[
https://issues.apache.org/jira/browse/SPARK-56312?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Yicong Huang updated SPARK-56312:
---------------------------------
Description:
Add ASV micro-benchmarks for SQL_COGROUPED_MAP_ARROW_UDF in bench_eval_type.py.
This follows the established pattern from other eval type benchmarks (e.g.,
SPARK-55947 for grouped map, SPARK-56085 for grouped agg).
was:
Refactor SQL_WINDOW_AGG_ARROW_UDF to be self-contained in read_udfs(), moving
logic from ArrowStreamAggArrowUDFSerializer and wrapper functions into
worker.py, using ArrowStreamSerializer as pure I/O.
This follows the same pattern as SPARK-56123 (SQL_GROUPED_AGG_ARROW_UDF
refactor).
Summary: Add ASV micro-benchmarks for SQL_COGROUPED_MAP_ARROW_UDF
(was: Refactor SQL_WINDOW_AGG_ARROW_UDF to use ArrowStreamSerializer)
> Add ASV micro-benchmarks for SQL_COGROUPED_MAP_ARROW_UDF
> --------------------------------------------------------
>
> Key: SPARK-56312
> URL: https://issues.apache.org/jira/browse/SPARK-56312
> Project: Spark
> Issue Type: Sub-task
> Components: PySpark, SQL
> Affects Versions: 4.2.0
> Reporter: Yicong Huang
> Priority: Major
>
> Add ASV micro-benchmarks for SQL_COGROUPED_MAP_ARROW_UDF in
> bench_eval_type.py.
> This follows the established pattern from other eval type benchmarks (e.g.,
> SPARK-55947 for grouped map, SPARK-56085 for grouped agg).
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
