Availability Score Calculation for Storage Server Failover

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current storage systems in distributed computing environments lack an effective method to determine the availability score based on various resource types, which hinders the decision-making process for failure operations, such as failover or failback, leading to potential service outages and data accessibility issues.

Innovation Solution

A computer program product and method that calculates an availability score by monitoring and aggregating the availability of different resource types, including computational and storage resources, and transmits this score to a failure manager to determine whether to initiate a storage system failure mode or migrate services, ensuring continuous access to customer resources.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a storage system implements monitoring of multiple resource types to determine availability, then the reliability of failure operation decisions is improved, but the device complexity increases

Engineering Contradiction:

Improveavailability score calculationVSAvoidresource monitoring system

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system segments resource monitoring into distinct resource types (computational resources, storage resources, network resources, etc.), with each type tracked independently through dedicated monitoring mechanisms. This segmentation allows comprehensive availability assessment while organizing complexity into manageable, modular components that can be monitored and evaluated separately.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The availability score calculation mechanism serves as a universal framework that integrates multiple resource type monitoring into a single comprehensive metric. This multi-functional system evaluates computational, storage, network, and other resource availabilities through a unified scoring approach, reducing the need for separate decision-making systems for each resource type.

Inventive Principle:

Principle #6Universality (Multi-functionality)

2Measurement precision

If the system calculates availability score as a function of multiple resource types, then the decision accuracy for failure operations is improved, but the computational power required increases

Engineering Contradiction:

Improveavailability scoreVSAvoidcomputational resources

Core Design Contradiction:

Measurement precisionVSPower

Solution Approach 1:

The system implements partial monitoring of resources by focusing on critical resource types and their key metrics rather than exhaustive monitoring of every possible parameter. The availability score calculation uses a weighted approach that emphasizes the most impactful resources, achieving sufficient measurement precision without requiring computational power to monitor and process every possible resource detail.

Inventive Principle:

Principle #16Partial or excessive action

3Speed

If the system transmits availability information to a failure manager, then the response time for failure operations is improved, but the loss of information increases due to data transmission

Engineering Contradiction:

Improvefailure operation responseVSAvoidavailability data

Core Design Contradiction:

SpeedVSLoss of information

Solution Approach 1:

The system extracts and transmits only the essential availability score and critical resource status information to the failure manager, rather than transmitting complete raw data from all monitoring mechanisms. This extraction approach enables rapid failure operation response while minimizing information loss by focusing on the most decision-critical data elements.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The system transforms detailed resource monitoring data into an aggregated availability score parameter that captures the essential system state. This parameter transformation condenses complex multi-resource information into a single actionable metric, reducing data transmission requirements while preserving the information necessary for failure operation decisions.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS11366730B2Determining an availability score based on available resources at a first server to determine whether to direct processing from a first server to a second server

Publication Date: 2022.06.21 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

Provided are a computer program product, system, and method for a computer program product, system, and method for determining an availability score based on available resources of different resource types in a distributed computing environment of storage servers to determine whether to perform a failure operation for one of the storage servers. A health status monitor program deployed in the storage servers performs: maintaining information indicating availability of a plurality of storage server resources for a plurality of resource types; calculating an availability score as a function of a number of available resources of the resource types; and transmitting information on the availability score to a management program. The management program uses the transmitted information to determine whether to migrate services from the storage server from which the availability score is received to at least one of the other storage servers in the distributed computing environment.