The upcoming version of POLARDB supports parallel execution of SQL queries. In this presentation, we will show how query execution times may be significantly improved by using multiple threads to scan a table or index in parallel. Each thread will be able to do filtering and aggregation in order to reduce the amount of data to be processed by the query coordinator. Parallel join execution is also supported. We will discuss which type of queries will benefit from this feature and present results that show performance and scalability characteristics. We will also show how to control the degree of parallelism for a query and discuss other aspects of tuning parallel queries.
