14/07/19 21:15:23 INFO MemoryStore: ensureFreeSpace(138763) called with curMem=0, maxMem=309225062
14/07/19 21:15:23 INFO MemoryStore: Block broadcast_0 stored as values to memory (estimated size 135.5 KB, free 294.8 MB)
rdd1: org.apache.spark.rdd.RDD[String] = MappedRDD[1] at textFile at <console>:12
scala> rdd1.toDebugString
java.lang.IllegalArgumentException: java.net.UnknownHostException: mycluster
at org.apache.hadoop.security.SecurityUtil.buildTokenService(SecurityUtil.java:418)
at org.apache.hadoop.hdfs.NameNodeProxies.createNonHAProxy(NameNodeProxies.java:231)
at org.apache.hadoop.hdfs.NameNodeProxies.createProxy(NameNodeProxies.java:139)
at org.apache.hadoop.hdfs.DFSClient.<init>(DFSClient.java:510)
at org.apache.hadoop.hdfs.DFSClient.<init>(DFSClient.java:453)
at org.apache.hadoop.hdfs.DistributedFileSystem.initialize(DistributedFileSystem.java:136)
at org.apache.hadoop.fs.FileSystem.createFileSystem(FileSystem.java:2433)
at org.apache.hadoop.fs.FileSystem.access$200(FileSystem.java:88)
at org.apache.hadoop.fs.FileSystem$Cache.getInternal(FileSystem.java:2467)
at org.apache.hadoop.fs.FileSystem$Cache.get(FileSystem.java:2449)
at org.apache.hadoop.fs.FileSystem.get(FileSystem.java:367)
at org.apache.hadoop.fs.Path.getFileSystem(Path.java:287)
at org.apache.hadoop.mapred.FileInputFormat.listStatus(FileInputFormat.java:221)
at org.apache.hadoop.mapred.FileInputFormat.getSplits(FileInputFormat.java:270)
at org.apache.spark.rdd.HadoopRDD.getPartitions(HadoopRDD.scala:172)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:204)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:202)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:202)
at org.apache.spark.rdd.MappedRDD.getPartitions(MappedRDD.scala:28)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:204)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:202)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:202)
at org.apache.spark.rdd.RDD.org$apache$spark$rdd$RDD$$debugString$1(RDD.scala:1194)
at org.apache.spark.rdd.RDD.toDebugString(RDD.scala:1197)
at $iwC$$iwC$$iwC$$iwC.<init>(<console>:15)
at $iwC$$iwC$$iwC.<init>(<console>:20)
at $iwC$$iwC.<init>(<console>:22)
at $iwC.<init>(<console>:24)
at <init>(<console>:26)
at .<init>(<console>:30)
at .<clinit>(<console>)
at .<init>(<console>:7)
at .<clinit>(<console>)
at $print(<console>)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:788)
at org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1056)
at org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:614)
at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:645)
at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:609)
at org.apache.spark.repl.SparkILoop.reallyInterpret$1(SparkILoop.scala:796)
at org.apache.spark.repl.SparkILoop.interpretStartingWith(SparkILoop.scala:841)
at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:753)
at org.apache.spark.repl.SparkILoop.processLine$1(SparkILoop.scala:601)
at org.apache.spark.repl.SparkILoop.innerLoop$1(SparkILoop.scala:608)
at org.apache.spark.repl.SparkILoop.loop(SparkILoop.scala:611)
at org.apache.spark.repl.SparkILoop$$anonfun$process$1.apply$mcZ$sp(SparkILoop.scala:936)
at org.apache.spark.repl.SparkILoop$$anonfun$process$1.apply(SparkILoop.scala:884)
at org.apache.spark.repl.SparkILoop$$anonfun$process$1.apply(SparkILoop.scala:884)
at scala.tools.nsc.util.ScalaClassLoader$.savingContextLoader(ScalaClassLoader.scala:135)
at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:884)
at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:982)
at org.apache.spark.repl.Main$.main(Main.scala:31)
at org.apache.spark.repl.Main.main(Main.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at org.apache.spark.deploy.SparkSubmit$.launch(SparkSubmit.scala:292)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:55)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: java.net.UnknownHostException: mycluster
... 66 more
scala>
我的hadoop2.2.0配置成了HA。這裏使用mycluster作爲hdfs的文件路徑提示找不到。不知道怎麼回事。
我通過查看Namenode的狀態。將val rdd1 = sc.textFile("hdfs://master:8020/spark/spark02/week2/directory/")
改成active的namenode的主機名master:8020就可以正常執行rdd1.toDebugString命令。
Inheriting Cluster Configuration
If you plan to read and write from HDFS using Spark, there are two Hadoop configuration files thatshould be included on Spark’s classpath:
hdfs-site.xml, which provides default behaviors for the HDFS client.core-site.xml, which sets the default filesystem name.
The location of these configuration files varies across CDH and HDP versions, buta common location is inside of
/etc/hadoop/conf. Some tools, such as Cloudera Manager, createconfigurations on-the-fly, but offer a mechanisms to download copies of them.
To make these files visible to Spark, set HADOOP_CONF_DIR in
$SPARK_HOME/spark-env.sh to a location containing the configuration files.
於是我在spark-env.sh中添加了
export HADOOP_CONF_DIR=/hadoop2.2.0/etc/hadoop
再次執行上面的代碼，就可以正常執行了。
可見使用hadoop的HA時，因爲添加了一個dfs.nameservices=mycluster代表整個集羣的namenode。spark環境中如果找不到hadoop的配置文件就不能正確解析mycluster這個名稱。
非HA配置下就無需添加這個HADOOP_CONF_DIR變量了，因爲namenode只有一個。