This commit is contained in:
2017-10-14 10:15:59 +08:00
parent fb55b8d12e
commit b513ffbbab
11 changed files with 61 additions and 91 deletions

View File

@@ -1,8 +1,8 @@
# based on sequenceiq/hadoop-docker
# based on alpine
## Create a hadoop cluster in swarm mode
`--hostname` needs 1.13 or higher
`--hostname` needs docker 1.13 or higher
```
docker service create \
@@ -84,4 +84,4 @@ YARN: hadoop-master:8088
HDFS: hadoop-master:50070
_Proxy needed, e.g. newnius/docker-proxy_
_Proxy needed: newnius/docker-proxy_

View File

@@ -17,13 +17,12 @@
<!-- Put site-specific property overrides in this file. -->
<configuration>
<property>
<name>fs.defaultFS</name>
<value>hdfs://hadoop-master:8020</value>
</property>
<property>
<name>fs.default.name</name>
<value>hdfs://hadoop-master:8020</value>
</property>
<property>
<name>fs.defaultFS</name>
<value>hdfs://hadoop-master:8020</value>
</property>
<property>
<name>fs.default.name</name>
<value>hdfs://hadoop-master:8020</value>
</property>
</configuration>

View File

@@ -17,30 +17,24 @@
<!-- Put site-specific property overrides in this file. -->
<configuration>
<property>
<name>dfs.permissions</name>
<value>false</value>
</property>
</propert>
<property>
<name>dfs.namenode.secondary.http-address</name>
<value>hadoop-slave1:50090</value>
</property>
</property>
<property>
<name>dfs.namenode.http-address</name>
<value>hadoop-master:50070</value>
</property>
<property>
<name>dfs.datanode.max.transfer.threads</name>
<value>8192</value>
<property>
<name>dfs.datanode.max.transfer.threads</name>
<value>8192</value>
</property>
<property>
<name>dfs.replication</name>
<value>3</value>
</property>
<property>
<name>dfs.replication</name>
<value>3</value>
</property>
</configuration>

View File

@@ -17,8 +17,7 @@
<!-- Put site-specific property overrides in this file. -->
<configuration>
<property>
<property>
<name>mapreduce.framework.name</name>
<value>yarn</value>
</property>
@@ -29,5 +28,5 @@
<property>
<name>mapreduce.jobhistory.webapp.address</name>
<value>hadoop-master:19888</value>
</property>
</property>
</configuration>

View File

@@ -14,33 +14,26 @@
-->
<!-- Site specific YARN configuration properties -->
<configuration>
<property>
<name>yarn.application.classpath</name>
<value>/usr/local/hadoop/etc/hadoop, /usr/local/hadoop/share/hadoop/common/*, /usr/local/hadoop/share/hadoop/common/lib/*, /usr/local/hadoop/share/hadoop/hdfs/*, /usr/local/hadoop/share/hadoop/hdfs/lib/*, /usr/local/hadoop/share/hadoop/mapreduce/*, /usr/local/hadoop/share/hadoop/mapreduce/lib/*, /usr/local/hadoop/share/hadoop/yarn/*, /usr/local/hadoop/share/hadoop/yarn/lib/*</value>
</property>
<property>
<name>yarn.application.classpath</name>
<value>/usr/local/hadoop/etc/hadoop, /usr/local/hadoop/share/hadoop/common/*, /usr/local/hadoop/share/hadoop/common/lib/*, /usr/local/hadoop/share/hadoop/hdfs/*, /usr/local/hadoop/share/hadoop/hdfs/lib/*, /usr/local/hadoop/share/hadoop/mapreduce/*, /usr/local/hadoop/share/hadoop/mapreduce/lib/*, /usr/local/hadoop/share/hadoop/yarn/*, /usr/local/hadoop/share/hadoop/yarn/lib/*</value>
</property>
<property>
<name>yarn.resourcemanager.hostname</name>
<value>hadoop-master</value>
</property>
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
<property>
<name>yarn.log-aggregation-enable</name>
<value>true</value>
</property>
<property>
<name>yarn.log-aggregation.retain-seconds</name>
<value>604800</value>
</property>
<property>
<name>yarn.nodemanager.resource.memory-mb</name>
<value>2048</value>
@@ -49,8 +42,8 @@
<name>yarn.nodemanager.resource.cpu-vcores</name>
<value>2</value>
</property>
<property>
<name>yarn.scheduler.minimum-allocation-mb</name>
<value>1024</value>
</property>
<property>
<name>yarn.scheduler.minimum-allocation-mb</name>
<value>1024</value>
</property>
</configuration>

View File

@@ -1,8 +1,8 @@
# based on sequenceiq/hadoop-docker
# based on alpine
## Create a hadoop cluster in swarm mode
`--hostname` needs 1.13 or higher
`--hostname` needs docker 1.13 or higher
```
docker service create \
@@ -66,7 +66,7 @@ bin/hadoop namenode -format
### Run a test job
bin/hadoop jar share/hadoop/mapreduce/hadoop-mapreduce-examples-2.8.1.jar grep input output 'dfs[a-z.]+'
bin/hadoop jar share/hadoop/mapreduce/hadoop-mapreduce-examples-2.7.4.jar grep input output 'dfs[a-z.]+'
Note: there is no such dir default, you can add data by
@@ -84,4 +84,4 @@ YARN: hadoop-master:8088
HDFS: hadoop-master:50070
_Proxy needed, e.g. newnius/docker-proxy_
_Proxy needed: newnius/docker-proxy_

View File

@@ -17,13 +17,12 @@
<!-- Put site-specific property overrides in this file. -->
<configuration>
<property>
<name>fs.defaultFS</name>
<value>hdfs://hadoop-master:8020</value>
</property>
<property>
<name>fs.default.name</name>
<value>hdfs://hadoop-master:8020</value>
</property>
<property>
<name>fs.defaultFS</name>
<value>hdfs://hadoop-master:8020</value>
</property>
<property>
<name>fs.default.name</name>
<value>hdfs://hadoop-master:8020</value>
</property>
</configuration>

View File

@@ -17,30 +17,24 @@
<!-- Put site-specific property overrides in this file. -->
<configuration>
<property>
<name>dfs.permissions</name>
<value>false</value>
</property>
</propert>
<property>
<name>dfs.namenode.secondary.http-address</name>
<value>hadoop-slave1:50090</value>
</property>
</property>
<property>
<name>dfs.namenode.http-address</name>
<value>hadoop-master:50070</value>
</property>
<property>
<name>dfs.datanode.max.transfer.threads</name>
<value>8192</value>
<property>
<name>dfs.datanode.max.transfer.threads</name>
<value>8192</value>
</property>
<property>
<name>dfs.replication</name>
<value>3</value>
</property>
<property>
<name>dfs.replication</name>
<value>3</value>
</property>
</configuration>

View File

@@ -17,8 +17,7 @@
<!-- Put site-specific property overrides in this file. -->
<configuration>
<property>
<property>
<name>mapreduce.framework.name</name>
<value>yarn</value>
</property>
@@ -29,5 +28,5 @@
<property>
<name>mapreduce.jobhistory.webapp.address</name>
<value>hadoop-master:19888</value>
</property>
</property>
</configuration>

View File

@@ -14,33 +14,26 @@
-->
<!-- Site specific YARN configuration properties -->
<configuration>
<property>
<name>yarn.application.classpath</name>
<value>/usr/local/hadoop/etc/hadoop, /usr/local/hadoop/share/hadoop/common/*, /usr/local/hadoop/share/hadoop/common/lib/*, /usr/local/hadoop/share/hadoop/hdfs/*, /usr/local/hadoop/share/hadoop/hdfs/lib/*, /usr/local/hadoop/share/hadoop/mapreduce/*, /usr/local/hadoop/share/hadoop/mapreduce/lib/*, /usr/local/hadoop/share/hadoop/yarn/*, /usr/local/hadoop/share/hadoop/yarn/lib/*</value>
</property>
<property>
<name>yarn.application.classpath</name>
<value>/usr/local/hadoop/etc/hadoop, /usr/local/hadoop/share/hadoop/common/*, /usr/local/hadoop/share/hadoop/common/lib/*, /usr/local/hadoop/share/hadoop/hdfs/*, /usr/local/hadoop/share/hadoop/hdfs/lib/*, /usr/local/hadoop/share/hadoop/mapreduce/*, /usr/local/hadoop/share/hadoop/mapreduce/lib/*, /usr/local/hadoop/share/hadoop/yarn/*, /usr/local/hadoop/share/hadoop/yarn/lib/*</value>
</property>
<property>
<name>yarn.resourcemanager.hostname</name>
<value>hadoop-master</value>
</property>
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
<property>
<name>yarn.log-aggregation-enable</name>
<value>true</value>
</property>
<property>
<name>yarn.log-aggregation.retain-seconds</name>
<value>604800</value>
</property>
<property>
<name>yarn.nodemanager.resource.memory-mb</name>
<value>2048</value>
@@ -49,8 +42,8 @@
<name>yarn.nodemanager.resource.cpu-vcores</name>
<value>2</value>
</property>
<property>
<name>yarn.scheduler.minimum-allocation-mb</name>
<value>1024</value>
</property>
<property>
<name>yarn.scheduler.minimum-allocation-mb</name>
<value>1024</value>
</property>
</configuration>