У меня есть простой код ниже для чтения паркетного файла из S3 с помощью S3a
import os
from pyspark.sql import SparkSession
import configparser
# os.environ['PYSPARK_SUBMIT_ARGS'] = "--packages=org.apache.hadoop:hadoop-aws:2.7.3 pyspark-shell"
# Get the AWS credentials for the mlandexps profile using configparser library
config = configparser.ConfigParser()
config.read(os.path.expanduser("~/.aws/credentials"))
access_key = config.get("mlandexps", "aws_access_key_id")
secret_key = config.get("mlandexps", "aws_secret_access_key")
print("Access Key : %s" % access_key)
print("Secret Key : %s" % secret_key)
# Create a Spark session
spark = SparkSession \
.builder \
.master("local") \
.appName("ReadFilesFromS3TestUsingS3a") \
.getOrCreate()
sc = spark.sparkContext
hadoop_conf=sc._jsc.hadoopConfiguration()
hadoop_conf.set("fs.s3a.endpoint", "s3.amazonaws.com")
hadoop_conf.set("fs.s3a.access.key", access_key)
hadoop_conf.set("fs.s3a.secret.key", secret_key)
hadoop_conf.set("fs.s3a.impl", "org.apache.hadoop.fs.s3a.S3AFileSystem");
df = spark.read.parquet("s3a://rppatwa/BlackWidowData/part-00000-5b22d5ed-2be1-4343-9aa2-53e2133916ae-c000.snappy.parquet")
df.printSchema()
df.show(3)
Я получаю следующее исключение, когда запускаю его локально
Py4JJavaError Traceback (most recent call last)
<ipython-input-17-ffd16a1a558f> in <module>
37 print("Spark Context : {}".format(sc))
38
---> 39 df = spark.read.parquet("s3a://rppatwa/BlackWidowData/part-00000-5b22d5ed-2be1-4343-9aa2-53e2133916ae-c000.snappy.parquet")
40 df.printSchema()
41 df.show(3)
~/Downloads/Spark/spark-2.4.5-bin-hadoop2.7/python/pyspark/sql/readwriter.py in parquet(self, *paths)
314 [('name', 'string'), ('year', 'int'), ('month', 'int'), ('day', 'int')]
315 """
--> 316 return self._df(self._jreader.parquet(_to_seq(self._spark._sc, paths)))
317
318 @ignore_unicode_prefix
~/Downloads/Spark/spark-2.4.5-bin-hadoop2.7/python/lib/py4j-0.10.7-src.zip/py4j/java_gateway.py in __call__(self, *args)
1255 answer = self.gateway_client.send_command(command)
1256 return_value = get_return_value(
-> 1257 answer, self.gateway_client, self.target_id, self.name)
1258
1259 for temp_arg in temp_args:
~/Downloads/Spark/spark-2.4.5-bin-hadoop2.7/python/pyspark/sql/utils.py in deco(*a, **kw)
61 def deco(*a, **kw):
62 try:
---> 63 return f(*a, **kw)
64 except py4j.protocol.Py4JJavaError as e:
65 s = e.java_exception.toString()
~/Downloads/Spark/spark-2.4.5-bin-hadoop2.7/python/lib/py4j-0.10.7-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
326 raise Py4JJavaError(
327 "An error occurred while calling {0}{1}{2}.\n".
--> 328 format(target_id, ".", name), value)
329 else:
330 raise Py4JError(
Py4JJavaError: An error occurred while calling o514.parquet.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 7.0 failed 1 times, most recent failure: Lost task 0.0 in stage 7.0 (TID 7, localhost, executor driver): java.io.IOException: Failed to connect to /192.168.19.237:62286
at org.apache.spark.network.client.TransportClientFactory.createClient(TransportClientFactory.java:245)
at org.apache.spark.network.client.TransportClientFactory.createClient(TransportClientFactory.java:187)
at org.apache.spark.rpc.netty.NettyRpcEnv.org$apache$spark$rpc$netty$NettyRpcEnv$$downloadClient(NettyRpcEnv.scala:368)
at org.apache.spark.rpc.netty.NettyRpcEnv$$anonfun$openChannel$1.apply$mcV$sp(NettyRpcEnv.scala:336)
at org.apache.spark.rpc.netty.NettyRpcEnv$$anonfun$openChannel$1.apply(NettyRpcEnv.scala:335)
at org.apache.spark.rpc.netty.NettyRpcEnv$$anonfun$openChannel$1.apply(NettyRpcEnv.scala:335)
at org.apache.spark.util.Utils$.tryWithSafeFinallyAndFailureCallbacks(Utils.scala:1394)
at org.apache.spark.rpc.netty.NettyRpcEnv.openChannel(NettyRpcEnv.scala:339)
at org.apache.spark.util.Utils$.doFetchFile(Utils.scala:693)
at org.apache.spark.util.Utils$.fetchFile(Utils.scala:509)
at org.apache.spark.executor.Executor$$anonfun$org$apache$spark$executor$Executor$$updateDependencies$5.apply(Executor.scala:816)
at org.apache.spark.executor.Executor$$anonfun$org$apache$spark$executor$Executor$$updateDependencies$5.apply(Executor.scala:808)
at scala.collection.TraversableLike$WithFilter$$anonfun$foreach$1.apply(TraversableLike.scala:733)
at scala.collection.mutable.HashMap$$anonfun$foreach$1.apply(HashMap.scala:130)
at scala.collection.mutable.HashMap$$anonfun$foreach$1.apply(HashMap.scala:130)
at scala.collection.mutable.HashTable$class.foreachEntry(HashTable.scala:236)
at scala.collection.mutable.HashMap.foreachEntry(HashMap.scala:40)
at scala.collection.mutable.HashMap.foreach(HashMap.scala:130)
at scala.collection.TraversableLike$WithFilter.foreach(TraversableLike.scala:732)
at org.apache.spark.executor.Executor.org$apache$spark$executor$Executor$$updateDependencies(Executor.scala:808)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:375)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
at java.lang.Thread.run(Thread.java:748)
Suppressed: java.lang.NullPointerException
at org.apache.spark.util.Utils$.tryWithSafeFinallyAndFailureCallbacks(Utils.scala:1402)
... 17 more
Caused by: io.netty.channel.AbstractChannel$AnnotatedConnectException: Operation timed out: /192.168.19.237:62286
Caused by: java.net.ConnectException: Operation timed out
at sun.nio.ch.SocketChannelImpl.checkConnect(Native Method)
at sun.nio.ch.SocketChannelImpl.finishConnect(SocketChannelImpl.java:717)
at io.netty.channel.socket.nio.NioSocketChannel.doFinishConnect(NioSocketChannel.java:327)
at io.netty.channel.nio.AbstractNioChannel$AbstractNioUnsafe.finishConnect(AbstractNioChannel.java:334)
at io.netty.channel.nio.NioEventLoop.processSelectedKey(NioEventLoop.java:688)
at io.netty.channel.nio.NioEventLoop.processSelectedKeysOptimized(NioEventLoop.java:635)
at io.netty.channel.nio.NioEventLoop.processSelectedKeys(NioEventLoop.java:552)
at io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:514)
at io.netty.util.concurrent.SingleThreadEventExecutor$6.run(SingleThreadEventExecutor.java:1044)
at io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74)
at io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30)
at java.lang.Thread.run(Thread.java:748)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1891)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1879)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1878)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1878)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:927)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:927)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:927)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2112)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2061)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2050)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:738)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2061)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2082)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2101)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2126)
at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:990)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:385)
at org.apache.spark.rdd.RDD.collect(RDD.scala:989)
at org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormat$.mergeSchemasInParallel(ParquetFileFormat.scala:633)
at org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormat.inferSchema(ParquetFileFormat.scala:241)
at org.apache.spark.sql.execution.datasources.DataSource$$anonfun$6.apply(DataSource.scala:180)
at org.apache.spark.sql.execution.datasources.DataSource$$anonfun$6.apply(DataSource.scala:180)
at scala.Option.orElse(Option.scala:289)
at org.apache.spark.sql.execution.datasources.DataSource.getOrInferFileFormatSchema(DataSource.scala:179)
at org.apache.spark.sql.execution.datasources.DataSource.resolveRelation(DataSource.scala:373)
at org.apache.spark.sql.DataFrameReader.loadV1Source(DataFrameReader.scala:223)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:211)
at org.apache.spark.sql.DataFrameReader.parquet(DataFrameReader.scala:645)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:282)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:238)
at java.lang.Thread.run(Thread.java:748)
Caused by: java.io.IOException: Failed to connect to /192.168.19.237:62286
at org.apache.spark.network.client.TransportClientFactory.createClient(TransportClientFactory.java:245)
at org.apache.spark.network.client.TransportClientFactory.createClient(TransportClientFactory.java:187)
at org.apache.spark.rpc.netty.NettyRpcEnv.org$apache$spark$rpc$netty$NettyRpcEnv$$downloadClient(NettyRpcEnv.scala:368)
at org.apache.spark.rpc.netty.NettyRpcEnv$$anonfun$openChannel$1.apply$mcV$sp(NettyRpcEnv.scala:336)
at org.apache.spark.rpc.netty.NettyRpcEnv$$anonfun$openChannel$1.apply(NettyRpcEnv.scala:335)
at org.apache.spark.rpc.netty.NettyRpcEnv$$anonfun$openChannel$1.apply(NettyRpcEnv.scala:335)
at org.apache.spark.util.Utils$.tryWithSafeFinallyAndFailureCallbacks(Utils.scala:1394)
at org.apache.spark.rpc.netty.NettyRpcEnv.openChannel(NettyRpcEnv.scala:339)
at org.apache.spark.util.Utils$.doFetchFile(Utils.scala:693)
at org.apache.spark.util.Utils$.fetchFile(Utils.scala:509)
at org.apache.spark.executor.Executor$$anonfun$org$apache$spark$executor$Executor$$updateDependencies$5.apply(Executor.scala:816)
at org.apache.spark.executor.Executor$$anonfun$org$apache$spark$executor$Executor$$updateDependencies$5.apply(Executor.scala:808)
at scala.collection.TraversableLike$WithFilter$$anonfun$foreach$1.apply(TraversableLike.scala:733)
at scala.collection.mutable.HashMap$$anonfun$foreach$1.apply(HashMap.scala:130)
at scala.collection.mutable.HashMap$$anonfun$foreach$1.apply(HashMap.scala:130)
at scala.collection.mutable.HashTable$class.foreachEntry(HashTable.scala:236)
at scala.collection.mutable.HashMap.foreachEntry(HashMap.scala:40)
at scala.collection.mutable.HashMap.foreach(HashMap.scala:130)
at scala.collection.TraversableLike$WithFilter.foreach(TraversableLike.scala:732)
at org.apache.spark.executor.Executor.org$apache$spark$executor$Executor$$updateDependencies(Executor.scala:808)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:375)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
... 1 more
Suppressed: java.lang.NullPointerException
at org.apache.spark.util.Utils$.tryWithSafeFinallyAndFailureCallbacks(Utils.scala:1402)
... 17 more
Caused by: io.netty.channel.AbstractChannel$AnnotatedConnectException: Operation timed out: /192.168.19.237:62286
Caused by: java.net.ConnectException: Operation timed out
at sun.nio.ch.SocketChannelImpl.checkConnect(Native Method)
at sun.nio.ch.SocketChannelImpl.finishConnect(SocketChannelImpl.java:717)
at io.netty.channel.socket.nio.NioSocketChannel.doFinishConnect(NioSocketChannel.java:327)
at io.netty.channel.nio.AbstractNioChannel$AbstractNioUnsafe.finishConnect(AbstractNioChannel.java:334)
at io.netty.channel.nio.NioEventLoop.processSelectedKey(NioEventLoop.java:688)
at io.netty.channel.nio.NioEventLoop.processSelectedKeysOptimized(NioEventLoop.java:635)
at io.netty.channel.nio.NioEventLoop.processSelectedKeys(NioEventLoop.java:552)
at io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:514)
at io.netty.util.concurrent.SingleThreadEventExecutor$6.run(SingleThreadEventExecutor.java:1044)
at io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74)
at io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30)
at java.lang.Thread.run(Thread.java:748)
Я предполагаю, что root причина этого исключения как-то связана с этой строкой
Вызвано: java .io.IOException: не удалось подключиться к /192.168.19.237:62286
Я поискал в Интернете и не нашел очень полезного ответа. Цени свои баллы!
Спасибо