Spark学习4： RDD详解

1RDD经典定义

package org.apache.spark.rdd

import java.util.Random

import scala.collection.{mutable, Map}
import scala.collection.mutable.ArrayBuffer
import scala.reflect.{classTag, ClassTag}

import com.clearspring.analytics.stream.cardinality.HyperLogLogPlus
import org.apache.hadoop.io.BytesWritable
import org.apache.hadoop.io.compress.CompressionCodec
import org.apache.hadoop.io.NullWritable
import org.apache.hadoop.io.Text
import org.apache.hadoop.mapred.TextOutputFormat

import org.apache.spark._
import org.apache.spark.Partitioner._
import org.apache.spark.SparkContext._
import org.apache.spark.annotation.{DeveloperApi, Experimental}
import org.apache.spark.api.java.JavaRDD
import org.apache.spark.broadcast.Broadcast
import org.apache.spark.partial.BoundedDouble
import org.apache.spark.partial.CountEvaluator
import org.apache.spark.partial.GroupedCountEvaluator
import org.apache.spark.partial.PartialResult
import org.apache.spark.storage.StorageLevel
import org.apache.spark.util.{BoundedPriorityQueue, Utils}
import org.apache.spark.util.collection.OpenHashMap
import org.apache.spark.util.random.{BernoulliSampler, PoissonSampler, SamplingUtils}

/**
 * A Resilient Distributed Dataset (RDD), the basic abstraction in Spark. Represents an immutable,
 * partitioned collection of elements that can be operated on in parallel. This class contains the
 * basic operations available on all RDDs, such as `map`, `filter`, and `persist`. In addition,
 * [[org.apache.spark.rdd.PairRDDFunctions]] contains operations available only on RDDs of key-value
 * pairs, such as `groupByKey` and `join`;
 * [[org.apache.spark.rdd.DoubleRDDFunctions]] contains operations available only on RDDs of
 * Doubles; and
 * [[org.apache.spark.rdd.SequenceFileRDDFunctions]] contains operations available on RDDs that
 * can be saved as SequenceFiles.
 * These operations are automatically available on any RDD of the right type (e.g. RDD[(Int, Int)]
 * through implicit conversions when you `import org.apache.spark.SparkContext._`.
 *
 * Internally, each RDD is characterized by five main properties:
 *
 *  - A list of partitions
 *  - A function for computing each split
 *  - A list of dependencies on other RDDs
 *  - Optionally, a Partitioner for key-value RDDs (e.g. to say that the RDD is hash-partitioned)
 *  - Optionally, a list of preferred locations to compute each split on (e.g. block locations for
 *    an HDFS file)
 *
 * All of the scheduling and execution in Spark is done based on these methods, allowing each RDD
 * to implement its own way of computing itself. Indeed, users can implement custom RDDs (e.g. for
 * reading data from a new storage system) by overriding these functions. Please refer to the
 * [[http://www.cs.berkeley.edu/~matei/papers/2012/nsdi_spark.pdf Spark paper]] for more details
 * on RDD internals.
 */
abstract class RDD[T: Cla