Yuming Wang created SPARK-38771:
-----------------------------------
Summary: Introduce adaptive Bloom filter Join to reduce spilling
to disk when doing SortMergeJoin
Key: SPARK-38771
URL: https://issues.apache.org/jira/browse/SPARK-38771
Project: Spark
Issue Type: Improvement
Components: SQL
Affects Versions: 3.4.0
Reporter: Yuming Wang
Insert a bloom filter on one side of the join if it may be spill when sorting
and the other side less than 100000000L rows.
A special case:
{code:java}
sql("set spark.sql.autoBroadcastJoinThreshold=10000")
sql("CREATE TABLE t1 using parquet AS SELECT id AS a, id AS b, id AS c FROM
range(200000000L)")
sql("CREATE TABLE t2 using parquet AS SELECT id AS x, id AS y FROM
range(8000000)")
sql("""SELECT a, b, c, x, y FROM t1 JOIN t2 ON t1.a = t2.x where t2.y =
1""").collect()
{code}
--
This message was sent by Atlassian Jira
(v8.20.1#820001)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
