Error message

java.lang.UnsatisfiedLinkError: org.apache.hadoop.io.nativeio.NativeIO$POSIX.stat(Ljava/lang/String;)Lorg/apache/hadoop/io/nativeio/NativeIO$POSIX$Stat;
        at org.apache.hadoop.io.nativeio.NativeIO$POSIX.stat(Native Method)
        at org.apache.hadoop.io.nativeio.NativeIO$POSIX.getStat(NativeIO.java:456)
        at org.apache.hadoop.fs.RawLocalFileSystem$DeprecatedRawLocalFileStatus.loadPermissionInfoByNativeIO(RawLocalFileSystem.java:821)
        at org.apache.hadoop.fs.RawLocalFileSystem$DeprecatedRawLocalFileStatus.loadPermissionInfo(RawLocalFileSystem.java:735)
        at org.apache.hadoop.fs.RawLocalFileSystem$DeprecatedRawLocalFileStatus.getPermission(RawLocalFileSystem.java:703)
        at org.apache.hadoop.fs.LocatedFileStatus.<init>(LocatedFileStatus.java:52)
        at org.apache.hadoop.fs.FileSystem$4.next(FileSystem.java:2091)
        at org.apache.hadoop.fs.FileSystem$4.next(FileSystem.java:2071)
        at org.apache.hadoop.fs.FileSystem$5.hasNext(FileSystem.java:2190)
        at org.apache.hudi.table.marker.DirectWriteMarkers.lambda$createdAndMergedDataPaths$69cdea3b$1(DirectWriteMarkers.java:138)
        at org.apache.hudi.client.common.HoodieSparkEngineContext.lambda$flatMap$7d470b86$1(HoodieSparkEngineContext.java:78)
        at org.apache.spark.api.java.JavaRDDLike.$anonfun$flatMap$1(JavaRDDLike.scala:125)
        at scala.collection.Iterator$$anon$11.nextCur(Iterator.scala:484)
        at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:490)
        at scala.collection.Iterator.foreach(Iterator.scala:941)
        at scala.collection.Iterator.foreach$(Iterator.scala:941)
        at scala.collection.AbstractIterator.foreach(Iterator.scala:1429)
        at scala.collection.generic.Growable.$plus$plus$eq(Growable.scala:62)
        at scala.collection.generic.Growable.$plus$plus$eq$(Growable.scala:53)
        at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:105)
        at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:49)
        at scala.collection.TraversableOnce.to(TraversableOnce.scala:315)
        at scala.collection.TraversableOnce.to$(TraversableOnce.scala:313)
        at scala.collection.AbstractIterator.to(Iterator.scala:1429)
        at scala.collection.TraversableOnce.toBuffer(TraversableOnce.scala:307)
        at scala.collection.TraversableOnce.toBuffer$(TraversableOnce.scala:307)
        at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1429)
        at scala.collection.TraversableOnce.toArray(TraversableOnce.scala:294)
        at scala.collection.TraversableOnce.toArray$(TraversableOnce.scala:288)
        at scala.collection.AbstractIterator.toArray(Iterator.scala:1429)
        at org.apache.spark.rdd.RDD.$anonfun$collect$2(RDD.scala:1030)
        at org.apache.spark.SparkContext.$anonfun$runJob$5(SparkContext.scala:2236)
        at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
        at org.apache.spark.scheduler.Task.run(Task.scala:131)
        at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:497)
        at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1439)
        at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:500)
        at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
        at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
        at java.lang.Thread.run(Thread.java:748)

Error reporting reason

Because the Hadoop version loaded at runtime is version 3.2, while the Hadoop version in the cluster is version 3.0.0-cdh6.3.2
this code is different for two different versions

Solution:

Download the spark source code, compile spark by yourself, and change the built-in Hadoop to version 3.0.0-cdh6.3.2