Merge pull request #1 from StreetHawkInc/master

Updated to support 2.0

prometheus/defaults.yaml

@@ -39,3 +39,8 @@ prometheus:
       source_hash: sha1=56849253e280db3db2aa80f1013ecfe242536d32
       args:
         scrape_uri: 'unix:/run/haproxy/admin.sock'
+    rabbitmq:
+      version: 0.24.0.linux-amd64
+      install_dir: /opt
+      source: https://github.com/kbudde/rabbitmq_exporter/releases/download/v0.24.0/rabbitmq_exporter-0.24.0.linux-amd64.tar.gz
+      source_hash: sha256=dbbd44a5a4b4a22ba338b9732c014587bc11513a5d6d2e3e519fc313b1cc46d4

prometheus/exporter/rabbitmq.sls

@@ -0,0 +1,49 @@
+{% from "prometheus/map.jinja" import prometheus with context %}
+
+include:
+  - prometheus.user
+
+rabbitmq_exporter_tarball:
+  archive.extracted:
+    - name: {{ prometheus.exporter.rabbitmq.install_dir }}
+    - source: {{ prometheus.exporter.rabbitmq.source }}
+    - source_hash: {{ prometheus.exporter.rabbitmq.source_hash }}
+    - user: {{ prometheus.user }}
+    - group: {{ prometheus.group }}
+    - archive_format: tar
+    - if_missing: {{ prometheus.exporter.rabbitmq.version_path }}
+
+rabbitmq_exporter_bin_link:
+  file.symlink:
+    - name: /usr/bin/rabbitmq_exporter
+    - target: {{ prometheus.exporter.rabbitmq.version_path }}/rabbitmq_exporter
+    - require:
+      - archive: rabbitmq_exporter_tarball
+
+rabbitmq_exporter_defaults:
+  file.managed:
+    - name: /etc/default/rabbitmq_exporter
+    - source: salt://prometheus/files/default-rabbitmq_exporter.jinja
+    - template: jinja
+
+rabbitmq_exporter_service_unit:
+  file.managed:
+{%- if grains.get('init') == 'systemd' %}
+    - name: /etc/systemd/system/rabbitmq_exporter.service
+    - source: salt://prometheus/files/rabbitmq_exporter.systemd.jinja
+{%- elif grains.get('init') == 'upstart' %}
+    - name: /etc/init/rabbitmq_exporter.conf
+    - source: salt://prometheus/files/rabbitmq_exporter.upstart.jinja
+{%- endif %}
+    - require_in:
+      - file: rabbitmq_exporter_service
+
+rabbitmq_exporter_service:
+  service.running:
+    - name: rabbitmq_exporter
+    - enable: True
+    - reload: True
+    - watch:
+      - file: rabbitmq_exporter_service_unit
+      - file: rabbitmq_exporter_defaults
+      - file: rabbitmq_exporter_bin_link

prometheus/files/default-alertmanager.jinja

@@ -1,5 +1,5 @@
 # Set the command-line arguments to pass to the server.
-ARGS="-config.file {{config_file}} -storage.path {{ storage_path }}"
+ARGS="--config.file {{config_file}} --storage.path {{ storage_path }}"
 
 # The alert manager supports the following options:
 #  -config.file string

prometheus/files/default-blackbox_exporter.jinja

@@ -1,5 +1,5 @@
 # Set the command-line arguments to pass to the blackbox_exporter service.
-ARGS="-config.file {{config_file}}"
+ARGS="--config.file {{config_file}}"
 
 # Blackbox exporter supports the following options:
 #   -config.file string

prometheus/files/default-haproxy_exporter.jinja

@@ -1,5 +1,5 @@
 # Set the command-line arguments to pass to the haproxy_exporter service.
-ARGS='-haproxy.scrape-uri="{{scrape_uri}}"'
+ARGS='--haproxy.scrape-uri="{{scrape_uri}}"'
 
 # Haproxy exporter supports the following options:
 #   -haproxy.scrape-uri string

prometheus/files/default-prometheus.jinja

@@ -1,178 +1,46 @@
 # Set the command-line arguments to pass to the server.
-ARGS="-config.file {{config_file}} -storage.local.path {{storage_local_path}} -web.console.libraries {{web_console_libraries}} -web.console.templates {{web_console_templates}}"
+ARGS="--config.file {{config_file}} --storage.tsdb.path {{storage_local_path}} --web.console.libraries {{web_console_libraries}} --web.console.templates {{web_console_templates}}"
 
-# Prometheus supports the following options:
+# usage: prometheus [<flags>]
-
+# 
-#   -config.file "/etc/prometheus/prometheus.yml"
+# The Prometheus monitoring server
-#      Prometheus configuration file name.
+# 
-#
+# Flags:
-# == ALERTMANAGER ==
+#   -h, --help                     Show context-sensitive help (also try --help-long and --help-man).
-#
+#       --version                  Show application version.
-#   -alertmanager.notification-queue-capacity 10000
+#       --config.file="prometheus.yml"
-#      The capacity of the queue for pending alert manager notifications.
+#                                  Prometheus configuration file path.
-#
+#       --web.listen-address="0.0.0.0:9090"
-#   -alertmanager.timeout 10s
+#                                  Address to listen on for UI, API, and telemetry.
-#      Alert manager HTTP API timeout.
+#       --web.read-timeout=5m      Maximum duration before timing out read of the request, and closing idle connections.
-#
+#       --web.max-connections=512  Maximum number of simultaneous connections.
-#   -alertmanager.url
+#       --web.external-url=<URL>   The URL under which Prometheus is externally reachable (for example, if Prometheus is served via a reverse proxy). Used for generating relative and absolute links back to Prometheus itself. If the URL has a
-#      The URL of the alert manager to send notifications to.
+#                                  path portion, it will be used to prefix all HTTP endpoints served by Prometheus. If omitted, relevant URL components will be derived automatically.
-#
+#       --web.route-prefix=<path>  Prefix for the internal routes of web endpoints. Defaults to path of --web.external-url.
-# == LOG ==
+#       --web.user-assets=<path>   Path to static asset directory, available at /user.
-#
+#       --web.enable-lifecycle     Enable shutdown and reload via HTTP request.
-#   -log.format
+#       --web.enable-admin-api     Enables API endpoints for admin control actions.
-#      If set use a syslog logger or JSON logging. Example:
+#       --web.console.templates="consoles"
-#      logger:syslog?appname=bob&local=7 or logger:stdout?json=true. Defaults to
+#                                  Path to the console template directory, available at /consoles.
-#      stderr.
+#       --web.console.libraries="console_libraries"
-#
+#                                  Path to the console library directory.
-#   -log.level "info"
+#       --storage.tsdb.path="data/"
-#      Only log messages with the given severity or above. Valid levels:
+#                                  Base path for metrics storage.
-#      [debug, info, warn, error, fatal].
+#       --storage.tsdb.min-block-duration=2h
-#
+#                                  Minimum duration of a data block before being persisted.
-# == QUERY ==
+#       --storage.tsdb.max-block-duration=<duration>
-#
+#                                  Maximum duration compacted blocks may span. (Defaults to 10% of the retention period)
-#   -query.max-concurrency 20
+#       --storage.tsdb.retention=15d
-#      Maximum number of queries executed concurrently.
+#                                  How long to retain samples in the storage.
-#
+#       --storage.tsdb.no-lockfile
-#   -query.staleness-delta 5m0s
+#                                  Do not create lockfile in data directory.
-#      Staleness delta allowance during expression evaluations.
+#       --alertmanager.notification-queue-capacity=10000
-#
+#                                  The capacity of the queue for pending alert manager notifications.
-#   -query.timeout 2m0s
+#       --alertmanager.timeout=10s
-#      Maximum time a query may take before being aborted.
+#                                  Timeout for sending alerts to Alertmanager.
-#
+#       --query.lookback-delta=5m  The delta difference allowed for retrieving metrics during expression evaluations.
-# == STORAGE ==
+#       --query.timeout=2m         Maximum time a query may take before being aborted.
-#
+#       --query.max-concurrency=20
-#   -storage.local.checkpoint-dirty-series-limit 5000
+#                                  Maximum number of queries executed concurrently.
-#      If approx. that many time series are in a state that would require
+#       --log.level=info           Only log messages with the given severity or above. One of: [debug, info, warn, error]
-#      a recovery operation after a crash, a checkpoint is triggered, even if
+# 
-#      the checkpoint interval hasn't passed yet. A recovery operation requires
-#      a disk seek. The default limit intends to keep the recovery time below
-#      1min even on spinning disks. With SSD, recovery is much faster, so you
-#      might want to increase this value in that case to avoid overly frequent
-#      checkpoints.
-#
-#   -storage.local.checkpoint-interval 5m0s
-#      The period at which the in-memory metrics and the chunks not yet
-#      persisted to series files are checkpointed.
-#
-#   -storage.local.chunk-encoding-version 1
-#      Which chunk encoding version to use for newly created chunks.
-#      Currently supported is 0 (delta encoding) and 1 (double-delta encoding).
-#
-#   -storage.local.dirty false
-#      If set, the local storage layer will perform crash recovery even if
-#      the last shutdown appears to be clean.
-#
-#   -storage.local.index-cache-size.fingerprint-to-metric 10485760
-#      The size in bytes for the fingerprint to metric index cache.
-#
-#   -storage.local.index-cache-size.fingerprint-to-timerange 5242880
-#      The size in bytes for the metric time range index cache.
-#
-#   -storage.local.index-cache-size.label-name-to-label-values 10485760
-#      The size in bytes for the label name to label values index cache.
-#
-#   -storage.local.index-cache-size.label-pair-to-fingerprints 20971520
-#      The size in bytes for the label pair to fingerprints index cache.
-#
-#   -storage.local.max-chunks-to-persist 524288
-#      How many chunks can be waiting for persistence before sample
-#      ingestion will be throttled. Many chunks waiting to be persisted will
-#      increase the checkpoint size.
-#
-#   -storage.local.memory-chunks 1048576
-#      How many chunks to keep in memory. While the size of a chunk is
-#      1kiB, the total memory usage will be significantly higher than this value
-#      * 1kiB. Furthermore, for various reasons, more chunks might have to be
-#      kept in memory temporarily. Sample ingestion will be throttled if the
-#      configured value is exceeded by more than 10%.
-#
-#   -storage.local.path "/var/lib/prometheus/metrics"
-#      Base path for metrics storage.
-#
-#   -storage.local.pedantic-checks false
-#      If set, a crash recovery will perform checks on each series file.
-#      This might take a very long time.
-#
-#   -storage.local.retention 360h0m0s
-#      How long to retain samples in the local storage.
-#
-#   -storage.local.series-file-shrink-ratio 0.1
-#      A series file is only truncated (to delete samples that have
-#      exceeded the retention period) if it shrinks by at least the provided
-#      ratio. This saves I/O operations while causing only a limited storage
-#      space overhead. If 0 or smaller, truncation will be performed even for a
-#      single dropped chunk, while 1 or larger will effectively prevent any
-#      truncation.
-#
-#   -storage.local.series-sync-strategy "adaptive"
-#      When to sync series files after modification. Possible values:
-#      'never', 'always', 'adaptive'. Sync'ing slows down storage performance
-#      but reduces the risk of data loss in case of an OS crash. With the
-#      'adaptive' strategy, series files are sync'd for as long as the storage
-#      is not too much behind on chunk persistence.
-#
-#   -storage.remote.graphite-address
-#      The host:port of the remote Graphite server to send samples to.
-#      None, if empty.
-#
-#   -storage.remote.graphite-prefix
-#      The prefix to prepend to all metrics exported to Graphite. None, if
-#      empty.
-#
-#   -storage.remote.graphite-transport "tcp"
-#      Transport protocol to use to communicate with Graphite. 'tcp', if
-#      empty.
-#
-#   -storage.remote.influxdb-url
-#      The URL of the remote InfluxDB server to send samples to. None, if
-#      empty.
-#
-#   -storage.remote.influxdb.database "prometheus"
-#      The name of the database to use for storing samples in InfluxDB.
-#
-#   -storage.remote.influxdb.retention-policy "default"
-#      The InfluxDB retention policy to use.
-#
-#   -storage.remote.influxdb.username
-#      The username to use when sending samples to InfluxDB. The
-#      corresponding password must be provided via the INFLUXDB_PW environment
-#      variable.
-#
-#   -storage.remote.opentsdb-url
-#      The URL of the remote OpenTSDB server to send samples to. None, if
-#      empty.
-#
-#   -storage.remote.timeout 30s
-#      The timeout to use when sending samples to the remote storage.
-#
-# == WEB ==
-#
-#   -web.console.libraries "/etc/prometheus/console_libraries"
-#      Path to the console library directory.
-#
-#   -web.console.templates "/etc/prometheus/consoles"
-#      Path to the console template directory, available at /consoles.
-#
-#   -web.enable-remote-shutdown false
-#      Enable remote service shutdown.
-#
-#   -web.external-url
-#      The URL under which Prometheus is externally reachable (for
-#      example, if Prometheus is served via a reverse proxy). Used for
-#      generating relative and absolute links back to Prometheus itself. If the
-#      URL has a path portion, it will be used to prefix all HTTP endpoints
-#      served by Prometheus. If omitted, relevant URL components will be derived
-#      automatically.
-#
-#   -web.listen-address ":9090"
-#      Address to listen on for the web interface, API, and telemetry.
-#
-#   -web.local-assets "/usr/share/prometheus/web/"
-#      Path to static assets/templates directory.
-#
-#   -web.telemetry-path "/metrics"
-#      Path under which to expose metrics.
-#
-#   -web.user-assets
-#      Path to static asset directory, available at /user.
-#

prometheus/files/default-rabbitmq_exporter.jinja

@@ -0,0 +1,20 @@
+#https://github.com/kbudde/rabbitmq_exporter
+RABBIT_CAPABILITIES=no_sort,bert
+
+
+#Environment variable|default|description
+#--------------------|-------|------------
+#RABBIT_URL | <http://localhost:15672>| url to rabbitMQ management plugin
+#RABBIT_USER | guest | username for rabbitMQ management plugin
+#RABBIT_PASSWORD | guest | password for rabbitMQ management plugin
+#RABBIT_USER_FILE| | location of file with username (useful for docker secrets)
+#RABBIT_PASSWORD_FILE | | location of file with password (useful for docker secrets)
+#PUBLISH_PORT | 9090 | Listening port for the exporter
+#OUTPUT_FORMAT | TTY | Log ouput format. TTY and JSON are suported
+#LOG_LEVEL | info | log level. possible values: "debug", "info", "warning", "error", "fatal", or "panic"
+#CAFILE | ca.pem | path to root certificate for access management plugin. Just needed if self signed certificate is used. Will be ignored if the file does not exist
+#SKIPVERIFY | false | true/0 will ignore certificate errors of the management plugin
+#INCLUDE_QUEUES | .* | reqgex queue filter. just matching names are exported
+#SKIP_QUEUES | ^$ |regex, matching queue names are not exported (useful for short-lived rpc queues). First performed INCLUDE, after SKIP
+#RABBIT_CAPABILITIES | | comma-separated list of extended scraping capabilities supported by the target RabbitMQ server
+#RABBIT_EXPORTERS | exchange,node,overview,queue | List of enabled modules. Just "connections" is not enabled by default

prometheus/files/rabbitmq_exporter.systemd.jinja

@@ -0,0 +1,18 @@
+[Unit]
+Description=Prometheus rabbitmq exporter
+Documentation=https://github.com/kbudde/rabbitmq_exporter
+Wants=basic.target
+After=basic.target network.target
+
+[Service]
+User=prometheus
+Group=prometheus
+EnvironmentFile=/etc/default/rabbitmq_exporter
+ExecStart=/usr/bin/rabbitmq_exporter
+ExecReload=/bin/kill -HUP $MAINPID
+KillMode=process
+Restart=always
+RestartSec=42s
+
+[Install]
+WantedBy=multi-user.target

prometheus/map.jinja

@@ -1,10 +1,12 @@
 {% import_yaml 'prometheus/defaults.yaml' as defaults %}
 
-{% do defaults.prometheus.alertmanager.update({'version_path': defaults.prometheus.alertmanager.install_dir ~ "/alertmanager-" ~ defaults.prometheus.alertmanager.version}) %}
-{% do defaults.prometheus.server.update({'version_path': defaults.prometheus.server.install_dir ~ "/prometheus-" ~ defaults.prometheus.server.version}) %}
-
-{% do defaults.prometheus.exporter.node.update({'version_path': defaults.prometheus.exporter.node.install_dir ~ "/node_exporter-" ~ defaults.prometheus.exporter.node.version}) %}
-{% do defaults.prometheus.exporter.blackbox.update({'version_path': defaults.prometheus.exporter.blackbox.install_dir ~ "/blackbox_exporter-" ~ defaults.prometheus.exporter.blackbox.version}) %}
-{% do defaults.prometheus.exporter.haproxy.update({'version_path': defaults.prometheus.exporter.haproxy.install_dir ~ "/haproxy_exporter-" ~ defaults.prometheus.exporter.haproxy.version}) %}
-
 {% set prometheus = salt['pillar.get']('prometheus', default=defaults.prometheus, merge=True) %}
+
+{% do prometheus.alertmanager.update({'version_path': prometheus.alertmanager.install_dir ~ "/alertmanager-" ~ prometheus.alertmanager.version}) %}
+{% do prometheus.server.update({'version_path': prometheus.server.install_dir ~ "/prometheus-" ~ prometheus.server.version}) %}
+
+{% do prometheus.exporter.node.update({'version_path': prometheus.exporter.node.install_dir ~ "/node_exporter-" ~ prometheus.exporter.node.version}) %}
+{% do prometheus.exporter.blackbox.update({'version_path': prometheus.exporter.blackbox.install_dir ~ "/blackbox_exporter-" ~ prometheus.exporter.blackbox.version}) %}
+{% do prometheus.exporter.haproxy.update({'version_path': prometheus.exporter.haproxy.install_dir ~ "/haproxy_exporter-" ~ prometheus.exporter.haproxy.version}) %}
+{% do prometheus.exporter.rabbitmq.update({'version_path': prometheus.exporter.rabbitmq.install_dir ~ "/rabbitmq_exporter-" ~ prometheus.exporter.rabbitmq.version}) %}
+