Dual Cache Data Segment Promotion and Pinning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In computing systems with multi-level caches, managing partial data segments in secondary caches, such as Flash Cache, leads to wasted memory space and increased input/output activity, as these systems often incur resource consumption and performance slowdowns when filling 'holes' in partial tracks.
Innovation Solution
The solution involves promoting whole data segments to both lower and higher levels of cache, where requested data is positioned in the Most Recently Used (MRU) portion of the higher level cache and unrequested data is pinned in the Least Recently Used (LRU) portion until the write to the lower level cache is complete, ensuring efficient management and elimination of partial data segments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If partial data segments are written to secondary cache, then cache storage capacity is utilized, but wasted memory space occurs and additional I/O activity is incurred
Solution Approach 1:
The patent segments data into whole data segments that are promoted to both lower and higher levels of cache simultaneously. By processing complete segments rather than partial tracks, the system avoids the fragmentation problem while maintaining efficient cache utilization across multiple cache levels.
Solution Approach 2:
The patent performs preliminary actions by promoting entire data segments to both cache levels before any write operations complete. This preliminary promotion ensures that cache space is efficiently utilized from the outset, preventing the need for subsequent I/O operations to fill partial tracks.
2Area of stationary object
If partial tracks are used in secondary cache, then some storage space is occupied, but returning to disk drives to fill holes incurs additional I/O activity
Solution Approach 1:
The patent merges the promotion of whole data segments to both lower and higher cache levels into a single coordinated operation. This merging eliminates the need for separate I/O operations to fill partial tracks, as the entire segment is properly positioned in cache space in one action.
Solution Approach 2:
The patent ensures continuity of useful action by maintaining pinned unrequested data in place until the write to lower level cache completes. This continuous management prevents interruptions and additional I/O operations, keeping the cache system operating efficiently without performance degradation.
3Loss of substance
If whole data segments are promoted to both lower and higher cache levels, then storage space waste is minimized, but data management complexity increases
Solution Approach 1:
The patent introduces pinned data as an intermediary state between promotion and write completion. This intermediary mechanism simplifies data management by automatically holding unrequested data in place without requiring complex coordination, thereby reducing management complexity while eliminating storage waste.
Data Source
AI summary
For movement of partial data segments within a computing storage environment having lower and higher levels of cache by a processor, a whole data segment containing one of the partial data segments is promoted to both the lower and higher levels of cache. Requested data of the whole data segment is split and positioned at a Most Recently Used (MRU) portion of a demotion queue of the higher level of cache. Unrequested data of the whole data segment is split and positioned at a Least Recently Used (LRU) portion of the demotion queue of the higher level of cache. The unrequested data is pinned in place until a write of the whole data segment to the lower level of cache completes.


