Clustered Storage Backup Automation via Dynamic Load Balancing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current clustered storage systems face inefficiencies in backup operations due to the need for manual configuration and lack of automated methods to optimize backup tasks across multiple storage nodes and backup devices, leading to suboptimal performance and resource overload.

Innovation Solution

A system and method that automatically determines configuration information for clustered storage systems, including detecting storage nodes, volumes, and backup devices, and dynamically distributes backup tasks to balance load across nodes and devices, using backup software to instruct nodes to backup volumes to available devices while updating activity information for resource management.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If manual configuration is used for backup tasks in clustered storage systems, then system complexity is reduced and ease of operation is improved, but backup efficiency and productivity deteriorate due to lack of optimization

Engineering Contradiction:
Improveease of operationVSAvoidbackup efficiency
Core Design Contradiction:
Ease of operationVSProductivity

Solution Approach 1:

The backup system automatically discovers storage nodes, volumes, and backup devices, then autonomously determines optimal backup tasks and their execution order without requiring manual configuration. The system self-manages the entire backup process including task distribution and resource allocation, eliminating the need for user intervention while achieving optimized backup efficiency.

Inventive Principle:
Principle #25Self-service

2Productivity

If backup tasks are distributed across multiple storage nodes and devices, then productivity and backup efficiency improve, but device complexity and system configuration complexity worsen

Engineering Contradiction:
Improvebackup efficiencyVSAvoidconfiguration complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The system continuously monitors the state of storage nodes and backup devices, using this feedback information to dynamically adjust and optimize backup task distribution. By gathering real-time status data and responding to system conditions, the backup software can efficiently manage complex multi-node operations without requiring complex manual configuration.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The backup software serves multiple functions including automatic discovery, configuration management, task optimization, and execution coordination across diverse storage nodes and backup devices. This multi-functional approach consolidates what would otherwise require separate complex configuration steps into a single universal backup management system.

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

3Productivity

If more backup tasks are executed simultaneously to improve productivity, then backup efficiency improves, but resource overload and system stability worsen

Engineering Contradiction:
Improvebackup efficiencyVSAvoidsystem stability
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The system determines an optimal number of concurrent backup tasks based on available system resources, executing a partial rather than maximum number of tasks simultaneously. This approach balances productivity improvement with resource conservation, preventing overload while still achieving efficient backup operations through optimized parallel task execution.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentUS8244998B1Optimized backup for a clustered storage system
Publication Date: 2012.08.14 COHESITY INC
  • US8244998B1 patent drawing
  • US8244998B1 patent drawing
  • US8244998B1 patent drawing

AI summary

A system and method for backing up data from a clustered storage system are described herein. The method may operate to automatically determine the configuration of the clustered storage system, e.g., by detecting each storage node in the clustered storage system, detecting the storage volumes hosted by each storage node, and detecting the backup storage devices to which each storage node is connected. The method may operate to backup the plurality of storage volumes by performing a plurality of backup tasks. Performing each respective backup task may comprises selecting a particular storage volume to backup from a particular storage node to a particular backup storage device depending upon the configuration information and information indicating currently active backup tasks in the clustered storage system.