标签:main map cli .net ups :link sample cer 链接
序号 | 主机名 | IP地址 | 角色 |
1 | nn-1 | 192.168.9.21 | NameNode、mr-jobhistory、zookeeper、JournalNode |
2 | nn-2 | 192.168.9.22 | Secondary NameNode、JournalNode |
3 | dn-1 | 192.168.9.23 | DataNode、JournalNode、zookeeper、ResourceManager、NodeManager |
4 | dn-2 | 192.168.9.24 | DataNode、zookeeper、NodeManager |
5 | dn-3 | 192.168.9.25 | DataNode、NodeManager |
--查看java版本
[root@dtgr ~]# java -version
java version "1.7.0_45"
OpenJDK Runtime Environment (rhel-2.4.3.3.el6-x86_64 u45-b15)
OpenJDK 64-Bit Server VM (build 24.45-b08, mixed mode)
--查看安装源
[root@dtgr ~]# rpm -qa | grep java
java-1.7.0-openjdk-1.7.0.45-2.4.3.3.el6.x86_64
-- 卸载
[root@dtgr ~]# rpm -e --nodeps java-1.7.0-openjdk-1.7.0.45-2.4.3.3.el6.x86_64
--验证是否卸载成功
[root@dtgr ~]# rpm -qa | grep java
[root@dtgr ~]# java -version
-bash: /usr/bin/java: 没有那个文件或目录
-- 下载并解压java源码包
[root@dtgr java]# mkdir /usr/local/java
[root@dtgr java]# mv jdk-7u79-linux-x64.tar.gz /usr/local/java
[root@dtgr java]# cd /usr/local/java
[root@dtgr java]# tar xvf jdk-7u79-linux-x64.tar.gz
[root@dtgr java]# ls
jdk1.7.0_79 jdk-7u79-linux-x64.tar.gz
[root@dtgr java]#
--- 添加环境变量
[root@dtgr java]# vim /etc/profile
[root@dtgr java]# tail /etc/profile
export JAVA_HOME=/usr/local/java/jdk1.7.0_79
export JRE_HOME=/usr/local/java/jdk1.7.0_79/jre
export CLASSPATH=.:$JAVA_HOME/lib/dt.jar:$JAVA_HOME/lib/tools.jar:$JRE_HOME/lib:$CLASSPATH
export PATH=$JAVA_HOME/bin:$PATH
-- 生效环境变量
[root@dtgr ~]# source /etc/profile
-- 验证
[root@dtgr ~]# java -version
java version "1.7.0_79"
Java(TM) SE Runtime Environment (build 1.7.0_79-b15)
Java HotSpot(TM) 64-Bit Server VM (build 24.79-b02, mixed mode)
[root@dtgr ~]# javac -version
javac 1.7.0_79
[root@dn-3 ~]# cat /etc/sysconfig/network
NETWORKING=yes
HOSTNAME=dn-3
[root@dn-3 ~]# hostname dn-3
[root@dn-3 ~]# cat /etc/hosts
127.0.0.1 localhost localhost.localdomain localhost4 localhost4.localdomain4
::1 localhost localhost.localdomain localhost6 localhost6.localdomain6
192.168.9.21 nn-1
192.168.9.22 nn-2
192.168.9.23 dn-1
192.168.9.24 dn-2
192.168.9.25 dn-3
[root@dn-3 ~]# useradd -d /hadoop hadoop
[root@dn-3 ~]# service iptables stop
[root@dn-3 ~]# chkconfig iptables off
[root@dn-3 ~]# chkconfig --list | grep iptables
iptables 0:关闭 1:关闭 2:关闭 3:关闭 4:关闭 5:关闭 6:关闭
[root@dn-3 ~]#
[root@dn-3 ~]# setenforce 0
setenforce: SELinux is disabled
[root@dn-3 ~]# vim /etc/sysconfig/selinux
SELINUX=disabled
[hadoop@nn-1 ~]$ ssh-keygen -t rsa
[hadoop@nn-1 ~]$ ssh nn-1 ‘cat ./.ssh/id_rsa.pub‘ >> authorized_keys
hadoop@nn-1‘s password:
[hadoop@nn-1 ~]$
[hadoop@nn-1 .ssh]$ chmod 644 authorized_keys
[hadoop@nn-1 .ssh]$ scp authorized_keys hadoop@nn-2:/hadoop/.ssh/
export JAVA_HOME=/usr/local/java/jdk1.7.0_79
export HADOOP_HEAPSIZE=2000
export HADOOP_NAMENODE_INIT_HEAPSIZE=10000
export HADOOP_OPTS="-server $HADOOP_OPTS -Djava.net.preferIPv4Stack=true"
export HADOOP_NAMENODE_OPTS="-Xmx15000m -Xms15000m -Dhadoop.security.logger=${HADOOP_SECURITY_LOGGER:-INFO,RFAS} -Dhdfs.audit.logger
=${HDFS_AUDIT_LOGGER:-INFO,NullAppender} $HADOOP_NAMENODE_OPTS"
<configuration>
<property>
<name>fs.defaultFS</name>
<value>hdfs://dpi</value>
</property>
<property>
<name>io.file.buffer.size</name>
<value>131072</value>
</property>
<property>
<name>hadoop.tmp.dir</name>
<value>file:/hadoop/hdfs/temp</value>
<description>Abase for other temporary directories.</description>
</property>
<property>
<name>hadoop.proxyuser.hduser.hosts</name>
<value>*</value>
</property>
<property>
<name>hadoop.proxyuser.hduser.groups</name>
<value>*</value>
</property>
<property>
<name>ha.zookeeper.quorum</name>
<value>dn-1:2181,dn-2:2181,dn-3:2181</value>
</property>
</configuration>
<configuration>
<property>
<name>dfs.namenode.secondary.http-address</name>
<value>nn-1:9001</value>
</property>
<property>
<name>dfs.namenode.name.dir</name>
<value>file:/hadoop/hdfs/name</value>
</property>
<property>
<name>dfs.datanode.data.dir</name>
<value>file:/hadoop/hdfs/data,file:/hadoopdata/hdfs/data</value>
</property>
<property>
<name>dfs.replication</name>
<value>3</value>
</property>
<property>
<name>dfs.webhdfs.enabled</name>
<value>true</value>
</property>
<property>
<name>dfs.nameservices</name>
<value>dpi</value>
</property>
<property>
<name>dfs.ha.namenodes.dpi</name>
<value>nn-1,nn-2</value>
</property>
<property>
<name>dfs.namenode.rpc-address.dpi.nn-1</name>
<value>nn-1:9000</value>
</property>
<property>
<name>dfs.namenode.http-address.dpi.nn-1</name>
<value>nn-1:50070</value>
</property>
<property>
<name>dfs.namenode.rpc-address.dpi.nn-2</name>
<value>nn-2:9000</value>
</property>
<property>
<name>dfs.namenode.http-address.dpi.nn-2</name>
<value>nn-2:50070</value>
</property>
<property>
<name>dfs.namenode.servicerpc-address.dpi.nn-1</name>
<value>nn-1:53310</value>
</property>
<property>
<name>dfs.namenode.servicerpc-address.dpi.nn-2</name>
<value>nn-2:53310</value>
</property>
<property>
<name>dfs.ha.automatic-failover.enabled</name>
<value>true</value>
</property>
<property>
<name>dfs.namenode.shared.edits.dir</name>
<value>qjournal://nn-1:8485;nn-2:8485;dn-1:8485/dpi</value>
</property>
<property>
<name>dfs.client.failover.proxy.provider.dpi</name>
<value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>
</property>
<property>
<name>dfs.journalnode.edits.dir</name>
<value>/hadoop/hdfs/journal</value>
</property>
<property>
<name>dfs.ha.fencing.methods</name>
<value>sshfence</value>
</property>
<property>
<name>dfs.ha.fencing.ssh.private-key-files</name>
<value>/hadoop/.ssh/id_rsa</value>
</property>
</configuration>
mkdir -p /hadoop/hdfs/name
mkdir -p /hadoop/hdfs/data
mkdir -p /hadoop/hdfs/temp
mkdir -p /hadoop/hdfs/journal
授权:chmod 755 /hadoop/hdfs
mkdir -p /hadoopdata/hdfs/data
chmod 755 /hadoopdata/hdfs
<configuration>
<property>
<name>mapreduce.framework.name</name>
<value>yarn</value>
</property>
<property>
<name>mapreduce.jobhistory.address</name>
<value>nn-1:10020</value>
</property>
<property>
<name>mapreduce.jobhistory.webapp.address</name>
<value>nn-1:19888</value>
</property>
</configuration>
<configuration>
<!-- Site specific YARN configuration properties -->
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
<property>
<name>yarn.nodemanager.aux-services.mapreduce.shuffle.class</name>
<value>org.apache.hadoop.mapred.ShuffleHandler</value>
</property>
<property>
<name>yarn.resourcemanager.address</name>
<value>dn-1:8032</value>
</property>
<property>
<name>yarn.resourcemanager.scheduler.address</name>
<value>dn-1:8030</value>
</property>
<property>
<name>yarn.resourcemanager.resource-tracker.address</name>
<value>dn-1:8031</value>
</property>
<property>
<name>yarn.resourcemanager.admin.address</name>
<value>dn-1:8033</value>
</property>
<property>
<name>yarn.resourcemanager.webapp.address</name>
<value>dn-1:8088</value>
</property>
</configuration>
dn-1
dn-2
dn-3
# some Java parameters
# export JAVA_HOME=/home/y/libexec/jdk1.6.0/
if [ "$JAVA_HOME" != "" ]; then
#echo "run java in $JAVA_HOME"
JAVA_HOME=/usr/local/java/jdk1.7.0_79
fi
JAVA_HEAP_MAX=-Xmx15000m
YARN_HEAPSIZE=15000
export YARN_RESOURCEMANAGER_HEAPSIZE=5000
export YARN_TIMELINESERVER_HEAPSIZE=10000
export YARN_NODEMANAGER_HEAPSIZE=10000
[hadoop@nn-1 ~]$ scp -rp hadoop hadoop@nn-2:/hadoop
[hadoop@nn-1 ~]$ scp -rp hadoop hadoop@dn-1:/hadoop
[hadoop@nn-1 ~]$ scp -rp hadoop hadoop@dn-2:/hadoop
[hadoop@nn-1 ~]$ scp -rp hadoop hadoop@dn-3:/hadoop
dataDir=/hadoop/zookeeper/data/
dataLogDir=/hadoop/zookeeper/log/
# the port at which the clients will connect
clientPort=2181
server.1=nn-1:2887:3887
server.2=dn-1:2888:3888
server.3=dn-2:2889:3889
[hadoop@nn-1 ~]$ scp -rp zookeeper hadoop@dn-1:/hadoop
[hadoop@nn-1 ~]$ scp -rp zookeeper hadoop@dn-2:/hadoop
[hadoop@dn-1 ~]$ mkdir /hadoop/zookeeper/data/
[hadoop@dn-1 ~]$ mkdir /hadoop/zookeeper/log/
[hadoop@nn-1 data]$ echo 1 > /hadoop/zookeeper/data/myid
$ echo "export ZOOKEEPER_HOME=/hadoop/zookeeper" >> $HOME/.bash_profile
$ echo "export PATH=$ZOOKEEPER_HOME/bin:\$PATH" >> $HOME/.bash_profile
$ source $HOME/.bash_profile
[hadoop@nn-1 ~]$ /hadoop/zookeeper/bin/zkServer.sh start
JMX enabled by default
Using config: /hadoop/zookeeper/bin/../conf/zoo.cfg
Starting zookeeper ... STARTED
[hadoop@nn-1 ~]$ jps
9382 QuorumPeerMain
9407 Jps
[hadoop@nn-1 ~]$ /hadoop/zookeeper/bin/zkServer.sh status
JMX enabled by default
Using config: /hadoop/zookeeper/bin/../conf/zoo.cfg
Mode: follower
[hadoop@dn-1 data]$ /hadoop/zookeeper/bin/zkServer.sh status
JMX enabled by default
Using config: /hadoop/zookeeper/bin/../conf/zoo.cfg
Mode: leader
[hadoop@nn-1 ~]$ /hadoop/hadoop/bin/hdfs zkfc -formatZK
[hadoop@nn-1 bin]$ ./zkCli.sh
[hadoop@nn-1 ~]$ /hadoop/hadoop/sbin/hadoop-daemon.sh start zkfc
starting zkfc, logging to /hadoop/hadoop/logs/hadoop-hadoop-zkfc-nn-1.out
[hadoop@nn-1 ~]$ jps
9681 Jps
9638 DFSZKFailoverController
9382 QuorumPeerMain
[hadoop@nn-1 ~]$ /hadoop/hadoop/sbin/hadoop-daemon.sh start journalnode
starting journalnode, logging to /hadoop/hadoop/logs/hadoop-hadoop-journalnode-nn-1.out
[hadoop@nn-1 ~]$ jps
9714 JournalNode
9638 DFSZKFailoverController
9382 QuorumPeerMain
9762 Jps
[hadoop@nn-1 ~]$ /hadoop/hadoop/bin/hadoop namenode -format
[hadoop@nn-1 ~]$ /hadoop/hadoop/sbin/hadoop-daemon.sh start namenode
starting namenode, logging to /hadoop/hadoop/logs/hadoop-hadoop-namenode-nn-1.out
[hadoop@nn-1 ~]$ jps
9714 JournalNode
9638 DFSZKFailoverController
9382 QuorumPeerMain
10157 NameNode
10269 Jps
[hadoop@nn-2 ~]$ /hadoop/hadoop/bin/hdfs namenode -bootstrapStandby
[hadoop@nn-2 ~]$ /hadoop/hadoop/sbin/hadoop-daemon.sh start namenode
starting namenode, logging to /hadoop/hadoop/logs/hadoop-hadoop-namenode-nn-2.out
[hadoop@nn-2 ~]$ jps
53990 NameNode
54083 Jps
53824 JournalNode
53708 DFSZKFailoverController
[hadoop@dn-1 ~]$ /hadoop/hadoop/sbin/hadoop-daemon.sh start datanode
[hadoop@dn-1 temp]$ jps
57007 Jps
56927 DataNode
56223 QuorumPeerMain
[hadoop@dn-1 ~]$ /hadoop/hadoop/sbin/yarn-daemon.sh start resourcemanager
starting resourcemanager, logging to /hadoop/hadoop/logs/yarn-hadoop-resourcemanager-dn-1.out
[hadoop@dn-1 ~]$ jps
57173 QuorumPeerMain
58317 Jps
57283 JournalNode
58270 ResourceManager
58149 DataNode
[hadoop@nn-1 ~]$ /hadoop/hadoop/sbin/mr-jobhistory-daemon.sh start historyserver
starting historyserver, logging to /hadoop/hadoop/logs/mapred-hadoop-historyserver-nn-1.out
[hadoop@nn-1 ~]$ jps
11210 JobHistoryServer
9714 JournalNode
9638 DFSZKFailoverController
9382 QuorumPeerMain
11039 NameNode
11303 Jps
[hadoop@dn-1 ~]$ /hadoop/hadoop/sbin/yarn-daemon.sh start nodemanager
starting nodemanager, logging to /hadoop/hadoop/logs/yarn-hadoop-nodemanager-dn-1.out
[hadoop@dn-1 ~]$ jps
58559 NodeManager
57173 QuorumPeerMain
58668 Jps
57283 JournalNode
58270 ResourceManager
58149 DataNode
[hadoop@nn-2 ~]$ /hadoop/hadoop/bin/hdfs haadmin -getServiceState nn-1
[hadoop@nn-2 ~]$ /hadoop/hadoop/bin/hdfs haadmin -DfSHAadmin -failover nn-1 nn-2
[hadoop@nn-2 ~]$ /hadoop/hadoop/bin/hdfs haadmin -checkHealth nn-1
[hadoop@nn-2 ~]$ /hadoop/hadoop/bin/hdfs dfsadmin -report | more
[hadoop@nn-2 ~]$ /hadoop/hadoop/bin/hdfs dfsadmin -report -live
17/03/01 22:49:43 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
Configured Capacity: 224954695680 (209.51 GB)
Present Capacity: 180557139968 (168.16 GB)
DFS Remaining: 179963428864 (167.60 GB)
DFS Used: 593711104 (566.21 MB)
DFS Used%: 0.33%
Under replicated blocks: 2
Blocks with corrupt replicas: 0
Missing blocks: 0
-------------------------------------------------
Live datanodes (3):
Name: 192.168.9.23:50010 (dn-1)
Hostname: dn-1
Rack: /rack2
Decommission Status : Normal
Configured Capacity: 74984898560 (69.84 GB)
DFS Used: 197902336 (188.73 MB)
Non DFS Used: 14869356544 (13.85 GB)
DFS Remaining: 59917639680 (55.80 GB)
DFS Used%: 0.26%
DFS Remaining%: 79.91%
Configured Cache Capacity: 0 (0 B)
Cache Used: 0 (0 B)
Cache Remaining: 0 (0 B)
Cache Used%: 100.00%
Cache Remaining%: 0.00%
Xceivers: 1
Last contact: Wed Mar 01 22:49:42 CST 2017
[hadoop@nn-2 ~]$ /hadoop/hadoop/bin/hdfs dfsadmin -report -dead
[hadoop@nn-2 ~]$ /hadoop/hadoop/bin/hdfs haadmin -checkHealth nn-2
17/03/01 22:55:01 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
[hadoop@nn-2 ~]$ /hadoop/hadoop/bin/hdfs haadmin -checkHealth nn-1
17/03/01 22:55:08 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
[hadoop@dn-1 hadoop]$ yarn rmadmin -getServiceState rm1
- active
[hadoop@dn-1 hadoop]$ yarn rmadmin -getServiceState rm2
- standby
[hadoop@dn-1 hadoop]$ /hadoop/hadoop/bin/yarn node -all -list
17/03/01 23:06:40 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
Total Nodes:3
Node-Id Node-State Node-Http-Address Number-of-Running-Containers
dn-2:55506 RUNNING dn-2:8042 0
dn-1:56447 RUNNING dn-1:8042 0
dn-3:37533 RUNNING dn-3:8042 0
[hadoop@dn-1 hadoop]$ /hadoop/hadoop/bin/yarn node -list
17/03/01 23:07:41 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
Total Nodes:3
Node-Id Node-State Node-Http-Address Number-of-Running-Containers
dn-2:55506 RUNNING dn-2:8042 0
dn-1:56447 RUNNING dn-1:8042 0
dn-3:37533 RUNNING dn-3:8042 0
[hadoop@dn-1 hadoop]$ /hadoop/hadoop/bin/yarn node -status dn-2:55506
17/03/01 23:08:16 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
Node Report :
Node-Id : dn-2:55506
Rack : /default-rack
Node-State : RUNNING
Node-Http-Address : dn-2:8042
Last-Health-Update : 星期三 01/三月/17 11:06:21:373CST
Health-Report :
Containers : 0
Memory-Used : 0MB
Memory-Capacity : 8192MB
CPU-Used : 0 vcores
CPU-Capacity : 8 vcores
Node-Labels :
[hadoop@dn-2 ~]$ /hadoop/hadoop/bin/yarn application -list
17/03/01 23:10:09 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
Total number of applications (application-types: [] and states: [SUBMITTED, ACCEPTED, RUNNING]):1
Application-Id Application-Name Application-Type User Queue State Final-State Progress Tracking-URL
application_1488375590901_0004 QuasiMonteCarlo MAPREDUCE hadoop default RUNNING UNDEFINED
[hadoop@dn-1 ~]$ cd hadoop/
[hadoop@dn-1 hadoop]$
[hadoop@dn-1 hadoop]$ ./bin/hadoop jar share/hadoop/mapreduce/hadoop-mapreduce-examples-2.6.0.jar pi 2 200
[hadoop@dn-1 hadoop]$ ./bin/hadoop jar share/hadoop/mapreduce/hadoop-mapreduce-examples-2.6.0.jar pi 2 200
Number of Maps = 2
Samples per Map = 200
17/02/28 01:51:12 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
Wrote input for Map #0
Wrote input for Map #1
Starting Job
17/02/28 01:51:15 INFO input.FileInputFormat: Total input paths to process : 2
17/02/28 01:51:15 INFO mapreduce.JobSubmitter: number of splits:2
17/02/28 01:51:15 INFO mapreduce.JobSubmitter: Submitting tokens for job: job_1488216892564_0001
17/02/28 01:51:16 INFO impl.YarnClientImpl: Submitted application application_1488216892564_0001
17/02/28 01:51:16 INFO mapreduce.Job: The url to track the job: http://dn-1:8088/proxy/application_1488216892564_0001/
17/02/28 01:51:16 INFO mapreduce.Job: Running job: job_1488216892564_0001
17/02/28 01:51:24 INFO mapreduce.Job: Job job_1488216892564_0001 running in uber mode : false
17/02/28 01:51:24 INFO mapreduce.Job: map 0% reduce 0%
17/02/28 01:51:38 INFO mapreduce.Job: map 100% reduce 0%
17/02/28 01:51:49 INFO mapreduce.Job: map 100% reduce 100%
17/02/28 01:51:49 INFO mapreduce.Job: Job job_1488216892564_0001 completed successfully
17/02/28 01:51:50 INFO mapreduce.Job: Counters: 49
File System Counters
FILE: Number of bytes read=50
FILE: Number of bytes written=326922
FILE: Number of read operations=0
FILE: Number of large read operations=0
FILE: Number of write operations=0
HDFS: Number of bytes read=510
HDFS: Number of bytes written=215
HDFS: Number of read operations=11
HDFS: Number of large read operations=0
HDFS: Number of write operations=3
Job Counters
Launched map tasks=2
Launched reduce tasks=1
Data-local map tasks=2
Total time spent by all maps in occupied slots (ms)=25604
Total time spent by all reduces in occupied slots (ms)=7267
Total time spent by all map tasks (ms)=25604
Total time spent by all reduce tasks (ms)=7267
Total vcore-seconds taken by all map tasks=25604
Total vcore-seconds taken by all reduce tasks=7267
Total megabyte-seconds taken by all map tasks=26218496
Total megabyte-seconds taken by all reduce tasks=7441408
Map-Reduce Framework
Map input records=2
Map output records=4
Map output bytes=36
Map output materialized bytes=56
Input split bytes=274
Combine input records=0
Combine output records=0
Reduce input groups=2
Reduce shuffle bytes=56
Reduce input records=4
Reduce output records=0
Spilled Records=8
Shuffled Maps =2
Failed Shuffles=0
Merged Map outputs=2
GC time elapsed (ms)=419
CPU time spent (ms)=6940
Physical memory (bytes) snapshot=525877248
Virtual memory (bytes) snapshot=2535231488
Total committed heap usage (bytes)=260186112
Shuffle Errors
BAD_ID=0
CONNECTION=0
IO_ERROR=0
WRONG_LENGTH=0
WRONG_MAP=0
WRONG_REDUCE=0
File Input Format Counters
Bytes Read=236
File Output Format Counters
Bytes Written=97
Job Finished in 35.466 seconds
Estimated value of Pi is 3.17000000000000000000
[hadoop@nn-1 ~]$ tar -xzvf spark-1.6.0-bin-hadoop2.6.tgz
[hadoop@nn-1 ~]$ tar -xzvf spark-1.6.0-bin-hadoop2.6.tgz
[hadoop@nn-1 conf]$ pwd
/hadoop/spark-1.6.0-bin-hadoop2.6/conf
[hadoop@nn-1 conf]$ cp spark-env.sh.template spark-env.sh
[hadoop@nn-1 conf]$ cp slaves.template slaves
export JAVA_HOME=/usr/local/java/jdk1.7.0_79
export SCALA_HOME=/hadoop/scala-2.11.7
export SPARK_HOME=/hadoop/spark-1.6.0-bin-hadoop2.6
export SPARK_MASTER_IP=nn-1
export SPARK_WORKER_MEMORY=2g
export HADOOP_CONF_DIR=/hadoop/hadoop/etc/hadoop
nn-2
dn-1
dn-2
dn-3
[hadoop@nn-1 ~]$ vim .bash_profile
export HADOOP_HOME=/hadoop/hadoop
export SCALA_HOME=/hadoop/scala-2.11.7
export SPARK_HOME=/hadoop/spark-1.6.0-bin-hadoop2.6
export PATH=$HADOOP_HOME/bin:$HADOOP_HOME/sbin:$SCALA_HOME/bin:$SPARK_HOME/bin:$SPARK_HOME/sbin:$PATH
[hadoop@nn-1 bin]$ cd /hadoop
[hadoop@nn-1 ~]$ scp -rp spark-1.6.0-bin-hadoop2.6 hadoop@dn-1:/hadoop
[hadoop@nn-1 ~]$ scp -rp scala-2.11.7 hadoop@dn-1:/hadoop
[hadoop@nn-1 ~]$ /hadoop/spark-1.6.0-bin-hadoop2.6/sbin/start-all.sh
[hadoop@nn-1 ~]$ jps
2473 JournalNode
2541 NameNode
4401 Jps
2399 DFSZKFailoverController
2687 JobHistoryServer
2775 Master
2351 QuorumPeerMain
[hadoop@dn-1 ~]$ jps
2522 NodeManager
3449 Jps
2007 QuorumPeerMain
2141 DataNode
2688 Worker
2061 JournalNode
2258 ResourceManager
./bin/spark-submit --class org.apache.spark.examples.SparkPi \
--master yarn --deploy-mode cluster \
--driver-memory 100M \
--executor-memory 200M \
--executor-cores 1 \
--queue default \
lib/spark-examples*.jar 10
或者:
./bin/spark-submit --class org.apache.spark.examples.SparkPi \
--master yarn --deploy-mode cluster \
--executor-cores 1 \
--queue default \
lib/spark-examples*.jar 10
<property>
<name>topology.script.file.name</name>
<value>/hadoop/hadoop/etc/hadoop/RackAware.py</value>
</property>
#!/usr/bin/python
#-*-coding:UTF-8 -*-
import sys
rack = {"dn-1":"rack2",
"dn-2":"rack1",
"dn-3":"rack1",
"192.168.9.23":"rack2",
"192.168.9.24":"rack1",
"192.168.9.25":"rack1",
}
if __name__=="__main__":
print "/" + rack.get(sys.argv[1],"rack0")
[root@nn-1 hadoop]# chmod +x RackAware.py
[root@nn-1 hadoop]# ll RackAware.py
-rwxr-xr-x 1 hadoop hadoop 294 3月 1 21:24 RackAware.py
[hadoop@nn-1 ~]$ hadoop-daemon.sh stop namenode
stopping namenode
[hadoop@nn-1 ~]$ hadoop-daemon.sh start namenode
starting namenode, logging to /hadoop/hadoop/logs/hadoop-hadoop-namenode-nn-1.out
[root@nn-1 logs]# pwd
/hadoop/hadoop/logs
[root@nn-1 logs]# vim hadoop-hadoop-namenode-nn-1.log
Apache Hadoop集群安装(NameNode HA + SPARK + 机架感知)
标签:main map cli .net ups :link sample cer 链接
原文地址:http://www.cnblogs.com/xiaohe001/p/6484468.html