[
https://issues.apache.org/jira/browse/SPARK-56642?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
L. C. Hsieh reassigned SPARK-56642:
-----------------------------------
Assignee: L. C. Hsieh
> Add pipelined JVM-Python UDF data transfer
> ------------------------------------------
>
> Key: SPARK-56642
> URL: https://issues.apache.org/jira/browse/SPARK-56642
> Project: Spark
> Issue Type: Improvement
> Components: SQL
> Affects Versions: 4.2.0
> Reporter: L. C. Hsieh
> Assignee: L. C. Hsieh
> Priority: Major
>
> The current single-threaded NIO selector model serializes input and reads
> output in the same thread alternately. For multi-column UDFs or compute-heavy
> UDFs, this leaves the JVM idle while waiting for Python output. We can add
> pipelined mode overlaps serialization with output reading to improve
> throughput.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
