軟件：jdk-8u201-linux-x64.tar.gz、hadoop-2.7.7.tar.gz
安裝：
登陸 192.168.1.17
hostnamectl set-hostname node1;mkdir /opt/namenode;mkdir /opt/datanode
vi /etc/hosts
192.168.1.17? node1
192.168.1.18? node2
tar -zxvf jdk-8u201-linux-x64.tar.gz;mv jdk1.8.0_201/ /opt/jdk
tar -zxvf hadoop-2.7.7.tar.gz;mv hadoop-2.7.7/ /opt/hadoop
vi ~/.bashrc
export JAVA_HOME=/opt/jdk
export HADOOP_HOME=/opt/hadoop
export PATH=$PATH:$JAVA_HOME/bin:$HADOOP_HOME/bin:$HADOOP_HOME/sbin
source ~/.bashrc
------------------------------------
登陸 192.168.1.18
hostnamectl set-hostname node2;mkdir /opt/namenode;mkdir /opt/datanode
vi /etc/hosts
192.168.1.17? node1
192.168.1.18? node2
tar -zxvf jdk-8u201-linux-x64.tar.gz;mv jdk1.8.0_201/ /opt/jdk
tar -zxvf hadoop-2.7.7.tar.gz;mv hadoop-2.7.7/ /opt/hadoop
vi ~/.bashrc
export JAVA_HOME=/opt/jdk
export HADOOP_HOME=/opt/hadoop
export PATH=$PATH:$JAVA_HOME/bin:$HADOOP_HOME/bin:$HADOOP_HOME/sbin
source ~/.bashrc
-----------------------------------
修改 core-site.xml 配置
<configuration>
<property>
<name>fs.defaultFS</name>
<value>hdfs://192.168.1.17:9000</value>
</property>
</configuration>
修改 hdfs-site.xml 配置
<configuration>
<property>
<name>dfs.replication</name>
<value>1</value>
</property>
<property>
<name>dfs.namenode.name.dir</name>
<value>file:///opt/namenode</value>
</property>
<property>
<name>dfs.datanode.data.dir</name>
<value>file:///opt/datanode</value>
</property>
<property>
<name>dfs.encrypt.data.transfer</name>
<value>true</value>
</property>
<property>
<name>dfs.encrypt.data.transfer.algorithm</name>
<value>3des</value>
</property>
<property>
<name>dfs.encrypt.data.transfer.cipher.suites</name>
<value>AES/CTR/NoPadding</value>
</property>
<property>
<name>dfs.block.access.token.enable</name>
<value>true</value>
</property>
</configuration>
-------------------------------
登陸 192.168.1.17
hadoop-daemon.sh start namenode;hadoop-daemon.sh start datanode
登陸 192.168.1.18
hadoop-daemon.sh start datanode
-------------------------------
測試
hadoop fs -mkdir? -p /user/linzw
hadoop fs -put anaconda-ks.cfg /user/linzw
備註：
如果不添加 dfs.block.access.token.enable = true，會出現如下報錯。添加該配置以後，可以正常寫入數據
20/10/28 21:29:12 INFO hdfs.DFSClient: Exception in createBlockOutputStream
java.io.IOException: Connection reset by peer
at sun.nio.ch.FileDispatcherImpl.read0(Native Method)
at sun.nio.ch.SocketDispatcher.read(SocketDispatcher.java:39)
at sun.nio.ch.IOUtil.readIntoNativeBuffer(IOUtil.java:223)
at sun.nio.ch.IOUtil.read(IOUtil.java:197)
at sun.nio.ch.SocketChannelImpl.read(SocketChannelImpl.java:380)
at org.apache.hadoop.net.SocketInputStream$Reader.performIO(SocketInputStream.java:57)
at org.apache.hadoop.net.SocketIOWithTimeout.doIO(SocketIOWithTimeout.java:142)
at org.apache.hadoop.net.SocketInputStream.read(SocketInputStream.java:161)
at org.apache.hadoop.net.SocketInputStream.read(SocketInputStream.java:131)
at org.apache.hadoop.net.SocketInputStream.read(SocketInputStream.java:118)
at java.io.FilterInputStream.read(FilterInputStream.java:83)
at java.io.FilterInputStream.read(FilterInputStream.java:83)
at org.apache.hadoop.hdfs.protocolPB.PBHelper.vintPrefixed(PBHelper.java:2292)
at org.apache.hadoop.hdfs.DFSOutputStream$DataStreamer.createBlockOutputStream(DFSOutputStream.java:1480)
at org.apache.hadoop.hdfs.DFSOutputStream$DataStreamer.nextBlockOutputStream(DFSOutputStream.java:1400)
at org.apache.hadoop.hdfs.DFSOutputStream$DataStreamer.run(DFSOutputStream.java:554)
20/10/28 21:29:12 INFO hdfs.DFSClient: Abandoning BP-304062021-127.0.0.1-1603891241969:blk_1073741825_1001
20/10/28 21:29:12 INFO hdfs.DFSClient: Excluding datanode DatanodeInfoWithStorage[192.168.1.17:50010,DS-d431ec75-6a89-42b2-b782-7a2d224873d8,DISK]
20/10/28 21:29:12 INFO hdfs.DFSClient: Exception in createBlockOutputStream
java.io.IOException: Connection reset by peer
at sun.nio.ch.FileDispatcherImpl.read0(Native Method)
at sun.nio.ch.SocketDispatcher.read(SocketDispatcher.java:39)
at sun.nio.ch.IOUtil.readIntoNativeBuffer(IOUtil.java:223)
at sun.nio.ch.IOUtil.read(IOUtil.java:197)
at sun.nio.ch.SocketChannelImpl.read(SocketChannelImpl.java:380)
at org.apache.hadoop.net.SocketInputStream$Reader.performIO(SocketInputStream.java:57)
at org.apache.hadoop.net.SocketIOWithTimeout.doIO(SocketIOWithTimeout.java:142)
at org.apache.hadoop.net.SocketInputStream.read(SocketInputStream.java:161)
at org.apache.hadoop.net.SocketInputStream.read(SocketInputStream.java:131)
at org.apache.hadoop.net.SocketInputStream.read(SocketInputStream.java:118)
at java.io.FilterInputStream.read(FilterInputStream.java:83)
at java.io.FilterInputStream.read(FilterInputStream.java:83)
at org.apache.hadoop.hdfs.protocolPB.PBHelper.vintPrefixed(PBHelper.java:2292)
at org.apache.hadoop.hdfs.DFSOutputStream$DataStreamer.createBlockOutputStream(DFSOutputStream.java:1480)
at org.apache.hadoop.hdfs.DFSOutputStream$DataStreamer.nextBlockOutputStream(DFSOutputStream.java:1400)
at org.apache.hadoop.hdfs.DFSOutputStream$DataStreamer.run(DFSOutputStream.java:554)
20/10/28 21:29:12 INFO hdfs.DFSClient: Abandoning BP-304062021-127.0.0.1-1603891241969:blk_1073741826_1002
20/10/28 21:29:12 INFO hdfs.DFSClient: Excluding datanode DatanodeInfoWithStorage[192.168.1.18:50010,DS-168fefa8-5ff0-4fcb-82be-ecd9f81c5861,DISK]
20/10/28 21:29:12 WARN hdfs.DFSClient: DataStreamer Exception
org.apache.hadoop.ipc.RemoteException(java.io.IOException): File /user/linzw/anaconda-ks.cfg._COPYING_ could only be replicated to 0 nodes instead of minReplication (=1).? There are 2 datanode(s) running and 2 node(s) are excluded in this operation.
at org.apache.hadoop.hdfs.server.blockmanagement.BlockManager.chooseTarget4NewBlock(BlockManager.java:1620)
at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getNewBlockTargets(FSNamesystem.java:3135)
at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getAdditionalBlock(FSNamesystem.java:3059)
at org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.addBlock(NameNodeRpcServer.java:725)
at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.addBlock(ClientNamenodeProtocolServerSideTranslatorPB.java:493)
at org.apache.hadoop.hdfs.protocol.proto.ClientNamenodeProtocolProtos$ClientNamenodeProtocol$2.callBlockingMethod(ClientNamenodeProtocolProtos.java)
at org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:616)
at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:982)
at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2217)
at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2213)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:422)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1762)
at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2211)
at org.apache.hadoop.ipc.Client.call(Client.java:1476)
at org.apache.hadoop.ipc.Client.call(Client.java:1413)
at org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:229)
at com.sun.proxy.$Proxy10.addBlock(Unknown Source)
at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolTranslatorPB.addBlock(ClientNamenodeProtocolTranslatorPB.java:418)
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:191)
at org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:102)
at com.sun.proxy.$Proxy11.addBlock(Unknown Source)
at org.apache.hadoop.hdfs.DFSOutputStream$DataStreamer.locateFollowingBlock(DFSOutputStream.java:1603)
at org.apache.hadoop.hdfs.DFSOutputStream$DataStreamer.nextBlockOutputStream(DFSOutputStream.java:1388)
at org.apache.hadoop.hdfs.DFSOutputStream$DataStreamer.run(DFSOutputStream.java:554)
put: File /user/linzw/anaconda-ks.cfg._COPYING_ could only be replicated to 0 nodes instead of minReplication (=1).? There are 2 datanode(s) running and 2 node(s) are excluded in this operation.