Spark 2.0：4 行。 IllegalArgumentException：界限必须为正

我正在 Amazon EMR 5.0 上的 Spark 2.0 上尝试一个超级简单的测试程序：

from pyspark.sql.types import Row
from pyspark.sql.types import *
import pyspark.sql.functions as spark_functions

schema = StructType([
    StructField("cola", StringType()),
    StructField("colb", IntegerType()),
])

rows = [
    Row("alpha", 1),
    Row("beta", 2),
    Row("gamma", 3),
    Row("delta", 4)
]

data_frame = spark.createDataFrame(rows, schema)

print("count={}".format(data_frame.count()))

data_frame.write.save("s3a://test3/test_data.parquet", mode="overwrite")

print("done")

结果是：

count=4
Py4JJavaError: An error occurred while calling o85.save.
: org.apache.spark.SparkException: Job aborted.
    at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand$$anonfun$run$1.apply$mcV$sp(InsertIntoHadoopFsRelationCommand.scala:149)
    at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand$$anonfun$run$1.apply(InsertIntoHadoopFsRelationCommand.scala:115)
    at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand$$anonfun$run$1.apply(InsertIntoHadoopFsRelationCommand.scala:115)
    at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:57)
    at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand.run(InsertIntoHadoopFsRelationCommand.scala:115)
    at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:60)
    at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:58)
    at org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:74)
    at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115)
    at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115)
    at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136)
    at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
    at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133)
    at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:114)
    at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:86)
    at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:86)
    at org.apache.spark.sql.execution.datasources.DataSource.write(DataSource.scala:487)
    at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:211)
    at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:194)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:498)
    at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:237)
    at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
    at py4j.Gateway.invoke(Gateway.java:280)
    at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:128)
    at py4j.commands.CallCommand.execute(CallCommand.java:79)
    at py4j.GatewayConnection.run(GatewayConnection.java:211)
    at java.lang.Thread.run(Thread.java:745)
Caused by: java.lang.IllegalArgumentException: bound must be positive
    at java.util.Random.nextInt(Random.java:388)
    at org.apache.hadoop.fs.LocalDirAllocator$AllocatorPerContext.confChanged(LocalDirAllocator.java:305)
    at org.apache.hadoop.fs.LocalDirAllocator$AllocatorPerContext.getLocalPathForWrite(LocalDirAllocator.java:344)
    at org.apache.hadoop.fs.LocalDirAllocator$AllocatorPerContext.createTmpFileForWrite(LocalDirAllocator.java:416)
    at org.apache.hadoop.fs.LocalDirAllocator.createTmpFileForWrite(LocalDirAllocator.java:198)
    at org.apache.hadoop.fs.s3a.S3AOutputStream.<init>(S3AOutputStream.java:87)
    at org.apache.hadoop.fs.s3a.S3AFileSystem.create(S3AFileSystem.java:421)
    at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:913)
    at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:894)
    at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:791)
    at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:780)
    at org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter.commitJob(FileOutputCommitter.java:336)
    at org.apache.parquet.hadoop.ParquetOutputCommitter.commitJob(ParquetOutputCommitter.java:46)
    at org.apache.spark.sql.execution.datasources.BaseWriterContainer.commitJob(WriterContainer.scala:222)
    at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand$$anonfun$run$1.apply$mcV$sp(InsertIntoHadoopFsRelationCommand.scala:144)
    ... 29 more
(<class 'py4j.protocol.Py4JJavaError'>, Py4JJavaError(u'An error occurred while calling o85.save.\n', JavaObject id=o86), <traceback object at 0x7fa65dec5368>)

遇到了同样的问题，经过一番混乱之后，似乎 s3:// 和 s3n:// 可以工作。但它们比 s3a:// 慢很多...我能让 s3a:// 工作的唯一方法是设置一个缓冲区目录，这样它就不会直接从内存进行快速复制 -

hadoopConf=sc._jsc.hadoopConfiguration()
hadoopConf.set("fs.s3a.buffer.dir", "/home/hadoop,/tmp")  

不幸的是，启用该功能后，它并不比普通 s3/s3n 快多少！

编辑：添加这个也可以消除错误，意识到我假设它正在快速复制。不幸的是没有更快... hadoopConf.set("fs.s3a.fast.upload", "true")