Make all hadoop site settings configurable

playbooks/roles/hadoop_common/defaults/main.yml

@@ -61,6 +61,21 @@ hadoop_common_debian_pkgs:
 
 hadoop_common_redhat_pkgs: []
 
+MAPRED_SITE_DEFAULT_CONFIG:
+  mapreduce.framework.name: "yarn"
+
+YARN_SITE_DEFAULT_CONFIG:
+  yarn.nodemanager.aux-services: "mapreduce_shuffle"
+  yarn.nodemanager.aux-services.mapreduce.shuffle.class: "org.apache.hadoop.mapred.ShuffleHandler"
+
+HADOOP_CORE_SITE_DEFAULT_CONFIG:
+  fs.default.name: "hdfs://localhost:9000"
+
+HDFS_SITE_DEFAULT_CONFIG:
+  dfs.replication: "1"
+  dfs.namenode.name.dir: "file:{{ HADOOP_COMMON_DATA }}/namenode"
+  dfs.datanode.data.dir: "file:{{ HADOOP_COMMON_DATA }}/datanode"
+
 #
 # MapReduce/Yarn memory config (defaults for m1.medium)
 # http://docs.aws.amazon.com/ElasticMapReduce/latest/DeveloperGuide/TaskConfiguration_H2.html
@@ -84,3 +99,5 @@ yarn_site_config:
   # 24 hour log retention
   yarn.log-aggregation.retain-seconds: 86400
 
+HADOOP_CORE_SITE_EXTRA_CONFIG: {}
+HDFS_SITE_EXTRA_CONFIG: {}

playbooks/roles/hadoop_common/templates/core-site.xml.j2

+{% do HADOOP_CORE_SITE_DEFAULT_CONFIG.update(HADOOP_CORE_SITE_EXTRA_CONFIG) %}
 <?xml version="1.0"?>
 <?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
 
 <!-- Put site-specific property overrides in this file. -->
 
 <configuration>
+
+{% for key, value in HADOOP_CORE_SITE_DEFAULT_CONFIG.iteritems() %}
   <property>
-    <name>fs.default.name</name>
-    <value>hdfs://localhost:9000</value>
+    <name>{{ key }}</name>
+    <value>{{ value }}</value>
   </property>
+
+{% endfor %}
 </configuration>
\ No newline at end of file

playbooks/roles/hadoop_common/templates/hdfs-site.xml.j2

+{% do HDFS_SITE_DEFAULT_CONFIG.update(HDFS_SITE_EXTRA_CONFIG) %}
 <?xml version="1.0"?>
 <?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
 
 <configuration>
-  <property>
-    <name>dfs.replication</name>
-    <value>1</value>
-  </property>
-
-  <property>
-    <name>dfs.namenode.name.dir</name>
-    <value>file:{{ HADOOP_COMMON_DATA }}/namenode</value>
-  </property>
 
+{% for key, value in HDFS_SITE_DEFAULT_CONFIG.iteritems() %}
   <property>
-    <name>dfs.datanode.data.dir</name>
-    <value>file:{{ HADOOP_COMMON_DATA }}/datanode</value>
+    <name>{{ key }}</name>
+    <value>{{ value }}</value>
   </property>
 
+{% endfor %}
 </configuration>
\ No newline at end of file

playbooks/roles/hadoop_common/templates/mapred-site.xml.j2

+{% do MAPRED_SITE_DEFAULT_CONFIG.update(mapred_site_config) %}
+
 <?xml version="1.0"?>
 <?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
 
 <configuration>
-  <property>
-    <name>mapreduce.framework.name</name>
-    <value>yarn</value>
-  </property>
 
-{% if mapred_site_config is defined %}
-{% for key,value in mapred_site_config.iteritems() %}
+{% for key, value in MAPRED_SITE_DEFAULT_CONFIG.iteritems() %}
   <property>
     <name>{{ key }}</name>
     <value>{{ value }}</value>
   </property>
-{% endfor %}
-{% endif %}
 
+{% endfor %}
 </configuration>

playbooks/roles/hadoop_common/templates/yarn-site.xml.j2

+{% do YARN_SITE_DEFAULT_CONFIG.update(yarn_site_config) %}
+
 <?xml version="1.0"?>
 
 <configuration>
-  <property>
-    <name>yarn.nodemanager.aux-services</name>
-    <value>mapreduce_shuffle</value>
-  </property>
-
-  <property>
-    <name>yarn.nodemanager.aux-services.mapreduce.shuffle.class</name>
-    <value>org.apache.hadoop.mapred.ShuffleHandler</value>
-  </property>
 
-{% if yarn_site_config is defined %}
-{% for key,value in yarn_site_config.iteritems() %}
+{% for key, value in YARN_SITE_DEFAULT_CONFIG.iteritems() %}
   <property>
     <name>{{ key }}</name>
     <value>{{ value }}</value>
   </property>
-{% endfor %}
-{% endif %}
 
+{% endfor %}
 </configuration>

playbooks/roles/hive/defaults/main.yml

@@ -30,6 +30,23 @@ HIVE_METASTORE_DATABASE:
   host: "{{ HIVE_METASTORE_DATABASE_HOST }}"
   port: "{{ HIVE_METASTORE_DATABASE_PORT }}"
 
+#
+# Vars are used to fill in the hive-site.xml file
+#
+HIVE_SITE_DEFAULT_CONFIG:
+  javax.jdo.option.ConnectionURL: "jdbc:mysql://{{ HIVE_METASTORE_DATABASE.host }}:{{ HIVE_METASTORE_DATABASE.port }}/{{ HIVE_METASTORE_DATABASE.name }}"
+  javax.jdo.option.ConnectionDriverName: "com.mysql.jdbc.Driver"
+  javax.jdo.option.ConnectionUserName: "{{ HIVE_METASTORE_DATABASE.user }}"
+  javax.jdo.option.ConnectionPassword: "{{ HIVE_METASTORE_DATABASE.password }}"
+  datanucleus.autoCreateSchema: "true"
+  hive.metastore.schema.verification: "true"
+
+#
+# Variables override the stock configuration for entry into
+# the hive-site.xml file. Ensure that you use unambiguous
+# string literals to avoid any confusion.
+#
+HIVE_SITE_EXTRA_CONFIG: {}
 
 #
 # vars are namespace with the module name.

playbooks/roles/hive/templates/hive-site.xml.j2

+{% do HIVE_SITE_DEFAULT_CONFIG.update(HIVE_SITE_EXTRA_CONFIG) %}
+
 <?xml version="1.0" encoding="UTF-8" standalone="no"?>
 <?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
+
 <configuration>
+
+{% for key, value in HIVE_SITE_DEFAULT_CONFIG.iteritems() %}
   <property>
-    <name>javax.jdo.option.ConnectionURL</name>  
-    <value>jdbc:mysql://{{ HIVE_METASTORE_DATABASE.host }}:{{ HIVE_METASTORE_DATABASE.port }}/{{ HIVE_METASTORE_DATABASE.name }}</value>
-  </property>
-  <property>
-    <name>javax.jdo.option.ConnectionDriverName</name>  
-    <value>com.mysql.jdbc.Driver</value>
-  </property>
-  <property>
-    <name>javax.jdo.option.ConnectionUserName</name>  
-    <value>{{ HIVE_METASTORE_DATABASE.user }}</value>
-  </property>
-  <property>
-    <name>javax.jdo.option.ConnectionPassword</name>  
-    <value>{{ HIVE_METASTORE_DATABASE.password }}</value>
-  </property>
-  <property>
-    <name>datanucleus.autoCreateSchema</name>  
-    <value>true</value>
-  </property>
-  <property>
-    <name>hive.metastore.schema.verification</name>  
-    <value>true</value>
+    <name>{{ key }}</name>
+    <value>{{ value }}</value>
   </property>
+
+{% endfor %}
 </configuration>