AWS Big Data

SEPTEMBER 14, 2023

We’ve already discussed how checkpoints, when triggered by the job manager, signal all source operators to snapshot their state, which is then broadcasted as a special record called a checkpoint barrier. When barriers from all upstream partitions have arrived, the sub-task takes a snapshot of its state.

Snapshot 93

Snapshot Broadcasting Optimization Management 93

AWS Big Data

MARCH 18, 2024

By default, the sink writes in batches to optimize throughput. SQL In Apache Flink SQL, users can provide hints to join queries that can be used to suggest the optimizer to have an effect in the query plan. The DataStream API now supports features like side outputs and broadcast state, and gaps on windowing API have been closed.

Management 105

Management Snapshot Broadcasting Optimization 105

AWS Big Data

SEPTEMBER 14, 2023

Internally, Apache Flink uses clever mechanisms to maintain exactly-once state consistency, while also optimizing for throughput and reduced latency. Each of the distributed components of an application asynchronously snapshots its state to an external persistent datastore. The default behavior works well for most use cases.

Optimization 85

Optimization Snapshot Management Broadcasting 85