disk Space Metrics for Cluster Compute Resources

Disk space metrics provide information about disk space use.

Metric

Description

Diskspace|Virtual machine used (GB)

Space used by virtual machine files in gigabytes.

Key: diskspace|used

Diskspace|Total disk space used

Total disk space used on all datastores visible to this object.

Key: diskspace|total_usage

Diskspace|Total disk space

Total disk space on all datastores visible to this object.

Key: diskspace|total_capacity

Diskspace|Total provisioned disk space

Total provisioned disk space on all datastores visible to this object.

Key: diskspace|total_provisioned

Diskspace|Virtual Disk Used (GB)

Space used by virtual disks in gigabytes.

Key: diskspace|diskused

Diskspace|Snapshot Space (GB)

Space used by snapshots in gigabytes.

Key: diskspace|snapshot

Diskspace|Shared Used (GB)

Shared used space in gigabytes.

Key: diskspace|shared

Diskspace|Not Shared (GB)

Space used by VMs that is not shared.

Key: diskspace|notshared

CPU Usage Metrics for Cluster Compute Resources

CPU usage metrics provide information about CPU use.

Metric

Description

CPU|Capacity Usage

This metric shows the percentage of the capacity used.

Key: cpu|capacity_usagepct_average

* CPU|CPU Contention (%)

This metric is an indicator of the overall contention for CPU resources that occurs across the workloads in the cluster. When contention occurs, it means that some of the virtual machines are not immediately getting the CPU resources they are requesting.

Use this metric to identify when a lack of CPU resources might be causing performance issues in the cluster.

This metric is the sum of the CPU contention across all hosts in the cluster averaged over two times the number of physical CPUs in the cluster to account for hyper-threading. CPU contention takes into account:

  • CPU Ready

  • CPU Co-stop

  • Power management

  • Hyper threading

This metric is more accurate than CPU Ready since it takes into account CPU Co-stop and Hyper threading.

When using this metric, the number should be lower than the performance you expect. If you expect performance at 10%, then the number should be lower than 10%.

Since this value is averaged across all hosts in the cluster, you may find that some hosts have a higher CPU contention while others are lower. In order to ensure that vSphere spreads out the running workloads across hosts, consider enabling a fully-automated DRS in the cluster.

Key: cpu|capacity_contentionPct

* CPU|Demand (%)

This metric is an indicator of the overall demand for CPU resources by the workloads in the cluster.

It shows the percentage of CPU resources that all the virtual machines would use if there were no CPU contention or CPU limits set. It represents the average active CPU load in the past five minutes.

Key: cpu|demandPct

CPU|Demand (MHz)

Demand in megahertz.

Key: cpu|demandmhz

CPU|IO Wait

IO wait time in milliseconds.

Key: cpu|iowait

CPU|Number of CPU Sockets

Number of CPU sockets.

Key: cpu|numpackages

CPU|Overall CPU Contention

Overall CPU contention in milliseconds.

Key: cpu|capacity_contention

CPU|Host Provisioned Capacity

Provisioned CPU capacity in megahertz.

Key: cpu|capacity_provisioned

CPU|Provisioned vCPUs

Number of provisioned CPU cores.

Key: cpu|corecount_provisioned

CPU|Reserved Capacity

The sum of the reservation properties of the (immediate) children of the host's root resource pool in megahertz.

Key: cpu|reservedCapacity_average

CPU|Wait

CPU time spent on idle state in milliseconds.

Key: cpu|wait

CPU|Usage (MHz)

Average CPU use in megahertz.

Key: cpu|usagemhz_average

CPU|Total Capacity

Total CPU capacity in megahertz.

Key: cpu|totalCapacity _average

CPU|Demand

CPU Demand.

Key: cpu|demand_average

CPU|Overhead

Amount of CPU overhead.

Key: cpu|overhead_average

CPU|Demand without overhead

Value of demand excluding any overhead.

Key: cpu|demand_without_overhead

CPU|Provisioned Capacity

Provisioned Capacity (MHz).

Key: cpu|vm_capacity_provisioned

CPU|Number of hosts stressed

Number of hosts stressed.

Key: cpu|num_hosts_stressed

CPU|Stress Balance Factor

Stress Balance Factor.

Key: cpu|stress_balance_factor

CPU|Lowest Provider Capacity Remaining

Lowest Provider Capacity Remaining.

Key: cpu|min_host_capacity_remaining

CPU|Workload Balance Factor

Workload Balance Factor.

Key: cpu|workload_balance_factor

CPU|Highest Provider Workload

Highest Provider Workload.

Key: cpu|max_host_workload

CPU|Host workload Max-Min Disparity

Difference of Max and Min host workload in the container.

Key: cpu|host_workload_disparity

CPU|Host stress Max-Min Disparity

Difference of Max and Min host stress in the container.

Key: cpu|host_stress_disparity

Disk Metrics for Cluster Compute Resources

Disk metrics provide information about disk use.

Metric

Description

Disk|Commands per second

Average number of commands issued per second during the collection interval.

Key: disk|commandsAveraged_average

Disk|Disk Command Latency (ms)

Average amount of time taken for a command from the perspective of the guest operating system. This metric is the sum of the Kernel Command Latency and Physical Device Command Latency metrics.

Key: disk|totalLatency_average

Disk|Disk Read Latency

Average amount of time for a read operation from the virtual disk. The total latency is the sum of Kernel latency and device latency.

Key: disk|totalReadLatency_average

Disk|Disk Write Latency

The average amount of time taken for a read from the perspective of a Guest OS. This is the sum of Kernel Read Latency and Physical Device Read Latency.

Key: disk|totalWriteLatency_averag

Disk|Read Rate (KBps)

Number of times data was read from the disk in the defined interval.

Key: disk|numberRead_summation

Disk|Reads per second

Average number of read commands issued per second during the collection interval.

Key: disk|numberReadAveraged_averag

Disk|Usage Rate (KBps)

Average of the sum of the data read and written for all of the disk instances of the host or virtual machine.

Key: disk|usage_average

Disk|Write Rate (KBps)

Number of times data was written to disk during the collection interval.

Key: disk|numberWrite_summation

Disk|Writes per second

Average number of write commands issued per second during the collection interval.

Key: disk|numberWriteAveraged_average

Disk|Read Requests

Amount of data read from the disk during the collection interval.

Key: disk|read_average

Disk|Write Requests

Amount of data written to the disk during the collection interval.

Key: disk|write_average

Disk|Commands Issued

Number of disk commands issued during the collection interval.

Key: disk|commands_summation

Disk|Total Queued Outstanding operations

Sum of queued operation and outstanding operations.

Key: disk|sum_queued_oio

Disk|Max Observed OIO

Max observed outstanding IO for a disk.

Key: disk|max_observed

Memory Metrics for Cluster Compute Resources

Memory metrics provide information about memory use and allocation.

Metric

Description

Mem|Active Write (KB)

Active writes in kilobytes.

Key: mem|activewrite_average

Mem|Compressed (KB)

Average compression in kilobytes.

Key: mem|compressed_average

Mem|Compression Rate (KBps)

Average compression rate in kilobytes.

Key: mem|compressionRate_average

Mem|Consumed (KB)

Amount of host memory consumed by the virtual machine for guest memory.

Key: mem|consumed_average

* Mem|Contention (%)

This metric is an indicator of the overall contention for memory resources that occurs across the workloads in the cluster. When contention occurs, it means that some portion of the VMs are not immediately getting the memory resources that they are requesting.

Use this metric to identify when lack of memory resources might be causing performance issues in the cluster.

Key: mem|host_contentionPct

Mem|Contention (KB)

Contention in kilobytes.

Key: mem|host_contention

Mem|Decompression Rate (KBps

Decompression rate in kilobytes.

Key: mem|decompressionRate_average

Mem|Granted (KB)

Amount of memory available for use.

Key: mem|granted_average

Mem|Guest Active (KB)

Amount of memory that is actively used.

Key: mem|active_average

Mem|Heap (KB)

Amount of memory allocated for heap.

Key: mem|heap_average

Mem|Heap Free (KB)

Free space in the heap.

Key: mem|heapfree_average

* Mem|Balloon

This metric shows the amount of memory currently used by the virtual machine memory control. It is only defined at the VM level.

Key: mem|vmmemctl_average

Mem|VM Overhead (KB)

Memory overhead reported by host.

Key: mem|overhead_average

Mem|Provisioned Memory (KB)

Provisioned memory in kilobytes.

Key: mem|host_provisioned

Mem|Reserved Capacity (KB)

Reserved capacity in kilobytes.

Key: mem|reservedCapacity_average

Mem|Shared (KB)

Amount of shared memory.

Key: mem|shared_average

Mem|Shared Common (KB)

Amount of shared common memory.

Key: mem|sharedcommon_average

Mem|Swap In (KB)

Amount of memory that is swapped in for the service console.

Key: mem|swapin_average

Mem|Swap In Rate (KBps)

Rate at which memory is swapped from disk into active memory during the interval.

Key: mem|swapinRate_average

Mem|Swap Out (KB)

Amount of memory that is swapped out for the service console.

Key: mem|swapout_average

Mem|Swap Out Rate (KBps)

Rate at which memory is being swapped from active memory into disk during the current interval.

Key: mem|swapoutRate_average

Mem|Swap Used (KB)

Amount of memory used for swap space.

Key: mem|swapused_average

Mem|Total Capacity (KB)

Total capacity in kilobytes.

Key: mem|totalCapacity_average

Mem|Reserved (KB)

Amount of unreserved memory.

Key: mem|unreserved_average

Mem|Usable Memory (KB)

Usable memory in kilobytes.

Key: mem|host_usable

Mem|Usage/Usable

Percent memory used.

Key: mem|host_usagePct

Mem|Host Usage (KB)

Memory use in kilobytes.

Key: mem|host_usage

Mem|Machine Demand

Memory Machine Demand in KB.

Key: mem|host_demand

Mem|ESX System Usage

Memory usage by the VMkernel and ESX user-level services.

Key: mem|host_systemUsage

* Mem|Usage (%)

This metric shows the portion of the total memory in all hosts in the cluster that is being used.

This metric is the sum of memory consumed across all hosts in the cluster divided by the sum of physical memory across all hosts in the cluster.

∑ memory consumed on all hosts

--------------------------------------------- X 100%

∑ physical memory on all hosts

Mem|Usage (KB)

Memory currently in use as a percentage of total available memory.

Key: mem|usage_average

Mem|VM kernel Usage (KB)

Amount of memory that the VM kernel uses.

Key: mem|sysUsage_average

Mem|Zero (KB)

Amount of memory that is all 0.

Key: mem|zero_average

Mem|Number of Hosts Stressed

Number of hosts stressed.

Key: mem|num_hosts_stressed

Mem|Stress Balance Factor

Stress balance factor.

Key: mem|stress_balance_factor

Mem|Lowest Provider Capacity Remaining

Lowest provider capacity remaining.

Key: mem|min_host_capacity_remaining

Mem|Workload Balance Factor

Workload balance factor.

Key: mem|workload_balance_factor

Mem|Highest Provider Workload

Highest provider workload.

Key: mem|max_host_workload

Mem|Host workload Max-Min Disparity

Difference of Max and Min host workload in the container.

Key: mem|host_workload_disparity

Mem|Host stress Max-Min Disparity

Difference of Max and Min host stress in the container.

Key: mem|host_stress_disparity

Network Metrics for Cluster Compute Resources

Network metrics provide information about network performance.

Metric

Description

Net|Data Receive Rate (KBps)

Average amount of data received per second.

Key: net|received_average

Net|Data Transmit Rate (KBps)

Average amount of data transmitted per second.

Key: net|transmitted_average

Net|Packets Dropped

Number of packets dropped in the performance interval.

Key: net|dropped

Net|Packets Dropped (%)

Percentage of packets dropped.

Key: net|droppedPct

Net|Packets Received

Number of packets received in the performance interval.

Key: net|packetsRx_summation

Net|Packets Transmitted

Number of packets transmitted in the performance interval.

Key: net|packetsTx_summation

Net|Received Packets Dropped

Number of received packets dropped in the performance interval.

Key: net|droppedRx_summation

Net|Transmitted Packets Dropped

Number of transmitted packets dropped in the performance interval.

Key: net|droppedTx_summation

Net|Usage Rate (KBps)

The sum of the data transmitted and received for all the NIC instances of the host or virtual machine.

Key: net|usage_average

Net|Max Observed Throughput

Max observed rate of network throughput.

Key: net|maxObservedKBps

Net|Max Observed Transmitted Throughput

Max observed transmitted rate of network throughput.

Key: net|maxObserved_Tx_KBps

Net|Max Observed Received Throughput

Max observed received rate of network throughput.

Key: net|maxObserved_Rx_KBps

Datastore Metrics for Cluster Compute Resources

Datastore metrics provide information about Datastore use.

Metric

Description

Datastore|Max Observed Reads per second

Max observed average number of read commands issued per second during the collection interval.

Key: datastore|maxObserved_NumberRead

Datastore|Max Observed Read Rate

Max observed rate of reading data from the datastore.

Key: datastore|maxObserved_Read

Datastore|Max Observed Writes per second

Max observed average number of write commands issued per second during the collection interval.

Key: datastore|maxObserved_NumberWrite

Datastore|Max Observed Write Rate

Max observed rate of writing data from the datastore.

Key: datastore|maxObserved_Write

Datastore|Max Observed Number of Outstanding IO Operations

Max Observed Number of Outstanding IO Operations.

Key: datastore|maxObserved_OIO

Datastore|Outstanding IO requests

OIO for datastore.

Key: datastore|demand_oio

Datastore|Reads per second

Average number of read commands issued per second during the collection interval.

Key: datastore|numberReadAveraged_average

Datastore|Writes per second

Average number of write commands issued per second during the collection interval.

Key: datastore|numberWriteAveraged_average

Datastore|Read Rate

Amount of data read in the performance interval.

Key: datastore|read_average

Datastore|Write Rate

Amount of data written to disk in the performance interval.

Key: datastore|write_average

Cluster Services Metrics for Cluster Compute Resources

Cluster Services metrics provide information about cluster services.

Metric

Description

ClusterServices|Effective CPU Resources (MHz)

VMware DRS effective CPU resources available.

Key: clusterServices|effectivecpu_average

ClusterServices|Effective Memory Resources (KB)

VMware DRS effective memory resources available.

Key: clusterServices|effectivemem_average

Power Metrics for Cluster Compute Resources

Power metrics provide information about power use.

Metric

Description

Power|Energy (Joule)

Energy use in joules.

Key: power|energy_summation

Power|Power (Watt)

Average power use in watts.

Key: power|power_average

Power|Power Cap (Watt)

Average power capacity in watts.

Key: power|powerCap_average

Summary Metrics for Cluster Compute Resources

Summary metrics provide information about overall performance.

Metric

Description

Summary|Number of Running Hosts

Number of running hosts.

Key: summary|number_running_hosts

* Summary|Number of Running VMs

This metric shows the total number of VMs running on all hosts in the cluster.

Key: summary|number_running_vms

* Summary|Number of vMotions

This metric shows the number of vMotions that occurred during the last collection cycle.

When using this metric, look for a low number which indicates that the cluster is able to serve its VMs. A vMotion can impact VM performance during the stun time.

Key: summary|number_vmotion

Summary|Total Number of Hosts

Total number of hosts.

Key: summary|total_number_hosts

Summary|Total Number of VMs

Total number of virtual machines.

Key: summary|total_number_vms

Summary|Maximum Number of VMs

Maximum Number of virtual machines.

Key: summary|max_number_vms

Summary|Workload Indicator

Percent workload indicator.

Key: summary|workload_indicator

Summary|Total Number of Datastores

Total number of datastores.

Key: summary|total_number_datastores

Summary|Number of VCPUs on Powered On VMs

Number of virtual CPUs on powered-on virtual machines.

Key: summary|number_running_vcpus

Summary|Average Running VM Count per Running Host

Average number of running virtual machines per running host.

Key: summary|avg_vm_density

Summary|Average Provisioned Capacity (MHz) per Running VM

Average provisioned capacity, in megahertz, per running virtual machine.

Key: summary|avg_vm_cpu

Summary|Average Provisioned Memory (KB) per Running VM

Average provisioned memory, in kilobytes. per running virtual machine.

Key: summary|avg_vm_mem