FileSourceStrategy

A strategy for planning scans over collections of files that might be partitioned or bucketed by user specified columns.

At a high level planning occurs in several phases:

Split filters by when they need to be evaluated.
Prune the schema of the data requested based on any projections present. Today this pruning is only done on top level columns, but formats should support pruning of nested columns as well.
Construct a reader function by passing filters and the schema into the FileFormat.
Using a partition pruning predicates, enumerate the list of files that should be read.
Split the files into tasks and construct a FileScanRDD.
Add any projection or filters that must be evaluated after the scan.

Files are assigned into tasks using the following algorithm:

If the table is bucketed, group files by bucket id into the correct number of partitions.
If the table is not bucketed or bucketing is turned off:
- If any file is larger than the threshold, split it into pieces based on that threshold
- Sort the files by decreasing file size.
- Assign the ordered files to buckets using the following algorithm. If the current partition is under the threshold with the addition of the next file, add it. If not, open a new bucket and add it. Proceed to the next file.

Linear Supertypes

SparkStrategy, GenericStrategy[SparkPlan], internal.Logging, AnyRef, Any

Value Members

final def !=(arg0: Any): Boolean

Definition Classes
AnyRef → Any
final def ##(): Int

Definition Classes
AnyRef → Any
final def ==(arg0: Any): Boolean

Definition Classes
AnyRef → Any
def apply(plan: LogicalPlan): Seq[SparkPlan]

Definition Classes
FileSourceStrategy → GenericStrategy
final def asInstanceOf[T0]: T0

Definition Classes
Any
def clone(): AnyRef

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
final def eq(arg0: AnyRef): Boolean

Definition Classes
AnyRef
def equals(arg0: Any): Boolean

Definition Classes
AnyRef → Any
def finalize(): Unit

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( classOf[java.lang.Throwable] )
final def getClass(): Class[_]

Definition Classes
AnyRef → Any
def hashCode(): Int

Definition Classes
AnyRef → Any
def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean = false): Boolean

Attributes
protected
Definition Classes
Logging
def initializeLogIfNecessary(isInterpreter: Boolean): Unit

Attributes
protected
Definition Classes
Logging
final def isInstanceOf[T0]: Boolean

Definition Classes
Any
def isTraceEnabled(): Boolean

Attributes
protected
Definition Classes
Logging
def log: Logger

Attributes
protected
Definition Classes
Logging
def logDebug(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logDebug(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
def logError(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logError(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
def logInfo(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logInfo(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
def logName: String

Attributes
protected
Definition Classes
Logging
def logTrace(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logTrace(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
def logWarning(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logWarning(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
final def ne(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def notify(): Unit

Definition Classes
AnyRef
final def notifyAll(): Unit

Definition Classes
AnyRef
def planLater(plan: LogicalPlan): SparkPlan

Returns a placeholder for a physical plan that executes plan.
Returns a placeholder for a physical plan that executes plan. This placeholder will be filled in automatically by the QueryPlanner using the other execution strategies that are available.

Attributes
protected
Definition Classes
SparkStrategy → GenericStrategy
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes
AnyRef
def toString(): String

Definition Classes
AnyRef → Any
final def wait(): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long, arg1: Int): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )

Related Doc: package datasources

object FileSourceStrategy extends Strategy with internal.Logging

Value Members

final def !=(arg0: Any): Boolean

final def ##(): Int

final def ==(arg0: Any): Boolean

def apply(plan: LogicalPlan): Seq[SparkPlan]

final def asInstanceOf[T0]: T0

def clone(): AnyRef

final def eq(arg0: AnyRef): Boolean

def equals(arg0: Any): Boolean

def finalize(): Unit

final def getClass(): Class[_]

def hashCode(): Int

def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean = false): Boolean

def initializeLogIfNecessary(isInterpreter: Boolean): Unit

final def isInstanceOf[T0]: Boolean

def isTraceEnabled(): Boolean

def log: Logger

def logDebug(msg: ⇒ String, throwable: Throwable): Unit

def logDebug(msg: ⇒ String): Unit

def logError(msg: ⇒ String, throwable: Throwable): Unit

def logError(msg: ⇒ String): Unit

def logInfo(msg: ⇒ String, throwable: Throwable): Unit

def logInfo(msg: ⇒ String): Unit

def logName: String

def logTrace(msg: ⇒ String, throwable: Throwable): Unit

def logTrace(msg: ⇒ String): Unit

def logWarning(msg: ⇒ String, throwable: Throwable): Unit

def logWarning(msg: ⇒ String): Unit

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

def planLater(plan: LogicalPlan): SparkPlan

final def synchronized[T0](arg0: ⇒ T0): T0

def toString(): String

final def wait(): Unit

final def wait(arg0: Long, arg1: Int): Unit

final def wait(arg0: Long): Unit

Inherited from SparkStrategy

Inherited from GenericStrategy[SparkPlan]

Inherited from internal.Logging

Inherited from AnyRef

Inherited from Any

Ungrouped