tools/salt-install/config_examples/multi_host/aws/pillars/prometheus_server.sls

   1 ---
   2 # Copyright (C) The Arvados Authors. All rights reserved.
   3 #
   4 # SPDX-License-Identifier: AGPL-3.0
   5
   6 {%- set controller_nodes = "__CONTROLLER_NODES__".split(',') %}
   7 {%- set enable_balancer = ("__ENABLE_BALANCER__"|to_bool) %}
   8 {%- set data_retention_time = "__PROMETHEUS_DATA_RETENTION_TIME__" %}
   9
  10 ### PROMETHEUS
  11 prometheus:
  12   wanted:
  13     component:
  14       - prometheus
  15       - alertmanager
  16       - node_exporter
  17       - blackbox_exporter
  18   pkg:
  19     use_upstream_repo: false
  20     use_upstream_archive: true
  21     component:
  22       blackbox_exporter:
  23         config_file: /etc/prometheus/blackbox_exporter.yml
  24         config:
  25           modules:
  26             http_2xx:
  27               prober: http
  28               timeout: 5s
  29               http:
  30                 valid_http_versions: [HTTP/1.1, HTTP/2]
  31                 valid_status_codes: []  # Default is [200]
  32                 fail_if_ssl: false
  33                 fail_if_not_ssl: false
  34       prometheus:
  35         service:
  36            args:
  37              storage.tsdb.retention.time: {{ data_retention_time }}
  38         config:
  39           global:
  40             scrape_interval: 15s
  41             evaluation_interval: 15s
  42           rule_files:
  43             - rules.yml
  44
  45           scrape_configs:
  46             - job_name: prometheus
  47               # metrics_path defaults to /metrics
  48               # scheme defaults to http.
  49               static_configs:
  50               - targets: ['localhost:9090']
  51                 labels:
  52                   instance: mon.__CLUSTER__
  53                   cluster: __CLUSTER__
  54
  55             - job_name: http_probe
  56               metrics_path: /probe
  57               params:
  58                 module: [http_2xx]
  59               static_configs:
  60                 - targets: ['https://__DOMAIN__']
  61                   labels:
  62                     instance: controller.__CLUSTER__
  63                 - targets: ['https://workbench.__DOMAIN__']
  64                   labels:
  65                     instance: workbench.__CLUSTER__
  66                 - targets: ['https://workbench2.__DOMAIN__']
  67                   labels:
  68                     instance: workbench2.__CLUSTER__
  69                 - targets: ['https://download.__DOMAIN__']
  70                   labels:
  71                     instance: download.__CLUSTER__
  72                 - targets: ['https://grafana.__DOMAIN__']
  73                   labels:
  74                     instance: grafana.__CLUSTER__
  75                 - targets: ['https://prometheus.__DOMAIN__']
  76                   labels:
  77                     instance: prometheus.__CLUSTER__
  78                 - targets: ['https://webshell.__DOMAIN__']
  79                   labels:
  80                     instance: webshell.__CLUSTER__
  81                 - targets: ['https://ws.__DOMAIN__']
  82                   labels:
  83                     instance: ws.__CLUSTER__
  84               relabel_configs:
  85                 - source_labels: [__address__]
  86                   target_label: __param_target
  87                 - source_labels: [__param_target]
  88                   target_label: instance
  89                 - target_label: __address__
  90                   replacement: 127.0.0.1:9115          # blackbox exporter.
  91
  92             ## Arvados unique jobs
  93             - job_name: arvados_ws
  94               bearer_token: __MANAGEMENT_TOKEN__
  95               scheme: https
  96               static_configs:
  97                 - targets: ['ws.__DOMAIN__:443']
  98                   labels:
  99                     instance: ws.__CLUSTER__
 100                     cluster: __CLUSTER__
 101             - job_name: arvados_controller
 102               bearer_token: __MANAGEMENT_TOKEN__
 103               {%- if enable_balancer %}
 104               scheme: http
 105               {%- else %}
 106               scheme: https
 107               {%- endif %}
 108               static_configs:
 109                 {%- if enable_balancer %}
 110                   {%- for controller in controller_nodes %}
 111                 - targets: ['{{ controller }}']
 112                   labels:
 113                     instance: {{ controller.split('.')[0] }}.__CLUSTER__
 114                     cluster: __CLUSTER__
 115                   {%- endfor %}
 116                 {%- else %}
 117                 - targets: ['__DOMAIN__:443']
 118                   labels:
 119                     instance: controller.__CLUSTER__
 120                     cluster: __CLUSTER__
 121                 {%- endif %}
 122             - job_name: keep_web
 123               bearer_token: __MANAGEMENT_TOKEN__
 124               scheme: https
 125               static_configs:
 126                 - targets: ['keep.__DOMAIN__:443']
 127                   labels:
 128                     instance: keep-web.__CLUSTER__
 129                     cluster: __CLUSTER__
 130             - job_name: keep_balance
 131               bearer_token: __MANAGEMENT_TOKEN__
 132               static_configs:
 133                 - targets: ['__KEEPBALANCE_INT_IP__:9005']
 134                   labels:
 135                     instance: keep-balance.__CLUSTER__
 136                     cluster: __CLUSTER__
 137             - job_name: keepstore
 138               bearer_token: __MANAGEMENT_TOKEN__
 139               static_configs:
 140                 - targets: ['__KEEPSTORE0_INT_IP__:25107']
 141                   labels:
 142                     instance: keep0.__CLUSTER__
 143                     cluster: __CLUSTER__
 144             - job_name: arvados_dispatch_cloud
 145               bearer_token: __MANAGEMENT_TOKEN__
 146               static_configs:
 147                 - targets: ['__DISPATCHER_INT_IP__:9006']
 148                   labels:
 149                     instance: arvados-dispatch-cloud.__CLUSTER__
 150                     cluster: __CLUSTER__
 151
 152             {%- if "__DATABASE_INT_IP__" != "" %}
 153             # Database
 154             - job_name: postgresql
 155               static_configs:
 156                 - targets: [
 157                     '__DATABASE_INT_IP__:9187',
 158                     '__DATABASE_INT_IP__:3903'
 159                   ]
 160                   labels:
 161                     instance: database.__CLUSTER__
 162                     cluster: __CLUSTER__
 163             {%- endif %}
 164
 165             # Nodes
 166             {%- set node_list = "__NODELIST__".split(',') %}
 167             {%- set nodes = [] %}
 168             {%- for node in node_list %}
 169               {%- set _ = nodes.append(node.split('.')[0]) %}
 170             {%- endfor %}
 171             - job_name: node
 172               static_configs:
 173                 {% for node in nodes %}
 174                 - targets: [ "{{ node }}.__DOMAIN__:9100" ]
 175                   labels:
 176                     instance: "{{ node }}.__CLUSTER__"
 177                     cluster: __CLUSTER__
 178                 {% endfor %}