[
https://issues.apache.org/jira/browse/FLINK-31655?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17712168#comment-17712168
]
tartarus commented on FLINK-31655:
----------------------------------
[~akalash] [~pnowojski] [~pltbkd] Thank you very much for your suggestions and
information, it was very valuable to me!
I will prepare a FLIP as soon, I tend to propose a new API to for Adaptive
Partitioner, so as not to bring any impact on the user's existing jobs,
adaptive Partitioner as an optional optimization attempt,
even though there is some performance overhead, users may be able to accept.
> Adaptive Channel selection for partitioner
> ------------------------------------------
>
> Key: FLINK-31655
> URL: https://issues.apache.org/jira/browse/FLINK-31655
> Project: Flink
> Issue Type: Improvement
> Components: Runtime / Task
> Reporter: tartarus
> Assignee: tartarus
> Priority: Major
>
> In Flink, if the upstream and downstream operator parallelism is not the
> same, then by default the RebalancePartitioner will be used to select the
> target channel.
> In our company, users often use flink to access redis, hbase or other rpc
> services, If some of the Operators are slow to return requests (for external
> service reasons), then because Rebalance/Rescale are Round-Robin the Channel
> selection policy, so the job is easy to backpressure.
> Because the Rebalance/Rescale policy does not care which subtask the data is
> sent to downstream, so we expect Rebalance/Rescale to refer to the processing
> power of the downstream subtask when choosing a Channel.
> Send more data to the free subtask, this ensures the best possible throughput
> of job!
>
>
>
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
