Dynamic Reader Task Allocation for Data Mirroring

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing data mirroring systems face inefficiencies due to static allocations of computing resources and parameters, which become inadequate as data generation rates vary over time, leading to insufficient resources and communication tasks for increased write activity, affecting application performance.

Innovation Solution

A method to dynamically modify the configuration of data mirroring by adjusting the number of reader tasks and communication bandwidth through active reader task aliases, based on real-time monitoring and predictive analytics, to align with changing data rates and infrastructure conditions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If static allocations of computing resources and parameters are used in data mirroring systems, then system configuration is simple and stable, but the system becomes inadequate when data generation rates vary over time, leading to insufficient resources for increased write activity

Engineering Contradiction:

Improveadaptability to varying data generation ratesVSAvoidcomplexity of dynamic configuration modification

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent implements dynamic configuration modification by allowing the storage system to automatically adjust reader task parameters (such as bandwidth allocation and task creation) based on real-time data generation rates. The system transitions from static to dynamic resource allocation, where configuration parameters are continuously monitored and modified without requiring manual intervention, thereby resolving the contradiction between adaptability and complexity.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system incorporates feedback mechanisms that monitor data generation rates and automatically trigger configuration changes when thresholds are exceeded. This closed-loop control enables the system to adapt to varying workloads by using real-time performance data to adjust reader task allocations, maintaining optimal performance while reducing the need for complex manual configuration.

Inventive Principle:

Principle #23Feedback

2Productivity

If additional reader tasks are created to increase bandwidth for data mirroring, then data mirroring performance improves, but system resource consumption and configuration complexity increase

Engineering Contradiction:

Improvedata mirroring throughputVSAvoidcomplexity of reader task management

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The storage system performs self-optimization by automatically creating and managing reader tasks based on monitored data generation rates. Rather than requiring external intervention to adjust bandwidth or create tasks, the system self-adjusts its configuration, thereby improving productivity while reducing the operational complexity of task management.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system dynamically modifies reader task parameters (bandwidth, priority, creation timing) based on real-time conditions. By changing parameters rather than creating entirely new tasks, the system achieves improved throughput while minimizing the complexity increase associated with managing multiple reader tasks.

Inventive Principle:

Principle #35Parameter changes

3Productivity

If manual configuration modifications are performed to optimize data mirroring, then resource allocation can be optimized, but the frequency of administrative interventions increases

Engineering Contradiction:

Improveresource allocation efficiencyVSAvoidtime spent on administrative interventions

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The storage system automatically performs resource allocation optimization by monitoring data generation rates and adjusting reader task configurations without requiring administrative intervention. This self-service capability maintains high productivity while eliminating the time loss associated with manual configuration changes.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system performs preliminary configuration adjustments by proactively creating reader tasks and allocating bandwidth before data generation rates increase. This predictive approach prevents resource shortages before they impact performance, reducing the need for reactive administrative interventions.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS11314607B2Modifying aspects of a storage system associated with data mirroring

Publication Date: 2022.04.26 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

A method for modifying a configuration of a storage system. The method includes a computer processor querying a network-accessible computing system to obtain information associated with an executing application that utilizes a storage system for a process of data mirroring. The method further includes identifying a set of parameters associated with a copy program executing within a logical partition (LPAR) of the storage system based on the obtained information, where the set of parameters dictates a number of reader tasks utilized by the copy program, where the copy program is a program associated with the process for data mirroring from the network-accessible computing system to the storage system. The method further includes executing the dictated number of reader tasks for the process of mirroring data associated with the executing application, from the network-accessible computing system to the storage system.