wangyum commented on PR #8908:
URL: https://github.com/apache/hadoop/pull/8908#issuecomment-6572285422
Spark executor log:
```
26/11/02 00:04:16 DEBUG PerformanceAdvisory: Unable to initialize NativeIO
libraries
java.lang.UnsatisfiedLinkError: 'void
org.apache.hadoop.io.nativeio.NativeIO$POSIX.initNativePosix(boolean)'
at org.apache.hadoop.io.nativeio.NativeIO$POSIX.initNativePosix(Native
Method)
at
org.apache.hadoop.io.nativeio.NativeIO$POSIX.<clinit>(NativeIO.java:341)
at org.apache.hadoop.io.nativeio.NativeIO.initNative(Native Method)
at org.apache.hadoop.io.nativeio.NativeIO.<clinit>(NativeIO.java:861)
at
org.apache.hadoop.hdfs.shortcircuit.ShortCircuitShm.<init>(ShortCircuitShm.java:469)
at
org.apache.hadoop.hdfs.shortcircuit.DfsClientShm.<init>(DfsClientShm.java:70)
at
org.apache.hadoop.hdfs.shortcircuit.DfsClientShmManager$EndpointShmManager.requestNewShm(DfsClientShmManager.java:181)
at
org.apache.hadoop.hdfs.shortcircuit.DfsClientShmManager$EndpointShmManager.allocSlot(DfsClientShmManager.java:251)
at
org.apache.hadoop.hdfs.shortcircuit.DfsClientShmManager.allocSlot(DfsClientShmManager.java:417)
at
org.apache.hadoop.hdfs.shortcircuit.ShortCircuitCache.allocShmSlot(ShortCircuitCache.java:1020)
at
org.apache.hadoop.hdfs.client.impl.BlockReaderFactory.createShortCircuitReplicaInfo(BlockReaderFactory.java:535)
at
org.apache.hadoop.hdfs.shortcircuit.ShortCircuitCache.create(ShortCircuitCache.java:800)
at
org.apache.hadoop.hdfs.shortcircuit.ShortCircuitCache.fetchOrCreate(ShortCircuitCache.java:737)
at
org.apache.hadoop.hdfs.client.impl.BlockReaderFactory.getBlockReaderLocal(BlockReaderFactory.java:483)
at
org.apache.hadoop.hdfs.client.impl.BlockReaderFactory.build(BlockReaderFactory.java:360)
at
org.apache.hadoop.hdfs.DFSInputStream.getBlockReader(DFSInputStream.java:723)
at
org.apache.hadoop.hdfs.DFSInputStream.blockSeekTo(DFSInputStream.java:653)
at
org.apache.hadoop.hdfs.DFSInputStream.readWithStrategy(DFSInputStream.java:887)
at org.apache.hadoop.hdfs.DFSInputStream.read(DFSInputStream.java:960)
at org.apache.hadoop.hdfs.DFSInputStream.read(DFSInputStream.java:773)
at java.base/java.io.FilterInputStream.read(FilterInputStream.java:71)
at
org.apache.parquet.io.DelegatingSeekableInputStream.read(DelegatingSeekableInputStream.java:61)
at
org.apache.parquet.bytes.BytesUtils.readIntLittleEndian(BytesUtils.java:87)
at
org.apache.parquet.hadoop.ParquetFileReader.readFooter(ParquetFileReader.java:607)
at
org.apache.parquet.hadoop.ParquetFileReader.readFooter(ParquetFileReader.java:578)
at
org.apache.parquet.hadoop.ParquetFileReader.<init>(ParquetFileReader.java:971)
at
org.apache.parquet.hadoop.ParquetFileReader.open(ParquetFileReader.java:744)
at
org.apache.spark.sql.execution.datasources.parquet.ParquetFooterReader.openFileAndReadFooter(ParquetFooterReader.java:102)
at
org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormat.$anonfun$buildParquetReader$4(ParquetFileFormat.scala:331)
at
org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormat.$anonfun$buildParquetReader$13(ParquetFileFormat.scala:424)
at
org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.org$apache$spark$sql$execution$datasources$FileScanRDD$$anon$$readCurrentFile(FileScanRDD.scala:242)
at
org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.nextIterator(FileScanRDD.scala:302)
at
org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext0(FileScanRDD.scala:142)
at
org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:151)
at
org.apache.spark.sql.execution.FileSourceScanExec$$anon$1.hasNext(DataSourceScanExec.scala:877)
at
org.apache.spark.sql.execution.ColumnarToRowExec$.advanceBatch(Columnar.scala:232)
at
org.apache.spark.sql.execution.ColumnarToRowExec.advanceBatch(Columnar.scala)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.columnartorow_nextBatch_0$(Unknown
Source)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown
Source)
at
org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:55)
at
org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:50)
at
org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$2(SparkPlan.scala:419)
at
org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:960)
at
org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:960)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:57)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:374)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:338)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at
org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:223)
at org.apache.spark.scheduler.Task.run(Task.scala:147)
at
org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$5(Executor.scala:912)
at
org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:86)
at
org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:83)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:97)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:915)
at
java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1090)
at
java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:614)
at java.base/java.lang.Thread.run(Thread.java:1474)
26/11/02 00:04:16 DEBUG PerformanceAdvisory: Unable to initialize NativeIO
libraries
java.lang.NoSuchFieldError: workaroundNonThreadSafePasswdCalls
at org.apache.hadoop.io.nativeio.NativeIO.initNative(Native Method)
at org.apache.hadoop.io.nativeio.NativeIO.<clinit>(NativeIO.java:861)
at
org.apache.hadoop.hdfs.shortcircuit.ShortCircuitShm.<init>(ShortCircuitShm.java:469)
at
org.apache.hadoop.hdfs.shortcircuit.DfsClientShm.<init>(DfsClientShm.java:70)
at
org.apache.hadoop.hdfs.shortcircuit.DfsClientShmManager$EndpointShmManager.requestNewShm(DfsClientShmManager.java:181)
at
org.apache.hadoop.hdfs.shortcircuit.DfsClientShmManager$EndpointShmManager.allocSlot(DfsClientShmManager.java:251)
at
org.apache.hadoop.hdfs.shortcircuit.DfsClientShmManager.allocSlot(DfsClientShmManager.java:417)
at
org.apache.hadoop.hdfs.shortcircuit.ShortCircuitCache.allocShmSlot(ShortCircuitCache.java:1020)
at
org.apache.hadoop.hdfs.client.impl.BlockReaderFactory.createShortCircuitReplicaInfo(BlockReaderFactory.java:535)
at
org.apache.hadoop.hdfs.shortcircuit.ShortCircuitCache.create(ShortCircuitCache.java:800)
at
org.apache.hadoop.hdfs.shortcircuit.ShortCircuitCache.fetchOrCreate(ShortCircuitCache.java:737)
at
org.apache.hadoop.hdfs.client.impl.BlockReaderFactory.getBlockReaderLocal(BlockReaderFactory.java:483)
at
org.apache.hadoop.hdfs.client.impl.BlockReaderFactory.build(BlockReaderFactory.java:360)
at
org.apache.hadoop.hdfs.DFSInputStream.getBlockReader(DFSInputStream.java:723)
at
org.apache.hadoop.hdfs.DFSInputStream.blockSeekTo(DFSInputStream.java:653)
at
org.apache.hadoop.hdfs.DFSInputStream.readWithStrategy(DFSInputStream.java:887)
at org.apache.hadoop.hdfs.DFSInputStream.read(DFSInputStream.java:960)
at org.apache.hadoop.hdfs.DFSInputStream.read(DFSInputStream.java:773)
at java.base/java.io.FilterInputStream.read(FilterInputStream.java:71)
at
org.apache.parquet.io.DelegatingSeekableInputStream.read(DelegatingSeekableInputStream.java:61)
at
org.apache.parquet.bytes.BytesUtils.readIntLittleEndian(BytesUtils.java:87)
at
org.apache.parquet.hadoop.ParquetFileReader.readFooter(ParquetFileReader.java:607)
at
org.apache.parquet.hadoop.ParquetFileReader.readFooter(ParquetFileReader.java:578)
at
org.apache.parquet.hadoop.ParquetFileReader.<init>(ParquetFileReader.java:971)
at
org.apache.parquet.hadoop.ParquetFileReader.open(ParquetFileReader.java:744)
at
org.apache.spark.sql.execution.datasources.parquet.ParquetFooterReader.openFileAndReadFooter(ParquetFooterReader.java:102)
at
org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormat.$anonfun$buildParquetReader$4(ParquetFileFormat.scala:331)
at
org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormat.$anonfun$buildParquetReader$13(ParquetFileFormat.scala:424)
at
org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.org$apache$spark$sql$execution$datasources$FileScanRDD$$anon$$readCurrentFile(FileScanRDD.scala:242)
at
org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.nextIterator(FileScanRDD.scala:302)
at
org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext0(FileScanRDD.scala:142)
at
org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:151)
at
org.apache.spark.sql.execution.FileSourceScanExec$$anon$1.hasNext(DataSourceScanExec.scala:877)
at
org.apache.spark.sql.execution.ColumnarToRowExec$.advanceBatch(Columnar.scala:232)
at
org.apache.spark.sql.execution.ColumnarToRowExec.advanceBatch(Columnar.scala)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.columnartorow_nextBatch_0$(Unknown
Source)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown
Source)
at
org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:55)
at
org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:50)
at
org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$2(SparkPlan.scala:419)
at
org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:960)
at
org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:960)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:57)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:374)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:338)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at
org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:223)
at org.apache.spark.scheduler.Task.run(Task.scala:147)
at
org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$5(Executor.scala:912)
at
org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:86)
at
org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:83)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:97)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:915)
at
java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1090)
at
java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:614)
at java.base/java.lang.Thread.run(Thread.java:1474)
26/11/02 00:04:16 WARN ShortCircuitCache: ShortCircuitCache(0x1e3dd5c2):
failed to load 3421868755_BP-1855921606-10.162.206.182-1754384840656
java.lang.UnsupportedOperationException: NativeIO is not available.
at
org.apache.hadoop.hdfs.shortcircuit.ShortCircuitShm.<init>(ShortCircuitShm.java:470)
at
org.apache.hadoop.hdfs.shortcircuit.DfsClientShm.<init>(DfsClientShm.java:70)
at
org.apache.hadoop.hdfs.shortcircuit.DfsClientShmManager$EndpointShmManager.requestNewShm(DfsClientShmManager.java:181)
at
org.apache.hadoop.hdfs.shortcircuit.DfsClientShmManager$EndpointShmManager.allocSlot(DfsClientShmManager.java:251)
at
org.apache.hadoop.hdfs.shortcircuit.DfsClientShmManager.allocSlot(DfsClientShmManager.java:417)
at
org.apache.hadoop.hdfs.shortcircuit.ShortCircuitCache.allocShmSlot(ShortCircuitCache.java:1020)
at
org.apache.hadoop.hdfs.client.impl.BlockReaderFactory.createShortCircuitReplicaInfo(BlockReaderFactory.java:535)
at
org.apache.hadoop.hdfs.shortcircuit.ShortCircuitCache.create(ShortCircuitCache.java:800)
at
org.apache.hadoop.hdfs.shortcircuit.ShortCircuitCache.fetchOrCreate(ShortCircuitCache.java:737)
at
org.apache.hadoop.hdfs.client.impl.BlockReaderFactory.getBlockReaderLocal(BlockReaderFactory.java:483)
at
org.apache.hadoop.hdfs.client.impl.BlockReaderFactory.build(BlockReaderFactory.java:360)
at
org.apache.hadoop.hdfs.DFSInputStream.getBlockReader(DFSInputStream.java:723)
at
org.apache.hadoop.hdfs.DFSInputStream.blockSeekTo(DFSInputStream.java:653)
at
org.apache.hadoop.hdfs.DFSInputStream.readWithStrategy(DFSInputStream.java:887)
at org.apache.hadoop.hdfs.DFSInputStream.read(DFSInputStream.java:960)
at org.apache.hadoop.hdfs.DFSInputStream.read(DFSInputStream.java:773)
at java.base/java.io.FilterInputStream.read(FilterInputStream.java:71)
at
org.apache.parquet.io.DelegatingSeekableInputStream.read(DelegatingSeekableInputStream.java:61)
at
org.apache.parquet.bytes.BytesUtils.readIntLittleEndian(BytesUtils.java:87)
at
org.apache.parquet.hadoop.ParquetFileReader.readFooter(ParquetFileReader.java:607)
at
org.apache.parquet.hadoop.ParquetFileReader.readFooter(ParquetFileReader.java:578)
at
org.apache.parquet.hadoop.ParquetFileReader.<init>(ParquetFileReader.java:971)
at
org.apache.parquet.hadoop.ParquetFileReader.open(ParquetFileReader.java:744)
at
org.apache.spark.sql.execution.datasources.parquet.ParquetFooterReader.openFileAndReadFooter(ParquetFooterReader.java:102)
at
org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormat.$anonfun$buildParquetReader$4(ParquetFileFormat.scala:331)
at
org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormat.$anonfun$buildParquetReader$13(ParquetFileFormat.scala:424)
at
org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.org$apache$spark$sql$execution$datasources$FileScanRDD$$anon$$readCurrentFile(FileScanRDD.scala:242)
at
org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.nextIterator(FileScanRDD.scala:302)
at
org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext0(FileScanRDD.scala:142)
at
org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:151)
at
org.apache.spark.sql.execution.FileSourceScanExec$$anon$1.hasNext(DataSourceScanExec.scala:877)
at
org.apache.spark.sql.execution.ColumnarToRowExec$.advanceBatch(Columnar.scala:232)
at
org.apache.spark.sql.execution.ColumnarToRowExec.advanceBatch(Columnar.scala)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.columnartorow_nextBatch_0$(Unknown
Source)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown
Source)
at
org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:55)
at
org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:50)
at
org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$2(SparkPlan.scala:419)
at
org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:960)
at
org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:960)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:57)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:374)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:338)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at
org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:223)
at org.apache.spark.scheduler.Task.run(Task.scala:147)
at
org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$5(Executor.scala:912)
at
org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:86)
at
org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:83)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:97)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:915)
at
java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1090)
at
java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:614)
at java.base/java.lang.Thread.run(Thread.java:1474)
```
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
