wqwl611 opened a new issue #4690:
URL: https://github.com/apache/hudi/issues/4690
* Hudi version : 0.10
* Spark version : 3.2
* Hive version :
* Hadoop version :2.7
* Storage (HDFS/S3/GCS..) : hdfs
Caused by: org.apache.hudi.exception.HoodieIOException: Failed to read
footer for parquet
hdfs://ns/user/.../1e4957b3-efff-47f3-b993-ef7c56538a3d-0_8-526-10774_20220126193401513.parquet
at
org.apache.hudi.common.util.ParquetUtils.readMetadata(ParquetUtils.java:185)
at
org.apache.hudi.common.util.ParquetUtils.readFooter(ParquetUtils.java:201)
at
org.apache.hudi.common.util.BaseFileUtils.readMinMaxRecordKeys(BaseFileUtils.java:109)
at
org.apache.hudi.io.storage.HoodieParquetReader.readMinMaxRecordKeys(HoodieParquetReader.java:49)
at
org.apache.hudi.io.HoodieRangeInfoHandle.getMinMaxKeys(HoodieRangeInfoHandle.java:39)
at
org.apache.hudi.index.bloom.HoodieBloomIndex.lambda$loadInvolvedFiles$4cbadf07$1(HoodieBloomIndex.java:149)
at
org.apache.spark.api.java.JavaPairRDD$.$anonfun$toScalaFunction$1(JavaPairRDD.scala:1070)
at scala.collection.Iterator$$anon$10.next(Iterator.scala:461)
at scala.collection.Iterator.foreach(Iterator.scala:943)
at scala.collection.Iterator.foreach$(Iterator.scala:943)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1431)
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$eq(ArrayBuffer.scala:49)
at scala.collection.TraversableOnce.to(TraversableOnce.scala:366)
at scala.collection.TraversableOnce.to$(TraversableOnce.scala:364)
at scala.collection.AbstractIterator.to(Iterator.scala:1431)
at scala.collection.TraversableOnce.toBuffer(TraversableOnce.scala:358)
at scala.collection.TraversableOnce.toBuffer$(TraversableOnce.scala:358)
at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1431)
at scala.collection.TraversableOnce.toArray(TraversableOnce.scala:345)
at scala.collection.TraversableOnce.toArray$(TraversableOnce.scala:339)
at scala.collection.AbstractIterator.toArray(Iterator.scala:1431)
at org.apache.spark.rdd.RDD.$anonfun$collect$2(RDD.scala:1030)
at
org.apache.spark.SparkContext.$anonfun$runJob$5(SparkContext.scala:2254)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:131)
at
org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:506)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1489)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:509)
... 3 more
Caused by: java.io.FileNotFoundException: File does not exist:
hdfs://ns/.../1e4957b3-efff-47f3-b993-ef7c56538a3d-0_8-526-10774_20220126193401513.parquet
at
org.apache.hadoop.hdfs.DistributedFileSystem$22.doCall(DistributedFileSystem.java:1289)
at
org.apache.hadoop.hdfs.DistributedFileSystem$22.doCall(DistributedFileSystem.java:1281)
at
org.apache.hadoop.fs.FileSystemLinkResolver.resolve(FileSystemLinkResolver.java:81)
at
org.apache.hadoop.hdfs.DistributedFileSystem.getFileStatus(DistributedFileSystem.java:1297)
at
org.apache.parquet.hadoop.util.HadoopInputFile.fromPath(HadoopInputFile.java:39)
at
org.apache.parquet.hadoop.ParquetFileReader.readFooter(ParquetFileReader.java:469)
at
org.apache.parquet.hadoop.ParquetFileReader.readFooter(ParquetFileReader.java:454)
at
org.apache.hudi.common.util.ParquetUtils.readMetadata(ParquetUtils.java:183)
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
