Merge pull request #738 from edx/e0d/es-cluster

E0d/es cluster

playbooks/edx-east/elasticsearch.yml

+- hosts: tag_play_elasticsearch:&tag_environment_stage:&tag_deployment_edx
+  sudo: True
+  vars_files:
+    - "{{ secure_dir }}/vars/common/common.yml"
+    - "{{ secure_dir }}/vars/stage/stage-edx.yml"
+  roles:
+    - common
+    - gh_users
+    - oraclejdk
+    - elasticsearch

playbooks/roles/elasticsearch/defaults/main.yml

 ---
-
-elasticsearch_version: "0.90.2"
-elasticsearch_sha: "397227ce37f616734f39f6e93539c9eaa82bec9"
+elasticsearch_app_dir: "{{ COMMON_APP_DIR }}/elasticsearch"
+elasticsearch_data_dir: "{{ COMMON_DATA_DIR }}/elasticsearch"
+elasticsearch_log_dir: "{{ COMMON_LOG_DIR }}/elasticsearch"
+elasticsearch_cfg_dir: "{{ COMMON_CFG_DIR }}/elasticsearch"
+elasticsearch_version: "0.90.11"
+elasticsearch_sha: "8e81388d0ba7e427b42514d96e25ba6499024c24"
 elasticsearch_file: "elasticsearch-{{ elasticsearch_version }}.deb"
 elasticsearch_url: "https://download.elasticsearch.org/elasticsearch/elasticsearch/{{ elasticsearch_file }}"
+elasticsearch_user: "elasticsearch"
+elasticsearch_group: "elasticsearch"
+
+#
+# Defaults for a single server installation.
+ELASTICSEARCH_CLUSTERED: true
+ELASTICSEARCH_HEAP_SIZE: "512m"
\ No newline at end of file

playbooks/roles/elasticsearch/tasks/main.yml

@@ -8,29 +8,61 @@
 #   * oraclejdk
 # 
 # Example play:
+#  
+# This role can be used to do a single-server or clustered
+# installation of the elasticsearch service.  When a cluster
+# is being installed, there are two important things that
+# you must know.
+
+# The ELASTICSEARCH_CLUSTERED var must be true.
+
+# All hosts targeted by your play will be cluster peers.
+# Elasticsearch will determine who the master should be.
+#
+# Ansible provides handy set operators for use in the
+# plays host declaration, as seen in the following example.
+#
+# -  hosts: tag_role_elasticsearch:&tag_environment_stage
+#    roles:
+#    - common
+#    - oraclejdk
+#    - elasticsearch
 #
-#   roles:
-#   - common
-#   - oraclejdk
-#   - elasticsearch 
 
 - name: download elasticsearch
   get_url: >
     url={{ elasticsearch_url }}
     dest=/var/tmp/{{ elasticsearch_file }}
     force=no
+  register: elasticsearch_reinstall
 
 - name: install elasticsearch from local package
   shell: >
-    dpkg -i /var/tmp/elasticsearch-{{ elasticsearch_version }}.deb
-    executable=/bin/bash 
-    creates=/usr/share/elasticsearch/bin/elasticsearch
-  tags:
-    - elasticsearch
-    - install
+    dpkg -i  --force-confold /var/tmp/elasticsearch-{{ elasticsearch_version }}.deb
+    executable=/bin/bash
+  when: elasticsearch_reinstall.changed
+
+- name: create directories
+  file: >
+    path="{{ item }}"
+    state=directory
+    owner="{{ elasticsearch_user }}"
+    group="{{ elasticsearch_group }}"
+  with_items:
+    - "{{ elasticsearch_data_dir }}"
+    - "{{ elasticsearch_log_dir }}"
+    - "{{ elasticsearch_cfg_dir }}"
 
+- name: update elasticsearch defaults
+  template: >
+    src=etc/default/elasticsearch.j2 dest=/etc/default/elasticsearch
+  when: ELASTICSEARCH_CLUSTERED
+    
+- name: drop the elasticsearch config
+  template: >
+    src=edx/etc/elasticsearch/elasticsearch.yml.j2 dest={{ elasticsearch_cfg_dir }}/elasticsearch.yml
+    mode=0744
+  when: ELASTICSEARCH_CLUSTERED
+    
 - name: Ensure elasticsearch is enabled and started
-  service: name=elasticsearch state=started enabled=yes
-  tags:
+  service: name=elasticsearch state=restarted enabled=yes
\ No newline at end of file
-    - elasticsearch
-    - install

playbooks/roles/elasticsearch/templates/edx/etc/elasticsearch/elasticsearch.yml.j2

+# {{ ansible_managed }}
+
+
+# Path to directory where to store index data allocated for this node.
+#
+path.data: {{elasticsearch_data_dir}}
+
+# Path to log files:
+#
+path.logs: {{elasticsearch_log_dir}}
+
+# ElasticSearch performs poorly when JVM starts swapping: you should ensure that
+# it _never_ swaps.
+#
+# Set this property to true to lock the memory:
+#
+bootstrap.mlockall: true
+
+# Unicast discovery allows to explicitly control which nodes will be used
+# to discover the cluster. It can be used when multicast is not present,
+# or to restrict the cluster communication-wise.
+#
+# 1. Disable multicast discovery (enabled by default):
+#
+# discovery.zen.ping.multicast.enabled: false
+#
+# 2. Configure an initial list of master nodes in the cluster
+#    to perform discovery when new nodes (master or data) are started:
+#
+# discovery.zen.ping.unicast.hosts: ["host1", "host2:port", "host3[portX-portY]"]
+{%- if ELASTICSEARCH_CLUSTERED -%}
+  {%- set hosts= [] -%}
+
+  {%- for host in hostvars.keys() -%}
+    {% do hosts.append(host) %}
+  {%- endfor %}
+
+discovery.zen.ping.unicast.hosts: ['{{hosts|join("\',\'") }}']
+
+{% endif -%}
\ No newline at end of file

playbooks/roles/elasticsearch/templates/etc/default/elasticsearch.j2

+# {{ ansible_managed }}
+
+
+# Run ElasticSearch as this user ID and group ID
+#ES_USER=elasticsearch
+#ES_GROUP=elasticsearch	
+
+# Heap Size (defaults to 256m min, 1g max)
+ES_HEAP_SIZE={{ ELASTICSEARCH_HEAP_SIZE }}
+
+# Heap new generation
+#ES_HEAP_NEWSIZE=
+
+# max direct memory
+#ES_DIRECT_SIZE=
+
+# Maximum number of open files, defaults to 65535.
+#MAX_OPEN_FILES=65535
+
+# Maximum locked memory size. Set to "unlimited" if you use the
+# bootstrap.mlockall option in elasticsearch.yml. You must also set
+# ES_HEAP_SIZE.
+#MAX_LOCKED_MEMORY=unlimited
+
+# ElasticSearch log directory
+LOG_DIR={{ elasticsearch_log_dir }}
+
+# ElasticSearch data directory
+DATA_DIR={{ COMMON_DATA_DIR }}
+
+# ElasticSearch work directory
+#WORK_DIR=/tmp/elasticsearch
+
+# ElasticSearch configuration directory
+CONF_DIR={{ elasticsearch_cfg_dir }}
+
+# ElasticSearch configuration file (elasticsearch.yml)
+# CONF_FILE=/etc/elasticsearch/elasticsearch.yml
+
+# Additional Java OPTS
+#ES_JAVA_OPTS=