Spark基础随笔：持久化&检查点

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
  /** Persist this RDD with the default storage level (`MEMORY_ONLY`). */
  def persist(): this.type = persist(StorageLevel.MEMORY_ONLY)

  /** Persist this RDD with the default storage level (`MEMORY_ONLY`). */
  def cache(): this.type = persist()

  /**
   * Mark the RDD as non-persistent, and remove all blocks for it from memory and disk.
   *
   * @param blocking Whether to block until all blocks are deleted.
   * @return This RDD.
   */
  def unpersist(blocking: Boolean = true): this.type = {
    logInfo("Removing RDD " + id + " from persistence list")
    sc.unpersistRDD(id, blocking)
    storageLevel = StorageLevel.NONE
    this
  }

1
2
3
4
5
6
7
8
9
10
11
12
13
object StorageLevel {
  val NONE = new StorageLevel(false, false, false, false)
  val DISK_ONLY = new StorageLevel(true, false, false, false)
  val DISK_ONLY_2 = new StorageLevel(true, false, false, false, 2)
  val MEMORY_ONLY = new StorageLevel(false, true, false, true)
  val MEMORY_ONLY_2 = new StorageLevel(false, true, false, true, 2)
  val MEMORY_ONLY_SER = new StorageLevel(false, true, false, false)
  val MEMORY_ONLY_SER_2 = new StorageLevel(false, true, false, false, 2)
  val MEMORY_AND_DISK = new StorageLevel(true, true, false, true)
  val MEMORY_AND_DISK_2 = new StorageLevel(true, true, false, true, 2)
  val MEMORY_AND_DISK_SER = new StorageLevel(true, true, false, false)
  val MEMORY_AND_DISK_SER_2 = new StorageLevel(true, true, false, false, 2)
  val OFF_HEAP = new StorageLevel(false, false, true, false)

1
2
3
4
5
6
7
class StorageLevel private(
    private var _useDisk: Boolean,
    private var _useMemory: Boolean,
    private var _useOffHeap: Boolean,
    private var _deserialized: Boolean,
    private var _replication: Int = 1)
 extends Externalizable 

1
2
3
4
5
6
7
8
9
10
11
12
13
14
  /**
   * Mark this RDD for checkpointing. It will be saved to a file inside the checkpoint
   * directory set with `SparkContext#setCheckpointDir` and all references to its parent
   * RDDs will be removed. This function must be called before any job has been
   * executed on this RDD. It is strongly recommended that this RDD is persisted in
   * memory, otherwise saving it on a file will require recomputation.
   */
  def checkpoint(): Unit = RDDCheckpointData.synchronized {
    if (context.checkpointDir.isEmpty) {
      throw new SparkException("Checkpoint directory has not been set in the SparkContext")
    } else if (checkpointData.isEmpty) {
      checkpointData = Some(new ReliableRDDCheckpointData(this))
    }
  }

1
2
3
4
5
6
7
8
9
/**
 * Enumeration to manage state transitions of an RDD through checkpointing
 * [ Initialized --> checkpointing in progress --> checkpointed ].
 */
private[spark] object CheckpointState extends Enumeration {
  type CheckpointState = Value
  val Initialized, CheckpointingInProgress, Checkpointed = Value
}