Capacity risk management for virtual machines

Patent metadata

Field	Value
Publication number	US-2019227835-A1
Application number	US-201916374079-A
Country	US
Kind code	A1
Filing date	Apr 3, 2019
Priority date	Jun 30, 2014
Publication date	Jul 25, 2019
Grant date	—

Abstract

An access data collector collects access assignment data characterizing active access assignment operations of a hypervisor in assigning host computing resources among virtual machines for use in execution of the virtual machines. Then, a capacity risk indicator calculator calculates a capacity risk indicator characterizing a capacity risk of the host computing resources with respect to meeting a prospective capacity demand of the virtual machines, based on the access assignment data

First claim

What is claimed is:

1 . A system including instructions stored on a non-transitory computer readable storage medium and executable by at least one semiconductor processor, the system comprising:
an access data collector configured to cause the at least one semiconductor processor to collect access assignment data characterizing active access assignment operations of a hypervisor in assigning host computing resources among virtual machines for use in execution of the virtual machines; and a capacity risk indicator calculator configured to cause the at least one semiconductor processor to calculate a capacity risk indicator characterizing a capacity risk of the host computing resources with respect to meeting a prospective capacity demand of the virtual machines, based on the access assignment data.

2 . The system of claim 1 , wherein the capacity risk indicator calculator includes at least one pressure index calculator configured to calculate at least one pressure index characterizing the active access assignments of the hypervisor relative to a corresponding threshold, and further wherein the capacity risk indicator calculator is configured to calculate the capacity risk indicator, based on the at least one pressure index.

3 . The system of claim 2 , wherein the capacity risk indicator calculator includes at least two pressure index calculators configured to calculate corresponding pressure indexes, and is configured to calculate the capacity risk indicator based on a weighted combination of the corresponding pressure indexes.

4 . The system of claim 2 , comprising a utilization monitor configured to collect utilization data characterizing utilization levels of the host computing resources, wherein the capacity risk indicator calculator is configured to calculate the capacity risk indicator based on the utilization data and the at least one pressure index.

5 . The system of claim 4 , wherein the capacity risk indicator calculator is configured to calculate the capacity risk indicator including adding the at least one pressure index as a penalty to a corresponding utilization level of the utilization levels.

6 . The system of claim 2 , wherein the at least one pressure index calculator includes a memory pressure index calculator, and the at least one pressure index includes a memory pressure index characterizing memory assignments of the hypervisor relative to a memory threshold.

7 . The system of claim 6 , wherein the memory pressure index is calculated based on at least one of ballooning and swapping operations of the hypervisor included in the memory assignments.

8 . The system of claim 2 , wherein the at least one pressure index calculator includes a central processor unit (CPU) pressure index calculator, and the at least one pressure index includes a CPU pressure index characterizing a wait time experienced by the virtual machines for access to CPU resources of the host computing resources, relative to a CPU threshold.

9 . The system of claim 2 , wherein the at least one pressure index calculator includes a storage pressure index calculator, and the at least one pressure index includes a storage pressure index characterizing an input/output (I/O) latency experienced by the virtual machines for access to storage resources of the host computing resources, relative to a storage threshold.

10 . The system of claim 1 , wherein the active access assignment data characterizes inclusion of at least one of the virtual machines within at least one access queue of the hypervisor.

11 . A method comprising:
collecting, using at least one semiconductor processor, access assignment data characterizing active access assignment operations of a hypervisor in assigning host computing resources among virtual machines for use in execution of the virtual machines; and calculating, using at least one semiconductor processor, a capacity risk indicator characterizing a capacity risk of the host computing resources with respect to meeting a prospective capacity demand of the virtual machines, based on the access assignment data.

12 . The method of claim 11 , wherein the calculating comprises:
calculating at least one pressure index characterizing the active access assignments of the hypervisor relative to a corresponding threshold; and calculating the capacity risk indicator, based on the at least one pressure index.

13 . The method of claim 12 , comprising collecting utilization data characterizing utilization levels of the host computing resources, wherein the calculating of the capacity risk indicator includes calculating the capacity risk indicator based on the utilization data and the at least one pressure index.

14 . The method of claim 12 , wherein the at least one pressure index characterizes overhead activity of the hypervisor in assigning the host computing resources among the virtual machines.

15 . The method of claim 11 , wherein the capacity risk indicator characterizes a saturation level of at least a portion of the host computing resources.

16 . A computer program product including instructions recorded on a non-transitory computer readable storage medium and configured, when executed by at least one semiconductor processor, to cause the at least one semiconductor processor to:
collect access assignment data characterizing active access assignment operations of a hypervisor in assigning host computing resources among virtual machines for use in execution of the virtual machines; and calculate a capacity risk indicator characterizing a capacity risk of the host computing resources with respect to meeting a prospective capacity demand of the virtual machines, based on the access assignment data.

17 . The computer program product of claim 16 , wherein the instructions, when executed, are further configured to cause the at least one semiconductor processor to:
calculate at least one pressure index characterizing the active access assignments of the hypervisor relative to a corresponding threshold, and calculate the capacity risk indicator, based on the at least one pressure index.

18 . The computer program product of claim 17 , wherein the instructions, when executed, are further configured to cause the at least one semiconductor processor to:
calculate at least two pressure indexes; and calculate the capacity risk indicator based on a weighted combination of the at least two pressure indexes.

19 . The computer program product of claim 17 , wherein the instructions, when executed, are further configured to cause the at least one semiconductor processor to
collect utilization data characterizing utilization levels of the host computing resources; and calculate the capacity risk indicator based on the utilization data and the at least one pressure index.

20 . The computer program product of claim 17 , wherein the at least one pressure index includes:
a memory pressure index characterizing memory assignments of the hypervisor relative to a memory threshold; a central processor unit (CPU) pressure index characterizing a wait time experienced by the virtual machines for access to CPU resources of the host computing resources, relative to a CPU threshold; and a storage pressure index characterizing an input/output (I/O) latency experienced by the virtual machines for access to storage resources of the host computing resources, relative to a storage threshold.

Assignees

• Bmc Software Inc

Inventors

• Sivasubramanian Jeyashree
• Apte Sudheer

Classifications

• G06F11/3086

  where the reporting involves the use of self describing data formats, i.e. metadata, markup languages, human readable formats · CPC title

• G06F2009/45591

  Monitoring or debugging support · CPC title

• G06F9/5083

  Techniques for rebalancing the load in a distributed system · CPC title

• G06F11/301

  where the computing system is a virtual computing platform, e.g. logically partitioned systems (virtual machines G06F9/45533; logical partitioning of resources G06F9/5077) · CPC title

• G06F11/30

  Monitoring · CPC title