org.apache.spark.sql.execution.adaptive
AdaptiveSparkPlanExec
Companion object AdaptiveSparkPlanExec
case class AdaptiveSparkPlanExec(inputPlan: SparkPlan, context: AdaptiveExecutionContext, preprocessingRules: Seq[Rule[SparkPlan]], isSubquery: Boolean, supportsColumnar: Boolean = false) extends SparkPlan with LeafExecNode with Product with Serializable
A root node to execute the query plan adaptively. It splits the query plan into independent stages and executes them in order according to their dependencies. The query stage materializes its output at the end. When one stage completes, the data statistics of the materialized output will be used to optimize the remainder of the query.
To create query stages, we traverse the query tree bottom up. When we hit an exchange node, and if all the child query stages of this exchange node are materialized, we create a new query stage for this exchange node. The new stage is then materialized asynchronously once it is created.
When one query stage finishes materialization, the rest query is re-optimized and planned based on the latest statistics provided by all materialized stages. Then we traverse the query plan again and create more stages if possible. After all stages have been materialized, we execute the rest of the plan.
- Alphabetic
- By Inheritance
- AdaptiveSparkPlanExec
- LeafExecNode
- LeafLike
- SparkPlan
- Serializable
- Logging
- QueryPlan
- SQLConfHelper
- TreeNode
- TreePatternBits
- Product
- Equals
- AnyRef
- Any
- Hide All
- Show All
- Public
- Protected
Instance Constructors
- new AdaptiveSparkPlanExec(inputPlan: SparkPlan, context: AdaptiveExecutionContext, preprocessingRules: Seq[Rule[SparkPlan]], isSubquery: Boolean, supportsColumnar: Boolean = false)
Value Members
- lazy val allAttributes: AttributeSeq
- Definition Classes
- QueryPlan
- def apply(number: Int): TreeNode[_]
- Definition Classes
- TreeNode
- def argString(maxFields: Int): String
- Definition Classes
- TreeNode
- def asCode: String
- Definition Classes
- TreeNode
- final lazy val canonicalized: SparkPlan
- Definition Classes
- QueryPlan
- Annotations
- @transient()
- final def children: Seq[SparkPlan]
- Definition Classes
- LeafLike
- def clone(): SparkPlan
- Definition Classes
- TreeNode → AnyRef
- def collect[B](pf: PartialFunction[SparkPlan, B]): Seq[B]
- Definition Classes
- TreeNode
- def collectFirst[B](pf: PartialFunction[SparkPlan, B]): Option[B]
- Definition Classes
- TreeNode
- def collectLeaves(): Seq[SparkPlan]
- Definition Classes
- TreeNode
- def collectWithSubqueries[B](f: PartialFunction[SparkPlan, B]): Seq[B]
- Definition Classes
- QueryPlan
- def conf: SQLConf
- Definition Classes
- AdaptiveSparkPlanExec → SparkPlan → SQLConfHelper
- final def containsAllPatterns(patterns: TreePattern*): Boolean
- Definition Classes
- TreePatternBits
- final def containsAnyPattern(patterns: TreePattern*): Boolean
- Definition Classes
- TreePatternBits
- lazy val containsChild: Set[TreeNode[_]]
- Definition Classes
- TreeNode
- final def containsPattern(t: TreePattern): Boolean
- Definition Classes
- TreePatternBits
- Annotations
- @inline()
- val context: AdaptiveExecutionContext
- def copyTagsFrom(other: SparkPlan): Unit
- Definition Classes
- TreeNode
- lazy val deterministic: Boolean
- Definition Classes
- QueryPlan
- def doCanonicalize(): SparkPlan
- Definition Classes
- AdaptiveSparkPlanExec → QueryPlan
- def doExecute(): RDD[InternalRow]
Produces the result of the query as an
RDD[InternalRow]Produces the result of the query as an
RDD[InternalRow]Overridden by concrete implementations of SparkPlan.
- Definition Classes
- AdaptiveSparkPlanExec → SparkPlan
- def doExecuteBroadcast[T](): Broadcast[T]
Produces the result of the query as a broadcast variable.
Produces the result of the query as a broadcast variable.
Overridden by concrete implementations of SparkPlan.
- Definition Classes
- AdaptiveSparkPlanExec → SparkPlan
- def doExecuteColumnar(): RDD[ColumnarBatch]
Produces the result of the query as an
RDD[ColumnarBatch]if supportsColumnar returns true.Produces the result of the query as an
RDD[ColumnarBatch]if supportsColumnar returns true. By convention the executor that creates a ColumnarBatch is responsible for closing it when it is no longer needed. This allows input formats to be able to reuse batches if needed.- Definition Classes
- AdaptiveSparkPlanExec → SparkPlan
- def equals(obj: Any): Boolean
- Definition Classes
- AdaptiveSparkPlanExec → Equals → AnyRef → Any
- final def execute(): RDD[InternalRow]
Returns the result of this query as an RDD[InternalRow] by delegating to
doExecuteafter preparations.Returns the result of this query as an RDD[InternalRow] by delegating to
doExecuteafter preparations.Concrete implementations of SparkPlan should override
doExecute.- Definition Classes
- SparkPlan
- final def executeBroadcast[T](): Broadcast[T]
Returns the result of this query as a broadcast variable by delegating to
doExecuteBroadcastafter preparations.Returns the result of this query as a broadcast variable by delegating to
doExecuteBroadcastafter preparations.Concrete implementations of SparkPlan should override
doExecuteBroadcast.- Definition Classes
- SparkPlan
- def executeCollect(): Array[InternalRow]
Runs this query returning the result as an array.
Runs this query returning the result as an array.
- Definition Classes
- AdaptiveSparkPlanExec → SparkPlan
- def executeCollectPublic(): Array[Row]
Runs this query returning the result as an array, using external Row format.
Runs this query returning the result as an array, using external Row format.
- Definition Classes
- SparkPlan
- final def executeColumnar(): RDD[ColumnarBatch]
Returns the result of this query as an RDD[ColumnarBatch] by delegating to
doColumnarExecuteafter preparations.Returns the result of this query as an RDD[ColumnarBatch] by delegating to
doColumnarExecuteafter preparations.Concrete implementations of SparkPlan should override
doColumnarExecuteifsupportsColumnarreturns true.- Definition Classes
- SparkPlan
- def executeTail(n: Int): Array[InternalRow]
Runs this query returning the last
nrows as an array.Runs this query returning the last
nrows as an array.This is modeled after
RDD.takebut never runs any job locally on the driver.- Definition Classes
- AdaptiveSparkPlanExec → SparkPlan
- def executeTake(n: Int): Array[InternalRow]
Runs this query returning the first
nrows as an array.Runs this query returning the first
nrows as an array.This is modeled after
RDD.takebut never runs any job locally on the driver.- Definition Classes
- AdaptiveSparkPlanExec → SparkPlan
- def executeToIterator(): Iterator[InternalRow]
Runs this query returning the result as an iterator of InternalRow.
Runs this query returning the result as an iterator of InternalRow.
- Definition Classes
- SparkPlan
- Note
Triggers multiple jobs (one for each partition).
- def executedPlan: SparkPlan
- def exists(f: (SparkPlan) => Boolean): Boolean
- Definition Classes
- TreeNode
- final def expressions: Seq[Expression]
- Definition Classes
- QueryPlan
- def fastEquals(other: TreeNode[_]): Boolean
- Definition Classes
- TreeNode
- def find(f: (SparkPlan) => Boolean): Option[SparkPlan]
- Definition Classes
- TreeNode
- def flatMap[A](f: (SparkPlan) => TraversableOnce[A]): Seq[A]
- Definition Classes
- TreeNode
- def foreach(f: (SparkPlan) => Unit): Unit
- Definition Classes
- TreeNode
- def foreachUp(f: (SparkPlan) => Unit): Unit
- Definition Classes
- TreeNode
- def generateTreeString(depth: Int, lastChildren: Seq[Boolean], append: (String) => Unit, verbose: Boolean, prefix: String = "", addSuffix: Boolean = false, maxFields: Int, printNodeId: Boolean, indent: Int = 0): Unit
- Definition Classes
- AdaptiveSparkPlanExec → TreeNode
- def getTagValue[T](tag: TreeNodeTag[T]): Option[T]
- Definition Classes
- TreeNode
- def hashCode(): Int
- Definition Classes
- AdaptiveSparkPlanExec → TreeNode → AnyRef → Any
- val id: Int
- Definition Classes
- SparkPlan
- val initialPlan: SparkPlan
- def innerChildren: Seq[QueryPlan[_]]
- Definition Classes
- QueryPlan → TreeNode
- val inputPlan: SparkPlan
- def inputSet: AttributeSet
- Definition Classes
- QueryPlan
- val isSubquery: Boolean
- def logicalLink: Option[LogicalPlan]
- returns
The logical plan this plan is linked to.
- Definition Classes
- SparkPlan
- def longMetric(name: String): SQLMetric
- returns
SQLMetric for the
name.
- Definition Classes
- SparkPlan
- def makeCopy(newArgs: Array[AnyRef]): SparkPlan
Overridden make copy also propagates sqlContext to copied plan.
Overridden make copy also propagates sqlContext to copied plan.
- Definition Classes
- SparkPlan → TreeNode
- def map[A](f: (SparkPlan) => A): Seq[A]
- Definition Classes
- TreeNode
- final def mapChildren(f: (SparkPlan) => SparkPlan): SparkPlan
- Definition Classes
- LeafLike
- def mapExpressions(f: (Expression) => Expression): AdaptiveSparkPlanExec.this.type
- Definition Classes
- QueryPlan
- def metrics: Map[String, SQLMetric]
- returns
All metrics containing metrics of this SparkPlan.
- Definition Classes
- SparkPlan
- final def missingInput: AttributeSet
- Definition Classes
- QueryPlan
- def nodeName: String
- Definition Classes
- TreeNode
- def numberedTreeString: String
- Definition Classes
- TreeNode
- val origin: Origin
- Definition Classes
- TreeNode
- def output: Seq[Attribute]
- Definition Classes
- AdaptiveSparkPlanExec → QueryPlan
- def outputOrdering: Seq[SortOrder]
Specifies how data is ordered in each partition.
Specifies how data is ordered in each partition.
- Definition Classes
- SparkPlan
- def outputPartitioning: Partitioning
Specifies how data is partitioned across different nodes in the cluster.
Specifies how data is partitioned across different nodes in the cluster. Note this method may fail if it is invoked before
EnsureRequirementsis applied sincePartitioningCollectionrequires all its partitionings to have the same number of partitions.- Definition Classes
- SparkPlan
- lazy val outputSet: AttributeSet
- Definition Classes
- QueryPlan
- Annotations
- @transient()
- def p(number: Int): SparkPlan
- Definition Classes
- TreeNode
- final def prepare(): Unit
Prepares this SparkPlan for execution.
Prepares this SparkPlan for execution. It's idempotent.
- Definition Classes
- SparkPlan
- val preprocessingRules: Seq[Rule[SparkPlan]]
- def prettyJson: String
- Definition Classes
- TreeNode
- def printSchema(): Unit
- Definition Classes
- QueryPlan
- def producedAttributes: AttributeSet
- Definition Classes
- LeafExecNode → QueryPlan
- def productElementNames: Iterator[String]
- Definition Classes
- Product
- lazy val references: AttributeSet
- Definition Classes
- QueryPlan
- Annotations
- @transient()
- def requiredChildDistribution: Seq[Distribution]
Specifies the data distribution requirements of all the children for this operator.
Specifies the data distribution requirements of all the children for this operator. By default it's UnspecifiedDistribution for each child, which means each child can have any distribution.
If an operator overwrites this method, and specifies distribution requirements(excluding UnspecifiedDistribution and BroadcastDistribution) for more than one child, Spark guarantees that the outputs of these children will have same number of partitions, so that the operator can safely zip partitions of these children's result RDDs. Some operators can leverage this guarantee to satisfy some interesting requirement, e.g., non-broadcast joins can specify HashClusteredDistribution(a,b) for its left child, and specify HashClusteredDistribution(c,d) for its right child, then it's guaranteed that left and right child are co-partitioned by a,b/c,d, which means tuples of same value are in the partitions of same index, e.g., (a=1,b=2) and (c=1,d=2) are both in the second partition of left and right child.
- Definition Classes
- SparkPlan
- def requiredChildOrdering: Seq[Seq[SortOrder]]
Specifies sort order for each partition requirements on the input data for this operator.
Specifies sort order for each partition requirements on the input data for this operator.
- Definition Classes
- SparkPlan
- def resetMetrics(): Unit
Resets all the metrics.
Resets all the metrics.
- Definition Classes
- AdaptiveSparkPlanExec → SparkPlan
- def rewriteAttrs(attrMap: AttributeMap[Attribute]): SparkPlan
- Definition Classes
- QueryPlan
- final def sameResult(other: SparkPlan): Boolean
- Definition Classes
- QueryPlan
- lazy val schema: StructType
- Definition Classes
- QueryPlan
- def schemaString: String
- Definition Classes
- QueryPlan
- final def semanticHash(): Int
- Definition Classes
- QueryPlan
- final val session: SparkSession
- Definition Classes
- SparkPlan
- def setLogicalLink(logicalPlan: LogicalPlan): Unit
Set logical plan link recursively if unset.
Set logical plan link recursively if unset.
- Definition Classes
- SparkPlan
- def setTagValue[T](tag: TreeNodeTag[T], value: T): Unit
- Definition Classes
- TreeNode
- def simpleString(maxFields: Int): String
- Definition Classes
- QueryPlan → TreeNode
- def simpleStringWithNodeId(): String
- Definition Classes
- QueryPlan → TreeNode
- lazy val subqueries: Seq[SparkPlan]
- Definition Classes
- QueryPlan
- Annotations
- @transient()
- def subqueriesAll: Seq[SparkPlan]
- Definition Classes
- QueryPlan
- val supportsColumnar: Boolean
Return true if this stage of the plan supports columnar execution.
Return true if this stage of the plan supports columnar execution. A plan can also support row-based execution (see
supportsRowBased). Spark will decide which execution to be called during query planning.- Definition Classes
- AdaptiveSparkPlanExec → SparkPlan
- def supportsRowBased: Boolean
Return true if this stage of the plan supports row-based execution.
Return true if this stage of the plan supports row-based execution. A plan can also support columnar execution (see
supportsColumnar). Spark will decide which execution to be called during query planning.- Definition Classes
- SparkPlan
- def toJSON: String
- Definition Classes
- TreeNode
- def toRowBased: SparkPlan
Converts the output of this plan to row-based if it is columnar plan.
Converts the output of this plan to row-based if it is columnar plan.
- Definition Classes
- SparkPlan
- def toString(): String
- Definition Classes
- TreeNode → AnyRef → Any
- def transform(rule: PartialFunction[SparkPlan, SparkPlan]): SparkPlan
- Definition Classes
- TreeNode
- def transformAllExpressions(rule: PartialFunction[Expression, Expression]): AdaptiveSparkPlanExec.this.type
- Definition Classes
- QueryPlan
- def transformAllExpressionsWithPruning(cond: (TreePatternBits) => Boolean, ruleId: RuleId)(rule: PartialFunction[Expression, Expression]): AdaptiveSparkPlanExec.this.type
- Definition Classes
- QueryPlan
- def transformDown(rule: PartialFunction[SparkPlan, SparkPlan]): SparkPlan
- Definition Classes
- TreeNode
- def transformDownWithPruning(cond: (TreePatternBits) => Boolean, ruleId: RuleId)(rule: PartialFunction[SparkPlan, SparkPlan]): SparkPlan
- Definition Classes
- TreeNode
- def transformDownWithSubqueries(f: PartialFunction[SparkPlan, SparkPlan]): SparkPlan
- Definition Classes
- QueryPlan
- def transformDownWithSubqueriesAndPruning(cond: (TreePatternBits) => Boolean, ruleId: RuleId)(f: PartialFunction[SparkPlan, SparkPlan]): SparkPlan
- Definition Classes
- QueryPlan
- def transformExpressions(rule: PartialFunction[Expression, Expression]): AdaptiveSparkPlanExec.this.type
- Definition Classes
- QueryPlan
- def transformExpressionsDown(rule: PartialFunction[Expression, Expression]): AdaptiveSparkPlanExec.this.type
- Definition Classes
- QueryPlan
- def transformExpressionsDownWithPruning(cond: (TreePatternBits) => Boolean, ruleId: RuleId)(rule: PartialFunction[Expression, Expression]): AdaptiveSparkPlanExec.this.type
- Definition Classes
- QueryPlan
- def transformExpressionsUp(rule: PartialFunction[Expression, Expression]): AdaptiveSparkPlanExec.this.type
- Definition Classes
- QueryPlan
- def transformExpressionsUpWithPruning(cond: (TreePatternBits) => Boolean, ruleId: RuleId)(rule: PartialFunction[Expression, Expression]): AdaptiveSparkPlanExec.this.type
- Definition Classes
- QueryPlan
- def transformExpressionsWithPruning(cond: (TreePatternBits) => Boolean, ruleId: RuleId)(rule: PartialFunction[Expression, Expression]): AdaptiveSparkPlanExec.this.type
- Definition Classes
- QueryPlan
- def transformUp(rule: PartialFunction[SparkPlan, SparkPlan]): SparkPlan
- Definition Classes
- TreeNode
- def transformUpWithBeforeAndAfterRuleOnChildren(cond: (SparkPlan) => Boolean, ruleId: RuleId)(rule: PartialFunction[(SparkPlan, SparkPlan), SparkPlan]): SparkPlan
- Definition Classes
- TreeNode
- def transformUpWithNewOutput(rule: PartialFunction[SparkPlan, (SparkPlan, Seq[(Attribute, Attribute)])], skipCond: (SparkPlan) => Boolean, canGetOutput: (SparkPlan) => Boolean): SparkPlan
- Definition Classes
- QueryPlan
- def transformUpWithPruning(cond: (TreePatternBits) => Boolean, ruleId: RuleId)(rule: PartialFunction[SparkPlan, SparkPlan]): SparkPlan
- Definition Classes
- TreeNode
- def transformUpWithSubqueries(f: PartialFunction[SparkPlan, SparkPlan]): SparkPlan
- Definition Classes
- QueryPlan
- def transformWithPruning(cond: (TreePatternBits) => Boolean, ruleId: RuleId)(rule: PartialFunction[SparkPlan, SparkPlan]): SparkPlan
- Definition Classes
- TreeNode
- def transformWithSubqueries(f: PartialFunction[SparkPlan, SparkPlan]): SparkPlan
- Definition Classes
- QueryPlan
- lazy val treePatternBits: BitSet
- Definition Classes
- QueryPlan → TreeNode → TreePatternBits
- def treeString(append: (String) => Unit, verbose: Boolean, addSuffix: Boolean, maxFields: Int, printOperatorId: Boolean): Unit
- Definition Classes
- TreeNode
- final def treeString(verbose: Boolean, addSuffix: Boolean, maxFields: Int, printOperatorId: Boolean): String
- Definition Classes
- TreeNode
- final def treeString: String
- Definition Classes
- TreeNode
- def unsetTagValue[T](tag: TreeNodeTag[T]): Unit
- Definition Classes
- TreeNode
- def vectorTypes: Option[Seq[String]]
The exact java types of the columns that are output in columnar processing mode.
The exact java types of the columns that are output in columnar processing mode. This is a performance optimization for code generation and is optional.
- Definition Classes
- SparkPlan
- def verboseString(maxFields: Int): String
- Definition Classes
- QueryPlan → TreeNode
- def verboseStringWithOperatorId(): String
- Definition Classes
- LeafExecNode → QueryPlan
- def verboseStringWithSuffix(maxFields: Int): String
- Definition Classes
- TreeNode
- final def withNewChildren(newChildren: Seq[SparkPlan]): SparkPlan
- Definition Classes
- TreeNode
- final def withNewChildrenInternal(newChildren: IndexedSeq[SparkPlan]): SparkPlan
- Definition Classes
- LeafLike