Storage Load Balancer for Virtual Server I/O Congestion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current storage I/O load balancing methods in virtual server environments are inadequate, as they focus on moving virtual machines (VMs) to different physical servers without addressing storage device bottlenecks and do not consider end-to-end service levels or resource tier levels, leading to inefficiencies and congestion.
Innovation Solution
The system periodically analyzes and balances storage loads by collecting and analyzing traffic and resource utilization data across the virtual server network, identifying and correcting imbalances by moving VMs from high-load storage devices to underutilized ones, thereby optimizing storage resource allocation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If virtual machines are moved to different physical servers, then server resource utilization is improved, but storage device bottlenecks and congestion are not resolved
Solution Approach 1:
The patent introduces a storage load balancer as an intermediary component that mediates between virtual machines and storage devices. This load balancer monitors storage device utilization and automatically migrates virtual machines between datastores to balance storage loads, thereby resolving storage bottlenecks while maintaining server resource utilization improvements.
Solution Approach 2:
The system implements continuous monitoring of storage device utilization metrics and uses this feedback to trigger automatic virtual machine migration. When storage devices approach capacity thresholds or exhibit bottlenecks, the feedback mechanism initiates load redistribution by migrating VMs to underutilized storage devices, thus maintaining optimal performance.
2Ease of operation
If storage load balancing is implemented by manual methods, then some load distribution is achieved, but the process is time-consuming and error-prone
Solution Approach 1:
The patent implements an automated storage load balancing system that performs self-service by automatically monitoring storage utilization metrics and triggering virtual machine migrations without human intervention. The system autonomously identifies imbalanced storage devices and executes load redistribution, eliminating manual operations and their associated time losses and errors.
Solution Approach 2:
The system accelerates the storage load balancing process by implementing continuous real-time monitoring and automated decision-making algorithms. This acceleration mechanism rapidly detects storage bottlenecks and immediately executes migration operations, reducing the time required for storage load management from weeks to minutes or seconds.
3Productivity
If more virtual machines are consolidated onto fewer physical servers, then resource utilization efficiency is improved, but storage network congestion and bottlenecks increase
Solution Approach 1:
The patent applies segmentation by dividing the storage network into multiple independent storage domains or pools, each managed separately. By distributing virtual machines across different storage segments rather than consolidating them onto single storage devices, the system maintains high resource utilization while preventing network congestion through decentralized storage access patterns.
Solution Approach 2:
The system introduces an additional dimension of storage resource management by implementing multi-layered storage hierarchies and distributed datastore assignments. Instead of single-dimensional consolidation, VMs are distributed across multiple storage dimensions (different datastores, arrays, or storage pools), which disperses I/O traffic and eliminates single-point congestion while maintaining consolidation benefits.
Data Source
AI summary
Methods and systems for periodically analyzing and correcting storage load imbalances in a storage network environment including virtual machines are described. These methods and systems account for various resource types, logical access paths, and relationships among different storage environment components. Load balancing may be managed in terms of input/output (I/O) traffic and storage utilization. The aggregated information is stored, and may be used to identify and correct load imbalances in a virtual server environment in order to prevent primary congestion and bottlenecks.