This page is meant as a template for writing a FLIP. To create a FLIP choose Tools->Copy on this page and modify with your content and replace the heading with the next FLIP number and a description of your issue. Replace anything in italics with your own description.

Document the state by adding a label to the FLIP page with one of "discussion", "accepted", "released", "rejected".

Please keep the discussion on the mailing list rather than commenting on the wiki (wiki discussions get unwieldy fast).

Motivation

Flink is a distributed processing engine, if some nodes are overloaded, then it may cause flink's subtask processing to slow down, which in turn leads to backpressure and lag.

There are various data Shuffle strategies in Flink, the common ones are Forward, Rebalance, Rescale, and Hsah.

Forward : The parallelism of upstream and downstream operators is the same, and the data transfer between upstream operators and downstream is one-to-one.【Data binding subtask】

Rebalance : There is no limit to the parallelism of upstream and downstream operators, each subtask of the upstream operator will send data to each subtask of the downstream in turn.【Data not bound to subtask】

Rescale : There is no limit to the parallelism of upstream and downstream operators, but each subtask of the upstream operator will only send data to some of the downstream subtasks in turn.【Data not bound to subtask】

Hash : There is no limit to the parallelism of upstream and downstream operators, the upstream operator calculates the data that should be sent to the downstream subtask based on the hash key.【Data binding subtask】

For 【Data not bound to subtask】 scenarios, I think flink can dynamically adjust the subtask of the received data according to the processing load of the downstream operator, so as to achieve the effect of peak-shaving and valley-filling, and try to ensure the throughput of flink jobs.

Public Interfaces

Briefly list any new interfaces that will be introduced as part of this proposal or any existing interfaces that will be removed or changed. The purpose of this section is to concisely call out the public contract that will come along with this feature.

A public interface is any change to the following:

• Binary log format

• The network protocol and api behavior

• Any class in the public packages under clientsConfiguration, especially client configuration

  • org/apache/kafka/common/serialization

  • org/apache/kafka/common

  • org/apache/kafka/common/errors

  • org/apache/kafka/clients/producer

  • org/apache/kafka/clients/consumer (eventually, once stable)

• Monitoring

• Command line tools and arguments

• Anything else that will likely break existing users in some way when they upgrade

Proposed Changes

Describe the new thing you want to do in appropriate detail. This may be fairly extensive and have large subsections of its own. Or it may be a few sentences. Use judgement based on the scope of the change.

Compatibility, Deprecation, and Migration Plan

• What impact (if any) will there be on existing users?
• If we are changing behavior how will we phase out the older behavior?
• If we need special migration tools, describe them here.
• When will we remove the existing behavior?

Test Plan

Describe in few sentences how the FLIP will be tested. We are mostly interested in system tests (since unit-tests are specific to implementation details). How will we know that the implementation works as expected? How will we know nothing broke?

Rejected Alternatives

If there are alternative ways of accomplishing the same thing, what were they? The purpose of this section is to motivate why the design is the way it is and not some other way.