show（）/ count（）永远不会完成while show（）快速运行

我在本地运行Spark并且出现了一个奇怪的问题。基本上，我可以使用DataFrame的show（）方法输出任意数量的行，但是，当我尝试使用count（）或collect（）（甚至是很少量的数据）时，Spark就会停留在该阶段。永远不会完成它的工作。我使用gradle来构建和运行。show（）/ count（）永远不会完成while show（）快速运行

当我运行

./gradlew clean run

程序卡住在

> Building 83% > :run

什么会导致这个问题？这是代码。

val moviesRatingsDF = MongoSpark.load(sc).toDF().select("movieId", "userId","rating") 

    val movieRatingsDF = moviesRatingsDF 
     .groupBy("movieId") 
     .pivot("userId") 
     .max("rating") 
     .na.fill(0) 

    val ratingColumns = movieRatingsDF.columns.drop(1) // drop the name column 

    val movieRatingsDS:Dataset[MovieRatingsVector] = movieRatingsDF 
     .select(col("movieId").as("movie_id"), array(ratingColumns.map(x => col(x)): _*).as("ratings")) 
     .as[MovieRatingsVector] 

    val moviePairs = movieRatingsDS.withColumnRenamed("ratings", "ratings1") 
     .withColumnRenamed("movie_id", "movie_id1") 
     .crossJoin(movieRatingsDS.withColumnRenamed("ratings", "ratings2").withColumnRenamed("movie_id", "movie_id2")) 
     .filter(col("movie_id1") < col("movie_id2")) 

    val movieSimilarities = moviePairs.map(row => { 
     val ratings1 = sc.parallelize(row.getAs[Seq[Double]]("ratings1")) 
     val ratings2 = sc.parallelize(row.getAs[Seq[Double]]("ratings2")) 
     val corr:Double = Statistics.corr(ratings1, ratings2) 

     MovieSimilarity(row.getAs[Long]("movie_id1"), row.getAs[Long]("movie_id2"), corr) 
    }).cache() 


    val collectedData = movieSimilarities.collect() 
    println(collectedData.length) 

    log.warn("I'm done") //never gets here 

    close