[
https://issues.apache.org/jira/browse/SPARK-51362?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Yuchen Liu updated SPARK-51362:
-------------------------------
Summary: Change toJSON to use NextIterator API to reduce latency (was:
change toJSON to use NextIterator API to reduce latency)
> Change toJSON to use NextIterator API to reduce latency
> -------------------------------------------------------
>
> Key: SPARK-51362
> URL: https://issues.apache.org/jira/browse/SPARK-51362
> Project: Spark
> Issue Type: Improvement
> Components: SQL
> Affects Versions: 4.0.0
> Reporter: Yuchen Liu
> Priority: Major
>
> The current toJSON operation uses the Iterator API where iter.hasNext is
> called after iter.next, which means the return of current row depends on the
> next row to arrive. If we change it to use the NextIterator API, iter.next
> will be called after iter.hasNext, so the current row will return
> immediately. This eliminates the dependency between adjacent rows, which
> reduces record-level latency.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
