开发者社区> 问答> 正文

spark 读取s3上数据失败?报错

使用spark 命令行执行

val file = sc.textFile("s3n://***:***@filepath")
file.count()



时报错,不知道啥原因啊。搞了半天,郁闷

java.lang.NullPointerException
at org.apache.hadoop.fs.s3native.NativeS3FileSystem.getFileStatus(NativeS3FileSystem.java:433)
at org.apache.hadoop.fs.Globber.getFileStatus(Globber.java:57)
at org.apache.hadoop.fs.Globber.glob(Globber.java:248)
at org.apache.hadoop.fs.FileSystem.globStatus(FileSystem.java:1642)
at org.apache.hadoop.mapred.FileInputFormat.singleThreadedListStatus(FileInputFormat.java:257)
at org.apache.hadoop.mapred.FileInputFormat.listStatus(FileInputFormat.java:228)
at org.apache.hadoop.mapred.FileInputFormat.getSplits(FileInputFormat.java:304)
at org.apache.spark.rdd.HadoopRDD.getPartitions(HadoopRDD.scala:201)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:205)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:203)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:203)
at org.apache.spark.rdd.MappedRDD.getPartitions(MappedRDD.scala:28)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:205)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:203)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:203)
at org.apache.spark.rdd.FilteredRDD.getPartitions(FilteredRDD.scala:29)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:205)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:203)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:203)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1328)
at org.apache.spark.rdd.RDD.count(RDD.scala:910)
at $iwC$$iwC$$iwC$$iwC.<init>(<console>:17)
at $iwC$$iwC$$iwC.<init>(<console>:22)
at $iwC$$iwC.<init>(<console>:24)
at $iwC.<init>(<console>:26)
at <init>(<console>:28)
at .<init>(<console>:32)
at .<clinit>(<console>)
at .<init>(<console>:7)
at .<clinit>(<console>)
at $print(<console>)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:852)
at org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1125)
at org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:674)
at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:705)
at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:669)
at org.apache.spark.repl.SparkILoop.reallyInterpret$1(SparkILoop.scala:828)
at org.apache.spark.repl.SparkILoop.interpretStartingWith(SparkILoop.scala:873)
at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:785)
at org.apache.spark.repl.SparkILoop.processLine$1(SparkILoop.scala:628)
at org.apache.spark.repl.SparkILoop.innerLoop$1(SparkILoop.scala:636)
at org.apache.spark.repl.SparkILoop.loop(SparkILoop.scala:641)
at org.apache.spark.repl.SparkILoop$$anonfun$process$1.apply$mcZ$sp(SparkILoop.scala:968)
at org.apache.spark.repl.SparkILoop$$anonfun$process$1.apply(SparkILoop.scala:916)
at org.apache.spark.repl.SparkILoop$$anonfun$process$1.apply(SparkILoop.scala:916)
at scala.tools.nsc.util.ScalaClassLoader$.savingContextLoader(ScalaClassLoader.scala:135)
at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:916)
at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:1011)
at org.apache.spark.repl.Main$.main(Main.scala:31)
at org.apache.spark.repl.Main.main(Main.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at org.apache.spark.deploy.SparkSubmit$.launch(SparkSubmit.scala:358)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:75)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)

有谁见过这个问题吗



展开
收起
爱吃鱼的程序员 2020-06-14 17:06:19 626 0
1 条回答
写回答
取消 提交回答
  • https://developer.aliyun.com/profile/5yerqm5bn5yqg?spm=a2c6h.12873639.0.0.6eae304abcjaIB

    <spanstyle="font-size:13.3333330154419px;">通过跟亚马逊方面3天的沟通,与测试发现:<spanstyle="font-size:13.3333330154419px;">endpoint指定global是可以成功的,而且在更新jets3t之后法兰克福Region也可以访问了。但是在访问北京区域时,数据包仍发往global。因为中国区和海外其他区域账号是隔离的,所以造成了s3n无法访问北京区域S3。最后给出结论:<spanstyle="font-size:13.3333330154419px;">在中国区S3n还未能很好地支持您好,我是未入门的spark菜鸟一只,想问您一下这个问题您最后是怎么解决的?最后移植到EMR上了。新加坡区应该是支持的。

    2020-06-15 11:05:53
    赞同 展开评论 打赏
问答排行榜
最热
最新

相关电子书

更多
Hybrid Cloud and Apache Spark 立即下载
Scalable Deep Learning on Spark 立即下载
Comparison of Spark SQL with Hive 立即下载

相关实验场景

更多