You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
This repo is archived. You can view files and clone it, but cannot push or open issues/pull-requests.
ansible-role-nginx/hadoop/playbooks/job.yml

21 lines
676 B

---
# Launch Job to count occurance of a word.
- hosts: $server
user: root
tasks:
- name: copy the file
copy: src=inputfile dest=/tmp/inputfile
- name: upload the file
shell: su - hdfs -c "hadoop fs -put /tmp/inputfile /inputfile"
- name: Run the MapReduce job to count the occurance of word hello
shell: su - hdfs -c "hadoop jar /usr/lib/hadoop-0.20-mapreduce/hadoop-examples.jar grep /inputfile /outputfile 'hello'"
- name: Fetch the outputfile to local tmp dir
shell: su - hdfs -c "hadoop fs -get /outputfile /tmp/outputfile"
- name: Get the outputfile to ansible server
fetch: dest=/tmp src=/tmp/outputfile/part-00000