Service Node Memory Partitioning for Fast Local Access
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing global memory resource pooling in service systems leads to conflicts and communication delays, resulting in reduced memory performance and increased costs due to simultaneous access by multiple service nodes and inefficient resource allocation.
Innovation Solution
Divide the memory of each service node into local and global resources, allowing local resources to be accessed independently without conflicts and using a memory management apparatus to adjust and balance the storage space sizes between local and global resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If memory resources are pooled globally across service nodes, then load balancing is improved, but memory access speed deteriorates due to communication delays
Solution Approach 1:
The memory system is segmented into local memory resources and global memory resources. Each service node has dedicated local memory for fast access and shares global memory resources through the resource pool. This segmentation allows service nodes to access local memory without communication delays while still benefiting from global load balancing through the shared resource pool.
2Adaptability or versatility
If memory resources are pooled globally across service nodes, then resource utilization is improved, but access conflicts increase
Solution Approach 1:
Different memory resources have different access qualities: local memory provides exclusive, conflict-free access for each service node, while global memory provides shared access with potential conflicts. The system assigns data to appropriate memory locations based on access patterns, ensuring high-utilization resources are used for shared data while critical data remains in local memory to avoid conflicts.
3Adaptability or versatility
If all memory resources are allocated to global pool, then system flexibility is improved, but local access performance deteriorates
Solution Approach 1:
The boundary between local and global memory resources is dynamic rather than fixed. The memory management apparatus can adjust the allocation, transferring resources between local and global pools based on changing system conditions, workload patterns, and performance requirements, allowing the system to optimize for both local performance and global flexibility as needed.
Data Source
AI summary
A service system and a memory management method and apparatus are provided. The service system includes a plurality of service nodes. A memory of at least one of the plurality of service nodes is divided into a local resource and a global resource. The local resource is used to provide memory storage space for a local service node, the global resource of the at least one service node forms a memory pool, and the memory pool is used to provide memory storage space for the plurality of service nodes. When a specific condition is satisfied, at least a part of space in the local resource is transferred to the memory pool.


