Skip to content

[SPARK-26840][SQL] Avoid cost-based join reorder in presence of join hints #23759

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
maryannxue wants to merge 5 commits into from
Closed

[SPARK-26840][SQL] Avoid cost-based join reorder in presence of join hints #23759

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
6949db5
fix
maryannxue Feb 10, 2019
eb70456
Update to one-liner
dongjoon-hyun Feb 10, 2019
41aa5ba
Merge pull request #1 from dongjoon-hyun/PR-23759
maryannxue Feb 11, 2019
534602b
Revert "Update to one-liner"
maryannxue Feb 11, 2019
d7c1567
fix
maryannxue Feb 11, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 8 additions & 7 deletions ...atalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/CostBasedJoinReorder.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,7 +51,7 @@ object CostBasedJoinReorder extends Rule[LogicalPlan] with PredicateHelper {
}
// After reordering is finished, convert OrderedJoin back to Join.
result transform {
case OrderedJoin(left, right, jt, cond) => Join(left, right, jt, cond, JoinHint.NONE)
case OrderedJoin(left, right, jt, cond, hint) => Join(left, right, jt, cond, hint)
}
}
}
Expand All @@ -77,24 +77,24 @@ object CostBasedJoinReorder extends Rule[LogicalPlan] with PredicateHelper {
*/
private def extractInnerJoins(plan: LogicalPlan): (Seq[LogicalPlan], Set[Expression]) = {
plan match {
case Join(left, right, _: InnerLike, Some(cond), _) =>
case Join(left, right, _: InnerLike, Some(cond), hint) if hint == JoinHint.NONE =>
Copy link
Member

@viirya viirya Feb 11, 2019

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think we can use pattern match as @dongjoon-hyun's PR, it will be simpler.

val (leftPlans, leftConditions) = extractInnerJoins(left)
val (rightPlans, rightConditions) = extractInnerJoins(right)
(leftPlans ++ rightPlans, splitConjunctivePredicates(cond).toSet ++
leftConditions ++ rightConditions)
case Project(projectList, j @ Join(_, _, _: InnerLike, Some(cond), _))
if projectList.forall(_.isInstanceOf[Attribute]) =>
case Project(projectList, j @ Join(_, _, _: InnerLike, Some(cond), hint))
if projectList.forall(_.isInstanceOf[Attribute]) && hint == JoinHint.NONE =>
extractInnerJoins(j)
case _ =>
(Seq(plan), Set())
}
}

private def replaceWithOrderedJoin(plan: LogicalPlan): LogicalPlan = plan match {
case j @ Join(left, right, jt: InnerLike, Some(cond), _) =>
case j @ Join(left, right, jt: InnerLike, Some(cond), hint) =>
val replacedLeft = replaceWithOrderedJoin(left)
val replacedRight = replaceWithOrderedJoin(right)
OrderedJoin(replacedLeft, replacedRight, jt, Some(cond))
OrderedJoin(replacedLeft, replacedRight, jt, Some(cond), hint)
case p @ Project(projectList, j @ Join(_, _, _: InnerLike, Some(cond), _)) =>
p.copy(child = replaceWithOrderedJoin(j))
case _ =>
Expand All @@ -107,7 +107,8 @@ case class OrderedJoin(
left: LogicalPlan,
right: LogicalPlan,
joinType: JoinType,
condition: Option[Expression]) extends BinaryNode {
condition: Option[Expression],
hint: JoinHint) extends BinaryNode {
override def output: Seq[Attribute] = left.output ++ right.output
}

Expand Down
92 changes: 47 additions & 45 deletions sql/core/src/test/scala/org/apache/spark/sql/JoinHintSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -102,58 +102,60 @@ class JoinHintSuite extends PlanTest with SharedSQLContext {
}

test("hints prevent join reorder") {
withTempView("a", "b", "c") {
df1.createOrReplaceTempView("a")
df2.createOrReplaceTempView("b")
df3.createOrReplaceTempView("c")
verifyJoinHint(
sql("select /*+ broadcast(a, c)*/ * from a, b, c " +
"where a.a1 = b.b1 and b.b1 = c.c1"),
JoinHint(
None,
Some(HintInfo(broadcast = true))) ::
JoinHint(
Some(HintInfo(broadcast = true)),
None):: Nil
)
verifyJoinHint(
sql("select /*+ broadcast(a, c)*/ * from a, c, b " +
"where a.a1 = b.b1 and b.b1 = c.c1"),
JoinHint.NONE ::
withSQLConf(SQLConf.CBO_ENABLED.key -> "true", SQLConf.JOIN_REORDER_ENABLED.key -> "true") {
withTempView("a", "b", "c") {
df1.createOrReplaceTempView("a")
df2.createOrReplaceTempView("b")
df3.createOrReplaceTempView("c")
verifyJoinHint(
sql("select /*+ broadcast(a, c)*/ * from a, b, c " +
"where a.a1 = b.b1 and b.b1 = c.c1"),
JoinHint(
Some(HintInfo(broadcast = true)),
Some(HintInfo(broadcast = true))):: Nil
)
verifyJoinHint(
sql("select /*+ broadcast(b, c)*/ * from a, c, b " +
"where a.a1 = b.b1 and b.b1 = c.c1"),
JoinHint(
None,
Some(HintInfo(broadcast = true))) ::
None,
Some(HintInfo(broadcast = true))) ::
JoinHint(
Some(HintInfo(broadcast = true)),
None) :: Nil
)
verifyJoinHint(
sql("select /*+ broadcast(a, c)*/ * from a, c, b " +
"where a.a1 = b.b1 and b.b1 = c.c1"),
JoinHint.NONE ::
JoinHint(
Some(HintInfo(broadcast = true)),
Some(HintInfo(broadcast = true))) :: Nil
)
verifyJoinHint(
sql("select /*+ broadcast(b, c)*/ * from a, c, b " +
"where a.a1 = b.b1 and b.b1 = c.c1"),
JoinHint(
None,
Some(HintInfo(broadcast = true))):: Nil
)

verifyJoinHint(
df1.join(df2, 'a1 === 'b1 && 'a1 > 5).hint("broadcast")
.join(df3, 'b1 === 'c1 && 'a1 < 10),
JoinHint(
Some(HintInfo(broadcast = true)),
None) ::
JoinHint.NONE:: Nil
)
Some(HintInfo(broadcast = true))) ::
JoinHint(
None,
Some(HintInfo(broadcast = true))) :: Nil
)

verifyJoinHint(
df1.join(df2, 'a1 === 'b1 && 'a1 > 5).hint("broadcast")
.join(df3, 'b1 === 'c1 && 'a1 < 10)
.join(df, 'b1 === 'id),
JoinHint.NONE ::
verifyJoinHint(
df1.join(df2, 'a1 === 'b1 && 'a1 > 5).hint("broadcast")
.join(df3, 'b1 === 'c1 && 'a1 < 10),
JoinHint(
Some(HintInfo(broadcast = true)),
None) ::
JoinHint.NONE:: Nil
)
JoinHint.NONE :: Nil
)

verifyJoinHint(
df1.join(df2, 'a1 === 'b1 && 'a1 > 5).hint("broadcast")
.join(df3, 'b1 === 'c1 && 'a1 < 10)
.join(df, 'b1 === 'id),
JoinHint.NONE ::
JoinHint(
Some(HintInfo(broadcast = true)),
None) ::
JoinHint.NONE :: Nil
)
}
}
}

Expand Down