spark-s3a-error

core-site.xml

<configuration>
 <property>
  <name>fs.s3a.access.key</name>
  <value>S3_ACCESS_KEY</value>
 </property>

 <property>
  <name>fs.s3a.secret.key</name>
  <value>S3_SECRET_KEY</value>
 </property>
</configuration>

pyspark-example.py

from pyspark import SparkContext

sc = SparkContext('spark://spark-master-1:7077,spark-master-2:7077')

# Load a text file and convert each line to a tuple.
dataFile = "s3a://mybucket/out.csv"
input = sc.textFile(dataFile)
header = input.take(1)[0]
print header

stacktrace

Driver stacktrace:
        at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1431)
        at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1419)
        at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1418)
        at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
        at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
        at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1418)
        at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
        at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
        at scala.Option.foreach(Option.scala:236)
        at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:799)
        at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1640)
        at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1599)
        at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1588)
        at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
        at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:620)
        at org.apache.spark.SparkContext.runJob(SparkContext.scala:1832)
        at org.apache.spark.SparkContext.runJob(SparkContext.scala:1845)
        at org.apache.spark.SparkContext.runJob(SparkContext.scala:1858)
        at org.apache.spark.api.python.PythonRDD$.runJob(PythonRDD.scala:393)
        at org.apache.spark.api.python.PythonRDD.runJob(PythonRDD.scala)
        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:231)
        at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:381)
        at py4j.Gateway.invoke(Gateway.java:259)
        at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:133)
        at py4j.commands.CallCommand.execute(CallCommand.java:79)
        at py4j.GatewayConnection.run(GatewayConnection.java:209)
        at java.lang.Thread.run(Thread.java:745)
Caused by: com.cloudera.com.amazonaws.services.s3.model.AmazonS3Exception: The provided security credentials are not valid. (Service: Amazon S3; Status Code: 403; Error Code: InvalidSecurity; Request ID: null), S3 Extended Request ID: null
        at com.cloudera.com.amazonaws.http.AmazonHttpClient.handleErrorResponse(AmazonHttpClient.java:1182)
        at com.cloudera.com.amazonaws.http.AmazonHttpClient.executeOneRequest(AmazonHttpClient.java:770)
        at com.cloudera.com.amazonaws.http.AmazonHttpClient.executeHelper(AmazonHttpClient.java:489)
        at com.cloudera.com.amazonaws.http.AmazonHttpClient.execute(AmazonHttpClient.java:310)
        at com.cloudera.com.amazonaws.services.s3.AmazonS3Client.invoke(AmazonS3Client.java:3785)
        at com.cloudera.com.amazonaws.services.s3.AmazonS3Client.getObject(AmazonS3Client.java:1191)
        at org.apache.hadoop.fs.s3a.S3AInputStream.reopen(S3AInputStream.java:91)
        at org.apache.hadoop.fs.s3a.S3AInputStream.openIfNeeded(S3AInputStream.java:62)
        at org.apache.hadoop.fs.s3a.S3AInputStream.read(S3AInputStream.java:156)
        at java.io.DataInputStream.read(DataInputStream.java:149)
        at org.apache.hadoop.mapreduce.lib.input.UncompressedSplitLineReader.fillBuffer(UncompressedSplitLineReader.java:59)
        at org.apache.hadoop.util.LineReader.readDefaultLine(LineReader.java:216)
        at org.apache.hadoop.util.LineReader.readLine(LineReader.java:174)
        at org.apache.hadoop.mapreduce.lib.input.UncompressedSplitLineReader.readLine(UncompressedSplitLineReader.java:91)
        at org.apache.hadoop.mapred.LineRecordReader.skipUtfByteOrderMark(LineRecordReader.java:208)
        at org.apache.hadoop.mapred.LineRecordReader.next(LineRecordReader.java:246)
        at org.apache.hadoop.mapred.LineRecordReader.next(LineRecordReader.java:48)
        at org.apache.spark.rdd.HadoopRDD$$anon$1.getNext(HadoopRDD.scala:246)
        at org.apache.spark.rdd.HadoopRDD$$anon$1.getNext(HadoopRDD.scala:208)
        at org.apache.spark.util.NextIterator.hasNext(NextIterator.scala:73)
        at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:39)
        at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
        at scala.collection.Iterator$class.foreach(Iterator.scala:727)
        at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
        at org.apache.spark.api.python.PythonRDD$.writeIteratorToStream(PythonRDD.scala:452)
        at org.apache.spark.api.python.PythonRunner$WriterThread$$anonfun$run$3.apply(PythonRDD.scala:280)
        at org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1741)
        at org.apache.spark.api.python.PythonRunner$WriterThread.run(PythonRDD.scala:239)