roles/prometheus_federate/files/prometheus

@@ -0,0 +1,112 @@
+# Set the command-line arguments to pass to the server.
+ARGS="--log.level=debug --storage.tsdb.retention.time=120d"
+
+# Prometheus supports the following options:
+#  --config.file="/etc/prometheus/prometheus.yml"
+#                             Prometheus configuration file path.
+#  --web.listen-address="0.0.0.0:9090"
+#                             Address to listen on for UI, API, and telemetry.
+#  --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.
+#  --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 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.
+#  --web.local-assets="/usr/share/prometheus/web/"
+#                             Path to static asset/templates directory.
+#  --web.user-assets=<path>   Path to user asset directory, available at
+#                             /user.
+#  --web.enable-lifecycle     Enable shutdown and reload via HTTP request.
+#  --web.enable-admin-api     Enable API endpoints for admin control actions.
+#  --web.console.templates="/etc/prometheus/consoles"
+#                             Path to the console template directory,
+#                             available at /consoles.
+#  --web.console.libraries="/etc/prometheus/console_libraries"
+#                             Path to the console library directory.
+#  --web.page-title="Prometheus Time Series Collection and Processing Server"
+#                             Document title of Prometheus instance.
+#  --web.cors.origin=".*"     Regex for CORS origin. It is fully anchored.
+#                             Example: 'https?://(domain1|domain2)\.com'
+#  --storage.tsdb.path="/var/lib/prometheus/metrics2/"
+#                             Base path for metrics storage.
+#  --storage.tsdb.retention=15d
+#                             [DEPRECATED] How long to retain samples in
+#                             storage. This flag has been deprecated, use
+#                             "storage.tsdb.retention.time" instead
+#  --storage.tsdb.retention.time=15d
+#                             How long to retain samples in storage. When this
+#                             flag is set it overrides
+#                             "storage.tsdb.retention".
+#                             If neither this flag nor "storage.tsdb.retention"
+#                             nor "storage.tsdb.retention.size" is set, the
+#                             retention time defaults to 15d.
+#                             Units Supported: y, w, d, h, m, s, ms.
+#  --storage.tsdb.retention.size=
+#                             [EXPERIMENTAL] Maximum number of bytes that can
+#                             be stored for blocks. Units supported: KB, MB,
+#                             GB, TB, PB. This flag is experimental and can be
+#                             changed in future releases.
+#  --storage.tsdb.use-lockfile
+#                             Create a lockfile in data directory.
+#  --storage.tsdb.allow-overlapping-blocks
+#                             [EXPERIMENTAL] Allow overlapping blocks, which
+#                             in turn enables vertical compaction and
+#                             vertical query merge.
+#  --storage.tsdb.wal-compression
+#                             Compress the tsdb WAL.
+#  --storage.remote.flush-deadline=<duration>
+#                             How long to wait flushing sample on shutdown or
+#                             config reload.
+#  --storage.remote.read-sample-limit=5e7
+#                             Maximum overall number of samples to return via
+#                             the remote read interface, in a single query. 0
+#                             means no limit. This limit is ignored for
+#                             streamed response types.
+#  --storage.remote.read-concurrent-limit=10
+#                             Maximum number of concurrent remote read calls.
+#                             0 means no limit.
+#  --storage.remote.read-max-bytes-in-frame=1048576
+#                             Maximum number of bytes in a single frame for
+#                             streaming remote read response types before
+#                             marshalling. Note that client might have limit on
+#                             frame size as well. 1MB as recommended by
+#                             protobuf by default.
+#  --rules.alert.for-outage-tolerance=1h
+#                             Max time to tolerate prometheus outage for
+#                             restoring "for" state of alert.
+#  --rules.alert.for-grace-period=10m
+#                             Minimum duration between alert and restored "for"
+#                             state. This is maintained only for alerts with
+#                             configured "for" time greater than grace period.
+#  --rules.alert.resend-delay=1m
+#                             Minimum amount of time to wait before resending
+#                             an alert to Alertmanager.
+#  --alertmanager.notification-queue-capacity=10000
+#                             The capacity of the queue for pending
+#                             Alertmanager notifications.
+#  --alertmanager.timeout=10s
+#                             Timeout for sending alerts to Alertmanager.
+#  --query.lookback-delta=5m  The maximum lookback duration for retrieving
+#                             metrics during expression evaluations and
+#                             federation.
+#  --query.timeout=2m         Maximum time a query may take before being
+#                             aborted.
+#  --query.max-concurrency=20
+#                             Maximum number of queries executed concurrently.
+#  --query.max-samples=50000000
+#                             Maximum number of samples a single query can load
+#                             into memory. Note that queries will fail if they
+#                             try to load more samples than this into memory,
+#                             so this also limits the number of samples a query
+#                             can return.
+#  --log.level=info           Only log messages with the given severity or
+#                             above. One of: [debug, info, warn, error]
+#  --log.format=logfmt        Output format of log messages. One of: [logfmt,
+#                             json]

roles/prometheus_federate/tasks/main.yml

@@ -21,10 +21,12 @@
   notify: Restart Prometheus
 
 - name: Define Prometheus retention time
-  lineinfile:
+  copy:
-    path: /etc/default/prometheus
+    src: files/prometheus
-    regexp: '^ARGS=\"--log.level=debug\"'
+    dest: /etc/default/prometheus
-    line: "ARGS=\"--log.level=debug --storage.tsdb.retention.time=120d\""
+    owner: prometheus
+    group: prometheus
+    mode: u=r,g=r,o=
   notify: Restart Prometheus
 
 # We don't need to restart Prometheus when updating nodes