Method and system for constructing highly extensible learning index perceived by NUMA (Non Uniform Memory Access) architecture and operation method

By adopting a hybrid node tree index structure and adaptive node evolution mechanism under the NUMA architecture, the data storage layout and resource allocation are optimized, and the performance and scalability of learning indexes under the NUMA architecture are solved, and efficient memory access and cache management are achieved.

CN120541272AActive Publication Date: 2025-08-26NANJING UNIV
14 Cites 2 Cited by

Patent Information

Application Number
CN202510647047.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-05-20
Publication Date
2025-08-26
Estimated Expiration
2045-05-20

AI Technical Summary

Technical Problem

The existing learning indexing technology cannot achieve high performance and scalability under the NUMA architecture, mainly due to performance problems caused by high memory access cardinality, cache loss rate and mismatch between NUMA nodes.

Method used

A hybrid node tree index structure is adopted, including internal nodes and leaf nodes, and the data storage layout is optimized through linear models and hashing methods, combined with adaptive node evolution mechanism and multi-threaded concurrency control strategy, dynamically adjust the data node layout and resource allocation, and optimize memory access under the NUMA architecture.

Benefits of technology

It significantly improves the index performance and scalability under the NUMA architecture, reduces the memory access cost and cache loss rate, reduces the remote memory access latency, and improves operational efficiency.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses an NUMA (Non Uniform Memory Access) architecture perceived high-scalability learning index construction method and system and an operation method. According to the construction method, a mixed node tree structure is adopted to organize data, the structure comprises internal nodes accurately searched by a linear model and leaf nodes for storing data, the leaf nodes are composed of ordered gap nodes and segment nodes, and the segment nodes support dynamic evolution from an ordered stage to a semi-ordered stage based on data density. Conflict data is managed using hierarchical benchmark buckets. According to the system, a self-adaptive node evolution mechanism based on an operation cost model is realized, index performance is optimized through node reconstruction triggered by foreground write operation and background hot and cold node compression, a multi-thread concurrency control strategy is adopted, and a memory management and thread scheduling framework perceived by NUMA is adopted. The operation method provides an efficient point query and point insertion operation process. The data layout can be dynamically optimized, the operation cost is reduced, and the method is suitable for high-performance database and memory management scenes.
Need to check novelty before this filing date? Find Prior Art