Multi-Tier Storage Configuration via Workload Skew Modeling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for configuring multi-tier data storage systems are imprecise, often resulting in either underdesign or overdesign, failing to meet performance requirements or cost targets due to imbalanced workload distributions.
Innovation Solution
A model-based technique that applies an input skew value to generate a desired proportion of total system IOPS for each storage tier, converting IOPS percentages into corresponding capacity percentages, and installing storage devices to match these capacities, ensuring neither overdesign nor underdesign.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional methods are used to configure multi-tier data storage systems, then the configuration process is simple, but the precision of meeting performance requirements and cost targets deteriorates
Solution Approach 1:
The patent applies parameter changes by using a skew value parameter to characterize workload distribution and transforming it into IOPS percentage allocations for different storage tiers. This mathematical transformation enables precise configuration by converting a single workload characteristic into multiple tier-specific performance parameters, resolving the contradiction between configuration precision and complexity.
Solution Approach 2:
The patent introduces an intermediary computational model that bridges the gap between workload characteristics (skew value) and storage tier configurations (IOPS percentages). This intermediary transformation layer enables precise configuration without requiring complex manual analysis, as the model automatically converts workload parameters into optimal tier allocations.
2Reliability
If too little high-performance storage is employed, then cost is reduced, but performance requirements are not met
Solution Approach 1:
The patent uses parameter changes to dynamically determine the optimal quantity of high-performance storage based on the skew value. By transforming the skew parameter into IOPS percentage allocations, the system precisely calculates the required high-performance storage capacity to meet performance requirements without over-provisioning, thus resolving the contradiction between reliability and quantity.
3Reliability
If too much high-performance storage is employed, then performance requirements are met, but cost targets are not met
Solution Approach 1:
The patent applies parameter transformation to convert the skew value into precise IOPS percentage allocations for each storage tier. This mathematical transformation enables the system to determine the exact amount of high-performance storage needed to meet performance requirements, avoiding both under-provisioning and over-provisioning, thus resolving the contradiction between reliability and quantity.
4Ease of operation
If storage tiers are configured without considering workload skew, then configuration is straightforward, but neither overdesign nor underdesign is avoided
Solution Approach 1:
The patent introduces an intermediary computational model that automatically transforms workload skew characteristics into optimal storage tier configurations. This intermediary layer maintains configuration simplicity by handling the complex analysis automatically, while simultaneously achieving high precision in tier allocations, thus resolving the contradiction between ease of operation and manufacturing precision.
Data Source
AI summary
Techniques for configuring multi-tier data storage systems provide a model of skewed workload distributions in such systems and configure them by applying a received input skew value representing a prediction of system skew and the model. The technique applies the input skew value to generate a desired proportion of total system IOPS to be handled by each storage tier in the system and applies the model to convert the IOPS percentage for each storage tier into a corresponding capacity percentage. The technique then generates actual capacity for each tier by applying the percent capacity for each tier to a design target for total storage capacity in the system. Advantageously, these techniques generate storage tier configurations that are likely to be neither overdesigned nor underdesigned, and are thus likely to meet both performance requirements and cost targets.