Data manipulation method, device and electronic equipment for memory data

Abstract

The embodiment of the present invention provides a data operation method, device and electronic equipment for memory data. Wherein, the method includes: when receiving a write operation instruction, performing the data write operation indicated by the write operation instruction on the main cache table in the preset memory data cache table group; After the table executes the data write operation, the data content in the main cache table is fully synchronized to the slave cache table with the write identifier; after the synchronization is completed, the identifiers of the two slave cache tables are exchanged; When a read operation instruction is received, the data query operation indicated by the read operation instruction is executed on the slave cache table with the read identifier. This solution can reduce memory usage on the premise of ensuring that the network has high performance and high concurrent processing capabilities.

Description

technical field [0001] The invention relates to the field of computer application technology, in particular to a data operation method, device and electronic equipment for memory data. Background technique [0002] A hash table belonging to an in-memory data cache table is a representation of in-memory data. The hash table is a data structure that is directly accessed according to the key value (Key value). Specifically, it accesses records by mapping the key value to a position in the table to speed up the lookup. [0003] Data operations on in-memory data include writing and querying in-memory data. In a multi-core / multi-thread system environment, because multi-core / multi-thread needs to consider the relationship between synchronization and competition in the process of using the hash table, it is usually implemented by adding a read-write lock or a spin lock to the hash table Read and write synchronization. Add a read-write lock or a spin lock to the hash table. When d...

AI Technical Summary

Problems solved by technology

[0006] In order for the network to have high-performance processing capabilities, in a multi-core / multi-threaded system environment, each core / thread maintains a hash table. The number of hash tables that need to be maintained is large and takes up a lot of memory.

Images