Cache Data Removal via Divided List Activeness Ranking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for removing cached data from flash disks are inefficient, as they fail to accurately determine the activeness of data, leading to suboptimal removal of frequently accessed data, which can result in lower read/write rates due to the removal of high-access data from active lists and retention of low-access data in inactive lists.
Innovation Solution
A method and apparatus that determine the activeness of divided lists by ranking them based on recently overall accessed timestamps or data not accessed within a predetermined time interval, allowing for the cyclic removal of cached data from the bottommost positions of each list, ensuring that data with lower heat of access is removed and data with higher access probability is retained.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If cached data are removed in a cyclic manner from each divided list without considering list activeness, then the cache area capacity is maintained, but frequently accessed data may be removed from active lists while data with lower access heat is retained in inactive lists, leading to reduced read/write rates
Solution Approach 1:
The patent divides the cache area into multiple divided lists corresponding to different disk partitions, and further segments the management approach by evaluating activeness at the divided list level rather than individual data level. This segmentation enables differentiated removal strategies for different lists based on their activeness, preventing uniform removal that would harm frequently accessed data in active lists.
Solution Approach 2:
The patent introduces activeness as a new parameter to evaluate divided lists, calculated based on the number of cached data items not accessed within a predetermined time interval. By changing from simple cyclic removal to parameter-based selective removal, the system accurately identifies which lists contain frequently accessed data and preserves them while removing data from inactive lists.
2Quantity of substance
If the cache area capacity is large to store more data, then storage capacity is improved, but the cache area cannot automatically release data after power off and requires constant manual or automated removal to maintain performance
Solution Approach 1:
The patent implements an automated cache management system that continuously monitors access patterns and performs self-service data removal without external intervention. The system automatically calculates activeness parameters, identifies inactive divided lists, and removes cached data from these lists based on predetermined thresholds, enabling the cache to maintain optimal performance autonomously.
Solution Approach 2:
The patent establishes a feedback mechanism where access patterns of cached data are continuously monitored and fed back into the activeness calculation. This feedback loop enables the system to dynamically adjust which data to remove based on real-time access behavior, ensuring that frequently accessed data is preserved while inactive data is removed to maintain cache performance.
Data Source
AI summary
Embodiments of the present invention provide a method and apparatus for removing cached data. The method comprises determining activeness of a plurality of divided lists; ranking the plurality of divided lists according to the determined activeness of the plurality of divided lists. The method comprises removing a predetermined amount of cached data from the plurality of divided lists according to the ranking result when the used capacity in the cache area reaches a predetermined threshold. Through embodiments of the present invention, the activeness of each divided list may be used to wholly measure the heat of access to the cached data included by each divided list, and upon removal, the cached data with lower heat of access in the whole system can be removed and the cached data with higher heat of access in the whole system can be retained so as to improve the read/write rate of the system.