Design and implementation of clustered in-memory database

摘要

An in-memory database system and method for managing a distributed in-memory database, comprising: a module configured to store and distribute a database partition of an aggregate partitioned by a partitioner associated with a search conductor Having one or more nodes. The database aggregate is partitioned according to the schema. Partitions, aggregates and records are updated and removed according to the schema as required by the system interface. The supervisor determines the node state based on the heartbeat signal received from each node. The user sends a query to the search manager through the system interface. The search manager applies the field processing technique, forwards the search query to the search conductor, and returns the set of result records to the analysis agent. The analysis agent performs an analysis process on candidate result records from the search manager. A search conductor that includes a party associated party aggregate searches and scores records in the partition and then returns a set of candidate result records after receiving a search query from the search manager.(FIG.