Databricks makes real-time mode generally available for Spark Declarative Pipelines
AIDatabricks announces general availability of Real-Time Mode for Spark Declarative Pipelines, bringing millisecond end-to-end latency to SDP pipelines. The company says RTM is up to 92% faster than Apache Flink on customer feature-computation workloads, and that SDP can now write to custom sinks such as Lakebase and Redis.
AIWhy it matters.
The source gives benchmark figures against Apache Flink and explains how the mode fits existing SDP pipelines, useful for teams weighing a dedicated streaming engine.
Source details
Databricks Blog · databricks.comPublished · added here
Original title: Announcing General Availability of Real-Time Mode for Spark Declarative Pipelines on Databricks