| - name: "install hadoop tarball" |
| unarchive: src={{ tarballs_dir }}/{{ hadoop_tarball }} dest={{ install_dir }} creates={{ hadoop_home }} copy=yes |
| - name: "configure hadoop with templates" |
| template: src={{ item }} dest={{ hadoop_home }}/etc/hadoop/{{ item }} |
| with_items: |
| - core-site.xml |
| - hdfs-site.xml |
| - yarn-site.xml |
| - mapred-site.xml |
| - name: "configure hadoop 2" |
| template: src={{ item }} dest={{ hadoop_home }}/etc/hadoop/{{ item }} |
| with_items: |
| - slaves |
| when: hadoop_major_version == '2' |
| - name: "configure hadoop 3" |
| template: src={{ item }} dest={{ hadoop_home }}/etc/hadoop/{{ item }} |
| with_items: |
| - workers |
| when: hadoop_major_version == '3' |
| - name: "copy spark yarn shuffle jar to hadoop lib" |
| command: cp {{ spark_home }}/yarn/spark-{{ spark_version }}-yarn-shuffle.jar {{ hadoop_home }}/share/hadoop/yarn/lib/ creates={{ hadoop_home }}/share/hadoop/yarn/lib/spark-{{ spark_version }}-yarn-shuffle.jar |
| when: "'spark' in groups" |
| - name: "setup hadoop short circuit socket dir" |
| file: path=/var/lib/hadoop-hdfs state=directory owner={{ cluster_user }} group={{ cluster_user }} mode=0755 |
| become: yes |
| - name: "Configure hadoop log dir" |
| replace: |
| path: "{{ hadoop_home }}/etc/hadoop/hadoop-env.sh" |
| regexp: '.*export\s+HADOOP_LOG_DIR.*' |
| replace: "export HADOOP_LOG_DIR={{ worker_data_dirs[0] }}/logs/hadoop" |
| - name: "Create hadoop log dir" |
| file: path={{ worker_data_dirs[0] }}/logs/hadoop state=directory |
| |