How it works
Why does it behave this way?
- 1
The job that never ends
Why does volume stop being the unit of capacity, and why must state outlive the process?
2 pages - 2
State
What do stateless operators get for free, and when does an operator stop being stateless?
5 pages - 3
Time-shaped state
When are sliding windows cheap, and why do session windows need a maximum length?
4 pages - 4
Joins and enrichment
Why is every stream-stream join an interval join, and why are its errors absences?
2 pages - 5
Changelogs and queryable state
Why is a stateful operator's output a changelog, and what does retraction demand downstream?
2 pages - 6
Checkpoints and exactly-once
How does a job take a consistent snapshot while records flow, and what do aligned and unaligned barriers cost?
3 pages - 7
Rescaling and upgrades
Why is keyBy a live shuffle through a fixed indirection table, and why is its size permanent?
3 pages - 8
Backpressure and batching
Why can a stream engine slow its source safely, and how do you find the real bottleneck?
2 pages - 9
What streaming forbids, and what the escapes cost
What can a streaming design never verify?