Query Execution Optimization for Broadcast Join using Replicated-Reads Strategy – George Wang, Ahana

Query Execution Optimization for Broadcast Join using Replicated-Reads Strategy – George Wang, Ahana

Today presto supports broadcast join by having a worker to fetch data from a small data source to build a hash table and then sending the entire data over the network to all other workers for hash lookup probed by large data source. This can be optimized by a new query execution strategy as source data from small tables is pulled directly by all workers which is known as replicated reads from dimension tables. This feature comes with a nice caching property given that all worker nodes N are now participating in scanning the data from remote sources. The table scan operation for dimension tables is cacheable per all worker nodes. In addition, there will be better resource utilization because the presto scheduler can now reduce the number plan fragment to execute as the same workers run tasks in parallel within a single stage to reduce data shuffles.

Presto on AWS using Ahana Cloud at Cartona – Omar Mohamed, Cartona

Presto on AWS using Ahana Cloud at Cartona – Omar Mohamed, Cartona

Cartona is one of the fastest growing B2B e-commerce marketplaces in Egypt that connects retailers with suppliers, wholesalers, and production companies. We needed to federate across multiple data sources, including transactional databases like Postgres and AWS S3 data lake. In this session, we’ll talk about how Presto allows us to join across all of these data sources without having to copy or ingest data – it’s all done in place. In addition, we’ll talk about how we were up and running in less than an hour with the Ahana Cloud managed service. It gives us the power of Presto and the ease of use without the need to manage it or have deep skills to deploy and operate it.