Modeling real capacity consumption changes using process-level data

Patent metadata

Field	Value
Publication number	US-9875169-B2
Application number	US-201514669817-A
Country	US
Kind code	B2
Filing date	Mar 26, 2015
Priority date	Mar 26, 2015
Publication date	Jan 23, 2018
Grant date	Jan 23, 2018

Abstract

A method includes receiving an expected growth rate for modeling future capacity utilization for a resource hosting a plurality of processes, each process being associated with a respective workload. The method also includes modifying, in a non-linear capacity utilization model for the resource, the respective workload for a particular process in the plurality of processes based on the expected growth rate, and, in response to modifying the respective workload, determining a change in total capacity utilization for the resource using the non-linear capacity utilization model. The method further includes determining a ratio between the change in the total capacity utilization for the resource and the modification to the respective workload. The method additionally includes modifying, based on the ratio, a configuration of the resource with respect to the particular process in anticipation of the expected growth rate.

First claim

What is claimed is:

1. A method, comprising:
receiving an expected growth rate for modeling future capacity utilization for a resource hosting a plurality of processes, each process being associated with a respective workload, wherein the resource is associated with a plurality of computing components, and wherein the plurality of processes comprise (1) system processes that do not experience increased workloads when demand for applications increases and (2) application specific processes;
modifying, in a non-linear capacity utilization model for the resource, the respective workload for a particular application specific process in the plurality of processes based on the expected growth rate, wherein the non-linear capacity utilization model (1) characterizes a capacity of the plurality of computing components associated with the resource to service additional workloads regardless of platform characteristics and (2) isolates the system processes from being affected by the modification to the respective workload for the particular application specific process;
in response to modifying the respective workload in the non-linear capacity utilization model for the resource, determining a predicted change in total capacity utilization for the resource in the non-linear capacity utilization model;
determining that the predicted change in total capacity utilization from the non-linear capacity utilization model exceeds an available capacity of the resource based on a ratio between the predicted change in the total capacity utilization for the resource and the modification to the respective workload; and
modifying, based on the ratio, a configuration of the resource with respect to the particular application specific process in anticipation of the expected growth rate.

2. The method of claim 1 , further comprising:
determining a portion of an initial total capacity utilization attributable to the particular application specific process; and
in response to modifying the respective workload, determining a ratio between the predicted change in the total capacity utilization for the resource and the portion of the initial total capacity utilization attributable to the particular application specific process.

3. The method of claim 1 , wherein the plurality of processes are divided into a first group, indicative of system-level processes, and a second group, indicative of application processes, and wherein the method further comprises:
determining a ratio between a first portion of an initial total capacity utilization attributable to the first group of processes and a second portion of the initial total capacity utilization attributable to the second group of processes.

4. The method of claim 1 , wherein the resource is a virtual resource, and wherein modifying the configuration of the resource comprises modifying virtual components of the virtual resource.

5. The method of claim 1 , wherein modifying the configuration of the resource comprises modifying a physical server infrastructure associated with the resource.

6. The method of claim 1 , wherein the non-linear capacity utilization model is assembled from a set of models configured to emulate:
hardware components associated with the resource;
an operating system of the resource; and
virtual components associated with the resource.

7. The method of claim 1 , wherein modifying the configuration of the resource with respect to the particular application specific process comprises consolidating virtual resources associated with the particular application specific process, wherein the growth rate is negative.

8. A computer configured to access a storage device, the computer comprising:
a processor; and
a non-transitory, computer-readable storage medium storing computer-readable instructions that when executed by the processor cause the computer to perform:
receiving an expected growth rate for modeling future capacity utilization for a resource hosting a plurality of processes, each process being associated with a respective workload, wherein the resource is associated with a plurality of computing components, and wherein the plurality of processes comprise (1) system processes that do not experience increased workloads when demand for applications increases and (2) application specific processes;
modifying, in a non-linear capacity utilization model for the resource, the respective workload for a particular application specific process in the plurality of processes based on the expected growth rate, wherein the non-linear capacity utilization model (1) characterizes a capacity of the plurality of computing components associated with the resource to service additional workloads regardless of platform characteristics and (2) isolates the system processes from being affected by the modification to the respective workload for the particular application specific process;
in response to modifying the respective workload in the non-linear capacity utilization model for the resource, determining a predicted change in total capacity utilization for the resource in the non-linear capacity utilization model;
determining that the predicted change in total capacity utilization from the non-linear capacity utilization model exceeds an available capacity of the resource based on a ratio between the predicted change in the total capacity utilization for the resource and the modification to the respective workload; and
modifying, based on the ratio, a configuration of the resource with respect to the particular application specific process in anticipation of the expected growth rate.

9. The computer of claim 8 , wherein the computer-readable instructions further cause the computer to perform:
determining a portion of an initial total capacity utilization attributable to the particular application specific process; and
in response to modifying the respective workload, determining a ratio between the predicted change in the total capacity utilization for the resource and the portion of the initial total capacity utilization attributable to the particular application specific process.

10. The computer of claim 8 , wherein the plurality of processes are divided into a first group, indicative of system-level processes, and a second group, indicative of application processes, and wherein the computer-readable instructions further cause the computer to perform:
determining a ratio between a first portion of an initial total capacity utilization attributable to the first group of processes and a second portion of the initial total capacity utilization attributable to the second group of processes.

11. The computer of claim 8 , wherein the resource is a virtual resource, and wherein modifying the configuration of the resource comprises modifying virtual components of the virtual resource.

12. The computer of claim 8 , wherein modifying the configuration of the resource comprises modifying a physical server infrastructure associated with the resource.

13. The computer of claim 8 , wherein the non-linear capacity utilization model is assembled from a set of models configured to emulate:
hardware components associated with the resource;
an operating system of the resource; and
virtual components associated with the resource.

14. The computer of claim 8 , wherein modifying the configuration of the resource with respect to the particular application specific process comprises consolidating virtual resources associated with the particular application specific process, wherein the growth rate is negative.

15. A computer program product comprising:
a non-transitory computer-readable stor

Assignees

• Ashby Jr John Wiley
• Varadaraju Balaji
• Ca Inc

Inventors

• Ashby Jr John Wiley
• Varadaraju Balaji

Classifications

• G06F2209/5019

  Workload prediction · CPC title

• G06F11/3452

  Performance evaluation by statistical analysis · CPC title

• G06F11/3442 Primary

  for planning or managing the needed capacity · CPC title

• G06F9/5077

  Logical partitioning of resources; Management or configuration of virtualized resources (specific details on emulation or internal functioning of virtual machines G06F9/455) · CPC title

• G06F9/5072 Primary

  Grid computing · CPC title