Thread-Level Memory Migration for Lower System Overhead
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for migrating memory data between physical cores, such as migratepages, increase system overhead due to global memory migration.
Innovation Solution
A method that migrates memory data on a thread-by-thread basis, determining whether the data is exclusively used by the target process, and if so, migrating it to a target memory block, while keeping non-exclusive data in the original block, utilizing thread-initiated and third-party processes for efficient memory data migration.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If global memory migration method (migratepages) is used to migrate all process memory data, then memory data can be moved between physical cores, but system overhead increases
Solution Approach 1:
The patent segments the memory migration process by thread, where each thread independently manages its own memory data migration. Instead of migrating all process memory globally, only the memory pages belonging to the specific thread being migrated are moved, reducing the scope and overhead of the migration operation.
Solution Approach 2:
The patent applies partial action by migrating only the necessary memory pages associated with the thread being migrated, rather than migrating all memory pages of the entire process. This selective migration approach reduces system overhead while maintaining migration effectiveness.
2Ease of operation
If all process memory data is migrated to target memory block, then thread can be migrated to new physical core, but other processes may be affected and system stability reduced
Solution Approach 1:
The patent segments memory data into thread-specific pages and shared pages. Only the thread-specific pages are migrated to the target memory block, while shared pages remain in the original memory block. This segmentation ensures that migration operations do not affect other processes using shared memory, maintaining system stability.
Solution Approach 2:
The patent applies local quality by treating different types of memory pages differently during migration. Thread-local pages are migrated to support thread relocation, while shared pages are retained to maintain accessibility for other processes. This differentiated approach ensures migration operations do not compromise system reliability.
Data Source
AI summary
A method for migrating memory data includes: obtaining a migration instruction for a target process; the target process including at least one target thread; and in response to the migration instruction, executing the following migration process for the target thread: obtaining memory data corresponding to the at least one target thread; determining whether the memory data is exclusively used by the target process; when the memory data is exclusively used by the target process, migrating the memory data to a target memory block; and when the memory data is not exclusively used by the target process, retaining the memory data in an original memory block.