Details
-
Bug
-
Status: Resolved
-
Major
-
Resolution: Invalid
-
2.2.0
-
None
-
None
-
spark2.2.0 ,scala 2.11.8 , hadoop-client2.6.0
-
Important
Description
class Exec3 { private val exec: SparkConf = new SparkConf().setMaster("local[1]").setAppName("exec3") private val context = new SparkContext(exec) context.setCheckpointDir("checkPoint") /** * get total number by key * in this project desired results are ("apple",25) ("huwei",20) * but in fact i get ("apple",150) ("huawei",20) * when i change it to local[3] the result is correct * i want to know which cause it and how to slove it */ @Test def testError(): Unit ={ val rdd = context.parallelize(Seq(("apple", 10), ("apple", 15), ("huawei", 20))) rdd.aggregateByKey(1.0)( seqOp = (zero, price) => price * zero, combOp = (curr, agg) => curr + agg).collect().foreach(println(_)) context.stop() } }