AWS has announced Parallel Query for Amazon Aurora. According to the company, this provides faster analytical queries over transactional data that can speed up queries by up to 2 orders of magnitude, while maintaining high throughput for core transactional workloads.
The feature is available for the MySQL 5.6-compatible edition of Amazon Aurora, and is currently available in the U.S. East (N. Virginia), U.S. East (Ohio), U.S. West (Oregon), EU (Ireland), and Asia Pacific (Tokyo) Regions.
The new capability was explained in a blog post by Jeff Barr , chief evangelist for AWS. According to Barr, "Parallel Query takes advantage of Aurora’s architecture by pushing processing down to the Aurora storage layer, spreading computation across thousands of nodes. By pushing query computation down to the storage layer where possible, Parallel Query limits CPU, memory, and network contention with the core workload."
He added that, "Parallel queries enhance the performance of over 200 types of single-table predicates and hash joins. The Aurora query optimizer will automatically decide whether to use Parallel Query based on the size of the table and the amount of table data that is already in memory; users can also use the aurora_pq_force session variable to override the optimizer for testing purposes."
Because this new model reduces network, CPU, and buffer pool contention, users can run a mix of analytical and transactional queries simultaneously on the same table while maintaining high throughput for both types of queries.
Users will need to create a fresh cluster in order to make use of the Parallel Query feature, using one created from scratch, or restoring a snapshot.
To access Barr's blog post, go to https://aws.amazon.com/blogs/aws/new-parallel-query-for-amazon-aurora