elasticsearch-rolling-upgrade.yml

---
- name: Elasticsearch rolling upgrade
  hosts: elasticsearch
  gather_facts: no
  serial: 1

  vars:
    es_disable_allocation: '{"transient":{"cluster.routing.allocation.enable":"none"}}'
    es_enable_allocation: '{"transient":{"cluster.routing.allocation.enable": "all","cluster.routing.allocation.node_concurrent_recoveries": 5,"indices.recovery.max_bytes_per_sec": "500mb"}}'
    es_http_port: 9200
    es_transport_port: 9300
    # s3_plugin_url: https://artifacts.elastic.co/downloads/elasticsearch-plugins/repository-s3/repository-s3-{{ elk_version }}.zip

  tasks:
  - name: Validate ELK Version
    fail: msg="Invalid ELK Version"
    when: elk_version is undefined or not elk_version is match("\d+\.\d+\.\d+")

  - name: Set the es_host for the first host
    set_fact:
      es_host: "{{ groups.elasticsearch[1] }}"
    when: "inventory_hostname == groups.elasticsearch[0]"

  - name: Set the es_host for the remaining hosts
    set_fact:
      es_host: "{{ groups.elasticsearch[0] }}"
    when: "inventory_hostname != groups.elasticsearch[0]"

  - name: Ensure elasticsearch service is running
    systemd:
      name: elasticsearch
      enabled: yes
      state: started
    register: response

  - name: Wait for elasticsearch node to come back up if it was stopped
    wait_for:
      port: "{{ es_transport_port }}"
      delay: 45
    when: response.changed == true

  - name: Check current version
    uri:
      url: http://localhost:{{ es_http_port }}
      method: GET
    register: version_found
    retries: 10
    delay: 10

  - name: Display Current Elasticsearch Version
    debug: var=version_found.json.version.number

  - block:
    - name: Enable shard allocation for the cluster
      uri:
        url: http://localhost:{{ es_http_port }}/_cluster/settings
        method: PUT
        body_format: json
        body: "{{ es_enable_allocation }}"

    - name: Wait for cluster health to return to green
      uri:
        url: http://localhost:{{ es_http_port }}/_cluster/health
        method: GET
      register: response
      until: "response.json.status == 'green'"
      retries: 500
      delay: 15

    - name: Disable shard allocation for the cluster
      uri:
        url: http://localhost:{{ es_http_port }}/_cluster/settings
        method: PUT
        body_format: json
        body: "{{ es_disable_allocation }}"

    - name: Perform a synced flush
      uri:
        url: http://localhost:{{ es_http_port }}/_flush/synced
        method: POST
        status_code: "200, 409"

    - name: Shutdown elasticsearch node
      systemd:
        name: elasticsearch
        state: stopped

    - name: Update elasticsearch
      yum:
        name: elasticsearch-{{ elk_version }}
        state: present

    # - name: Download repository-s3 plugin
    #   get_url: url={{ s3_plugin_url }} dest=/tmp/repository-s3-{{ elk_version }}.zip

    # - name: Remove repository-s3 plugin
    #   shell: /usr/share/elasticsearch/bin/elasticsearch-plugin remove -v repository-s3

    # - name: Upgrade repository-s3 plugin
    #   shell: /usr/share/elasticsearch/bin/elasticsearch-plugin install -v -b file:///tmp/repository-s3-{{ elk_version }}.zip

    # - name: Remove repository-s3 installer
    #   file: path=/tmp/repository-s3-{{ elk_version }}.zip state=absent

    - name: Wait for all shards to be reallocated
      uri:
        url: http://{{ es_host }}:{{ es_http_port }}/_cluster/health
        method: GET
      register: response
      until: "response.json.relocating_shards == 0"
      retries: 20
      delay: 15

    - name: Start elasticsearch
      systemd:
        name: elasticsearch
        state: restarted
        enabled: yes
        daemon_reload: yes

    - name: Wait for elasticsearch node to come back up
      wait_for:
        port: "{{ es_transport_port }}"
        delay: 35

    - name: Wait for elasticsearch http to come back up
      wait_for:
        port: "{{ es_http_port }}"
        delay: 5

    - name: Wait for cluster health to return to yellow or green
      uri:
        url: http://localhost:{{ es_http_port }}/_cluster/health
        method: GET
      register: response
      until: "response.json.status == 'yellow' or response.json.status == 'green'"
      retries: 500
      delay: 15

    - name: Enable shard allocation for the cluster
      uri:
        url: http://localhost:{{ es_http_port }}/_cluster/settings
        method: PUT
        body_format: json
        body: "{{ es_enable_allocation }}"
      register: response
      until: "response.json.acknowledged == true"
      retries: 10
      delay: 15

    - name: Wait for the node to recover
      uri:
        url: http://localhost:{{ es_http_port }}/_cat/health
        method: GET
        return_content: yes
      register: response
      until: "'green' in response.content"
      retries: 500
      delay: 15
    when: version_found.json.version.number is version_compare(elk_version, '<')