Support for configuration per node and multiple nodes per server

.gitignore

@@ -4,3 +4,4 @@
 .vendor
 .bundle
 Converging
+TODO

.kitchen.yml

@@ -64,4 +64,14 @@ suites:
     attributes:
     provisioner:
       playbook: test/integration/package.yml
+  - name: config
+    run_list:
+    attributes:
+    provisioner:
+      playbook: test/integration/config.yml
+  - name: multi
+    run_list:
+    attributes:
+    provisioner:
+      playbook: test/integration/multi.yml
 

README.md

@@ -24,44 +24,88 @@ Then create your playbook yaml adding the role elasticsearch and overriding any
 ---
 hosts: my_host
   roles:
-    - elasticsearch
+    - { role: elasticsearch, es_multicast_enabled: true}
   tasks:
     - .... your tasks ...
 ```
 
-or more complex..
+By default es_multicast_enabled is false.  If this is not to true, the user is required to specify the following additional parameters:
 
+1. es_http_port - the http port for the node
+2. es_transport_tcp_port - the transport port for the node
+3. es_unicast_hosts - the unicast discovery list, in the comma separated format "<host>:<port>,<host>:<port>" (typically the clusters dedicated masters)
+
+
+If set to true, the ports will be auto defined and node discovery will be performed using multicast.
+
+A more complex example:
 
 ```
 ---
-hosts: my_host
+hosts: localhost
-  roles:
+roles:
-    - elasticsearch
+  - { role: elasticsearch, es_unicast_hosts: "localhost:9301", es_http_port: "9201", es_transport_tcp_port: "9301", es_data_node: false, es_master_node: true, es_m_lock_enabled: true, es_multicast_enabled: false, es_node_name_prefix: "node1_", es_cluster_name: "custom-cluster" }
-  vars:
+vars:
-    java_packages:
+  es_scripts: false
-      - "oracle-java7-installer"
+  es_templates: false
-    es_major_version: 1.4
+  es_version_lock: false
-    es_version: 1.4.4
+  es_m_lock_enabled: true
-    es_start_service: false
+  es_start_service: false
-    es_plugins_reinstall: false
+  es_plugins_reinstall: false
-    es_plugins:
+  es_plugins:
-      - plugin: elasticsearch/elasticsearch-cloud-aws
+    - plugin: elasticsearch/elasticsearch-cloud-aws
-        version: 2.5.0
+      version: 2.5.0
-      - plugin: elasticsearch/marvel
+    - plugin: elasticsearch/marvel
-        version: latest
+      version: latest
-      - plugin: elasticsearch/license
+    - plugin: elasticsearch/license
-        version: latest
+      version: latest
-      - plugin: elasticsearch/shield
+    - plugin: elasticsearch/shield
-        version: latest
+      version: latest
-      - plugin: elasticsearch/elasticsearch-support-diagnostics
+    - plugin: elasticsearch/elasticsearch-support-diagnostics
-        version: latest
+      version: latest
-      - plugin: lmenezes/elasticsearch-kopf
+    - plugin: lmenezes/elasticsearch-kopf
-        version: master
+      version: master
-  tasks:
+tasks:
-    - .... your tasks ...
+  - .... your tasks ...
 ```
 
-Make sure your hosts are defined in your ```hosts``` file with the appropriate ```ansible_ssh_host```,  ```ansible_ssh_user``` and ```ansible_ssh_private_key_file``` values.
+The above example illustrates the ability to control the configuration.  
+
+The application of a role results in the installation of a node on a host. Multiple roles equates to multiple nodes for a single host.  If specifying multiple roles for a host, and thus multiple nodes, the user must:
+
+1. Provide a es_node_name_prefix.  This is used to ensure seperation of data, log, config and init scripts.
+2. Ensure those playbooks responsible for installing and starting master eligble roles are specified first. These are required for cluster initalization.
+
+An example of a two server deployment, each with 1 node on one server and 2 nodes on another.  The first server holds the master and is thus declared first.
+
+```
+---
+hosts: masters
+roles:
+  - { role: elasticsearch, es_node_name_prefix: "node1_", es_unicast_hosts: "localhost:9300", es_http_port: "9201", es_transport_tcp_port: "9301", es_data_node: true, es_master_node: false, es_m_lock_enabled: true, es_multicast_enabled: false }
+vars:
+  es_scripts: false
+  es_templates: false
+  es_version_lock: false
+  es_cluster_name: example-cluster
+  m_lock_enabled: false
+
+- hosts: data_nodes
+  roles:
+    - { role: elasticsearch, es_data_node: true, es_master_node: false, es_m_lock_enabled: true, es_multicast_enabled: false, es_node_name_prefix: "node1_" }
+    - { role: elasticsearch, es_data_node: true, es_master_node: false, es_m_lock_enabled: true, es_multicast_enabled: false, es_node_name_prefix: "node2_" }
+  vars:
+    es_scripts: false
+    es_templates: false
+    es_version_lock: false
+    es_cluster_name: example-cluster
+    m_lock_enabled: true
+    es_plugins:
+```
+
+Parameters can additionally be assigned to hosts using the inventory file if desired.
+
+Make sure your hosts are defined in your ```inventory``` file with the appropriate ```ansible_ssh_host```,  ```ansible_ssh_user``` and ```ansible_ssh_private_key_file``` values.
 
 Then run it:
 

defaults/main.yml

@@ -9,3 +9,6 @@ es_scripts: false
 es_templates: false
 es_user: elasticsearch
 es_group: elasticsearch
+es_cluster_name: elasticsearch
+es_multicast_enabled: false
+es_node_name_prefix: ""

elasticsearch.iml

@@ -0,0 +1,9 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="RUBY_MODULE" version="4">
+  <component name="NewModuleRootManager" inherit-compiler-output="true">
+    <exclude-output />
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

meta/main.yml

@@ -1,5 +1,6 @@
 ---
-dependencies: []
+
+allow_duplicates: yes
 
 galaxy_info:
   author: Robin Clarke

tasks/checkParameters.yml

@@ -0,0 +1,10 @@
+# Check for mandatory parameters
+
+- fail: msg="Parameter 'es_http_port' must be defined when multicast is disabled"
+  when: es_multicast_enabled == false and es_http_port is not defined
+
+- fail: msg="Parameter 'es_transport_tcp_port' must be defined when multicast is disabled"
+  when: es_multicast_enabled == false and es_transport_tcp_port is not defined
+
+- fail: msg="Parameter 'es_unicast_hosts' must be defined when multicast is disabled"
+  when: es_multicast_enabled == false and es_unicast_hosts is not defined

tasks/elasticsearch-Debian.yml

@@ -19,24 +19,4 @@
 - name: Debian - Ensure elasticsearch is installed from downloaded package
   apt: deb=/tmp/elasticsearch-{{ es_version }}.deb
   when: not es_use_repository
-  register: elasticsearch_install
+  register: elasticsearch_install
-
-- name: Debian - configure memory
-  lineinfile: dest=/etc/default/elasticsearch regexp="^ES_HEAP_SIZE" insertafter="^#ES_HEAP_SIZE" line="ES_HEAP_SIZE={{ es_heap_size }}"
-  when: es_heap_size is defined
-  register: elasticsearch_configure
-- name: Debian - configure data store
-  lineinfile: dest=/etc/default/elasticsearch regexp="^DATA_DIR" insertafter="^#DATA_DIR" line="DATA_DIR={{ es_data_dir }}"
-  when: es_data_dir is defined
-  register: elasticsearch_configure
-- name: Debian - configure elasticsearch user
-  lineinfile: dest=/etc/default/elasticsearch regexp="^ES_USER" insertafter="^#ES_USER" line="ES_USER={{ es_user }}"
-  when: es_user is defined
-  register: elasticsearch_configure
-- name: Debian - configure elasticsearch group
-  lineinfile: dest=/etc/default/elasticsearch regexp="^ES_GROUP" insertafter="^#ES_GROUP" line="ES_GROUP={{ es_group }}"
-  when: es_group is defined
-  register: elasticsearch_configure
-- name: Debian - create data dir
-  file: state=directory path={{ es_data_dir }} owner={{ es_user }} group={{ es_group }}
-  when: es_data_dir is defined

tasks/elasticsearch-RedHat.yml

@@ -19,24 +19,4 @@
 - name: RedHat - Install Elasticsearch from url
   yum: name={% if es_custom_package_url is defined %}{{ es_custom_package_url }}{% else %}{{ es_package_url }}-{{ es_version }}.noarch.rpm{% endif %} state=present
   when: not es_use_repository
-  register: elasticsearch_install
+  register: elasticsearch_install
-
-- name: RedHat - configure memory
-  lineinfile: dest=/etc/sysconfig/elasticsearch regexp="^ES_HEAP_SIZE" insertafter="^#ES_HEAP_SIZE" line="ES_HEAP_SIZE={{ es_heap_size }}"
-  when: es_heap_size is defined
-  register: elasticsearch_configure
-- name: RedHat - configure data store
-  lineinfile: dest=/etc/sysconfig/elasticsearch regexp="^DATA_DIR" insertafter="^#DATA_DIR" line="DATA_DIR={{ es_data_dir }}"
-  when: es_data_dir is defined
-  register: elasticsearch_configure
-- name: RedHat - configure elasticsearch user
-  lineinfile: dest=/etc/sysconfig/elasticsearch regexp="^ES_USER" insertafter="^#ES_USER" line="ES_USER={{ es_user }}"
-  when: es_user is defined
-  register: elasticsearch_configure
-- name: RedHat - configure elasticsearch group
-  lineinfile: dest=/etc/sysconfig/elasticsearch regexp="^ES_GROUP" insertafter="^#ES_GROUP" line="ES_GROUP={{ es_group }}"
-  when: es_group is defined
-  register: elasticsearch_configure
-- name: RedHat - create data dir
-  file: state=directory path={{ es_data_dir }} owner={{ es_user }} group={{ es_group }}
-  when: es_data_dir is defined

tasks/elasticsearch-config.yml

@@ -0,0 +1,117 @@
+---
+
+# Configure Elasticsearch Node
+
+# Create an instance specific default file
+- name: Copy Default File for Instance
+  command: creates={{instance_default_file}} cp "{{default_file}}"  "{{instance_default_file}}"
+  when: instance_default_file != default_file
+
+- debug: msg="DEBUG {{ hostvars[inventory_hostname] }}"
+
+# Create an instance specific init file
+- name: Copy Init File for Instance
+  command: creates={{instance_init_script}} cp "{{init_script}}" "{{instance_init_script}}"
+  when: instance_init_script != init_script
+
+
+#Create Config directory
+- name: Create Config Directory
+  file: path={{ instance_config_directory }} state=directory owner={{ es_user }} group={{ es_group }}
+
+#Copy the config template
+- name: Copy configuration file
+  template: src=elasticsearch.yml.j2 dest={{instance_config_directory}}/elasticsearch.yml owner={{ es_user }} group={{ es_group }} mode=0644 force=yes
+
+# Apply changes to the default file for this instance
+- name: Configure config directory
+  lineinfile: dest={{instance_default_file}} regexp="^CONF_DIR" insertafter="^#CONF_DIR" line="CONF_DIR={{ instance_config_directory }}"
+  register: elasticsearch_configure
+
+- name: Configure config file
+  lineinfile: dest={{instance_default_file}} regexp="^CONF_FILE" insertafter="^#CONF_FILE" line="CONF_FILE={{ instance_config_directory }}/elasticsearch.yml"
+  register: elasticsearch_configure
+
+- name: Configure memory in defaults
+  lineinfile: dest={{instance_default_file}} regexp="^ES_HEAP_SIZE" insertafter="^#ES_HEAP_SIZE" line="ES_HEAP_SIZE={{ es_heap_size }}"
+  when: es_heap_size is defined
+  register: elasticsearch_configure
+
+#We only have to set these if they are specified. The start scripts will by default use the NAME set later on constructing directory names to avoid collisions.
+
+- name: Configure max open files
+  lineinfile: dest={{instance_default_file}} regexp="^MAX_OPEN_FILES" insertafter="^#MAX_OPEN_FILES" line="MAX_OPEN_FILES={{ es_max_open_files }}"
+  when: es_max_open_files is defined
+  register: elasticsearch_configure
+
+#For directories we also use the {{ es_node_name_prefix }}{{inventory_hostname}} - this helps if we have a shared SAN.  {{es_node_name_prefix}}{{default_file | basename} could potentially be used -
+#init script effectively means this is the default.
+
+#Create PID directory
+- name: Create PID Directory
+  file: path={{pid_dir}}/{{ es_node_name_prefix }}{{inventory_hostname}} state=directory owner={{ es_user }} group={{ es_group }}
+
+- name: Configure PID directory
+  lineinfile: dest={{instance_default_file}} regexp="^PID_DIR" insertafter="^#PID_DIR" line="PID_DIR={{pid_dir}}/{{ es_node_name_prefix }}{{inventory_hostname}}"
+  register: elasticsearch_configure
+
+- set_fact: es_data_dir={{default_data_dir}}
+  when: es_data_dir is undefined
+
+#include the host name as potentially shared SAN
+- name: Create data dir
+  file: state=directory path={{ es_data_dir }}/{{ es_node_name_prefix }}{{inventory_hostname}} owner={{ es_user }} group={{ es_group }}
+
+- name: Configure data store
+  lineinfile: dest={{instance_default_file}} regexp="^DATA_DIR" insertafter="^#DATA_DIR" line="DATA_DIR={{ es_data_dir }}/{{ es_node_name_prefix }}{{inventory_hostname}}"
+  register: elasticsearch_configure
+
+- set_fact: es_work_dir={{default_work_dir}}
+  when: es_work_dir is undefined
+
+- name: Create work dir
+  file: state=directory path={{ es_work_dir }}/{{ es_node_name_prefix }}{{inventory_hostname}} owner={{ es_user }} group={{ es_group }}
+
+- name: Configure work directory
+  lineinfile: dest={{instance_default_file}} regexp="^WORK_DIR" insertafter="^#WORK_DIR" line="WORK_DIR={{ es_work_dir }}/{{ es_node_name_prefix }}{{inventory_hostname}}"
+  register: elasticsearch_configure
+
+- set_fact: es_log_dir={{default_log_dir}}
+  when: es_log_dir is undefined
+
+- name: Create log dir
+  file: state=directory path={{ es_log_dir }}/{{ es_node_name_prefix }}{{inventory_hostname}} owner={{ es_user }} group={{ es_group }}
+
+- name: Configure log directory
+  lineinfile: dest={{instance_default_file}} regexp="^LOG_DIR" insertafter="^#LOG_DIR" line="LOG_DIR={{ es_log_dir }}/{{ es_node_name_prefix }}{{inventory_hostname}}"
+  register: elasticsearch_configure
+
+#required so that the ES_HOME does not change between instances
+
+- name: Configure elasticsearch home
+  lineinfile: dest={{instance_default_file}} regexp="^ES_HOME" insertafter="^#ES_HOME" line="ES_HOME={{es_home}}"
+  register: elasticsearch_configure
+
+- name: Configure elasticsearch user
+  lineinfile: dest={{instance_default_file}} regexp="^ES_USER" insertafter="^#ES_USER" line="ES_USER={{ es_user }}"
+  when: es_user is defined
+  register: elasticsearch_configure
+
+- name: Configure elasticsearch group
+  lineinfile: dest={{instance_default_file}} regexp="^ES_GROUP" insertafter="^#ES_GROUP" line="ES_GROUP={{ es_group }}"
+  when: es_group is defined
+  register: elasticsearch_configure
+
+#Apply changes to init script - NAME can be changed in Debian start script
+- name: Name Node in Init Script
+  lineinfile: dest={{instance_init_script}} regexp="^NAME" line="NAME={{es_node_name_prefix}}{{default_file | basename}}"
+  register: elasticsearch_configure
+  when: ansible_os_family == 'Debian'
+
+- debug: msg="For {{ instance_init_script }} using default {{ instance_default_file }}"
+
+- name: Environment in Init Script
+  lineinfile: dest={{instance_init_script}} regexp="^ES_ENV_FILE" line="ES_ENV_FILE={{instance_default_file}}"
+  register: elasticsearch_configure
+  when: ansible_os_family == 'RedHat'
+

tasks/elasticsearch.yml

@@ -1,21 +1,31 @@
 ---
-# Trigger Debian section
+- set_fact: instance_default_file={{default_file | dirname}}/{{es_node_name_prefix}}{{default_file | basename}}
-- name: Include Debian specific Elasticsearch
+- set_fact: instance_init_script={{init_script | dirname }}/{{es_node_name_prefix}}{{init_script | basename}}
+- set_fact: instance_config_directory={{ es_conf_dir }}/{{es_node_name_prefix}}elasticsearch
+
+
+
+# Install OS specific elasticsearch - this can be abbreviated in version 2.0.0
+- name: Include specific Elasticsearch
   include: elasticsearch-Debian.yml
   when: ansible_os_family == 'Debian'
 
-# Trigger Redhat section
+- name: Include specific Elasticsearch
-- name: Include RedHat specific Elasticsearch
   include: elasticsearch-RedHat.yml
   when: ansible_os_family == 'RedHat'
 
+#Configuration file for elasticsearch
+- name: Elasticsearch configuration
+  include: elasticsearch-config.yml
+
 # Make sure the service is started, and restart if necessary
 - name: Start elasticsearch service
-  service: name=elasticsearch state=started
+  service: name={{instance_init_script | basename}} state=started
   when: es_start_service
   register: elasticsearch_started
+
 - name: Restart elasticsearch service if new version installed
-  service: name=elasticsearch state=restarted
+  service: name={{instance_init_script | basename}} state=restarted
   when: es_start_service and 
     ( elasticsearch_install.changed or elasticsearch_configure.changed )
     and not elasticsearch_started.changed

tasks/java.yml

@@ -1,8 +1,8 @@
 ---
 - name: RedHat - Ensure Java is installed
-  yum: name={{ java_rhel }} state=latest
+  yum: name={{ java }} state=latest
   when: ansible_os_family == 'RedHat'
   
 - name: Debian - Ensure Java is installed
-  apt: name={{ java_debian }} state=present update_cache=yes
+  apt: name={{ java }} state=present update_cache=yes force=yes
   when: ansible_os_family == 'Debian'

tasks/main.yml

@@ -1,4 +1,8 @@
 ---
+- name: check-parameters
+  include: checkParameters.yml
+- name: os-specific vars
+  include_vars: "{{ansible_os_family}}.yml"
 - include: java.yml
 - include: elasticsearch.yml
 - include: elasticsearch-plugins.yml

templates/elasticsearch.yml.j2

@@ -0,0 +1,390 @@
+##################### Elasticsearch Configuration Example #####################
+
+# This file contains an overview of various configuration settings,
+# targeted at operations staff. Application developers should
+# consult the guide at <http://elasticsearch.org/guide>.
+#
+# The installation procedure is covered at
+# <http://elasticsearch.org/guide/en/elasticsearch/reference/current/setup.html>.
+#
+# Elasticsearch comes with reasonable defaults for most settings,
+# so you can try it out without bothering with configuration.
+#
+# Most of the time, these defaults are just fine for running a production
+# cluster. If you're fine-tuning your cluster, or wondering about the
+# effect of certain configuration option, please _do ask_ on the
+# mailing list or IRC channel [http://elasticsearch.org/community].
+
+# Any element in the configuration can be replaced with environment variables
+# by placing them in ${...} notation. For example:
+#
+#node.rack: ${RACK_ENV_VAR}
+
+# For information on supported formats and syntax for the config file, see
+# <http://elasticsearch.org/guide/en/elasticsearch/reference/current/setup-configuration.html>
+
+
+################################### Cluster ###################################
+
+# Cluster name identifies your cluster for auto-discovery. If you're running
+# multiple clusters on the same network, make sure you're using unique names.
+#
+cluster.name: {{ es_cluster_name }}
+
+#################################### Node #####################################
+
+# Node names are generated dynamically on startup, so you're relieved
+# from configuring them manually. You can tie this node to a specific name:
+#
+node.name: {{es_node_name_prefix}}{{inventory_hostname}}
+
+# Every node can be configured to allow or deny being eligible as the master,
+# and to allow or deny to store the data.
+#
+# Allow this node to be eligible as a master node (enabled by default):
+#
+{% if es_master_node is defined %}
+node.master: {{es_master_node | lower}}
+{% endif %}
+
+#
+# Allow this node to store data (enabled by default):
+#
+{% if es_data_node is defined %}
+node.data: {{es_data_node | lower}}
+{% endif %}
+
+# Use the Cluster Health API [http://localhost:9200/_cluster/health], the
+# Node Info API [http://localhost:9200/_nodes] or GUI tools
+# such as <http://www.elasticsearch.org/overview/marvel/>,
+# <http://github.com/karmi/elasticsearch-paramedic>,
+# <http://github.com/lukas-vlcek/bigdesk> and
+# <http://mobz.github.com/elasticsearch-head> to inspect the cluster state.
+
+# A node can have generic attributes associated with it, which can later be used
+# for customized shard allocation filtering, or allocation awareness. An attribute
+# is a simple key value pair, similar to node.key: value, here is an example:
+#
+{% if es_node_rack is defined %}
+node.rack: {{ es_node_rack }}
+{% endif %}
+
+# By default, multiple nodes are allowed to start from the same installation location
+# to disable it, set the following:
+#node.max_local_storage_nodes: 1
+
+
+#################################### Index ####################################
+
+# You can set a number of options (such as shard/replica options, mapping
+# or analyzer definitions, translog settings, ...) for indices globally,
+# in this file.
+#
+# Note, that it makes more sense to configure index settings specifically for
+# a certain index, either when creating it or by using the index templates API.
+#
+# See <http://elasticsearch.org/guide/en/elasticsearch/reference/current/index-modules.html> and
+# <http://elasticsearch.org/guide/en/elasticsearch/reference/current/indices-create-index.html>
+# for more information.
+
+# Set the number of shards (splits) of an index (5 by default) if provided:
+
+{% if es_index_number_of_shards is defined %}
+index.number_of_shards: {{ es_index_number_of_shards }}
+{% endif %}
+
+# Set the number of replicas (additional copies) of an index (1 by default) if provided:
+{% if es_index_number_of_replicas is defined %}
+index.number_of_replicas: {{ es_index_number_of_replicas }}
+{% endif %}
+
+
+# These settings directly affect the performance of index and search operations
+# in your cluster. Assuming you have enough machines to hold shards and
+# replicas, the rule of thumb is:
+#
+# 1. Having more *shards* enhances the _indexing_ performance and allows to
+#    _distribute_ a big index across machines.
+# 2. Having more *replicas* enhances the _search_ performance and improves the
+#    cluster _availability_.
+#
+# The "number_of_shards" is a one-time setting for an index.
+#
+# The "number_of_replicas" can be increased or decreased anytime,
+# by using the Index Update Settings API.
+#
+# Elasticsearch takes care about load balancing, relocating, gathering the
+# results from nodes, etc. Experiment with different settings to fine-tune
+# your setup.
+
+# Use the Index Status API (<http://localhost:9200/A/_status>) to inspect
+# the index status.
+
+
+#################################### Paths ####################################
+
+# Path to directory containing configuration (this file and logging.yml):
+#
+{% if es_conf_dir is defined %}
+path.conf: {{ es_conf_dir }}
+{% endif %}
+
+
+# Path to directory where to store index data allocated for this node.
+#
+# Can optionally include more than one location, causing data to be striped across
+# the locations (a la RAID 0) on a file level, favouring locations with most free
+# space on creation. For example:
+#
+{% if es_data_dir is defined %}
+path.data: {{ es_data_dir }}
+{% endif %}
+
+# Path to temporary files:
+{% if es_work_dir is defined %}
+path.work: {{ es_work_dir }}
+{% endif %}
+
+# Path to log files:
+{% if es_log_dir is defined %}
+path.logs: {{ es_log_dir }}
+{% endif %}
+
+# Path to where plugins are installed:
+#
+#path.plugins: /path/to/plugins
+
+
+#################################### Plugin ###################################
+
+# If a plugin listed here is not installed for current node, the node will not start.
+#
+#plugin.mandatory: mapper-attachments,lang-groovy
+
+
+################################### Memory ####################################
+
+# Elasticsearch performs poorly when JVM starts swapping: you should ensure that
+# it _never_ swaps.
+#
+# Set this property to true to lock the memory:
+#
+{% if es_m_lock_enabled is defined %}
+bootstrap.mlockall: {{es_m_lock_enabled | lower}}
+{% endif %}
+
+
+# Make sure that the ES_MIN_MEM and ES_MAX_MEM environment variables are set
+# to the same value, and that the machine has enough memory to allocate
+# for Elasticsearch, leaving enough memory for the operating system itself.
+#
+# You should also make sure that the Elasticsearch process is allowed to lock
+# the memory, eg. by using `ulimit -l unlimited`.
+
+
+############################## Network And HTTP ###############################
+
+# Elasticsearch, by default, binds itself to the 0.0.0.0 address, and listens
+# on port [9200-9300] for HTTP traffic and on port [9300-9400] for node-to-node
+# communication. (the range means that if the port is busy, it will automatically
+# try the next port).
+
+# Set the bind address specifically (IPv4 or IPv6):
+#
+#network.bind_host: 192.168.0.1
+
+# Set the address other nodes will use to communicate with this node. If not
+# set, it is automatically derived. It must point to an actual IP address.
+#
+#network.publish_host: 192.168.0.1
+
+# Set both 'bind_host' and 'publish_host':
+#
+{% if es_network_host is defined %}
+network.host: {{ es_network_host }}
+{% endif %}
+
+
+# Set a custom port for the node to node communication (9300 by default):
+#
+{% if es_transport_tcp_port is defined %}
+transport.tcp.port: {{ es_transport_tcp_port }}
+{% endif %}
+
+# Enable compression for all communication between nodes (disabled by default):
+#
+#transport.tcp.compress: true
+
+# Set a custom port to listen for HTTP traffic (9200 by default):
+#
+{% if es_http_port is defined %}
+http.port: {{ es_http_port }}
+{% endif %}
+
+# Set a custom allowed content length:
+#
+#http.max_content_length: 100mb
+
+# Disable HTTP completely:
+#
+#http.enabled: false
+
+
+################################### Gateway ###################################
+
+# The gateway allows for persisting the cluster state between full cluster
+# restarts. Every change to the state (such as adding an index) will be stored
+# in the gateway, and when the cluster starts up for the first time,
+# it will read its state from the gateway.
+
+# There are several types of gateway implementations. For more information, see
+# <http://elasticsearch.org/guide/en/elasticsearch/reference/current/modules-gateway.html>.
+
+# The default gateway type is the "local" gateway (recommended):
+#
+#gateway.type: local
+
+# Settings below control how and when to start the initial recovery process on
+# a full cluster restart (to reuse as much local data as possible when using shared
+# gateway).
+
+# Allow recovery process after N nodes in a cluster are up:
+#
+#gateway.recover_after_nodes: 1
+
+# Set the timeout to initiate the recovery process, once the N nodes
+# from previous setting are up (accepts time value):
+#
+#gateway.recover_after_time: 5m
+
+# Set how many nodes are expected in this cluster. Once these N nodes
+# are up (and recover_after_nodes is met), begin recovery process immediately
+# (without waiting for recover_after_time to expire):
+#
+#gateway.expected_nodes: 2
+
+
+############################# Recovery Throttling #############################
+
+# These settings allow to control the process of shards allocation between
+# nodes during initial recovery, replica allocation, rebalancing,
+# or when adding and removing nodes.
+
+# Set the number of concurrent recoveries happening on a node:
+#
+# 1. During the initial recovery
+#
+#cluster.routing.allocation.node_initial_primaries_recoveries: 4
+#
+# 2. During adding/removing nodes, rebalancing, etc
+#
+#cluster.routing.allocation.node_concurrent_recoveries: 2
+
+# Set to throttle throughput when recovering (eg. 100mb, by default 20mb):
+#
+#indices.recovery.max_bytes_per_sec: 20mb
+
+# Set to limit the number of open concurrent streams when
+# recovering a shard from a peer:
+#
+#indices.recovery.concurrent_streams: 5
+
+
+################################## Discovery ##################################
+
+# Discovery infrastructure ensures nodes can be found within a cluster
+# and master node is elected. Multicast discovery is the default.
+
+# Set to ensure a node sees N other master eligible nodes to be considered
+# operational within the cluster. This should be set to a quorum/majority of 
+# the master-eligible nodes in the cluster.
+#
+#discovery.zen.minimum_master_nodes: 1
+
+# Set the time to wait for ping responses from other nodes when discovering.
+# Set this option to a higher value on a slow or congested network
+# to minimize discovery failures:
+#
+#discovery.zen.ping.timeout: 3s
+
+# For more information, see
+# <http://elasticsearch.org/guide/en/elasticsearch/reference/current/modules-discovery-zen.html>
+
+# 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: {{es_multicast_enabled | lower }}
+
+#
+# 2. Configure an initial list of master nodes in the cluster
+#    to perform discovery when new nodes (master or data) are started:
+#
+
+#We put all the current eligible masters in here.  If not specified, we assumes its a master
+
+{% if es_multicast_enabled is defined and not es_multicast_enabled %}
+discovery.zen.ping.unicast.hosts: {{es_unicast_hosts}}
+{% endif %}
+
+
+# EC2 discovery allows to use AWS EC2 API in order to perform discovery.
+#
+# You have to install the cloud-aws plugin for enabling the EC2 discovery.
+#
+# For more information, see
+# <http://elasticsearch.org/guide/en/elasticsearch/reference/current/modules-discovery-ec2.html>
+#
+# See <http://elasticsearch.org/tutorials/elasticsearch-on-ec2/>
+# for a step-by-step tutorial.
+
+# GCE discovery allows to use Google Compute Engine API in order to perform discovery.
+#
+# You have to install the cloud-gce plugin for enabling the GCE discovery.
+#
+# For more information, see <https://github.com/elasticsearch/elasticsearch-cloud-gce>.
+
+# Azure discovery allows to use Azure API in order to perform discovery.
+#
+# You have to install the cloud-azure plugin for enabling the Azure discovery.
+#
+# For more information, see <https://github.com/elasticsearch/elasticsearch-cloud-azure>.
+
+################################## Slow Log ##################################
+
+# Shard level query and fetch threshold logging.
+
+index.search.slowlog.threshold.query.warn: 2s
+index.search.slowlog.threshold.query.info: 2s
+index.search.slowlog.threshold.query.debug: 1s
+index.search.slowlog.threshold.query.trace: 500ms
+
+#index.search.slowlog.threshold.fetch.warn: 1s
+#index.search.slowlog.threshold.fetch.info: 800ms
+#index.search.slowlog.threshold.fetch.debug: 500ms
+#index.search.slowlog.threshold.fetch.trace: 200ms
+
+#index.indexing.slowlog.threshold.index.warn: 10s
+#index.indexing.slowlog.threshold.index.info: 5s
+#index.indexing.slowlog.threshold.index.debug: 2s
+#index.indexing.slowlog.threshold.index.trace: 500ms
+
+################################## GC Logging ################################
+
+#monitor.jvm.gc.young.warn: 1000ms
+#monitor.jvm.gc.young.info: 700ms
+#monitor.jvm.gc.young.debug: 400ms
+
+#monitor.jvm.gc.old.warn: 10s
+#monitor.jvm.gc.old.info: 5s
+#monitor.jvm.gc.old.debug: 2s
+
+################################## Security ################################
+
+# Uncomment if you want to enable JSONP as a valid return transport on the
+# http server. With this enabled, it may pose a security risk, so disabling
+# it unless you need it is recommended (it is disabled by default).
+#
+#http.jsonp.enable: true

test/integration/config.yml

@@ -0,0 +1,12 @@
+---
+#Test explicit setting of parameters and variables
+- name: Elasticsearch Package tests
+  hosts: localhost
+  roles:
+    #expand to all available parameters
+    - { role: elasticsearch, es_unicast_hosts: "localhost:9301", es_http_port: "9201", es_transport_tcp_port: "9301", es_data_node: false, es_master_node: true, es_m_lock_enabled: true, es_multicast_enabled: false, es_node_name_prefix: "node1_", es_cluster_name: "custom-cluster" }
+  vars:
+    es_scripts: false
+    es_templates: false
+    es_version_lock: false
+    es_m_lock_enabled: true

test/integration/config/config.yml

@@ -0,0 +1,2 @@
+---
+- host: test-kitchen

test/integration/config/serverspec/default_spec.rb

@@ -0,0 +1,42 @@
+require 'spec_helper'
+
+context "basic tests" do
+
+  describe user('elasticsearch') do
+    it { should exist }
+  end
+
+  describe service('node1_elasticsearch') do
+    it { should be_running }
+  end
+
+  describe package('elasticsearch') do
+    it { should be_installed }
+  end
+
+  describe file('/etc/elasticsearch/node1_elasticsearch/elasticsearch.yml') do
+    it { should be_file }
+  end
+
+  #test configuration parameters have been set - test all appropriately set in config file
+  describe file('/etc/elasticsearch/node1_elasticsearch/elasticsearch.yml') do
+    it { should contain 'http.port: 9201' }
+    it { should contain 'transport.tcp.port: 9301' }
+    it { should contain 'node.data: false' }
+    it { should contain 'node.master: true' }
+    it { should contain 'discovery.zen.ping.multicast.enabled: false' }
+    it { should contain 'cluster.name: custom-cluster' }
+    it { should contain 'node.name: node1_localhost' }
+    it { should contain 'discovery.zen.ping.unicast.hosts: localhost:9301' }
+  end
+
+  #test we started on the correct port was used
+  describe command('curl "localhost:9201" | grep status') do
+    #TODO: This is returning an empty string
+    #its(:stdout) { should match /\"status\" : 200/ }
+    its(:exit_status) { should eq 0 }
+  end
+
+
+end
+

test/integration/config/serverspec/spec_helper.rb

@@ -0,0 +1,2 @@
+require 'serverspec'
+set :backend, :exec

test/integration/multi.yml

@@ -0,0 +1,8 @@
+---
+#Test ability to deploy multiple instances to a machine
+- name: Elasticsearch Config tests
+  hosts: localhost
+  roles:
+    - { role: elasticsearch, es_node_name_prefix: "node1_", es_unicast_hosts: "localhost:9300", es_http_port: "9201", es_transport_tcp_port: "9301", es_data_node: true, es_master_node: false, es_m_lock_enabled: true, es_multicast_enabled: false }
+    - { role: elasticsearch, es_node_name_prefix: "master_", es_unicast_hosts: "localhost:9300", es_http_port: "9200", es_transport_tcp_port: "9300", es_data_node: false, es_master_node: true, es_m_lock_enabled: true, es_multicast_enabled: false }
+  vars:

test/integration/multi/multi.yml

@@ -0,0 +1,2 @@
+---
+- host: test-kitchen

test/integration/multi/serverspec/default_spec.rb

@@ -0,0 +1,81 @@
+require 'spec_helper'
+
+context "basic tests" do
+
+  describe user('elasticsearch') do
+    it { should exist }
+  end
+
+  describe service('node1_elasticsearch') do
+    it { should be_running }
+  end
+
+  describe service('master_elasticsearch') do
+    it { should be_running }
+  end
+
+  describe package('elasticsearch') do
+    it { should be_installed }
+  end
+
+  describe file('/etc/elasticsearch/node1_elasticsearch/elasticsearch.yml') do
+    it { should be_file }
+  end
+
+  describe file('/etc/elasticsearch/master_elasticsearch/elasticsearch.yml') do
+    it { should be_file }
+  end
+
+  #test configuration parameters have been set - test all appropriately set in config file
+  describe file('/etc/elasticsearch/node1_elasticsearch/elasticsearch.yml') do
+    it { should contain 'http.port: 9201' }
+    it { should contain 'transport.tcp.port: 9301' }
+    it { should contain 'node.data: true' }
+    it { should contain 'node.master: false' }
+    it { should contain 'discovery.zen.ping.multicast.enabled: false' }
+    it { should contain 'node.name: node1_localhost' }
+  end
+
+
+  #test configuration parameters have been set for master - test all appropriately set in config file
+  describe file('/etc/elasticsearch/master_elasticsearch/elasticsearch.yml') do
+    it { should contain 'http.port: 9200' }
+    it { should contain 'transport.tcp.port: 9300' }
+    it { should contain 'node.data: false' }
+    it { should contain 'node.master: true' }
+    it { should contain 'discovery.zen.ping.multicast.enabled: false' }
+    it { should contain 'node.name: master_localhost' }
+  end
+
+  describe 'Master listening' do
+    it 'listening in port 9200' do
+      expect(port 9200).to be_listening
+    end
+  end
+
+  describe 'Node listening' do
+    it 'node should be listening in port 9201' do
+      expect(port 9201).to be_listening
+    end
+  end
+
+  #test we started on the correct port was used for master
+  describe 'master started' do
+    it 'master node should be running', :retry => 3, :retry_wait => 10 do
+      command = command('curl "localhost:9200" | grep name')
+      #expect(command.stdout).should match '/*master_localhost*/'
+      expect(command.exit_status).to eq(0)
+    end
+  end
+
+  #test we started on the correct port was used for node 1
+  describe 'node1 started' do
+    it 'node should be running', :retry => 3, :retry_wait => 10 do
+      command = command('curl "localhost:9201" | grep name')
+      #expect(command.stdout).should match '/*node1_localhost*/'
+      expect(command.exit_status).to eq(0)
+    end
+  end
+
+end
+

test/integration/multi/serverspec/spec_helper.rb

@@ -0,0 +1,2 @@
+require 'serverspec'
+set :backend, :exec

test/integration/package.yml

@@ -2,5 +2,5 @@
 - name: Elasticsearch Package tests
   hosts: localhost
   roles:
-    - elasticsearch
+    - { role: elasticsearch, es_multicast_enabled: true}
-  vars:
+  vars:

test/integration/package/serverspec/default_spec.rb

@@ -14,7 +14,7 @@ context "basic tests" do
     it { should be_installed }
   end
 
-  describe file('/etc/elasticsearch/elasticsearch.yml') do
+  describe file('/etc/elasticsearch/elasticsearch/elasticsearch.yml') do
     it { should be_file }
   end
 

test/integration/standard.yml

@@ -2,7 +2,7 @@
 - name: wrapper playbook for kitchen testing "elasticsearch"
   hosts: localhost
   roles:
-    - elasticsearch
+    - { role: elasticsearch, es_multicast_enabled: true}
   vars:
     es_use_repository: "true"
     es_plugins:

test/integration/standard/serverspec/default_spec.rb

@@ -14,7 +14,7 @@ context "basic tests" do
     it { should be_installed }
   end
 
-  describe file('/etc/elasticsearch/elasticsearch.yml') do
+  describe file('/etc/elasticsearch/elasticsearch/elasticsearch.yml') do
     it { should be_file }
   end
 

vars/Debian.yml

@@ -0,0 +1,11 @@
+---
+java: "openjdk-7-jre-headless"
+default_file: "/etc/default/elasticsearch"
+init_script: "/etc/init.d/elasticsearch"
+es_conf_dir: "/etc/elasticsearch"
+es_home: "/usr/share/elasticsearch"
+
+default_data_dir: "/var/lib/elasticsearch"
+default_log_dir: "/var/log/elasticsearch"
+default_work_dir: "/tmp/elasticsearch"
+default_pid_dir: "/var/run/elasticsearch"

vars/Linux.yml

@@ -1 +0,0 @@
----

vars/RedHat.yml

@@ -0,0 +1,6 @@
+---
+java: "java-1.8.0-openjdk.x86_64"
+default_file: "/etc/sysconfig/elasticsearch"
+init_script: "/etc/init.d/elasticsearch"
+es_conf_dir: "/etc/elasticsearch/"
+es_home: "/usr/share/elasticsearch"

vars/main.yml

@@ -1,4 +1,8 @@
 ---
-java_debian: "openjdk-7-jre-headless"
+es_package_url: "https://download.elastic.co/elasticsearch/elasticsearch/elasticsearch"
-java_rhel: "java-1.8.0-openjdk.x86_64"
+pid_dir: "/var/run/elasticsearch"
-es_package_url: "https://download.elastic.co/elasticsearch/elasticsearch/elasticsearch"
+
+#Needed to provide default directories
+default_data_dir: "/var/lib/elasticsearch"
+default_log_dir: "/var/log/elasticsearch"
+default_work_dir: "/tmp/elasticsearch"