Intent-Based Storage Volume Provisioning System
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing storage provisioning systems struggle to select the optimal storage system from a heterogeneous collection for provisioning storage volumes, especially when users lack knowledge about expected workload characteristics such as I/O operations per second (IOPS), read/write ratios, and I/O sizes.
Innovation Solution
An intent-based provisioning system that receives simple input regarding storage volumes from requesting entities, infers a workload profile, simulates workload execution across storage systems, determines headroom usage, and selects the most suitable storage system for provisioning based on available headroom and other performance parameters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If detailed workload characteristics (IOPS, read/write ratios, I/O sizes) are required for storage system selection, then storage system selection accuracy is improved, but user operation complexity increases
Solution Approach 1:
The system automatically collects workload characteristics from monitoring data and historical information without requiring users to manually input these parameters. The provisioning system self-generates the detailed workload profile needed for accurate storage system selection, eliminating the burden of complex user input while maintaining high selection accuracy
Solution Approach 2:
The system introduces an intermediary layer that translates simple user intents into detailed workload characteristics. This intermediary process automatically infers comprehensive workload profiles from minimal user input, bridging the gap between simple operation and precise measurement
2Measurement precision
If workload simulation is performed across multiple storage systems, then storage system selection accuracy is improved, but processing time increases
Solution Approach 1:
The system pre-calculates and stores performance metrics and workload characteristics from historical data before actual provisioning is needed. By preparing simulation data and performance benchmarks in advance, the system can quickly match storage volumes to appropriate systems without performing time-consuming real-time simulations
Solution Approach 2:
The system performs workload simulation selectively on a subset of candidate storage systems rather than all available systems. By using filtering criteria to narrow down candidates first, then simulating only on the most promising options, the system achieves high accuracy while minimizing processing time
Data Source
AI summary
In some examples, a system receives input information of characteristics relating to a storage volume to be provisioned in a collection of storage systems, determines, based on the input information of the characteristics relating to the storage volume, a workload profile, and simulates execution of a workload according to the workload profile in each storage system of the collection of storage systems. Based on the simulation, the system determines a respective amount of headroom used by the workload in each storage system of the collection of storage systems, and selects, based on the determined respective amounts of headroom used by the workload in respective storage systems of the collection of storage systems, a storage system from the collection of storage systems on which the storage volume is to be provisioned.