Nonvolatile Cache Flush Time Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional storage systems lack a mechanism to determine the estimated time required to flush data from a non-volatile cache to storage devices, making it difficult for users to plan system shutdowns and manage storage operations efficiently.
Innovation Solution
A method is implemented to gather information from the storage system to estimate the time needed to flush data from a non-volatile cache, using predictive analysis techniques and mathematical formulas based on the number of flash disk drives, dirty pages, RAID type, and disk drive speeds.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If conventional storage systems are used without cache time estimation mechanisms, then system simplicity is maintained, but users cannot effectively plan system shutdowns or manage storage operations
Solution Approach 1:
The storage system automatically gathers information about flash disk drives, dirty pages, RAID type, and disk drive speeds to compute and provide the estimated cache flush time without requiring manual intervention. The system serves itself by autonomously collecting parameters, applying the mathematical formula, and presenting the result to users, thereby improving ease of operation without proportionally increasing complexity
Solution Approach 2:
The patent introduces an intermediary estimation mechanism that acts as a bridge between the complex cache system and users. This intermediary component computes the estimated flush time using a mathematical formula based on system parameters, translating complex internal cache operations into a simple, actionable time estimate that users can rely on for planning shutdowns and management tasks
2Measurement precision
If cache flush time is estimated using detailed system parameters and mathematical formulas, then accuracy of time estimation is improved, but complexity of the estimation mechanism increases
Solution Approach 1:
The patent achieves accurate time estimation by changing and utilizing multiple system parameters including the number of flash disk drives, number of dirty pages, RAID type, and disk drive speeds. By dynamically incorporating these varying parameters into the mathematical formula, the system maintains high measurement precision for cache flush time estimation
Solution Approach 2:
Instead of implementing a complex simulation or model of the entire cache flush process, the patent uses a simplified mathematical formula that copies only the essential relationships between parameters. This formula-based approach captures the critical factors affecting flush time without replicating the full complexity of the underlying cache management operations
Data Source
AI summary
A method is used in managing cache systems of storage systems. Information is gathered from a storage system to determine an estimated amount of time required to flush data of a nonvolatile cache of the storage system to storage devices. The data cached in the nonvolatile cache is associated with a set of logical objects configured to cache the data in the nonvolatile cache. Based on the information gathered from the storage system, the estimated amount of time required to flush the data of the nonvolatile cache is determined.