openstack-helm/alertmanager/values.yaml

# Copyright 2017 The Openstack-Helm Authors.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

# Default values for alertmanager.
# This is a YAML-formatted file.
# Declare name/value pairs to be passed into your templates.
# name: value

images:
  tags:
    alertmanager: docker.io/prom/alertmanager:v0.11.0
    dep_check: quay.io/stackanetes/kubernetes-entrypoint:v0.2.1
    image_repo_sync: docker.io/docker:17.07.0
  pull_policy: IfNotPresent
  local_registry:
    active: false
    exclude:
      - dep_check
      - image_repo_sync

labels:
  node_selector_key: openstack-control-plane
  node_selector_value: enabled

pod:
  affinity:
      anti:
        type:
          default: preferredDuringSchedulingIgnoredDuringExecution
        topologyKey:
          default: kubernetes.io/hostname
  mounts:
    alertmanager:
      alertmanager:
      init_container: null
  replicas:
    alertmanager: 1
  lifecycle:
    upgrades:
      revision_history: 3
      pod_replacement_strategy: RollingUpdate
      rolling_update:
        max_unavailable: 1
        max_surge: 3
    termination_grace_period:
      alertmanager:
        timeout: 30
  resources:
    enabled: false
    alertmanager:
      limits:
        memory: "1024Mi"
        cpu: "2000m"
      requests:
        memory: "128Mi"
        cpu: "500m"
    jobs:
      image_repo_sync:
        requests:
          memory: "128Mi"
          cpu: "100m"
        limits:
          memory: "1024Mi"
          cpu: "2000m"

endpoints:
  cluster_domain_suffix: cluster.local
  local_image_registry:
    name: docker-registry
    namespace: docker-registry
    hosts:
      default: localhost
      internal: docker-registry
      node: localhost
    host_fqdn_override:
      default: null
    port:
      registry:
        node: 5000
  alerts:
    name: alertmanager
    namespace: null
    hosts:
      default: alerts-api
      public: alertmanager
    host_fqdn_override:
      default: null
    path:
      default: null
    scheme:
      default: 'http'
    port:
      api:
        default: 9093
        public: 80

dependencies:
  alertmanager:
    services: null
  image_repo_sync:
    services:
      - service: local_image_registry
        endpoint: internal

conditional_dependencies:
  local_image_registry:
    jobs:
      - alertmanager-image-repo-sync
    services:
      - service: local_image_registry
        endpoint: node

network:
  alertmanager:
    ingress:
      public: true
      proxy_body_size: 1024M
    node_port:
      enabled: false
      port: 30903
    port: 9093

storage:
  enabled: true
  pvc:
    name: alertmanager-pvc
    access_mode: ReadWriteMany
  requests:
    storage: 5Gi
  storage_class: general

manifests:
  clusterrolebinding: true
  configmap_bin: true
  configmap_etc: true
  ingress: true
  job_image_repo_sync: true
  pvc: true
  rbac_entrypoint: true
  service: true
  service_ingress: true
  serviceaccount: true
  statefulset: true

conf:
  alertmanager: |
    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_api_url: 'https://hipchat.foobar.org/'
    # The directory from which notification templates are read.
    templates:
    - '/etc/alertmanager/template/*.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