o

org.apache.spark.sql.execution.adaptive

OptimizeSkewInRebalancePartitions

object OptimizeSkewInRebalancePartitions extends Rule[SparkPlan] with AQEShuffleReadRule

A rule to optimize the skewed shuffle partitions in RebalancePartitions based on the map output statistics, which can avoid data skew that hurt performance.

We use ADVISORY_PARTITION_SIZE_IN_BYTES size to decide if a partition should be optimized. Let's say we have 3 maps with 3 shuffle partitions, and assuming r1 has data skew issue. the map side looks like: m0:[b0, b1, b2], m1:[b0, b1, b2], m2:[b0, b1, b2] and the reduce side looks like: (without this rule) r1[m0-b1, m1-b1, m2-b1] / \ r0:[m0-b0, m1-b0, m2-b0], r1-0:[m0-b1], r1-1:[m1-b1], r1-2:[m2-b1], r2[m0-b2, m1-b2, m2-b2]

Linear Supertypes
AQEShuffleReadRule, Rule[SparkPlan], Logging, SQLConfHelper, AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. OptimizeSkewInRebalancePartitions
  2. AQEShuffleReadRule
  3. Rule
  4. Logging
  5. SQLConfHelper
  6. AnyRef
  7. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. Protected

Type Members

  1. implicit class LogStringContext extends AnyRef
    Definition Classes
    Logging

Value Members

  1. final def !=(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  2. final def ##: Int
    Definition Classes
    AnyRef → Any
  3. final def ==(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  4. def MDC(key: LogKey, value: Any): MDC
    Attributes
    protected
    Definition Classes
    Logging
  5. def apply(plan: SparkPlan): SparkPlan
    Definition Classes
    OptimizeSkewInRebalancePartitions → Rule
  6. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  7. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.CloneNotSupportedException]) @IntrinsicCandidate() @native()
  8. def conf: SQLConf
    Definition Classes
    SQLConfHelper
  9. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  10. def equals(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef → Any
  11. final def getClass(): Class[_ <: AnyRef]
    Definition Classes
    AnyRef → Any
    Annotations
    @IntrinsicCandidate() @native()
  12. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @IntrinsicCandidate() @native()
  13. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  14. def initializeLogIfNecessary(isInterpreter: Boolean): Unit
    Attributes
    protected
    Definition Classes
    Logging
  15. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  16. def isSupported(shuffle: ShuffleExchangeLike): Boolean
    Attributes
    protected
    Definition Classes
    AQEShuffleReadRule
  17. def isTraceEnabled(): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  18. def log: Logger
    Attributes
    protected
    Definition Classes
    Logging
  19. def logBasedOnLevel(level: Level)(f: => MessageWithContext): Unit
    Attributes
    protected
    Definition Classes
    Logging
  20. def logDebug(msg: => String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  21. def logDebug(entry: LogEntry, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  22. def logDebug(entry: LogEntry): Unit
    Attributes
    protected
    Definition Classes
    Logging
  23. def logDebug(msg: => String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  24. def logError(msg: => String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  25. def logError(entry: LogEntry, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  26. def logError(entry: LogEntry): Unit
    Attributes
    protected
    Definition Classes
    Logging
  27. def logError(msg: => String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  28. def logInfo(msg: => String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  29. def logInfo(entry: LogEntry, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  30. def logInfo(entry: LogEntry): Unit
    Attributes
    protected
    Definition Classes
    Logging
  31. def logInfo(msg: => String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  32. def logName: String
    Attributes
    protected
    Definition Classes
    Logging
  33. def logTrace(msg: => String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  34. def logTrace(entry: LogEntry, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  35. def logTrace(entry: LogEntry): Unit
    Attributes
    protected
    Definition Classes
    Logging
  36. def logTrace(msg: => String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  37. def logWarning(msg: => String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  38. def logWarning(entry: LogEntry, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  39. def logWarning(entry: LogEntry): Unit
    Attributes
    protected
    Definition Classes
    Logging
  40. def logWarning(msg: => String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  41. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  42. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @IntrinsicCandidate() @native()
  43. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @IntrinsicCandidate() @native()
  44. lazy val ruleId: RuleId
    Attributes
    protected
    Definition Classes
    Rule
  45. val ruleName: String
    Definition Classes
    Rule
  46. val supportedShuffleOrigins: Seq[ShuffleOrigin]

    Returns the list of ShuffleOrigins supported by this rule.

    Returns the list of ShuffleOrigins supported by this rule.

    Definition Classes
    OptimizeSkewInRebalancePartitions → AQEShuffleReadRule
  47. final def synchronized[T0](arg0: => T0): T0
    Definition Classes
    AnyRef
  48. def toString(): String
    Definition Classes
    AnyRef → Any
  49. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.InterruptedException])
  50. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.InterruptedException]) @native()
  51. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.InterruptedException])
  52. def withLogContext(context: Map[String, String])(body: => Unit): Unit
    Attributes
    protected
    Definition Classes
    Logging
  53. def withSQLConf[T](pairs: (String, String)*)(f: => T): T
    Attributes
    protected
    Definition Classes
    SQLConfHelper

Deprecated Value Members

  1. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.Throwable]) @Deprecated
    Deprecated

    (Since version 9)

Inherited from AQEShuffleReadRule

Inherited from Rule[SparkPlan]

Inherited from Logging

Inherited from SQLConfHelper

Inherited from AnyRef

Inherited from Any

Ungrouped