spark RDD 详解

什么是RDD

1. Resilient Distributed Dataset(RDD)

• A Resilient Distributed Dataset (RDD), 弹性分布式数据集
• the basic abstraction in Spark. spark中最小的抽象单元
• Represents an immutable,不可变的
• partitioned collection of elements that can be operated on in parallel. 集合元素可分区，进行并行操作

2. RDD定义

abstract class RDD[T: ClassTag](
   @transient private var _sc: SparkContext,
   @transient private var deps: Seq[Dependency[_]]
 ) extends 
 Serializable 
 with Logging {

• abstract RDD是一个抽象类不能直接使用，子类必须实现内部的抽象方法
• Serializable 可序列化进行网络传输
• T: ClassTag 泛型
• Logging log4j 日志

3. RDD五大特性

1）- A list of partitions
一系列的分片
2）- A function for computing each split/partition
每个分片都有一个函数来计算
3）- A list of dependencies on other RDDs RDD
有一系列的父RDD(数据源除外)
4）- Optionally, a Partitioner for key-value RDDs (e.g. to say that the RDD is hash-partitioned)
key-value类型的RDD会有分区器
5）- Optionally, a list of preferred locations to compute each split on (e.g. block locations for an HDFS file)
每个分片计算都有计算数据本地形特点

4. RDD五大特性在源码中的体现

• compute

 /**
   * :: DeveloperApi ::
   * Implemented by subclasses to compute a given partition.
   */
  @DeveloperApi
  //对应第2点
  def compute(split: Partition, context: TaskContext): Iterator[T]

• getPartitions

/**
   * Implemented by subclasses to return the set of partitions in this RDD. This method will only
   * be called once, so it is safe to implement a time-consuming computation in it.
   *
   * The partitions in this array must satisfy the following property:
   *   `rdd.partitions.zipWithIndex.forall { case (partition, index) => partition.index == index }`
   */
   //第1点
  protected def getPartitions: Array[Partition]

• getDependencies

 /**
   * Implemented by subclasses to return how this RDD depends on parent RDDs. This method will only
   * be called once, so it is safe to implement a time-consuming computation in it.
   */
   //第3点
  protected def getDependencies: Seq[Dependency[_]] = deps

• getPreferredLocations

/**
   * Optionally overridden by subclasses to specify placement preferences.
   */
   //第5点
  protected def getPreferredLocations(split: Partition): Seq[String] = Nil
  

• partitioner

 /** Optionally overridden by subclasses to specify how they are partitioned. */
  //第4点
  @transient val partitioner: Option[Partitioner] = None

5. RDD的子类实现

• JdbcRDD

private[spark] class JdbcPartition(idx: Int, val lower: Long, val upper: Long) extends Partition {
  override def index: Int = idx
}


class JdbcRDD[T: ClassTag](
    sc: SparkContext,
    getConnection: () => Connection,
    sql: String,
    lowerBound: Long,
    upperBound: Long,
    numPartitions: Int,
    mapRow: (ResultSet) => T = JdbcRDD.resultSetToObjectArray _)
  extends RDD[T](sc, Nil) with Logging {
************重写getPartitions获取分区list******************
  override def getPartitions: Array[Partition] = {
    // bounds are inclusive, hence the + 1 here and - 1 on end
    val length = BigInt(1) + upperBound - lowerBound
    (0 until numPartitions).map { i =>
      val start = lowerBound + ((i * length) / numPartitions)
      val end = lowerBound + (((i + 1) * length) / numPartitions) - 1
      new JdbcPartition(i, start.toLong, end.toLong)
    }.toArray
  }
************重写compute获取jdbc数据进行处理********************************
  override def compute(thePart: Partition, context: TaskContext): Iterator[T] = new NextIterator[T]
  {
    context.addTaskCompletionListener{ context => closeIfNeeded() }
    val part = thePart.asInstanceOf[JdbcPartition]
    val conn = getConnection()
    val stmt = conn.prepareStatement(sql, ResultSet.TYPE_FORWARD_ONLY, ResultSet.CONCUR_READ_ONLY)

    val url = conn.getMetaData.getURL
    if (url.startsWith("jdbc:mysql:")) {
      // setFetchSize(Integer.MIN_VALUE) is a mysql driver specific way to force
      // streaming results, rather than pulling entire resultset into memory.
      // See the below URL
      // dev.mysql.com/doc/connector-j/5.1/en/connector-j-reference-implementation-notes.html

      stmt.setFetchSize(Integer.MIN_VALUE)
    } else {
      stmt.setFetchSize(100)
    }

    logInfo(s"statement fetch size set to: ${stmt.getFetchSize}")

    stmt.setLong(1, part.lower)
    stmt.setLong(2, part.upper)
    val rs = stmt.executeQuery()

    override def getNext(): T = {
      if (rs.next()) {
        mapRow(rs)
      } else {
        finished = true
        null.asInstanceOf[T]
      }
    }

    override def close() {
      try {
        if (null != rs) {
          rs.close()
        }
      } catch {
        case e: Exception => logWarning("Exception closing resultset", e)
      }
      try {
        if (null != stmt) {
          stmt.close()
        }
      } catch {
        case e: Exception => logWarning("Exception closing statement", e)
      }
      try {
        if (null != conn) {
          conn.close()
        }
        logInfo("closed connection")
      } catch {
        case e: Exception => logWarning("Exception closing connection", e)
      }
    }
  }
}

• HadoopRDD

/**
 * A Spark split class that wraps around a Hadoop InputSplit.
 */
private[spark] class HadoopPartition(rddId: Int, override val index: Int, s: InputSplit)
  extends Partition {

  val inputSplit = new SerializableWritable[InputSplit](s)

  override def hashCode(): Int = 31 * (31 + rddId) + index

  override def equals(other: Any): Boolean = super.equals(other)


}


@DeveloperApi
class HadoopRDD[K, V](
    sc: SparkContext,
    broadcastedConf: Broadcast[SerializableConfiguration],
    initLocalJobConfFuncOpt: Option[JobConf => Unit],
    inputFormatClass: Class[_ <: InputFormat[K, V]],
    keyClass: Class[K],
    valueClass: Class[V],
    minPartitions: Int)
  extends RDD[(K, V)](sc, Nil) with Logging {

  if (initLocalJobConfFuncOpt.isDefined) {
    sparkContext.clean(initLocalJobConfFuncOpt.get)
  }

  def this(
      sc: SparkContext,
      conf: JobConf,
      inputFormatClass: Class[_ <: InputFormat[K, V]],
      keyClass: Class[K],
      valueClass: Class[V],
      minPartitions: Int) = {
    this(
      sc,
      sc.broadcast(new SerializableConfiguration(conf))
        .asInstanceOf[Broadcast[SerializableConfiguration]],
      initLocalJobConfFuncOpt = None,
      inputFormatClass,
      keyClass,
      valueClass,
      minPartitions)
  }

  protected val jobConfCacheKey: String = "rdd_%d_job_conf".format(id)

  protected val inputFormatCacheKey: String = "rdd_%d_input_format".format(id)

  // used to build JobTracker ID
  private val createTime = new Date()

  private val shouldCloneJobConf = sparkContext.conf.getBoolean("spark.hadoop.cloneConf", false)

  private val ignoreCorruptFiles = sparkContext.conf.get(IGNORE_CORRUPT_FILES)

  

  protected def getInputFormat(conf: JobConf): InputFormat[K, V] = {
    val newInputFormat = ReflectionUtils.newInstance(inputFormatClass.asInstanceOf[Class[_]], conf)
      .asInstanceOf[InputFormat[K, V]]
    newInputFormat match {
      case c: Configurable => c.setConf(conf)
      case _ =>
    }
    newInputFormat
  }

  override def getPartitions: Array[Partition] = {
    val jobConf = getJobConf()
    // add the credentials here as this can be called before SparkContext initialized
    SparkHadoopUtil.get.addCredentials(jobConf)
    val inputFormat = getInputFormat(jobConf)
    //获取splits
    val inputSplits = inputFormat.getSplits(jobConf, minPartitions)
    val array = new Array[Partition](inputSplits.size)
    for (i <- 0 until inputSplits.size) {
      array(i) = new HadoopPartition(id, i, inputSplits(i))
    }
    array
  }

  override def compute(theSplit: Partition, context: TaskContext): InterruptibleIterator[(K, V)] = {
    val iter = new NextIterator[(K, V)] {

      private val split = theSplit.asInstanceOf[HadoopPartition]
      logInfo("Input split: " + split.inputSplit)
      private val jobConf = getJobConf()

      private val inputMetrics = context.taskMetrics().inputMetrics
      private val existingBytesRead = inputMetrics.bytesRead

      // Sets InputFileBlockHolder for the file block's information
      split.inputSplit.value match {
        case fs: FileSplit =>
          InputFileBlockHolder.set(fs.getPath.toString, fs.getStart, fs.getLength)
        case _ =>
          InputFileBlockHolder.unset()
      }

      // Find a function that will return the FileSystem bytes read by this thread. Do this before
      // creating RecordReader, because RecordReader's constructor might read some bytes
      private val getBytesReadCallback: Option[() => Long] = split.inputSplit.value match {
        case _: FileSplit | _: CombineFileSplit =>
          Some(SparkHadoopUtil.get.getFSBytesReadOnThreadCallback())
        case _ => None
      }

      // We get our input bytes from thread-local Hadoop FileSystem statistics.
      // If we do a coalesce, however, we are likely to compute multiple partitions in the same
      // task and in the same thread, in which case we need to avoid override values written by
      // previous partitions (SPARK-13071).
      private def updateBytesRead(): Unit = {
        getBytesReadCallback.foreach { getBytesRead =>
          inputMetrics.setBytesRead(existingBytesRead + getBytesRead())
        }
      }
    // 读取分片数据
      private var reader: RecordReader[K, V] = null
      private val inputFormat = getInputFormat(jobConf)
      HadoopRDD.addLocalConfiguration(
        new SimpleDateFormat("yyyyMMddHHmmss", Locale.US).format(createTime),
        context.stageId, theSplit.index, context.attemptNumber, jobConf)

      reader =
        try {
          inputFormat.getRecordReader(split.inputSplit.value, jobConf, Reporter.NULL)
        } catch {
          case e: IOException if ignoreCorruptFiles =>
            logWarning(s"Skipped the rest content in the corrupted file: ${split.inputSplit}", e)
            finished = true
            null
        }
      // Register an on-task-completion callback to close the input stream.
      context.addTaskCompletionListener { context =>
        // Update the bytes read before closing is to make sure lingering bytesRead statistics in
        // this thread get correctly added.
        updateBytesRead()
        closeIfNeeded()
      }