Dynamic Resource Allocation for Cloud Partition Recovery

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Cloud computing systems face performance degradation due to abnormal events like hardware or software failures, which require additional computing resources for recovery and diagnostic processes, leading to increased costs and downtime.

Innovation Solution

A resource management module dynamically allocates additional computing resources to affected partitions to enhance processing capacity during abnormal events, such as initial program loads, and adjusts billing statements based on actual usage during these events.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If additional computing resources are allocated to partitions during abnormal events, then processing capacity and recovery speed are improved, but system complexity and resource management difficulty increase

Engineering Contradiction:
Improveprocessing capacityVSAvoidresource management complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent implements dynamic resource allocation by monitoring partition status and automatically adjusting computing resource distribution based on detected abnormal events. The system transitions from static resource allocation to dynamic reallocation, enabling the system to adapt resource capacity according to actual operational conditions and recovery needs.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system incorporates feedback mechanisms where the resource management module continuously monitors partition performance and abnormal event status. Based on this feedback, the system automatically adjusts resource allocation decisions, creating a closed-loop control system that optimizes resource distribution without manual intervention.

Inventive Principle:
Principle #23Feedback

2Loss of time

If computing resources are increased during abnormal events, then recovery time is reduced, but billing costs increase

Engineering Contradiction:
Improverecovery timeVSAvoidbilling cost
Core Design Contradiction:
Loss of timeVSLoss of energy

Solution Approach 1:

The system performs preliminary actions by pre-defining resource allocation policies and thresholds for abnormal events. When an abnormal event is detected, the system has pre-established protocols for resource reallocation, enabling rapid response without delay for decision-making. This preliminary preparation reduces recovery time while controlling resource expenditure through predefined parameters.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent changes operational parameters by adjusting resource allocation levels based on the severity and type of abnormal events. The system dynamically modifies computing resource parameters (such as CPU cycles, memory allocation, storage access) according to real-time monitoring data, optimizing the balance between recovery speed and resource consumption to minimize billing costs.

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If real-time monitoring of resource usage is implemented, then billing accuracy is improved, but system complexity and processing overhead increase

Engineering Contradiction:
Improvebilling accuracyVSAvoidmonitoring system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The resource management module performs multiple functions including abnormal event detection, resource allocation, usage monitoring, and billing calculation within a single integrated component. This multi-functional approach eliminates the need for separate monitoring systems, reducing overall system complexity while maintaining accurate real-time tracking of resource consumption for precise billing.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentUS10944581B2Increasing processing capacity of processor cores during initial program load processing
Publication Date: 2021.03.09 INTERNATIONAL BUSINESS MACHINE CORPORATION
  • US10944581B2 patent drawing
  • US10944581B2 patent drawing
  • US10944581B2 patent drawing

AI summary

According to one or more embodiments of the present invention, a computer-implemented method includes allocating a set of computing resources to a first partition from a plurality of partitions in a computer server, and monitoring a usage duration of the set of computing resources by the first partition. The method further includes generating a billing statement based on the usage duration of the computing resources by the first partition. The method further includes detecting an abnormal event in operation of the first partition and adjusting one or more settings of the set of computing resources to increase processing capacity associated with the first partition to complete the abnormal event. The method further includes monitoring a first usage duration of the computing resources during completion of the abnormal event and adjusting the usage duration of based on the first usage duration, and adjusting the billing statement using the adjusted usage duration.