Apache Flink® - 数据流上的有状态计算

  • 事件驱动应用
  • 流批分析
  • 数据管道 & ETL
  • Exactly-once 状态一致性
  • 事件时间处理
  • 成熟的迟到数据处理
分层 API
  • SQL on Stream & Batch Data
  • DataStream API & DataSet API
  • ProcessFunction (Time & State)
  • 灵活部署
  • 高可用
  • 保存点
  • 水平扩展架构
  • 支持超大状态
  • 增量检查点机制
  • 低延迟
  • 高吞吐
  • 内存计算

Apache Flink 1.14.5 Release Announcement
The Apache Flink Community is pleased to announce another bug fix release for Flink 1.14.
Adaptive Batch Scheduler: Automatically Decide Parallelism of Flink Batch Jobs
To automatically decide parallelism of Flink batch jobs, we introduced adaptive batch scheduler in Flink 1.15. In this post, we'll take a close look at the design & implementation details.
Apache Flink Kubernetes Operator 1.0.0 Release Announcement

In the last two months since our initial preview release the community has been hard at work to stabilize and improve the core Flink Kubernetes Operator logic. We are now proud to announce the first production ready release of the operator project.

Improving speed and stability of checkpointing with generic log-based incremental checkpoints
This post describes the mechanism introduced in Flink 1.15 that continuously uploads state changes to a durable storage while performing materialization in the background
Getting into Low-Latency Gears with Apache Flink - Part Two
This multi-part series of blog post presents a collection of low-latency techniques in Flink. Following with part one, Part two continues with a few more techniques that optimize latency directly.