Skip to content

[WIP][SPARK-30621][SQL] Dynamic Pruning thread propagates the localProperties to executionContext #27343

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
wants to merge 1 commit into from
Closed

[WIP][SPARK-30621][SQL] Dynamic Pruning thread propagates the localProperties to executionContext #27343

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
8 changes: 8 additions & 0 deletions sql/catalyst/src/main/scala/org/apache/spark/sql/internal/StaticSQLConf.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -156,6 +156,14 @@ object StaticSQLConf {
.checkValue(thres => thres > 0 && thres <= 128, "The threshold must be in (0,128].")
.createWithDefault(16)

val DYNAMIC_PRUNING_MAX_THREAD_THRESHOLD =
buildStaticConf("spark.sql.dynamic.pruning.maxThreadThreshold")
.internal()
.doc("The maximum degree of parallelism to execute the dynamic pruning.")
.intConf
.checkValue(thres => thres > 0 && thres <= 128, "The threshold must be in (0,128].")
.createWithDefault(16)

val SQL_EVENT_TRUNCATE_LENGTH = buildStaticConf("spark.sql.event.truncate.length")
.doc("Threshold of SQL length beyond which it will be truncated before adding to " +
"event. Defaults to no truncation. If set to 0, callsite will be logged instead.")
Expand Down
10 changes: 7 additions & 3 deletions sql/core/src/main/scala/org/apache/spark/sql/execution/SubqueryBroadcastExec.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,7 @@ import org.apache.spark.sql.catalyst.expressions._
import org.apache.spark.sql.catalyst.plans.QueryPlan
import org.apache.spark.sql.execution.joins.{HashedRelation, HashJoin, LongHashedRelation}
import org.apache.spark.sql.execution.metric.SQLMetrics
import org.apache.spark.sql.internal.{SQLConf, StaticSQLConf}
import org.apache.spark.util.ThreadUtils

/**
Expand Down Expand Up @@ -57,7 +58,9 @@ case class SubqueryBroadcastExec(
private lazy val relationFuture: Future[Array[InternalRow]] = {
// relationFuture is used in "doExecute". Therefore we can get the execution id correctly here.
val executionId = sparkContext.getLocalProperty(SQLExecution.EXECUTION_ID_KEY)
Future {
SQLExecution.withThreadLocalCaptured[Array[InternalRow]](
sqlContext.sparkSession,
SubqueryBroadcastExec.executionContext) {
// This will run in another thread. Set the execution id so that we can connect these jobs
// with the correct execution.
SQLExecution.withExecutionId(sqlContext.sparkSession, executionId) {
Expand All @@ -83,7 +86,7 @@ case class SubqueryBroadcastExec(

rows
}
}(SubqueryBroadcastExec.executionContext)
}
}

protected override def doPrepare(): Unit = {
Expand All @@ -104,5 +107,6 @@ case class SubqueryBroadcastExec(

object SubqueryBroadcastExec {
private[execution] val executionContext = ExecutionContext.fromExecutorService(
ThreadUtils.newDaemonCachedThreadPool("dynamicpruning", 16))
ThreadUtils.newDaemonCachedThreadPool("dynamicpruning",
SQLConf.get.getConf(StaticSQLConf.DYNAMIC_PRUNING_MAX_THREAD_THRESHOLD)))
}