Abstract: A data virtualization layer (DV) receives a join query request related to a plurality of tables respectively stored in a plurality of distributed database servers. A plurality of candidate query plans for the join query request is generated where each of the plurality of candidate query plans indicates an order for transmitting the tables respectively stored in the database servers to the DV. For each of the plurality of candidate query plans, a query cost for the candidate query plan is calculated based on a data amount of the tables to be transmitted according to the candidate query plan. From the plurality of candidate query plans, a query plan is determined for the join query request which has a lowest query cost.

Abstract: A data virtualization layer (DV) receives a join query request related to a plurality of tables respectively stored in a plurality of distributed database servers. A plurality of candidate query plans for the join query request is generated where each of the plurality of candidate query plans indicates an order for transmitting the tables respectively stored in the database servers to the DV. For each of the plurality of candidate query plans, a query cost for the candidate query plan is calculated based on a data amount of the tables to be transmitted according to the candidate query plan. From the plurality of candidate query plans, a query plan is determined for the join query request which has a lowest query cost.

Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: collecting real time system statistics on a system environment in a remote platform running a remote data source amongst a plurality of remote data sources of a virtual database. Real time data source statistics on one or more data source objects from the remote data source of the virtual database is also gathered. A global catalog of the virtual database is updated with the real time system statistics and the real time data source statistics. An access plan to process a query to the virtual database is optimized based on the real time system statistics and the real time data source statistics and a response is produced based on the access plan, with improved performance and reduced cost.

Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: collecting real time system statistics on a system environment in a remote platform running a remote data source amongst a plurality of remote data sources of a virtual database. Real time data source statistics on one or more data source objects from the remote data source of the virtual database is also gathered. A global catalog of the virtual database is updated with the real time system statistics and the real time data source statistics. An access plan to process a query to the virtual database is optimized based on the real time system statistics and the real time data source statistics and a response is produced based on the access plan, with improved performance and reduced cost.