TSC 2024/09/19 (Monitoring Queries)

Date: Sep 19, 2024 8 AM PT

 

EdgeLake TSC Meeting: Optimizing Query Processing and Monitoring

Join us for an in-depth discussion on EdgeLake Queries and their role in distributed edge deployments.

In EdgeLake environments, data is spread across multiple edge nodes. A query is typically issued to a single node, which serves as the orchestrator. This node is responsible for distributing the query to the relevant nodes that hold the data, gathering the results, and returning a unified dataset to the user.

During this session, we’ll explore the key aspects of query execution, focusing on scalability, efficiency, and monitoring. A special emphasis will be placed on query monitoring—despite the distributed nature of queries across multiple nodes, users can easily track which nodes are involved in each query and monitor processing times at each node.

We will also cover the application of window and pushdown functions, which are commonly used to optimize query performance in distributed edge environments.

Agenda:

  1. Overview of EdgeLake Query Execution

  2. Query Monitoring: Tracking Nodes and Processing Times

  3. Window and Pushdown Functions: Enhancing Query Efficiency

  4. Open Discussion

 

Meeting Recording

Presentation

Â