Dynamic Storage Resource Allocation by Connection Type

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing storage systems lack optimal dynamic allocation of non-volatile memory resources among multiple hosts with varying workloads in multi-tenant systems, leading to inefficient resource utilization and potential performance issues.

Innovation Solution

A system with a resource allocation engine that determines the connection type and allocates storage resources based on connection type subsets, capping connections to ensure optimal utilization by monitoring read/write operations and adjusting resource ratios dynamically.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If storage resources are statically allocated among multiple hosts, then resource allocation is simple and stable, but resource utilization efficiency deteriorates when hosts have varying workloads

Engineering Contradiction:
Improveresource utilization efficiencyVSAvoidresource allocation complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent implements dynamic resource allocation where the storage system automatically adjusts resource distribution based on real-time connection types and workload characteristics. The system transitions from static to dynamic allocation by monitoring connection protocols (e.g., NVMe, FC, SAS) and adjusting resource shares accordingly, allowing resource utilization to adapt to varying host workloads while maintaining manageable complexity through automated policies

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system changes allocation parameters based on connection type characteristics. Different connection types (NVMe, Fibre Channel, SAS) have different performance requirements and resource consumption patterns. The patent adjusts resource allocation parameters such as I/O weights, queue depths, and cache sizes according to the detected connection type, optimizing resource utilization for each protocol while maintaining systematic control

Inventive Principle:
Principle #35Parameter changes

2Productivity

If storage resources are dynamically allocated based on workload, then resource utilization efficiency improves, but system complexity and difficulty of managing allocation policies increases

Engineering Contradiction:
Improveresource utilization efficiencyVSAvoidallocation management complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The storage system implements self-service dynamic allocation by automatically detecting connection types and applying appropriate allocation policies without manual intervention. The system monitors incoming connections, identifies their protocols and performance requirements, and autonomously adjusts resource allocation accordingly. This self-managing approach improves resource utilization while keeping allocation management complexity contained through automated decision-making algorithms

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system employs feedback mechanisms where allocation decisions are based on continuous monitoring of connection types, workload patterns, and resource usage metrics. The feedback loop allows the system to adjust allocation dynamically in response to changing conditions, improving resource utilization while maintaining manageable complexity through rule-based or machine learning-driven feedback control policies

Inventive Principle:
Principle #23Feedback

3Reliability

If connection type-specific resource allocation is implemented, then QoS for different connection types improves, but device complexity increases

Engineering Contradiction:
ImproveQuality of ServiceVSAvoidconnection management complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments resource allocation by connection type, creating separate resource pools or weight categories for different protocols (NVMe, FC, SAS). Each connection type receives tailored resource allocation based on its specific requirements, improving QoS for each protocol. The segmentation is managed through modular policies that assign different I/O weights, queue priorities, and cache allocations to each connection type, enhancing service quality while maintaining systematic control through structured segmentation

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS11520715B2Dynamic allocation of storage resources based on connection type
Publication Date: 2022.12.06 WESTERN DIGITAL TECHNOLOGIES INC
  • US11520715B2 patent drawing
  • US11520715B2 patent drawing
  • US11520715B2 patent drawing

AI summary

Systems and methods for capped allocation of storage resources based on connection type are described. A new storage connection request from a host system to a group of data storage devices includes a connection type, such as a remote direct memory access connection or transmission control protocol connection. Based on the connection type, a subset of a pool of allocated storage resources for that connection type is determined. If the new connection request does not exceed the maximum number of connections allocated to the subset, a new storage connection is established. If the new connection request exceeds the maximum number of connections allocated to the subset, the new storage connection request fails.