Dynamic Storage Tiering Hot Spot Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual sizing of storage tiers in Dynamic Storage Tiering systems is challenging, leading to overprovisioning or underprovisioning, resulting in inefficient resource allocation and performance issues, especially as workloads change over time.
Innovation Solution
A system and method that monitor storage tier utilization and hot spots, logically dividing address ranges to move segments between storage tiers based on performance characteristics, optimizing capacity allocation and system performance without taking the system offline.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If manual sizing approach is used for storage tiers, then system administrator can configure storage capacity, but overprovisioning or underprovisioning occurs leading to inefficient resource allocation
Solution Approach 1:
The storage system automatically monitors its own utilization metrics and performs self-optimization by dynamically adjusting tier configurations based on detected hot spots, eliminating the need for manual intervention while maintaining optimal resource allocation
Solution Approach 2:
The system continuously monitors storage tier utilization and uses this feedback to automatically adjust configurations, creating a closed-loop control system that adapts to changing workload patterns and prevents both overprovisioning and underprovisioning
2Reliability
If higher performing storage tiers are overprovisioned to ensure capacity, then performance requirements are met, but system cost increases unnecessarily
Solution Approach 1:
The system dynamically adjusts the capacity allocation of higher performing storage tiers based on real-time hot spot detection, allowing the configuration to adapt to changing workload patterns and ensuring optimal performance guarantee without static overprovisioning
Solution Approach 2:
The system segments storage capacity into different tiers and dynamically adjusts the segmentation boundaries based on hot spot analysis, allowing precise control over how much capacity is allocated to higher performing tiers without unnecessary overprovisioning
3Adaptability or versatility
If storage tier configuration is changed to handle new workloads, then adaptability improves, but system complexity increases for administrators
Solution Approach 1:
The storage system automatically detects workload changes and performs self-reconfiguration by identifying hot spots and adjusting tier configurations accordingly, providing workload adaptability without increasing administrative complexity
Solution Approach 2:
The system performs preliminary analysis of workload patterns and proactively adjusts storage tier configurations before performance degradation occurs, enabling smooth adaptation to new workloads without requiring complex administrative intervention
Data Source
AI summary
A method for Dynamic Storage Tiering (DST) may include identifying a first storage tier with a performance characteristic. The method may include monitoring the utilization of the first storage tier to detect the placement of a hot spot. The method may include logically dividing a continuous range of a plurality of logical addresses into at least a first segment and a second segment so the first segment includes a proportionally larger amount of the hot spot. The method may include moving the first segment into a second storage tier or moving the second segment into the second storage tier. The method may include determining an amount of utilization of the first storage tier by hot spots. The method may include recommending a change in an amount of storage space in the first storage tier based upon the amount of utilization of the first storage tier by the hot spots.