$sudo apt-get install default-jdk
[user1@node1] $sudo adduser hadoop $wget http://ftp.jaist.ac.jp/pub/apache/hadoop/common/hadoop-2.0.3-alpha/hadoop-2.0.3-alpha.tar.gz $tar zxvf hadoop-2.0.3-alpha.tar.gz $sudo mv hadoop-2.0.3-alpha /usr/local/hadoop $sudo rm hadoop-2.0.3-alpha.tar.gz $sudo chown hadoop:hadoop -R /usr/local/hadoop/ $sudo su hadoop [hadoop@node1] $cd ~ $ which java /usr/bin/java $vim .bashrc export JAVA_HOME=/usr export HADOOP_INSTALL=/usr/local/hadoop export PATH=$HADOOP_INSTALL/bin:$JAVA_HOME/bin:$PATH $source .bashrc $hadoop version Hadoop 2.0.3-alpha Subversion https://svn.apache.org/repos/asf/hadoop/common/branches/branch-2.0.3-alpha/hadoop-common-project/hadoop-common -r 1443299 Compiled by hortonmu on Thu Feb 7 03:33:19 UTC 2013 From source with checksum 30d3d872f9f4a8d4c53d8cfaa17393f4
[hadoop@node1]
$cp /usr/local/hadoop/etc/hadoop/mapred-site.xml.template /usr/local/hadoop/etc/hadoop/mapred-site.xml
$vim /usr/local/hadoop/etc/hadoop/hadoop-env.sh
export HADOOP_CLIENT_OPTS="-Xmx1024m $HADOOP_CLIENT_OPTS"
(128m -> 1024m)
$mkdir -p hadoop-job/input
$vim hadoop-job/input/a
a b c
$vim hadoop-job/input/b
a a b c c c
$cd hadoop-job/
$hadoop jar /usr/local/hadoop/share/hadoop/mapreduce/hadoop-mapreduce-examples-2.0.3-alpha.jar wordcount input output
13/03/23 14:26:41 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
13/03/23 14:26:41 WARN conf.Configuration: session.id is deprecated. Instead, use dfs.metrics.session-id
13/03/23 14:26:41 INFO jvm.JvmMetrics: Initializing JVM Metrics with processName=JobTracker, sessionId=
13/03/23 14:26:42 INFO input.FileInputFormat: Total input paths to process : 2
13/03/23 14:26:43 INFO mapreduce.JobSubmitter: number of splits:2
13/03/23 14:26:43 WARN conf.Configuration: mapred.jar is deprecated. Instead, use mapreduce.job.jar
13/03/23 14:26:43 WARN conf.Configuration: mapred.output.value.class is deprecated. Instead, use mapreduce.job.output.value.class
13/03/23 14:26:43 WARN conf.Configuration: mapreduce.combine.class is deprecated. Instead, use mapreduce.job.combine.class
13/03/23 14:26:43 WARN conf.Configuration: mapreduce.map.class is deprecated. Instead, use mapreduce.job.map.class
13/03/23 14:26:43 WARN conf.Configuration: mapred.job.name is deprecated. Instead, use mapreduce.job.name
13/03/23 14:26:43 WARN conf.Configuration: mapreduce.reduce.class is deprecated. Instead, use mapreduce.job.reduce.class
13/03/23 14:26:43 WARN conf.Configuration: mapred.input.dir is deprecated. Instead, use mapreduce.input.fileinputformat.inputdir
13/03/23 14:26:43 WARN conf.Configuration: mapred.output.dir is deprecated. Instead, use mapreduce.output.fileoutputformat.outputdir
13/03/23 14:26:43 WARN conf.Configuration: mapred.map.tasks is deprecated. Instead, use mapreduce.job.maps
13/03/23 14:26:43 WARN conf.Configuration: mapred.output.key.class is deprecated. Instead, use mapreduce.job.output.key.class
13/03/23 14:26:43 WARN conf.Configuration: mapred.working.dir is deprecated. Instead, use mapreduce.job.working.dir
13/03/23 14:26:43 INFO mapreduce.JobSubmitter: Submitting tokens for job: job_local780961261_0001
13/03/23 14:26:43 WARN conf.Configuration: file:/tmp/hadoop-hadoop/mapred/staging/hadoop780961261/.staging/job_local780961261_0001/job.xml:an attempt to override final parameter: mapreduce.job.end-notification.max.retry.interval; Ignoring.
13/03/23 14:26:43 WARN conf.Configuration: file:/tmp/hadoop-hadoop/mapred/staging/hadoop780961261/.staging/job_local780961261_0001/job.xml:an attempt to override final parameter: mapreduce.job.end-notification.max.attempts; Ignoring.
13/03/23 14:26:44 WARN conf.Configuration: file:/tmp/hadoop-hadoop/mapred/local/localRunner/job_local780961261_0001.xml:an attempt to override final parameter: mapreduce.job.end-notification.max.retry.interval; Ignoring.
13/03/23 14:26:44 WARN conf.Configuration: file:/tmp/hadoop-hadoop/mapred/local/localRunner/job_local780961261_0001.xml:an attempt to override final parameter: mapreduce.job.end-notification.max.attempts; Ignoring.
13/03/23 14:26:44 INFO mapreduce.Job: The url to track the job: http://localhost:8080/
13/03/23 14:26:44 INFO mapreduce.Job: Running job: job_local780961261_0001
13/03/23 14:26:44 INFO mapred.LocalJobRunner: OutputCommitter set in config null
13/03/23 14:26:44 INFO mapred.LocalJobRunner: OutputCommitter is org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter
13/03/23 14:26:44 INFO mapred.LocalJobRunner: Waiting for map tasks
13/03/23 14:26:44 INFO mapred.LocalJobRunner: Starting task: attempt_local780961261_0001_m_000000_0
13/03/23 14:26:44 INFO mapred.Task: Using ResourceCalculatorProcessTree : [ ]
13/03/23 14:26:44 INFO mapred.MapTask: Processing split: file:/home/hadoop/hadoop-job/input/b:0+12
13/03/23 14:26:44 INFO mapred.MapTask: Map output collector class = org.apache.hadoop.mapred.MapTask$MapOutputBuffer
13/03/23 14:26:45 INFO mapred.MapTask: (EQUATOR) 0 kvi 26214396(104857584)
13/03/23 14:26:45 INFO mapred.MapTask: mapreduce.task.io.sort.mb: 100
13/03/23 14:26:45 INFO mapred.MapTask: soft limit at 83886080
13/03/23 14:26:45 INFO mapred.MapTask: bufstart = 0; bufvoid = 104857600
13/03/23 14:26:45 INFO mapred.MapTask: kvstart = 26214396; length = 6553600
13/03/23 14:26:45 INFO mapred.LocalJobRunner:
13/03/23 14:26:45 INFO mapred.MapTask: Starting flush of map output
13/03/23 14:26:45 INFO mapred.MapTask: Spilling map output
13/03/23 14:26:45 INFO mapred.MapTask: bufstart = 0; bufend = 36; bufvoid = 104857600
13/03/23 14:26:45 INFO mapred.MapTask: kvstart = 26214396(104857584); kvend = 26214376(104857504); length = 21/6553600
13/03/23 14:26:45 INFO mapred.MapTask: Finished spill 0
13/03/23 14:26:45 INFO mapreduce.Job: Job job_local780961261_0001 running in uber mode : false
13/03/23 14:26:45 INFO mapreduce.Job: map 0% reduce 0%
13/03/23 14:26:45 INFO mapred.Task: Task:attempt_local780961261_0001_m_000000_0 is done. And is in the process of committing
13/03/23 14:26:45 INFO mapred.LocalJobRunner: map
13/03/23 14:26:45 INFO mapred.Task: Task 'attempt_local780961261_0001_m_000000_0' done.
13/03/23 14:26:45 INFO mapred.LocalJobRunner: Finishing task: attempt_local780961261_0001_m_000000_0
13/03/23 14:26:45 INFO mapred.LocalJobRunner: Starting task: attempt_local780961261_0001_m_000001_0
13/03/23 14:26:45 INFO mapred.Task: Using ResourceCalculatorProcessTree : [ ]
13/03/23 14:26:45 INFO mapred.MapTask: Processing split: file:/home/hadoop/hadoop-job/input/a:0+6
13/03/23 14:26:45 INFO mapred.MapTask: Map output collector class = org.apache.hadoop.mapred.MapTask$MapOutputBuffer
13/03/23 14:26:45 INFO mapred.MapTask: (EQUATOR) 0 kvi 26214396(104857584)
13/03/23 14:26:45 INFO mapred.MapTask: mapreduce.task.io.sort.mb: 100
13/03/23 14:26:45 INFO mapred.MapTask: soft limit at 83886080
13/03/23 14:26:45 INFO mapred.MapTask: bufstart = 0; bufvoid = 104857600
13/03/23 14:26:45 INFO mapred.MapTask: kvstart = 26214396; length = 6553600
13/03/23 14:26:45 INFO mapred.LocalJobRunner:
13/03/23 14:26:45 INFO mapred.MapTask: Starting flush of map output
13/03/23 14:26:45 INFO mapred.MapTask: Spilling map output
13/03/23 14:26:45 INFO mapred.MapTask: bufstart = 0; bufend = 18; bufvoid = 104857600
13/03/23 14:26:45 INFO mapred.MapTask: kvstart = 26214396(104857584); kvend = 26214388(104857552); length = 9/6553600
13/03/23 14:26:45 INFO mapred.MapTask: Finished spill 0
13/03/23 14:26:45 INFO mapred.Task: Task:attempt_local780961261_0001_m_000001_0 is done. And is in the process of committing
13/03/23 14:26:45 INFO mapred.LocalJobRunner: map
13/03/23 14:26:45 INFO mapred.Task: Task 'attempt_local780961261_0001_m_000001_0' done.
13/03/23 14:26:45 INFO mapred.LocalJobRunner: Finishing task: attempt_local780961261_0001_m_000001_0
13/03/23 14:26:45 INFO mapred.LocalJobRunner: Map task executor complete.
13/03/23 14:26:45 INFO mapred.Task: Using ResourceCalculatorProcessTree : [ ]
13/03/23 14:26:45 INFO mapred.Merger: Merging 2 sorted segments
13/03/23 14:26:45 INFO mapred.Merger: Down to the last merge-pass, with 2 segments left of total size: 44 bytes
13/03/23 14:26:45 INFO mapred.LocalJobRunner:
13/03/23 14:26:45 WARN conf.Configuration: mapred.skip.on is deprecated. Instead, use mapreduce.job.skiprecords
13/03/23 14:26:45 INFO mapred.Task: Task:attempt_local780961261_0001_r_000000_0 is done. And is in the process of committing
13/03/23 14:26:45 INFO mapred.LocalJobRunner:
13/03/23 14:26:45 INFO mapred.Task: Task attempt_local780961261_0001_r_000000_0 is allowed to commit now
13/03/23 14:26:45 INFO output.FileOutputCommitter: Saved output of task 'attempt_local780961261_0001_r_000000_0' to file:/home/hadoop/hadoop-job/output/_temporary/0/task_local780961261_0001_r_000000
13/03/23 14:26:45 INFO mapred.LocalJobRunner: reduce > reduce
13/03/23 14:26:45 INFO mapred.Task: Task 'attempt_local780961261_0001_r_000000_0' done.
13/03/23 14:26:46 INFO mapreduce.Job: map 100% reduce 100%
13/03/23 14:26:46 INFO mapreduce.Job: Job job_local780961261_0001 completed successfully
13/03/23 14:26:46 INFO mapreduce.Job: Counters: 27
File System Counters
FILE: Number of bytes read=815788
FILE: Number of bytes written=1328068
FILE: Number of read operations=0
FILE: Number of large read operations=0
FILE: Number of write operations=0
Map-Reduce Framework
Map input records=2
Map output records=9
Map output bytes=54
Map output materialized bytes=60
Input split bytes=202
Combine input records=9
Combine output records=6
Reduce input groups=3
Reduce shuffle bytes=0
Reduce input records=6
Reduce output records=3
Spilled Records=12
Shuffled Maps =0
Failed Shuffles=0
Merged Map outputs=0
GC time elapsed (ms)=209
CPU time spent (ms)=0
Physical memory (bytes) snapshot=0
Virtual memory (bytes) snapshot=0
Total committed heap usage (bytes)=437268480
File Input Format Counters
Bytes Read=18
File Output Format Counters
Bytes Written=24
$vim output/part-r-00000
a 3
b 2
c 4
[hadoop@node1] $cd ~ $ssh-keygen -t dsa Generating public/private dsa key pair. Enter file in which to save the key (/home/hadoop/.ssh/id_dsa): /home/hadoop/.ssh/id_dsa Created directory '/home/hadoop/.ssh'. Enter passphrase (empty for no passphrase): --- no passphrase --- Enter same passphrase again: --- no passphrase --- Your identification has been saved in /home/hadoop/.ssh/id_dsa. Your public key has been saved in /home/hadoop/.ssh/id_dsa.pub. The key fingerprint is: The key's randomart image is: $mv .ssh/id_dsa.pub .ssh/authorized_keys $chmod 600 .ssh/authorized_keys $ssh localhost $exit
$vim /usr/local/hadoop/etc/hadoop/hadoop-env.sh
export HADOOP_CLIENT_OPTS="-Xmx1024m $HADOOP_CLIENT_OPTS"
(128m -> 1024m)
export JAVA_HOME=/usr
$vim /usr/local/hadoop/etc/hadoop/core-site.xml
<configuration>
<property>
<name>fs.default.name</name>
<value>hdfs://localhost:9010</value>
</property>
</configuration>
$cp /usr/local/hadoop/etc/hadoop/mapred-site.xml.template /usr/local/hadoop/etc/hadoop/mapred-site.xml
$vim /usr/local/hadoop/etc/hadoop/mapred-site.xml
<configuration>
<property>
<name>mapred.job.tracker</name>
<value>localhost:9011</value>
</property>
</configuration>
$vim /usr/local/hadoop/etc/hadoop/hdfs-site.xml
<configuration>
<property>
<name>dfs.replication</name>
<value>1</value>
</property>
</configuration>
$hadoop namenode -format DEPRECATED: Use of this script to execute hdfs command is deprecated. Instead use the hdfs command for it. 13/03/24 08:12:01 INFO namenode.NameNode: STARTUP_MSG: /************************************************************ STARTUP_MSG: Starting NameNode STARTUP_MSG: host = ip-10-249-88-174.us-west-2.compute.internal/10.249.88.174 STARTUP_MSG: args = [-format] STARTUP_MSG: version = 2.0.3-alpha STARTUP_MSG: classpath = /usr/local/hadoop/etc/hadoop:/usr/local/hadoop/share/hadoop/common/lib/jsr305-1.3.9.jar:/usr/local/hadoop/share/hadoop/common/lib/asm-3.2.jar:/usr/local/hadoop/share/hadoop/common/lib/slf4j-log4j12-1.6.1.jar:/usr/local/hadoop/share/hadoop/common/lib/paranamer-2.3.jar:/usr/local/hadoop/share/hadoop/common/lib/jetty-util-6.1.26.jar:/usr/local/hadoop/share/hadoop/common/lib/hadoop-annotations-2.0.3-alpha.jar:/usr/local/hadoop/share/hadoop/common/lib/hadoop-auth-2.0.3-alpha.jar:/usr/local/hadoop/share/hadoop/common/lib/commons-codec-1.4.jar:/usr/local/hadoop/share/hadoop/common/lib/commons-beanutils-1.7.0.jar:/usr/local/hadoop/share/hadoop/common/lib/jsp-api-2.1.jar:/usr/local/hadoop/share/hadoop/common/lib/protobuf-java-2.4.0a.jar:/usr/local/hadoop/share/hadoop/common/lib/netty-3.2.4.Final.jar:/usr/local/hadoop/share/hadoop/common/lib/jersey-json-1.8.jar:/usr/local/hadoop/share/hadoop/common/lib/commons-math-2.1.jar:/usr/local/hadoop/share/hadoop/common/lib/jettison-1.1.jar:/usr/local/hadoop/share/hadoop/common/lib/commons-cli-1.2.jar:/usr/local/hadoop/share/hadoop/common/lib/jsch-0.1.42.jar:/usr/local/hadoop/share/hadoop/common/lib/jetty-6.1.26.jar:/usr/local/hadoop/share/hadoop/common/lib/zookeeper-3.4.2.jar:/usr/local/hadoop/share/hadoop/common/lib/commons-io-2.1.jar:/usr/local/hadoop/share/hadoop/common/lib/kfs-0.3.jar:/usr/local/hadoop/share/hadoop/common/lib/jline-0.9.94.jar:/usr/local/hadoop/share/hadoop/common/lib/commons-logging-1.1.1.jar:/usr/local/hadoop/share/hadoop/common/lib/commons-beanutils-core-1.8.0.jar:/usr/local/hadoop/share/hadoop/common/lib/avro-1.5.3.jar:/usr/local/hadoop/share/hadoop/common/lib/jackson-mapper-asl-1.8.8.jar:/usr/local/hadoop/share/hadoop/common/lib/commons-collections-3.2.1.jar:/usr/local/hadoop/share/hadoop/common/lib/jaxb-impl-2.2.3-1.jar:/usr/local/hadoop/share/hadoop/common/lib/stax-api-1.0.1.jar:/usr/local/hadoop/share/hadoop/common/lib/commons-net-3.1.jar:/usr/local/hadoop/share/hadoop/common/lib/commons-lang-2.5.jar:/usr/local/hadoop/share/hadoop/common/lib/commons-el-1.0.jar:/usr/local/hadoop/share/hadoop/common/lib/jasper-runtime-5.5.23.jar:/usr/local/hadoop/share/hadoop/common/lib/guava-11.0.2.jar:/usr/local/hadoop/share/hadoop/common/lib/commons-httpclient-3.1.jar:/usr/local/hadoop/share/hadoop/common/lib/jaxb-api-2.2.2.jar:/usr/local/hadoop/share/hadoop/common/lib/jersey-core-1.8.jar:/usr/local/hadoop/share/hadoop/common/lib/activation-1.1.jar:/usr/local/hadoop/share/hadoop/common/lib/commons-digester-1.8.jar:/usr/local/hadoop/share/hadoop/common/lib/servlet-api-2.5.jar:/usr/local/hadoop/share/hadoop/common/lib/jasper-compiler-5.5.23.jar:/usr/local/hadoop/share/hadoop/common/lib/xmlenc-0.52.jar:/usr/local/hadoop/share/hadoop/common/lib/snappy-java-1.0.3.2.jar:/usr/local/hadoop/share/hadoop/common/lib/jets3t-0.6.1.jar:/usr/local/hadoop/share/hadoop/common/lib/jersey-server-1.8.jar:/usr/local/hadoop/share/hadoop/common/lib/slf4j-api-1.6.1.jar:/usr/local/hadoop/share/hadoop/common/lib/commons-configuration-1.6.jar:/usr/local/hadoop/share/hadoop/common/lib/jackson-xc-1.8.8.jar:/usr/local/hadoop/share/hadoop/common/lib/jackson-jaxrs-1.8.8.jar:/usr/local/hadoop/share/hadoop/common/lib/jackson-core-asl-1.8.8.jar:/usr/local/hadoop/share/hadoop/common/lib/log4j-1.2.17.jar:/usr/local/hadoop/share/hadoop/common/hadoop-common-2.0.3-alpha.jar:/usr/local/hadoop/share/hadoop/common/hadoop-common-2.0.3-alpha-tests.jar:/contrib/capacity-scheduler/*.jar:/contrib/capacity-scheduler/*.jar:/usr/local/hadoop/share/hadoop/hdfs:/usr/local/hadoop/share/hadoop/hdfs/lib/jsr305-1.3.9.jar:/usr/local/hadoop/share/hadoop/hdfs/lib/asm-3.2.jar:/usr/local/hadoop/share/hadoop/hdfs/lib/jetty-util-6.1.26.jar:/usr/local/hadoop/share/hadoop/hdfs/lib/commons-codec-1.4.jar:/usr/local/hadoop/share/hadoop/hdfs/lib/jsp-api-2.1.jar:/usr/local/hadoop/share/hadoop/hdfs/lib/protobuf-java-2.4.0a.jar:/usr/local/hadoop/share/hadoop/hdfs/lib/commons-cli-1.2.jar:/usr/local/hadoop/share/hadoop/hdfs/lib/commons-daemon-1.0.3.jar:/usr/local/hadoop/share/hadoop/hdfs/lib/jetty-6.1.26.jar:/usr/local/hadoop/share/hadoop/hdfs/lib/commons-io-2.1.jar:/usr/local/hadoop/share/hadoop/hdfs/lib/commons-logging-1.1.1.jar:/usr/local/hadoop/share/hadoop/hdfs/lib/jackson-mapper-asl-1.8.8.jar:/usr/local/hadoop/share/hadoop/hdfs/lib/commons-lang-2.5.jar:/usr/local/hadoop/share/hadoop/hdfs/lib/commons-el-1.0.jar:/usr/local/hadoop/share/hadoop/hdfs/lib/jasper-runtime-5.5.23.jar:/usr/local/hadoop/share/hadoop/hdfs/lib/guava-11.0.2.jar:/usr/local/hadoop/share/hadoop/hdfs/lib/jersey-core-1.8.jar:/usr/local/hadoop/share/hadoop/hdfs/lib/servlet-api-2.5.jar:/usr/local/hadoop/share/hadoop/hdfs/lib/xmlenc-0.52.jar:/usr/local/hadoop/share/hadoop/hdfs/lib/jersey-server-1.8.jar:/usr/local/hadoop/share/hadoop/hdfs/lib/jackson-core-asl-1.8.8.jar:/usr/local/hadoop/share/hadoop/hdfs/lib/log4j-1.2.17.jar:/usr/local/hadoop/share/hadoop/hdfs/hadoop-hdfs-2.0.3-alpha-tests.jar:/usr/local/hadoop/share/hadoop/hdfs/hadoop-hdfs-2.0.3-alpha.jar:/usr/local/hadoop/share/hadoop/yarn/lib/asm-3.2.jar:/usr/local/hadoop/share/hadoop/yarn/lib/junit-4.8.2.jar:/usr/local/hadoop/share/hadoop/yarn/lib/paranamer-2.3.jar:/usr/local/hadoop/share/hadoop/yarn/lib/jersey-guice-1.8.jar:/usr/local/hadoop/share/hadoop/yarn/lib/hadoop-annotations-2.0.3-alpha.jar:/usr/local/hadoop/share/hadoop/yarn/lib/protobuf-java-2.4.0a.jar:/usr/local/hadoop/share/hadoop/yarn/lib/guice-servlet-3.0.jar:/usr/local/hadoop/share/hadoop/yarn/lib/netty-3.2.4.Final.jar:/usr/local/hadoop/share/hadoop/yarn/lib/javax.inject-1.jar:/usr/local/hadoop/share/hadoop/yarn/lib/commons-io-2.1.jar:/usr/local/hadoop/share/hadoop/yarn/lib/avro-1.5.3.jar:/usr/local/hadoop/share/hadoop/yarn/lib/jackson-mapper-asl-1.8.8.jar:/usr/local/hadoop/share/hadoop/yarn/lib/guice-3.0.jar:/usr/local/hadoop/share/hadoop/yarn/lib/jersey-core-1.8.jar:/usr/local/hadoop/share/hadoop/yarn/lib/aopalliance-1.0.jar:/usr/local/hadoop/share/hadoop/yarn/lib/snappy-java-1.0.3.2.jar:/usr/local/hadoop/share/hadoop/yarn/lib/jersey-server-1.8.jar:/usr/local/hadoop/share/hadoop/yarn/lib/jackson-core-asl-1.8.8.jar:/usr/local/hadoop/share/hadoop/yarn/lib/log4j-1.2.17.jar:/usr/local/hadoop/share/hadoop/yarn/hadoop-yarn-applications-unmanaged-am-launcher-2.0.3-alpha.jar:/usr/local/hadoop/share/hadoop/yarn/hadoop-yarn-client-2.0.3-alpha.jar:/usr/local/hadoop/share/hadoop/yarn/hadoop-yarn-applications-distributedshell-2.0.3-alpha.jar:/usr/local/hadoop/share/hadoop/yarn/hadoop-yarn-server-resourcemanager-2.0.3-alpha.jar:/usr/local/hadoop/share/hadoop/yarn/hadoop-yarn-common-2.0.3-alpha.jar:/usr/local/hadoop/share/hadoop/yarn/hadoop-yarn-server-common-2.0.3-alpha.jar:/usr/local/hadoop/share/hadoop/yarn/hadoop-yarn-server-tests-2.0.3-alpha-tests.jar:/usr/local/hadoop/share/hadoop/yarn/hadoop-yarn-server-web-proxy-2.0.3-alpha.jar:/usr/local/hadoop/share/hadoop/yarn/hadoop-yarn-server-tests-2.0.3-alpha.jar:/usr/local/hadoop/share/hadoop/yarn/hadoop-yarn-server-nodemanager-2.0.3-alpha.jar:/usr/local/hadoop/share/hadoop/yarn/hadoop-yarn-site-2.0.3-alpha.jar:/usr/local/hadoop/share/hadoop/yarn/hadoop-yarn-api-2.0.3-alpha.jar:/usr/local/hadoop/share/hadoop/mapreduce/lib/asm-3.2.jar:/usr/local/hadoop/share/hadoop/mapreduce/lib/junit-4.8.2.jar:/usr/local/hadoop/share/hadoop/mapreduce/lib/paranamer-2.3.jar:/usr/local/hadoop/share/hadoop/mapreduce/lib/jersey-guice-1.8.jar:/usr/local/hadoop/share/hadoop/mapreduce/lib/hadoop-annotations-2.0.3-alpha.jar:/usr/local/hadoop/share/hadoop/mapreduce/lib/protobuf-java-2.4.0a.jar:/usr/local/hadoop/share/hadoop/mapreduce/lib/guice-servlet-3.0.jar:/usr/local/hadoop/share/hadoop/mapreduce/lib/netty-3.2.4.Final.jar:/usr/local/hadoop/share/hadoop/mapreduce/lib/javax.inject-1.jar:/usr/local/hadoop/share/hadoop/mapreduce/lib/commons-io-2.1.jar:/usr/local/hadoop/share/hadoop/mapreduce/lib/avro-1.5.3.jar:/usr/local/hadoop/share/hadoop/mapreduce/lib/jackson-mapper-asl-1.8.8.jar:/usr/local/hadoop/share/hadoop/mapreduce/lib/guice-3.0.jar:/usr/local/hadoop/share/hadoop/mapreduce/lib/jersey-core-1.8.jar:/usr/local/hadoop/share/hadoop/mapreduce/lib/aopalliance-1.0.jar:/usr/local/hadoop/share/hadoop/mapreduce/lib/snappy-java-1.0.3.2.jar:/usr/local/hadoop/share/hadoop/mapreduce/lib/jersey-server-1.8.jar:/usr/local/hadoop/share/hadoop/mapreduce/lib/jackson-core-asl-1.8.8.jar:/usr/local/hadoop/share/hadoop/mapreduce/lib/log4j-1.2.17.jar:/usr/local/hadoop/share/hadoop/mapreduce/hadoop-mapreduce-client-core-2.0.3-alpha.jar:/usr/local/hadoop/share/hadoop/mapreduce/hadoop-mapreduce-client-app-2.0.3-alpha.jar:/usr/local/hadoop/share/hadoop/mapreduce/hadoop-mapreduce-examples-2.0.3-alpha.jar:/usr/local/hadoop/share/hadoop/mapreduce/hadoop-mapreduce-client-jobclient-2.0.3-alpha.jar:/usr/local/hadoop/share/hadoop/mapreduce/hadoop-mapreduce-client-shuffle-2.0.3-alpha.jar:/usr/local/hadoop/share/hadoop/mapreduce/hadoop-mapreduce-client-hs-2.0.3-alpha.jar:/usr/local/hadoop/share/hadoop/mapreduce/hadoop-mapreduce-client-hs-plugins-2.0.3-alpha.jar:/usr/local/hadoop/share/hadoop/mapreduce/hadoop-mapreduce-client-common-2.0.3-alpha.jar:/usr/local/hadoop/share/hadoop/mapreduce/hadoop-mapreduce-client-jobclient-2.0.3-alpha-tests.jar STARTUP_MSG: build = https://svn.apache.org/repos/asf/hadoop/common/branches/branch-2.0.3-alpha/hadoop-common-project/hadoop-common -r 1443299; compiled by 'hortonmu' on Thu Feb 7 03:33:19 UTC 2013 STARTUP_MSG: java = 1.6.0_27 ************************************************************/ 13/03/24 08:12:02 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable Formatting using clusterid: CID-b82f0b89-aa2c-4f49-a08a-60e2f7e41ead 13/03/24 08:12:03 INFO util.HostsFileReader: Refreshing hosts (include/exclude) list 13/03/24 08:12:03 INFO blockmanagement.DatanodeManager: dfs.block.invalidate.limit=1000 13/03/24 08:12:03 INFO blockmanagement.BlockManager: dfs.block.access.token.enable=false 13/03/24 08:12:03 INFO blockmanagement.BlockManager: defaultReplication = 1 13/03/24 08:12:03 INFO blockmanagement.BlockManager: maxReplication = 512 13/03/24 08:12:03 INFO blockmanagement.BlockManager: minReplication = 1 13/03/24 08:12:03 INFO blockmanagement.BlockManager: maxReplicationStreams = 2 13/03/24 08:12:03 INFO blockmanagement.BlockManager: shouldCheckForEnoughRacks = false 13/03/24 08:12:03 INFO blockmanagement.BlockManager: replicationRecheckInterval = 3000 13/03/24 08:12:03 INFO blockmanagement.BlockManager: encryptDataTransfer = false 13/03/24 08:12:03 INFO namenode.FSNamesystem: fsOwner = hadoop (auth:SIMPLE) 13/03/24 08:12:03 INFO namenode.FSNamesystem: supergroup = supergroup 13/03/24 08:12:03 INFO namenode.FSNamesystem: isPermissionEnabled = true 13/03/24 08:12:03 INFO namenode.FSNamesystem: HA Enabled: false 13/03/24 08:12:03 INFO namenode.FSNamesystem: Append Enabled: true 13/03/24 08:12:03 INFO namenode.NameNode: Caching file names occuring more than 10 times 13/03/24 08:12:03 INFO namenode.FSNamesystem: dfs.namenode.safemode.threshold-pct = 0.9990000128746033 13/03/24 08:12:03 INFO namenode.FSNamesystem: dfs.namenode.safemode.min.datanodes = 0 13/03/24 08:12:03 INFO namenode.FSNamesystem: dfs.namenode.safemode.extension = 30000 13/03/24 08:12:04 INFO common.Storage: Storage directory /tmp/hadoop-hadoop/dfs/name has been successfully formatted. 13/03/24 08:12:04 INFO namenode.FSImage: Saving image file /tmp/hadoop-hadoop/dfs/name/current/fsimage.ckpt_0000000000000000000 using no compression 13/03/24 08:12:04 INFO namenode.FSImage: Image file of size 121 saved in 0 seconds. 13/03/24 08:12:04 INFO namenode.NNStorageRetentionManager: Going to retain 1 images with txid >= 0 13/03/24 08:12:04 INFO util.ExitUtil: Exiting with status 0 13/03/24 08:12:04 INFO namenode.NameNode: SHUTDOWN_MSG: /************************************************************ SHUTDOWN_MSG: Shutting down NameNode at ip-10-249-88-174.us-west-2.compute.internal/10.249.88.174 ************************************************************/ $ls /tmp/hadoop-hadoop/dfs/name/current/ fsimage_0000000000000000000 seen_txid fsimage_0000000000000000000.md5 VERSION $/usr/local/hadoop/sbin/start-all.sh This script is Deprecated. Instead use start-dfs.sh and start-yarn.sh 13/03/24 08:15:04 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable Starting namenodes on [localhost] localhost: starting namenode, logging to /usr/local/hadoop/logs/hadoop-hadoop-namenode-ip-10-249-88-174.out localhost: starting datanode, logging to /usr/local/hadoop/logs/hadoop-hadoop-datanode-ip-10-249-88-174.out Starting secondary namenodes [0.0.0.0] 0.0.0.0: starting secondarynamenode, logging to /usr/local/hadoop/logs/hadoop-hadoop-secondarynamenode-ip-10-249-88-174.out 13/03/24 08:15:26 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 /usr/local/hadoop/logs/yarn-hadoop-resourcemanager-ip-10-249-88-174.out localhost: starting nodemanager, logging to /usr/local/hadoop/logs/yarn-hadoop-nodemanager-ip-10-249-88-174.out $jps 1659 DataNode 2201 NodeManager 1891 SecondaryNameNode 2231 Jps 2031 ResourceManager 1470 NameNode $hadoop fs -ls / Found 1 items drwxr-xr-x - hadoop supergroup 0 2013-03-24 07:39 /tmp $cd hadoop-job $hadoop fs -put input input $hadoop fs -ls input Found 2 items -rw-r--r-- 1 hadoop supergroup 6 2013-03-24 07:40 /user/hadoop/input/a -rw-r--r-- 1 hadoop supergroup 12 2013-03-24 07:40 /user/hadoop/input/b
$hadoop jar /usr/local/hadoop/share/hadoop/mapreduce/hadoop-mapreduce-examples-2.0.3-alpha.jar wordcount input output $hadoop fs -cat output/part-00000 a 3 b 2 c 4
// cc NewMaxTemperature Application to find the maximum temperature in the weather dataset using the new context objects MapReduce API
import java.io.IOException;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapreduce.*;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
// vv NewMaxTemperature
public class NewMaxTemperature {
static class NewMaxTemperatureMapper
/*[*/extends Mapper<LongWritable, Text, Text, IntWritable>/*]*/ {
private static final int MISSING = 9999;
public void map(LongWritable key, Text value, /*[*/Context context/*]*/)
throws IOException, /*[*/InterruptedException/*]*/ {
String line = value.toString();
String year = line.substring(15, 19);
int airTemperature;
if (line.charAt(87) == '+') { // parseInt doesn't like leading plus signs
airTemperature = Integer.parseInt(line.substring(88, 92));
} else {
airTemperature = Integer.parseInt(line.substring(87, 92));
}
String quality = line.substring(92, 93);
if (airTemperature != MISSING && quality.matches("[01459]")) {
/*[*/context.write/*]*/(new Text(year), new IntWritable(airTemperature));
}
}
}
static class NewMaxTemperatureReducer
/*[*/extends Reducer<Text, IntWritable, Text, IntWritable>/*]*/ {
public void reduce(Text key, /*[*/Iterable/*]*/<IntWritable> values,
/*[*/Context context/*]*/)
throws IOException, /*[*/InterruptedException/*]*/ {
int maxValue = Integer.MIN_VALUE;
for (IntWritable value : values) {
maxValue = Math.max(maxValue, value.get());
}
/*[*/context.write/*]*/(key, new IntWritable(maxValue));
}
}
public static void main(String[] args) throws Exception {
if (args.length != 2) {
System.err.println("Usage: NewMaxTemperature <input path> <output path>");
System.exit(-1);
}
/*[*/Job job = new Job();
job.setJarByClass(NewMaxTemperature.class);/*]*/
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
job.setMapperClass(NewMaxTemperatureMapper.class);
job.setReducerClass(NewMaxTemperatureReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
/*[*/System.exit(job.waitForCompletion(true) ? 0 : 1);/*]*/
}
}
// ^^ NewMaxTemperature 0067011990999991950051507004+68750+023550FM-12+038299999V0203301N00671220001CN9999999N9+00001+99999999999 0043011990999991950051512004+68750+023550FM-12+038299999V0203201N00671220001CN9999999N9+00221+99999999999 0043011990999991950051518004+68750+023550FM-12+038299999V0203201N00261220001CN9999999N9-00111+99999999999 0043012650999991949032412004+62300+010750FM-12+048599999V0202701N00461220001CN0500001N9+01111+99999999999 0043012650999991949032418004+62300+010750FM-12+048599999V0202701N00461220001CN0500001N9+00781+99999999999
$ls sample/ NewMaxTemperature.java sample.txt $hadoop fs -put sample/sample.txt sample.txt $javac -classpath /usr/local/hadoop/hadoop-core-1.1.2.jar sample/NewMaxTemperature.java $jar -cvf sample/newmaxtemperature.jar sample $hadoop jar sample/newmaxtemperature.jar sample.NewMaxTemperature sample.txt sample-out $hadoop fs -cat sample-out/part-r-00000 1949 111 1950 22
Streamlit is a …
I bought M5Stac…