Method and apparatus for computing a distance metric between computer system workloads

A computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for computing a distance metric between computer system workloads, the method comprising:

• receiving a database containing metrics that have been collected for a number of workloads of interest, wherein the metrics were stored to a file during the collection process;
• using splines to define bases for a regression model which uses a performance indicator y as a response and uses the metrics (represented by a vector x) as predictors;
• fitting the regression model to the dataset using a penalized least squares (PLS) criterion to obtain functions f1, . . . , fP, which are smooth univariate functions of individual metrics that add up to the regression function f, such that
• y
• =
• f
• ⁡
• (
• x
• )
• +
• ɛ
• =
• ∑
• i
• =
• 3
• P
• ⁢
• f
• i
• ⁡
• (
• x
• i
• )
• +
• ɛ
• ,
• wherein ε represents noise;
• using the fitted regression function to define the distance metric;
• and
• using the distance metric to analyze similarities between workloads;
• and
• displaying results of the analysis to a user.

A system that computes a distance metric between computer system workloads, comprising:

• a processor;
• a memory;
• a receiving mechanism within the processor and the memory configured to receive a dataset containing metrics that have been collected for a number of workloads of interest, wherein the metrics were stored to a file during the collection process;
• a regression module generator within the processor and the memory configured to,
• use splines to define bases for a regression model which uses a performance indicator y as a response and uses the metrics (represented by a vector x) as predictors, and to
• fit the regression model to the dataset using a penalized least squares (PLS) criterion to obtain functions f1, . . . , fP, which are smooth univariate functions of individual metrics that add up to the regression function f, such that
• y
• =
• f
• ⁡
• (
• x
• )
• +
• ɛ
• =
• ∑
• i
• =
• 1
• P
• ⁢
• f
• i
• ⁡
• (
• x
• i
• )
• +
• ɛ
• ,
• wherein ε represents noise;
• a distance metric generator within the processor and the memory configured to use the fitted regression function to define the distance metric;
• an analysis mechanism configured to use the distance metric to analyze similarities between workloads;
• and
• an output mechanism configured to display results of the analysis to a user.