5.8.5

If FSDB home directories exist on more than one Windows drive or Linux file system,
runvcopsServerConfiguration uses the minimum amount of available space on any of the defined drives or
file systems and multiplies it by the defined number of drives or file systems. If the drives or files systems
have very different amounts of available space, runvcopsServerConfiguration might underestimate the
amount of available space. For example, if FSDB home directories exist on two drives and one drive has
40GB available and the other drive has 300GB available, runvcopsServerConfiguration estimates the disk
space as 80GB (40GB multiplied by 2).
The maximum number of resources that runvcopsServerConfiguration calculates is an approximation. In
many cases, the server host might be able to support a slightly higher number of resources. For example, if
runvcopsServerConfiguration estimates that the host can support 1485 resources, the host might be able to
support 1500 resources.
Eliminating Linearly Correlated Metrics from the DT Calculation
In certain circumstances, you might want to eliminate linearly correlated metrics from the dynamic
threshold calculation. For example, if the CPU | Usage (%) metric is outside of normal bounds for a virtual
machine, the CPU | Usage (MHz) metric also will be outside of normal bounds because the metrics are
correlated. In this case, calculating dynamic thresholds on both metrics is not necessary.
The PCA tool eliminates linearly correlated metrics from the dynamic threshold calculation. You use the
pca.properties file to identify the resource kinds on which to run the PCA tool, specify the number of days
of data to include in the PCA calculation, and configure other properties.
pca.properties File
The pca.properties file in the vcenter-ops\tools\pca\conf folder contains configuration information for
the PCA tool. In a vApp installation, you edit the pca.properties file on the Analytics virtual machine.
Table 12‑4. pca.properties File Properties
Property Description
pcaRKList
Comma-separated list of resource kind keys. This list determines the resource kinds
on which to run the PCA tool.
pcaDaysToProcess
Number of days of data to include in the PCA calculation.
pcaDaysAgoEnd
End date for the metric data to include in the PCA calculation, counted in number of
days from the current date.
pcaTimeWindowIncrement
Size of the interval between data windows, expressed as a number of samples.
pcaTimeWindowSize
Size of each data window, expressed as a number of samples.
pcaPFraction
Value of the p fraction variable to use in the PCA calculation.
pcaDataSetSamplePercent
Percentage, from 0 to 100, of the data set to use as a random sample when
determining the monitoring cycle.
pcaConstantPercentile
Percentile to take when determining when data sets are constant.
pcaEpsilon
Rounding error for determining when data sets are constant.
The following example is a sample pca.properties file.
pcaRKList = Tier
pcaDaysToProcess = 1
pcaDaysAgoEnd = 0
pcaTimeWindowIncrement = 10.0
pcaTimeWindowSize = 20.0
Chapter 12 Using System Tools
VMware, Inc. 155