Omega359 commented on code in PR #24803:
URL: https://github.com/apache/datafusion/pull/24803#discussion_r3889883810
##########
benchmarks/sql_benchmarks/sort_tpch/init/load.sql:
##########
@@ -1,3 +1,4 @@
-CREATE EXTERNAL TABLE lineitem_raw STORED AS PARQUET LOCATION
'${DATA_DIR:-data}/tpch_sf${BENCH_SIZE:-1}/lineitem/lineitem.1.parquet';
-
-CREATE TABLE lineitem as (SELECT * FROM lineitem_raw${BENCH_SORTED:-false|
order by l_orderkey asc| });
\ No newline at end of file
+CREATE EXTERNAL TABLE lineitem
+STORED AS PARQUET
+LOCATION '${DATA_DIR:-data}/tpch_sf${BENCH_SIZE:-1}/lineitem'
+${BENCH_SORTED:-false|WITH ORDER (l_orderkey ASC NULLS LAST)| };
Review Comment:
This change was to not use ctas (thus a mem table) but rather use parquet
level sorting.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
