SparkRDD之checkpoint

计算两个RDD之间的笛卡尔积（即第一个RDD的每个项与第二个RDD的每个项连接）并将它们作为新的RDD返回。 （警告：使用此功能时要小心。！内存消耗很快就会成为问题！）

java示例如下:

package com.cb.spark.sparkrdd;

import java.util.Arrays;

import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;

public class CheckpoinExample {
	public static void main(String[] args) {
		SparkConf conf = new SparkConf().setAppName("AggregateByKey").setMaster("local");
		JavaSparkContext jsc = new JavaSparkContext(conf);
		jsc.setCheckpointDir("./checkpoint_path");
		JavaRDD<Integer> javaRDD = jsc.parallelize(Arrays.asList(1, 2, 3, 4, 5, 6));
		javaRDD.checkpoint();
		System.out.println(javaRDD.count());
		jsc.stop();
	}
}

scala示例如下：

package com.cb.spark.core

import org.apache.spark.SparkConf
import org.apache.spark.SparkContext

object Checkpoint {
  def main(args: Array[String]): Unit = {
    val conf = new SparkConf()
      .setAppName("Checkpoint")
      .setMaster("local")
    val sc = new SparkContext(conf)
    sc.setLogLevel("ERROR")

    val z = sc.parallelize(List("a", "b", "c", "d", "e", "f"), 2)
    sc.setCheckpointDir("./checkpoint_path")
    z.checkpoint()
    sc.stop()
  }
}