docker hadoop v3.1.1

aarshthakkar18 · Oct 5, 2018 · 654ad4b · 654ad4b
1 parent f1080e9
commit 654ad4b
Show file tree

Hide file tree

Showing 12 changed files with 40 additions and 33 deletions.
diff --git a/Makefile b/Makefile
@@ -1,4 +1,4 @@
-DOCKER_NETWORK = dockerhadoop_default
+DOCKER_NETWORK = docker-hadoop_default
 ENV_FILE = hadoop.env
 current_branch := $(shell git rev-parse --abbrev-ref HEAD)
 build:
@@ -13,7 +13,7 @@ build:
 wordcount:
 	docker build -t hadoop-wordcount ./submit
 	docker run --network ${DOCKER_NETWORK} --env-file ${ENV_FILE} bde2020/hadoop-base:$(current_branch) hdfs dfs -mkdir -p /input/
-	docker run --network ${DOCKER_NETWORK} --env-file ${ENV_FILE} bde2020/hadoop-base:$(current_branch) hdfs dfs -copyFromLocal /opt/hadoop-2.7.4/README.txt /input/
+	docker run --network ${DOCKER_NETWORK} --env-file ${ENV_FILE} bde2020/hadoop-base:$(current_branch) hdfs dfs -copyFromLocal /opt/hadoop-3.1.1/README.txt /input/
 	docker run --network ${DOCKER_NETWORK} --env-file ${ENV_FILE} hadoop-wordcount
 	docker run --network ${DOCKER_NETWORK} --env-file ${ENV_FILE} bde2020/hadoop-base:$(current_branch) hdfs dfs -cat /output/*
 	docker run --network ${DOCKER_NETWORK} --env-file ${ENV_FILE} bde2020/hadoop-base:$(current_branch) hdfs dfs -rm -r /output

diff --git a/README.md b/README.md
@@ -7,8 +7,7 @@ Version 2.0.0 introduces uses wait_for_it script for the cluster startup
 # Hadoop Docker
 
 ## Supported Hadoop Versions
-* 2.7.1 with OpenJDK 7
-* 2.7.1 with OpenJDK 8
+See repository branches for supported hadoop versions
 
 ## Quick Start
 
@@ -17,6 +16,11 @@ To deploy an example HDFS cluster, run:
   docker-compose up
 ```
 
+Run example wordcount job:
+```
+  make wordcount
+```
+
 Or deploy in swarm:
 ```
 docker stack deploy -c docker-compose-v3.yml hadoop
@@ -26,9 +30,9 @@ docker stack deploy -c docker-compose-v3.yml hadoop
 
 Run `docker network inspect` on the network (e.g. `dockerhadoop_default`) to find the IP the hadoop interfaces are published on. Access these interfaces with the following URLs:
 
-* Namenode: http://<dockerhadoop_IP_address>:50070/dfshealth.html#tab-overview
+* Namenode: http://<dockerhadoop_IP_address>:9870/dfshealth.html#tab-overview
 * History server: http://<dockerhadoop_IP_address>:8188/applicationhistory
-* Datanode: http://<dockerhadoop_IP_address>:50075/
+* Datanode: http://<dockerhadoop_IP_address>:9864/
 * Nodemanager: http://<dockerhadoop_IP_address>:8042/node
 * Resource manager: http://<dockerhadoop_IP_address>:8088/
 

diff --git a/base/Dockerfile b/base/Dockerfile
@@ -40,11 +40,12 @@ RUN gpg --keyserver pool.sks-keyservers.net --recv-keys \
     0445B7BFC4515847C157ECD16BA72FF1C99785DE \
     B74F188889D159F3D7E64A7F348C6D7A0DCED714 \
     4A6AC5C675B6155682729C9E08D51A0A7501105C \
-    8B44A05C308955D191956559A5CEE20A90348D47
+    8B44A05C308955D191956559A5CEE20A90348D47 \
+    57300D45
 
 RUN gpg --keyserver pool.sks-keyservers.net --recv-key C36C5F0F
 
-ENV HADOOP_VERSION 2.7.4
+ENV HADOOP_VERSION 3.1.1
 ENV HADOOP_URL https://www.apache.org/dist/hadoop/common/hadoop-$HADOOP_VERSION/hadoop-$HADOOP_VERSION.tar.gz
 RUN set -x \
     && curl -fSL "$HADOOP_URL" -o /tmp/hadoop.tar.gz \
@@ -54,7 +55,6 @@ RUN set -x \
     && rm /tmp/hadoop.tar.gz*
 
 RUN ln -s /opt/hadoop-$HADOOP_VERSION/etc/hadoop /etc/hadoop
-RUN cp /etc/hadoop/mapred-site.xml.template /etc/hadoop/mapred-site.xml
 RUN mkdir /opt/hadoop-$HADOOP_VERSION/logs
 
 RUN mkdir /hadoop-data

diff --git a/datanode/Dockerfile b/datanode/Dockerfile
@@ -1,7 +1,7 @@
-FROM bde2020/hadoop-base:2.0.0-hadoop2.7.4-java8
+FROM bde2020/hadoop-base:2.0.0-hadoop3.1.1-java8
 MAINTAINER Ivan Ermilov <[email protected]>
 
-HEALTHCHECK CMD curl -f http://localhost:50075/ || exit 1
+HEALTHCHECK CMD curl -f http://localhost:9864/ || exit 1
 
 ENV HDFS_CONF_dfs_datanode_data_dir=file:///hadoop/dfs/data
 RUN mkdir -p /hadoop/dfs/data
@@ -10,6 +10,6 @@ VOLUME /hadoop/dfs/data
 ADD run.sh /run.sh
 RUN chmod a+x /run.sh
 
-EXPOSE 50075
+EXPOSE 9864
 
 CMD ["/run.sh"]
diff --git a/docker-compose-v3.yml b/docker-compose-v3.yml
@@ -2,7 +2,7 @@ version: '3'
 
 services:
   namenode:
-    image: bde2020/hadoop-namenode:2.0.0-hadoop2.7.4-java8
+    image: bde2020/hadoop-namenode:2.0.0-hadoop3.1.1-java8
     networks:
       - hbase
     volumes:
@@ -24,7 +24,7 @@ services:
         traefik.port: 50070
 
   datanode:
-    image: bde2020/hadoop-datanode:2.0.0-hadoop2.7.4-java8
+    image: bde2020/hadoop-datanode:2.0.0-hadoop3.1.1-java8
     networks:
       - hbase
     volumes:
@@ -42,7 +42,7 @@ services:
         traefik.port: 50075
 
   resourcemanager:
-    image: bde2020/hadoop-resourcemanager:2.0.0-hadoop2.7.4-java8
+    image: bde2020/hadoop-resourcemanager:2.0.0-hadoop3.1.1-java8
     networks:
       - hbase
     environment:
@@ -64,7 +64,7 @@ services:
       disable: true
 
   nodemanager:
-    image: bde2020/hadoop-nodemanager:2.0.0-hadoop2.7.4-java8
+    image: bde2020/hadoop-nodemanager:2.0.0-hadoop3.1.1-java8
     networks:
       - hbase
     environment:
@@ -80,7 +80,7 @@ services:
         traefik.port: 8042
 
   historyserver:
-    image: bde2020/hadoop-historyserver:2.0.0-hadoop2.7.4-java8
+    image: bde2020/hadoop-historyserver:2.0.0-hadoop3.1.1-java8
     networks:
       - hbase
     volumes:

diff --git a/docker-compose.yml b/docker-compose.yml
@@ -2,7 +2,7 @@ version: "3"
 
 services:
   namenode:
-    image: bde2020/hadoop-namenode:2.0.0-hadoop2.7.4-java8
+    image: bde2020/hadoop-namenode:2.0.0-hadoop3.1.1-java8
     container_name: namenode
     volumes:
       - hadoop_namenode:/hadoop/dfs/name
@@ -12,36 +12,36 @@ services:
       - ./hadoop.env
 
   datanode:
-    image: bde2020/hadoop-datanode:2.0.0-hadoop2.7.4-java8
+    image: bde2020/hadoop-datanode:2.0.0-hadoop3.1.1-java8
     container_name: datanode
     volumes:
       - hadoop_datanode:/hadoop/dfs/data
     environment:
-      SERVICE_PRECONDITION: "namenode:50070"
+      SERVICE_PRECONDITION: "namenode:9870"
     env_file:
       - ./hadoop.env
 
   resourcemanager:
-    image: bde2020/hadoop-resourcemanager:2.0.0-hadoop2.7.4-java8
+    image: bde2020/hadoop-resourcemanager:2.0.0-hadoop3.1.1-java8
     container_name: resourcemanager
     environment:
-      SERVICE_PRECONDITION: "namenode:50070 datanode:50075"
+      SERVICE_PRECONDITION: "namenode:9870 datanode:9864"
     env_file:
       - ./hadoop.env
 
   nodemanager1:
-    image: bde2020/hadoop-nodemanager:2.0.0-hadoop2.7.4-java8
+    image: bde2020/hadoop-nodemanager:2.0.0-hadoop3.1.1-java8
     container_name: nodemanager
     environment:
-      SERVICE_PRECONDITION: "namenode:50070 datanode:50075 resourcemanager:8088"
+      SERVICE_PRECONDITION: "namenode:9870 datanode:9864 resourcemanager:8088"
     env_file:
       - ./hadoop.env
 
   historyserver:
-    image: bde2020/hadoop-historyserver:2.0.0-hadoop2.7.4-java8
+    image: bde2020/hadoop-historyserver:2.0.0-hadoop3.1.1-java8
     container_name: historyserver
     environment:
-      SERVICE_PRECONDITION: "namenode:50070 datanode:50075 resourcemanager:8088"
+      SERVICE_PRECONDITION: "namenode:9870 datanode:9864 resourcemanager:8088"
     volumes:
       - hadoop_historyserver:/hadoop/yarn/timeline
     env_file:

diff --git a/hadoop.env b/hadoop.env
@@ -38,3 +38,6 @@ MAPRED_CONF_mapreduce_map_memory_mb=4096
 MAPRED_CONF_mapreduce_reduce_memory_mb=8192
 MAPRED_CONF_mapreduce_map_java_opts=-Xmx3072m
 MAPRED_CONF_mapreduce_reduce_java_opts=-Xmx6144m
+MAPRED_CONF_yarn_app_mapreduce_am_env=HADOOP_MAPRED_HOME=/opt/hadoop-3.1.1/
+MAPRED_CONF_mapreduce_map_env=HADOOP_MAPRED_HOME=/opt/hadoop-3.1.1/
+MAPRED_CONF_mapreduce_reduce_env=HADOOP_MAPRED_HOME=/opt/hadoop-3.1.1/
diff --git a/historyserver/Dockerfile b/historyserver/Dockerfile
@@ -1,4 +1,4 @@
-FROM bde2020/hadoop-base:2.0.0-hadoop2.7.4-java8
+FROM bde2020/hadoop-base:2.0.0-hadoop3.1.1-java8
 MAINTAINER Ivan Ermilov <[email protected]>
 
 HEALTHCHECK CMD curl -f http://localhost:8188/ || exit 1

diff --git a/namenode/Dockerfile b/namenode/Dockerfile
@@ -1,7 +1,7 @@
-FROM bde2020/hadoop-base:2.0.0-hadoop2.7.4-java8
+FROM bde2020/hadoop-base:2.0.0-hadoop3.1.1-java8
 MAINTAINER Ivan Ermilov <[email protected]>
 
-HEALTHCHECK CMD curl -f http://localhost:50070/ || exit 1
+HEALTHCHECK CMD curl -f http://localhost:9870/ || exit 1
 
 ENV HDFS_CONF_dfs_namenode_name_dir=file:///hadoop/dfs/name
 RUN mkdir -p /hadoop/dfs/name
@@ -10,6 +10,6 @@ VOLUME /hadoop/dfs/name
 ADD run.sh /run.sh
 RUN chmod a+x /run.sh
 
-EXPOSE 50070
+EXPOSE 9870
 
 CMD ["/run.sh"]
diff --git a/nodemanager/Dockerfile b/nodemanager/Dockerfile
@@ -1,4 +1,4 @@
-FROM bde2020/hadoop-base:2.0.0-hadoop2.7.4-java8
+FROM bde2020/hadoop-base:2.0.0-hadoop3.1.1-java8
 MAINTAINER Ivan Ermilov <[email protected]>
 
 HEALTHCHECK CMD curl -f http://localhost:8042/ || exit 1

diff --git a/resourcemanager/Dockerfile b/resourcemanager/Dockerfile
@@ -1,4 +1,4 @@
-FROM bde2020/hadoop-base:2.0.0-hadoop2.7.4-java8
+FROM bde2020/hadoop-base:2.0.0-hadoop3.1.1-java8
 MAINTAINER Ivan Ermilov <[email protected]>
 
 HEALTHCHECK CMD curl -f http://localhost:8088/ || exit 1

diff --git a/submit/Dockerfile b/submit/Dockerfile
@@ -1,4 +1,4 @@
-FROM bde2020/hadoop-base:2.0.0-hadoop2.7.4-java8
+FROM bde2020/hadoop-base:2.0.0-hadoop3.1.1-java8
 MAINTAINER Ivan Ermilov <[email protected]>
 
 COPY WordCount.jar /opt/hadoop/applications/WordCount.jar