Separate LRU Lists for Favored Storage Cache Management
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems face challenges in improving cache hit ratios for selected volumes when using synchronous I/O technologies like zHyperLink, which can lead to delays and failures due to cache misses, resulting in suboptimal I/O response times.
Innovation Solution
Implementing a method that differentiates between favored and non-favored storage elements by maintaining favored elements in the cache longer, using separate LRU lists for eviction and periodically scanning for changes, ensuring that favored elements are retained in the cache longer than non-favored ones.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single LRU list is used for cache eviction, then the cache management is simple, but the cache hit ratio for selected volumes is reduced
Solution Approach 1:
The patent divides the single LRU list into multiple separate LRU lists (first LRU list for non-favored volumes, second LRU list for favored volumes). This segmentation allows differential eviction policies where favored volumes can be retained longer in cache while non-favored volumes are evicted more aggressively, thereby improving cache hit ratio for selected volumes without excessive complexity increase.
2Reliability
If favored storage elements are retained in cache longer, then cache hit ratio for favored elements is improved, but cache space for other elements is reduced
Solution Approach 1:
The patent applies local quality by creating different retention policies for different portions of the cache. Favored volumes receive preferential treatment with longer retention periods through the separate second LRU list, while non-favored volumes in the first LRU list are subject to standard eviction. This localized quality enhancement improves cache hit ratio for specific volumes without uniformly reducing overall cache space availability.
Solution Approach 2:
The system dynamically adjusts cache retention based on volume classification. The periodic scanning mechanism allows volumes to transition between favored and non-favored status, and the separate LRU lists enable dynamic retention adjustment without manual intervention. This dynamic approach optimizes cache space utilization while maintaining high hit ratios for currently favored volumes.
3Speed
If synchronous I/O operations are used, then I/O response time is reduced, but the system becomes more sensitive to cache misses
Solution Approach 1:
The patent implements preliminary action by pre-classifying volumes as favored or non-favored and pre-establishing separate LRU lists for them. This preparation ensures that when synchronous I/O operations occur, the cache is already optimized to retain data from favored volumes, reducing the likelihood of cache misses during actual I/O operations and maintaining high success rates.
Data Source
AI summary
A method for improving cache hit ratios for selected storage elements within a storage system includes storing, in a cache of a storage system, non-favored storage elements and favored storage elements. The favored storage elements are retained in the cache longer than the non-favored storage elements. The method maintains a first LRU list containing entries associated with non-favored storage elements and designating an order in which the non-favored storage elements are evicted from the cache, and a second LRU list containing entries associated with favored storage elements and designating an order in which the favored storage elements are evicted from the cache. The method periodically scans the first LRU list for non-favored storage elements that have changed to favored storage elements, and the second LRU list for favored storage elements that have changed to non-favored storage elements. A corresponding system and computer program product are also disclosed.