Hi,
The following code – which has worked in the past – is throwing an error now. This error has been duplicated across multiple user accounts. Thank you for investigating.
// Load CSV file ‘car-milage.csv’
var filename = “Big_Data/Spark_DataFrames/car-milage.csv”
val carsDF = spark.read.
option(“header”,“true”).
option(“inferSchema”,“true”).
csv(filename)
println(filename + " has " + carsDF.count() + " rows")
carsDF.show(5)
carsDF.printSchema()
Name: org.apache.hadoop.ipc.RemoteException
Message: Cannot create file/spark2-history/local-1709169133459.inprogress. Name node is in safe mode.
The reported blocks 172449 needs additional 112 blocks to reach the threshold 1.0000 of total blocks 172560.
The number of live datanodes 3 has reached the minimum number 0. Safe mode will be turned off automatically once the thresholds have been reached.
at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.checkNameNodeSafeMode(FSNamesystem.java:1392)
at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.startFileInt(FSNamesystem.java:2667)
at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.startFile(FSNamesystem.java:2556)
at org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.create(NameNodeRpcServer.java:736)
at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.create(ClientNamenodeProtocolServerSideTranslatorPB.java:409)
at org.apache.hadoop.hdfs.protocol.proto.ClientNamenodeProtocolProtos$ClientNamenodeProtocol$2.callBlockingMethod(ClientNamenodeProtocolProtos.java)
at org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:640)
at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:982)
at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2351)
at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2347)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:422)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1866)
at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2345)
StackTrace: The reported blocks 172449 needs additional 112 blocks to reach the threshold 1.0000 of total blocks 172560.
The number of live datanodes 3 has reached the minimum number 0. Safe mode will be turned off automatically once the thresholds have been reached.
at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.checkNameNodeSafeMode(FSNamesystem.java:1392)
at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.startFileInt(FSNamesystem.java:2667)
at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.startFile(FSNamesystem.java:2556)
at org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.create(NameNodeRpcServer.java:736)
at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.create(ClientNamenodeProtocolServerSideTranslatorPB.java:409)
at org.apache.hadoop.hdfs.protocol.proto.ClientNamenodeProtocolProtos$ClientNamenodeProtocol$2.callBlockingMethod(ClientNamenodeProtocolProtos.java)
at org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:640)
at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:982)
at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2351)
at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2347)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:422)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1866)
at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2345)
at org.apache.hadoop.ipc.Client.getRpcResponse(Client.java:1554)
at org.apache.hadoop.ipc.Client.call(Client.java:1498)
at org.apache.hadoop.ipc.Client.call(Client.java:1398)
at org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:233)
at com.sun.proxy.$Proxy19.create(Unknown Source)
at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolTranslatorPB.create(ClientNamenodeProtocolTranslatorPB.java:313)
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 org.apache.hadoop.io.retry.RetryInvocationHandler.invokeMethod(RetryInvocationHandler.java:291)
at org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:203)
at org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:185)
at com.sun.proxy.$Proxy20.create(Unknown Source)
at org.apache.hadoop.hdfs.DFSOutputStream.newStreamForCreate(DFSOutputStream.java:1822)
at org.apache.hadoop.hdfs.DFSClient.create(DFSClient.java:1701)
at org.apache.hadoop.hdfs.DFSClient.create(DFSClient.java:1636)
at org.apache.hadoop.hdfs.DistributedFileSystem$8.doCall(DistributedFileSystem.java:480)
at org.apache.hadoop.hdfs.DistributedFileSystem$8.doCall(DistributedFileSystem.java:476)
at org.apache.hadoop.fs.FileSystemLinkResolver.resolve(FileSystemLinkResolver.java:81)
at org.apache.hadoop.hdfs.DistributedFileSystem.create(DistributedFileSystem.java:476)
at org.apache.hadoop.hdfs.DistributedFileSystem.create(DistributedFileSystem.java:417)
at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:930)
at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:911)
at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:807)
at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:796)
at org.apache.spark.scheduler.EventLoggingListener.start(EventLoggingListener.scala:113)
at org.apache.spark.SparkContext.(SparkContext.scala:531)
at org.apache.spark.SparkContext$.getOrCreate(SparkContext.scala:2323)
at org.apache.spark.sql.SparkSession$Builder$$anonfun$6.apply(SparkSession.scala:876)
at org.apache.spark.sql.SparkSession$Builder$$anonfun$6.apply(SparkSession.scala:868)
at scala.Option.getOrElse(Option.scala:121)
at org.apache.spark.sql.SparkSession$Builder.getOrCreate(SparkSession.scala:868)
at org.apache.toree.kernel.api.Kernel.sparkSession(Kernel.scala:444)
at spark(:17)