peter-toth edited a comment on issue #23802: [SPARK-26893][SQL] Allow partition pruning with subquery filters on file source URL: https://github.com/apache/spark/pull/23802#issuecomment-465186995 It seems there is not a query among TPCDS that could benefit from this change. (Unfortunately, I didn't find any that use subquery filtering on partitioning columns. But actually there are quite a lot of queries that use partitioning columns with joins and I think this PR can help to address https://issues.apache.org/jira/browse/SPARK-26769 and then even TPCDS can benefit from it.) So to run a benchmark I came up with this query that computes the count of distinct items sold since 2000 on the web channel: ``` SELECT COUNT(DISTINCT ws_item_sk) FROM web_sales WHERE ws_sold_date_sk >= ( SELECT MIN(d_date_sk) FROM date_dim WHERE d_year >= 2000 ) ``` Results are in ms: |run|master|this PR| |-|-|-| |1|8724|5846| |2|3852|3172| |3|3385|2432| |4|3320|2251| |5|3013|2178| |6|2959|2227| |7|3038|2353| |8|3157|2224| |9|2929|1967| |10|2943|2048| |11|2973|1967|
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
