Storage Tier Priority Hints for Business Process Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data storage subsystems lack the ability to dynamically adjust storage tier priorities based on anticipated activity, applying the same priority to all business processes that use a device, which hampers efficiency.
Innovation Solution
A method and apparatus that define and assign priorities to business processes, monitor IO activity, and generate priority hints to dynamically associate data extents with appropriate storage tiers based on calculated priorities, allowing different priorities for different business processes and adjusting them according to anticipated activity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If storage resources are organized in hierarchical tiers with automatic data movement based on IO activity, then storage performance is improved for frequently accessed data, but the system cannot dynamically adjust priorities for different business processes
Solution Approach 1:
The patent segments the storage system by introducing extent-level granularity and business process-level categorization. Each extent can be independently tagged with business process identifiers, allowing differential priority treatment within the same storage tier structure. This segmentation enables the system to apply different priority policies to different business processes while maintaining the overall hierarchical tiered storage architecture.
Solution Approach 2:
The patent implements dynamic priority adjustment by continuously monitoring IO activity patterns and automatically recalculating extent priorities based on observed usage. The system dynamically reclassifies extents between different priority levels and adjusts their placement in the storage hierarchy accordingly, allowing the storage system to adapt to changing business process requirements in real-time without manual intervention.
2Device complexity
If the same priority is applied to all business processes that use a device, then system simplicity is maintained, but efficiency is hampered due to inability to differentiate critical data
Solution Approach 1:
The patent applies local quality by assigning different priority characteristics to different extents based on their associated business processes. Instead of uniform priority treatment, each extent can have its own priority level determined by the specific business process requirements. This allows critical business processes to receive higher priority treatment while non-critical processes use standard priority, optimizing overall system efficiency without requiring complete redesign of the storage management architecture.
Solution Approach 2:
The patent changes the priority parameter from a fixed device-level attribute to a dynamic extent-level attribute that can be independently adjusted. By modifying the granularity and flexibility of the priority parameter, the system can differentiate between various business processes and their data requirements, enabling more efficient resource allocation while maintaining manageable system complexity through automated policy-based control.
3Loss of energy
If data is moved between storage tiers based on access time, then storage cost is optimized by placing inactive data in lower tiers, but the system cannot anticipate future activity patterns
Solution Approach 1:
The patent implements preliminary action by proactively monitoring and analyzing IO activity patterns to predict future data access requirements. Before data is actually needed, the system identifies extents that are likely to become hot based on observed patterns and pre-positions them in appropriate storage tiers. This anticipatory approach allows the system to optimize storage cost by keeping data in lower-tier storage until just before it is needed, then automatically promoting it to higher-performance tiers in advance of actual access requirements.
Solution Approach 2:
The patent employs feedback mechanisms by continuously monitoring IO activity and using this information to dynamically adjust extent priorities and storage tier placement. The system observes actual usage patterns, compares them against expected patterns, and automatically adjusts data placement decisions based on this feedback loop. This enables the system to adapt to changing activity patterns and improve both cost efficiency and performance over time through learned behavioral patterns.
Data Source
AI summary
Data access is monitored in order to calculate priorities for extents of data based on extent access activity and priority of a business process associated with the extent. The priorities of the extents are used to generate priority hints for a tiered storage array. The priority may be time-dependent, including being indicative of anticipated future activity.