在docker上运行字数统计的例子

我有一个容器上安装了hadoop 2.7.4。 我用这个命令运行这个容器：

sudo docker run -it -v somewhere/project/:/root/project/ --net=host --name hadoop -p 22:22 hadoop-img 

我已经改变了下面的文件，

在〜/ .bashrc

 ... #hadoop variables, start export JAVA_HOME=$(readlink -f /usr/bin/java | sed "s:bin/java::") export HADOOP_INSTALL=/opt/hadoop-2.7.4 export PATH=$PATH:$HADOOP_INSTALL/bin export PATH=$PATH:$HADOOP_INSTALL/sbin export HADOOP_MAPRED_HOME=$HADOOP_INSTALL export HADOOP_COMMON_HOME=$HADOOP_INSTALL export HADOOP_HDFS_HOME=$HADOOP_INSTALL export YARN_HOME=$HADOOP_INSTALL export HADOOP_COMMON_LIB_NATIVE_DIR=$HADOOP_INSTALL/lib/native export HADOOP_OPTS="-Djava.library.path=$HADOOP_INSTALL/lib" #hadoop variables, end 

核心的site.xml

 <?xml version="1.0" encoding="UTF-8"?> <?xml-stylesheet type="text/xsl" href="configuration.xsl"?> <!-- Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License. You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0 Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions and limitations under the License. See accompanying LICENSE file. --> <!-- Put site-specific property overrides in this file. --> <configuration> <property> <name>hadoop.tmp.dir</name> <value>/app/hadoop/tmp</value> <description>A base for other temporary directories.</description> </property> <property> <name>fs.default.name</name> <value>hdfs://localhost:22</value> <description>The name of the default file system. A URI whose scheme and authority determine the FileSystem implementation. The uri's scheme determines the config property (fs.SCHEME.impl) naming the FileSystem implementation class. The uri's authority is used to determine the host, port, etc. for a filesystem.</description> </property> </configuration> 

hadoop-env.sh

 ... export JAVA_HOME=$(readlink -f /usr/bin/java | sed "s:bin/java::") ... 

HDFS-site.xml中

 <?xml version="1.0" encoding="UTF-8"?> <?xml-stylesheet type="text/xsl" href="configuration.xsl"?> <!-- Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License. You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0 Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions and limitations under the License. See accompanying LICENSE file. --> <!-- Put site-specific property overrides in this file. --> <configuration> <property> <name>dfs.replication</name> <value>0</value> <description>Default block replication. The actual number of replications can be specified when the file is created. The default is used if replication is not specified in create time. </description> </property> <property> <name>dfs.namenode.name.dir</name> <value>file:/usr/local/hadoop_store/hdfs/namenode</value> </property> <property> <name>dfs.datanode.data.dir</name> <value>file:/usr/local/hadoop_store/hdfs/datanode</value> </property> </configuration> 

mapred-site.xml中

 <?xml version="1.0"?> <?xml-stylesheet type="text/xsl" href="configuration.xsl"?> <!-- Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License. You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0 Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions and limitations under the License. See accompanying LICENSE file. --> <!-- Put site-specific property overrides in this file. --> <configuration> <property> <name>mapred.job.tracker</name> <value>localhost:22</value> <description>The host and port that the MapReduce job tracker runs at. If "local", then jobs are run in-process as a single map and reduce task. </description> </property> </configuration> 

我有一个WordCount的例子，我要运行一个数据集。 当我用./start-all.sh启动hadoop时，我得到了这个：

 This script is Deprecated. Instead use start-dfs.sh and start-yarn.sh 17/10/11 10:04:34 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable Starting namenodes on [localhost] localhost: ssh: connect to host localhost port 22: Connection refused localhost: ssh: connect to host localhost port 22: Connection refused Starting secondary namenodes [0.0.0.0] 0.0.0.0: ssh: connect to host 0.0.0.0 port 22: Connection refused 17/10/11 10:04:37 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable starting yarn daemons starting resourcemanager, logging to /opt/hadoop-2.7.4/logs/yarn--resourcemanager-saeed-X550CC.out localhost: ssh: connect to host localhost port 22: Connection refused 

为什么我总是得到这个错误？

连接到主机localhost端口22：连接被拒绝