大数据开发-从cogroup的实现来看join是宽依赖还是窄依赖
前面一篇文章提到大数据开发-Spark Join原理详解,本文从源码角度来看cogroup 的join实现 1.分析下面的代码 import org.apache.spark.rdd.RDD import org.apache.spark.{SparkConf, SparkContext} object JoinDemo { def main(args: Array[String]): Unit = { val conf = new SparkConf().setAppName(this.getClass.getCanonicalName.init).setMaster("local[*]") val sc = new SparkContext(conf) sc.setLogLevel("WARN") val random = scala.util.Random val col1 = Range(1, 50).map(idx => (random.nextInt(10), s"user$idx")) val col2 = Array((0, "BJ"), (1, "SH"), (...

