Elastic storage volume type selection and optimization engine for public cloud environments

Patent metadata

Field	Value
Publication number	US-10712958-B2
Application number	US-201816154174-A
Country	US
Kind code	B2
Filing date	Oct 8, 2018
Priority date	Jul 24, 2018
Publication date	Jul 14, 2020
Grant date	Jul 14, 2020

Abstract

A system for elastic volume type selection and optimization is provided. The system may detect that a block storage volume was provisioned by a public cloud computing platform based on a first volume type identifier of a first volume type. The system may determine, based on a normalization model, a baseline operation rate and a baseline throughput rate for the provisioned block storage volume. The system may determine, based on a selected transition mode and historical performance measurements, a simulated operation rate and a simulated throughput rate. The system may communicate, in response to the simulated throughput being greater than the baseline throughput rate or the simulated operation rate being greater than the baseline operation rate, a provisioning instruction to re-provision the provisioned block storage volume on the cloud computing platform.

First claim

What is claimed is:

1. A method, the method comprising:
storing, in a repository, a plurality of transition models that each include a rule that governs dynamic resource allocation on a cloud computing platform for providing access to block storage volumes, the rule within each transition model is associated with respective volume type identifiers of volume types;
detecting that a block storage volume was provisioned by a cloud computing platform based on a first volume type identifier of a first volume type, wherein the first volume type causes the cloud computing platform to control a runtime operation rate permitted for accessing at least one of the block storage volumes, the runtime operation rate characterizing a rate at which distinct memory operations are performed;
determining a baseline operation rate and a baseline throughput rate for the provisioned block storage volume using a normalization model to support comparison with a second volume type, the baseline throughput rate characterizing a data volume transmission over time regardless of a number of distinct memory operations;
obtaining historical performance measurements for the provisioned block storage volume;
selecting from the plurality of transition models a transition model that is associated with a second volume type identifier of the second volume type, wherein the second volume type causes the cloud computing platform to control a runtime throughput rate permitted for accessing the at least one of the block storage volumes;
determining, based on the selected transition model and the historical performance measurements for the provisioned block storage volume, a simulated operation rate and a simulated throughput rate; and
communicating, in response to at least one of the simulated throughput rate being greater than the baseline throughput rate or the simulated operation rate being greater than the determined baseline operation rate, a provisioning instruction to re-provision the provisioned block storage volume on the cloud computing platform, the provision instruction comprising provisioning settings, the provisioning settings comprising the second volume type identifier.

2. The method of claim 1 , wherein the provisioning settings further comprise at least one of a volume name, a volume size, a throughput rate, or an operation rate.

3. The method of claim 1 , wherein determining the baseline operation rate and the baseline throughput rate for the provisioned block storage volume further comprises:
generating a percentile-based operation rate based on a plurality of operation rate measurements derived from the historical performance measurements;
normalizing the percentile-based operation rate based a burst balance mode associated with the first volume type identifier, the burst balance mode indicative of a permission to increase the runtime operation rate higher than the baseline operation rate; and
converting the normalized percentile-based operation rate to a normalized throughput rate, wherein the baseline throughput rate comprises the normalized throughput rate.

4. The method of claim 1 , further comprising:
selecting a plurality of transition models that are respectively associated with the volume types, each of the transition models configured to determine a respective simulated operation rate and a respective simulated throughput rate for a corresponding volume type;
flagging at least one of the volume types in response to the respective simulated throughput rate for the at least one of the volume types being greater than the baseline throughput rate or the respective simulated operation rate for the at least one of the volume types being greater than the baseline operation rate; and
generating respective provisioning instructions for each of the flagged volume types, wherein each of the respective provisioning instructions comprise an instruction to provision a new block storage volume with a volume type identifier indicative of a corresponding flagged volume type.

5. The method of claim 1 , wherein communicating the provisioning instruction further comprises:
transmitting the provisioning instruction to a cloud computing platform, wherein the cloud computing platform is configured to provision a new block storage volume based on the provisioning settings of the provisioning instruction.

6. The method of claim 5 , wherein before transmitting the provisioning instruction to the cloud computing platform, the method further comprises:
transmitting a plurality of provisioning instruction candidates to a remote terminal; and
receiving a selection input indicative of at least one of the provisioning instruction candidates.

7. The method of claim 1 , wherein determining, based on the transition model and the historical performance measurements, a simulated operation rate and a simulated throughput further comprises:
determining, based on the historical performance measurements, a high-load operation rate and a percentile-based operation rate over an operational time range;
increasing the high-load operation based on a buffer value;
generating a utilization ratio of the high-load operation rate and the percentile -based operation rate; and
determining the simulated operation rate based on the utilization ratio.

8. The method of claim 7 , further comprising:
receiving an update parameter for at least one of the transition models, the update parameter comprising an update buffer value; and
updating the transition model with the updated buffer value.

9. The method of claim 1 , further comprising
displaying a graphical user interface comprising a recommendation table, the recommendation table comprising a recommendation row corresponding to the block storage volume, the recommendation row comprising the first volume type identifier, the second volume type identifier, a base line performance metric, a simulated performance metric and a performance change metric;
receiving an operation input corresponding to the recommendation row; and
generating the provisioning instruction in response to receipt of the operation input.

10. A system comprising:
circuitry configured to store, in a repository, a plurality of transition models associated with respective volume types, where each of the plurality of transition models include a rule that governs dynamic resource allocation on a cloud computing platform for providing access to block storage volumes, the rule within each transition model is associated with respective volume type identifiers of volume types;
circuitry configured to detect that a block storage volume was provisioned with a first volume type included in the respective volume types, wherein the first volume type causes the cloud computing platform to restrict a runtime throughput rate or a runtime operation rate for accessing the provisioned block storage volume, the runtime operation rate characterizing a rate at which distinct memory operations are performed, the runtime throughput rate characterizing a data volume transmission over time regardless of a number of distinct memory operations;
circuitry configured to obtain historical performance measurements for the provisioned block storage volume;
circuitry configured to determine a baseline operation rate and a baseline throughput rate for the provisioned block storage volume via a normalization model to support comparison between the provisioned volume type and at least one other one of the volume types;
circuitry configured to select a plurality of transition models that are associated with at least one of the respective volume types;
circuitry configured to determine, based on historical performance measurements of the provisioned block storage volume a

Assignees

• Accenture Global Solutions Ltd

Inventors

• Srinivasan Madhan Kumar
• Purushothaman Arun
• Pv Guruprasad

Classifications

• H04L41/145 Primary

  involving simulating, designing, planning or modelling of a network · CPC title

• H04L43/0852

  Delays · CPC title

• H04L41/16

  using machine learning or artificial intelligence · CPC title

• G06F3/0665

  at area level, e.g. provisioning of virtual or logical volumes · CPC title

• G06F3/067

  Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS] · CPC title