prometheus-splash 0.4.3 → 0.4.4

data/templates/ansible-splash/roles/mq/handlers/main.yml

@@ -0,0 +1,5 @@
+
+---
+- name: restart rabbitmq
+  service: name=rabbitmq-server state=restarted
+  become: yes

data/templates/ansible-splash/roles/mq/tasks/main.yml

@@ -0,0 +1,42 @@
+---
+- name : MQ install MQ service (RabbitMQ)
+  package:
+    pkg: rabbitmq-server
+    state: present
+
+- name: MQ enable rabbitmq plugins
+  rabbitmq_plugin: names=rabbitmq_management,rabbitmq_tracing,rabbitmq_federation state=enabled
+  notify: restart rabbitmq
+
+- name: add Admin users
+  rabbitmq_user:
+    user: "{{ mq_admin_username }}"
+    password: "{{ mq_admin_password }}"
+    tags: administrator,"{{ mq_admin_username }}"
+    vhost: /
+    configure_priv: .*
+    write_priv: .*
+    read_priv: .*
+    state: present
+
+
+- name: remove default guest user
+  rabbitmq_user:
+    user: guest
+    state: absent
+
+
+- name: MQ Configure Splash vhost
+  rabbitmq_vhost:
+    name: "{{ mq_splash_vhost }}"
+    state: present
+
+- name: MQ Add Splash service user
+  rabbitmq_user:
+    user: "{{ mq_splash_username }}"
+    password: "{{ mq_splash_password }}"
+    vhost: "{{ mq_splash_vhost}}"
+    configure_priv: .*
+    read_priv: .*
+    write_priv: .*
+    state: present

data/templates/ansible-splash/roles/splash/tasks/main.yml

@@ -0,0 +1,28 @@
+---
+- name : SPLASH install infra (ruby)
+  package:
+    pkg: ruby
+    state: present
+
+- name : SPLASH install Splash (gem)
+  gem:
+    name: prometheus-splash
+    state: present
+
+- name: SPLASH Check if setup done
+  stat:
+    path: /etc/splash.yml
+  register: stat_result
+
+- name: SPLASH Installation
+  shell: splash conf set
+  when: not stat_result.stat.exists
+
+- name: SPLASH Configuration
+  template:
+    src: splash.yml.j2
+    dest: /etc/splash.yml
+    owner: root
+    group: root
+    mode: 0644
+  #notify: restart Splash

data/templates/ansible-splash/roles/splash/templates/splash.yml.j2

@@ -0,0 +1,105 @@
+# Splash Configuration
+:splash:
+
+### Main Configuration
+  :loggers:
+    :level: :info
+    :daemon:
+      :file: /var/log/splash.log
+    :cli:
+      :emoji: true
+      :color: true
+  :templates:
+    :execution:
+      :path: /etc/splash_execution_report.tpl
+  :backends:
+    :stores:
+      :execution_trace:
+        :type: :redis
+        :host: "{{ redis_host }}"
+        :port: "{{ redis_port }}"
+        :auth: "{{ redis_password }}"
+        :base: "{{ redis_base }}"
+  :transports:
+    :active: :rabbitmq
+    :rabbitmq:
+      :vhost: {{ mq_splash_vhost }}
+      :port: {{ mq_port }}
+      :host: {{ hostvars[groups['mq'][0]]['ansible_host'] }}
+      :passwd: {{ mq_splash_password }}
+      :user: {{ mq_splash_username }}
+  :daemon:
+    :logmon_scheduling:
+      :every: 20s
+    :process_name: "Splash : daemon."
+    :paths:
+      :pid_path: /var/run/splash
+      :trace_path: /var/run/splash/traces
+    :files:
+      :stdout_trace: stdout.txt
+      :stderr_trace: stderr.txt
+      :pid_file: splash.pid
+  :prometheus:
+    :pushgateway:
+      :host: "{{ pushgateway_host }}"
+      :port: "{{ pushgateway_port }}"
+
+
+### configuration of commands and scheduling
+  :commands:
+    :id_root:
+      :desc: run id command on root
+      :command: id root
+    :true_test:
+      :desc: "test command returning true : 0"
+      :command: "true"
+      :schedule:
+        :every: "1h"
+      :on_failure: :ls_slash_tmp
+      :on_success: :pwd
+    :false_test:
+      :desc: "test command returning false > 0"
+      :command: "false"
+      :schedule:
+        :every: "1h"
+      :on_failure: :ls_slash_tmp
+      :on_success: :pwd
+    :ls_slash_tmp:
+      :desc: list file in /tmp
+      :command: ls -al /tmp
+      :user: daemon
+      :on_success: :echo1
+    :pwd:
+      :desc: run pwd
+      :command: pwd
+      :on_success: :echo1
+      :on_failure: :echo2
+    :echo1:
+      :desc: echo 'foo'
+      :command: echo foo
+      :on_failure: :echo3
+    :echo2:
+      :desc: echo 'bar'
+      :command: echo bar
+    :echo3:
+      :desc: echo 'been'
+      :command: echo been
+    :rand_sleep_5:
+      :desc: sleep on a rand 5
+      :command: ruby -e 'sleep rand(5)'
+      :schedule:
+        :every: "10s"
+    :test_remote_call:
+      :desc: remote call test
+      :delegate_to:
+        :host: omicron
+        :remote_command: :echo2
+      :on_success: :echo3
+
+
+### configuration of monitored logs
+  :logs:
+    - :log: /tmp/test
+      :pattern: ERROR
+    - :log: /tmp/test2
+      :pattern: ERROR

data/templates/ansible-splash/roles/supervision_gateway/handlers/main.yml

@@ -0,0 +1,4 @@
+---
+- name: restart Prometheus Gateway
+  service: name=prometheus-pushgateway state=restarted
+  become: yes

data/templates/ansible-splash/roles/supervision_gateway/tasks/main.yml

@@ -0,0 +1,5 @@
+---
+- name : SUPERVISION install gateway service (Prometheus PushGateway)
+  package:
+    pkg: prometheus-pushgateway
+    state: present

data/templates/ansible-splash/roles/supervision_master/handlers/main.yml

@@ -0,0 +1,8 @@
+---
+- name: restart Prometheus
+  service: name=prometheus state=restarted
+  become: yes
+
+- name: restart Alertmanager
+  service: name=prometheus-alertmanager state=restarted
+  become: yes

data/templates/ansible-splash/roles/supervision_master/tasks/main.yml

@@ -0,0 +1,29 @@
+---
+- name : SUPERVISION install master service (Prometheus)
+  package:
+    pkg: prometheus
+    state: present
+
+- name : SUPERVISION install alert service (alertmanager)
+  package:
+    pkg: prometheus-alertmanager
+    state: present
+
+- name: SUPERVISION Configuration
+  template:
+    src: prometheus.yml.j2
+    dest: /etc/prometheus/prometheus.yml
+    owner: root
+    group: root
+    mode: 0644
+  notify: restart Prometheus
+
+
+- name: SUPERVISION Configuration
+  template:
+    src: alertmanager.yml.j2
+    dest: /etc/prometheus/alertmanager.yml
+    owner: root
+    group: root
+    mode: 0644
+  notify: restart Alertmanager

data/templates/ansible-splash/roles/supervision_master/templates/alertmanager.yml.j2

@@ -0,0 +1,126 @@
+# Sample configuration.
+# See https://prometheus.io/docs/alerting/configuration/ for documentation.
+
+global:
+  # The smarthost and SMTP sender used for mail notifications.
+  smtp_smarthost: 'localhost:25'
+  smtp_from: 'alertmanager@example.org'
+  smtp_auth_username: 'alertmanager'
+  smtp_auth_password: 'password'
+  # The auth token for Hipchat.
+  hipchat_auth_token: '1234556789'
+  # Alternative host for Hipchat.
+  hipchat_url: 'https://hipchat.foobar.org/'
+
+# The directory from which notification templates are read.
+templates: 
+- '/etc/prometheus/alertmanager_templates/*.tmpl'
+
+# The root route on which each incoming alert enters.
+route:
+  # The labels by which incoming alerts are grouped together. For example,
+  # multiple alerts coming in for cluster=A and alertname=LatencyHigh would
+  # be batched into a single group.
+  group_by: ['alertname', 'cluster', 'service']
+
+  # When a new group of alerts is created by an incoming alert, wait at
+  # least 'group_wait' to send the initial notification.
+  # This way ensures that you get multiple alerts for the same group that start
+  # firing shortly after another are batched together on the first 
+  # notification.
+  group_wait: 30s
+
+  # When the first notification was sent, wait 'group_interval' to send a batch
+  # of new alerts that started firing for that group.
+  group_interval: 5m
+
+  # If an alert has successfully been sent, wait 'repeat_interval' to
+  # resend them.
+  repeat_interval: 3h 
+
+  # A default receiver
+  receiver: team-X-mails
+
+  # All the above attributes are inherited by all child routes and can 
+  # overwritten on each.
+
+  # The child route trees.
+  routes:
+  # This routes performs a regular expression match on alert labels to
+  # catch alerts that are related to a list of services.
+  - match_re:
+      service: ^(foo1|foo2|baz)$
+    receiver: team-X-mails
+    # The service has a sub-route for critical alerts, any alerts
+    # that do not match, i.e. severity != critical, fall-back to the
+    # parent node and are sent to 'team-X-mails'
+    routes:
+    - match:
+        severity: critical
+      receiver: team-X-pager
+  - match:
+      service: files
+    receiver: team-Y-mails
+
+    routes:
+    - match:
+        severity: critical
+      receiver: team-Y-pager
+
+  # This route handles all alerts coming from a database service. If there's
+  # no team to handle it, it defaults to the DB team.
+  - match:
+      service: database
+    receiver: team-DB-pager
+    # Also group alerts by affected database.
+    group_by: [alertname, cluster, database]
+    routes:
+    - match:
+        owner: team-X
+      receiver: team-X-pager
+    - match:
+        owner: team-Y
+      receiver: team-Y-pager
+
+
+# Inhibition rules allow to mute a set of alerts given that another alert is
+# firing.
+# We use this to mute any warning-level notifications if the same alert is 
+# already critical.
+inhibit_rules:
+- source_match:
+    severity: 'critical'
+  target_match:
+    severity: 'warning'
+  # Apply inhibition if the alertname is the same.
+  equal: ['alertname', 'cluster', 'service']
+
+
+receivers:
+- name: 'team-X-mails'
+  email_configs:
+  - to: 'team-X+alerts@example.org'
+
+- name: 'team-X-pager'
+  email_configs:
+  - to: 'team-X+alerts-critical@example.org'
+  pagerduty_configs:
+  - service_key: <team-X-key>
+
+- name: 'team-Y-mails'
+  email_configs:
+  - to: 'team-Y+alerts@example.org'
+
+- name: 'team-Y-pager'
+  pagerduty_configs:
+  - service_key: <team-Y-key>
+
+- name: 'team-DB-pager'
+  pagerduty_configs:
+  - service_key: <team-DB-key>
+- name: 'team-X-hipchat'
+  hipchat_configs:
+  - auth_token: <auth_token>
+    room_id: 85
+    message_format: html
+    notify: true

data/templates/ansible-splash/roles/supervision_master/templates/prometheus.yml.j2

@@ -0,0 +1,33 @@
+# Sample config for Prometheus.
+
+global:
+  scrape_interval:     15s
+  evaluation_interval: 15s
+
+
+  external_labels:
+      monitor: 'example'
+
+
+rule_files:
+  # - "first.rules"
+  # - "second.rules"
+
+# himself
+scrape_configs:
+  - job_name: 'prometheus'
+    scrape_interval: 5s
+    scrape_timeout: 5s
+    static_configs:
+      - targets: ['{{ groups['supervision_master'][0] }}:9090']
+
+ # PushGateway
+  - job_name: node
+    static_configs:
+      - targets: ['{{ groups['supervision_gateway'][0] }}:9091']
+
+alerting:
+  alertmanagers:
+  - static_configs:
+    - targets:
+      -  '{{ groups['supervision_master'][0] }}:9093'

data/templates/splashd.service

@@ -3,13 +3,14 @@ Description=Splash Daemon
 After=network-online.target
 
 [Service]
-Type=simple
+Type=forking
 
-User=splash
-Group=splash
+User=root
+Group=root
 UMask=007
 
-ExecStart=/splash daemon start
+ExecStart=/usr/local/bin/splash daemon start
+ExecStop=/usr/local/bin/splash daemon stop
 
 Restart=on-failure
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: prometheus-splash
 version: !ruby/object:Gem::Version
-  version: 0.4.3
+  version: 0.4.4
 platform: ruby
 authors:
 - Romain GEORGES
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2020-04-14 00:00:00.000000000 Z
+date: 2020-04-16 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: thor
@@ -273,6 +273,26 @@ files:
 - lib/splash/transports/rabbitmq.rb
 - prometheus-splash.gemspec
 - spec/templates_spec.rb
+- templates/ansible-splash/Vagrantfile
+- templates/ansible-splash/deploy.yml
+- templates/ansible-splash/group_vars/DEV.yml
+- templates/ansible-splash/group_vars/PROD.yml
+- templates/ansible-splash/group_vars/all.yml
+- templates/ansible-splash/inventory.dev
+- templates/ansible-splash/inventory.prod
+- templates/ansible-splash/roles/backend/handlers/main.yml
+- templates/ansible-splash/roles/backend/tasks/main.yml
+- templates/ansible-splash/roles/backend/templates/redis.conf.j2
+- templates/ansible-splash/roles/mq/handlers/main.yml
+- templates/ansible-splash/roles/mq/tasks/main.yml
+- templates/ansible-splash/roles/splash/tasks/main.yml
+- templates/ansible-splash/roles/splash/templates/splash.yml.j2
+- templates/ansible-splash/roles/supervision_gateway/handlers/main.yml
+- templates/ansible-splash/roles/supervision_gateway/tasks/main.yml
+- templates/ansible-splash/roles/supervision_master/handlers/main.yml
+- templates/ansible-splash/roles/supervision_master/tasks/main.yml
+- templates/ansible-splash/roles/supervision_master/templates/alertmanager.yml.j2
+- templates/ansible-splash/roles/supervision_master/templates/prometheus.yml.j2
 - templates/report.txt
 - templates/splashd.service
 - ultragreen_roodi_coding_convention.yml