[
https://issues.apache.org/jira/browse/FLINK-30536?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Dong Lin updated FLINK-30536:
-----------------------------
Description:
For the example program shown below, a CountingOutput will be added to the
per-record code path for each map operation added in the program. This reduces
the program performance as it unnecessarily increases the function call stack
depth for the critical code path.
{code:java}
DataStream<Long> stream = env.fromSequence(1, 1000000000L)
.map(x -> x)
.map(x -> x)
.map(x -> x)
.map(x -> x)
.map(x -> x)
.addSink(new DiscardingSink<>());
{code}
> Remove CountingOutput from per-record code path for most operators
> ------------------------------------------------------------------
>
> Key: FLINK-30536
> URL: https://issues.apache.org/jira/browse/FLINK-30536
> Project: Flink
> Issue Type: Sub-task
> Reporter: Dong Lin
> Priority: Major
> Labels: pull-request-available
>
> For the example program shown below, a CountingOutput will be added to the
> per-record code path for each map operation added in the program. This
> reduces the program performance as it unnecessarily increases the function
> call stack depth for the critical code path.
>
> {code:java}
> DataStream<Long> stream = env.fromSequence(1, 1000000000L)
> .map(x -> x)
> .map(x -> x)
> .map(x -> x)
> .map(x -> x)
> .map(x -> x)
> .addSink(new DiscardingSink<>());
> {code}
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
