将Spark程序的HDFS复制因子从3更改为1
val sparkConf = new SparkConf()
sparkConf.set("spark.driver.maxResultSize", "10g")//.set("autoBroadcastJoinThresho1d","8388608000").set("spark.sql.broadcastTimeout","")
val spark =SparkSession.builder().config(sparkConf).config("spark.sql.crossJoin.enabled","true").appName("indexSimilarity").getOrCreate()
val hconf: org.apache.hadoop.conf.Configuration = spark.sparkContext.hadoopConfiguration
hconf.setInt("dfs.replication", 1)