Abstract: The present disclosure provides methods, systems and apparatus for efficient data management in distributed database system. According to an aspect, a method is provided. The method includes relocating a first table and a second table of a database to a first node of the database, wherein the first table and a second table (or one or more tables which have a colocation relationship with the first table) are associated with one or more distribution keys corresponding to one or more columns of the first table and the second table. The method further includes defining a colocation relationship between the first table and the second table based on a distribution key of the one or more distribution keys. The colocation relationship may indicate that data of the first table and the second table that correspond according to the distribution key are to reside on a same node of the database.

Abstract: A method and system of processing database transactions in a distributed online transaction processing (OLTP) database is provided. Overhead and network bandwidth associated with a global transaction manager are reduced and scalability improved by determining whether incoming statements are single-shard or multi-shard. For single-shard statements, a local transaction identifier (TXID) stored and associated with a data record reference by the statement is retrieved. The retrieved TXID is compared against a copy of a list of prepared transactions that are pending in a respective data node. If the TXID is in the copy of the prepared list, the statement is caused to await until the previous transaction has been committed or aborted. The visibility of a change committed by the previous is then determined, and the statement is processed.

Abstract: A method and system of processing database transactions in a distributed online transaction processing (OLTP) database is provided. Overhead and network bandwidth associated with a global transaction manager are reduced and scalability improved by determining whether incoming statements are single-shard or multi-shard. For single-shard statements, a local transaction identifier (TXID) stored and associated with a data record reference by the statement is retrieved. The retrieved TXID is compared against a copy of a list of prepared transactions that are pending in a respective data node. If the TXID is in the copy of the prepared list, the statement is caused to await until the previous transaction has been committed or aborted. The visibility of a change committed by the previous is then determined, and the statement is processed.