Memory Data Block Shifting for Fragmentation Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Memory management in computing systems faces issues such as memory leaks, external fragmentation, and poor locality of reference, leading to inefficient memory allocation and reuse, which affects system performance.
Innovation Solution
A memory management process that shifts data within allocated memory to aggregate blocks towards either the head or tail, based on data distribution, reducing the number of actions required and improving efficiency by eliminating non-used memory areas without the need for new memory allocation, thereby preventing memory leaks and optimizing data aggregation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If memory is allocated to programs without prediction, then memory availability is improved, but memory allocation efficiency deteriorates due to fragmentation and leaks
Solution Approach 1:
The patent segments memory management into distinct operational modes (read-ahead mode and write-back mode) and separates data movement operations into specific phases. This segmentation allows the system to handle memory allocation and recycling more efficiently by treating different memory states and access patterns separately, thereby improving allocation efficiency while maintaining availability.
Solution Approach 2:
The patent implements preliminary actions by performing read-ahead operations to load data into memory before it is actually needed, and by pre-establishing write-back mechanisms. This preliminary preparation reduces the need for frequent memory allocation operations during actual data access, thereby improving allocation efficiency while ensuring memory availability when needed.
2Adaptability or versatility
If memory is reused by cleaning up old memory, then memory recyclability is improved, but system complexity increases due to management overhead
Solution Approach 1:
The patent implements self-service mechanisms where the memory management system automatically identifies and recycles obsolete data without requiring complex external intervention. The read-ahead and write-back modes enable the system to self-regulate memory usage patterns, automatically determining which data to retain and which to discard, thereby improving recyclability while managing complexity through automation.
Solution Approach 2:
The patent employs feedback mechanisms by monitoring memory access patterns and using this information to dynamically adjust memory management decisions. The system continuously evaluates data usage and adjusts its recycling strategy based on observed patterns, improving memory recyclability while keeping management complexity manageable through adaptive, data-driven decisions rather than rigid complex rules.
3Productivity
If data is shifted within allocated memory, then memory consolidation is improved, but number of operations increases
Solution Approach 1:
The patent implements periodic action by performing data shifting and consolidation operations at scheduled intervals rather than continuously. The read-ahead mode periodically loads data into memory, and the write-back mode periodically writes data back to storage. This periodic approach consolidates memory efficiently while minimizing the total number of operations compared to continuous shifting, thereby improving consolidation efficiency while reducing operational overhead and time loss.
Data Source
AI summary
Provided are a device and method of managing data stored in memory. The device may include a buffer for storing data blocks including a head data block, a tail data block, and intermediate data blocks. Non-used blocks may be further included in the buffer between the head data block and the tail data block. The device may further include a controller for managing the data blocks within the buffer. The managing may include determining a shift direction for the data blocks based on a distribution of the data blocks within the buffer, shifting at least one data block from among the data blocks in the determined direction, and shifting the one or more non-used blocks in an opposite direction from which the at least one data block is shifted. As a result of the shifting, the data blocks may be aggregated within the buffer.