From 63063da9ed34c9f657be7c44568d189687f60c77 Mon Sep 17 00:00:00 2001
From: Brian Christner <brian.christner@gmail.com>
Date: Tue, 21 Feb 2017 13:38:27 +0100
Subject: [PATCH] adding Prometheus configs

---
 alertmanager/config.yml   | 11 +++++++++++
 config.monitoring         |  2 ++
 prometheus/alert.rules    | 13 +++++++++++++
 prometheus/prometheus.yml | 31 +++++++++++++++++++++++++++++++
 4 files changed, 57 insertions(+)
 create mode 100644 alertmanager/config.yml
 create mode 100644 config.monitoring
 create mode 100644 prometheus/alert.rules
 create mode 100644 prometheus/prometheus.yml

diff --git a/alertmanager/config.yml b/alertmanager/config.yml
new file mode 100644
index 0000000..120697b
--- /dev/null
+++ b/alertmanager/config.yml
@@ -0,0 +1,11 @@
+route:
+    receiver: 'slack'
+    repeat_interval: 1m
+
+receivers:
+    - name: 'slack'
+      slack_configs:
+          - send_resolved: true
+            username: 'vegasbrianc'
+            channel: '#notifications'
+            api_url: 'https://hooks.slack.com/services/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'
diff --git a/config.monitoring b/config.monitoring
new file mode 100644
index 0000000..f12466b
--- /dev/null
+++ b/config.monitoring
@@ -0,0 +1,2 @@
+GF_SECURITY_ADMIN_PASSWORD=foobar
+GF_USERS_ALLOW_SIGN_UP=false
diff --git a/prometheus/alert.rules b/prometheus/alert.rules
new file mode 100644
index 0000000..1da000a
--- /dev/null
+++ b/prometheus/alert.rules
@@ -0,0 +1,13 @@
+ALERT service_down
+  IF up == 0
+  ANNOTATIONS {
+      summary = "Instance {{ $labels.instance }} is down :( ",
+      description = "{{ $labels.instance }} of job {{ $labels.job }} is not happy.",
+  }
+  
+ALERT high_load
+  IF node_load1 > 0.5
+  ANNOTATIONS {
+      summary = "Instance {{ $labels.instance }} under high load",
+      description = "{{ $labels.instance }} of job {{ $labels.job }} is under high load.",
+  }
diff --git a/prometheus/prometheus.yml b/prometheus/prometheus.yml
new file mode 100644
index 0000000..03c3e51
--- /dev/null
+++ b/prometheus/prometheus.yml
@@ -0,0 +1,31 @@
+# my global config
+global:
+  scrape_interval:     15s # By default, scrape targets every 15 seconds.
+  evaluation_interval: 15s # By default, scrape targets every 15 seconds.
+  # scrape_timeout is set to the global default (10s).
+
+  # Attach these labels to any time series or alerts when communicating with
+  # external systems (federation, remote storage, Alertmanager).
+  external_labels:
+      monitor: 'Alertmanager'
+
+# Load and evaluate rules in this file every 'evaluation_interval' seconds.
+rule_files:
+  - "alert.rules"
+  # - "first.rules"
+  # - "second.rules"
+
+# A scrape configuration containing exactly one endpoint to scrape:
+# Here it's Prometheus itself.
+scrape_configs:
+  # The job name is added as a label `job=<job_name>` to any timeseries scraped from this config.
+  - job_name: 'Monitoring_Mayhem'
+
+    # Override the global default and scrape targets from this job every 5 seconds.
+#    scrape_interval: 5s
+
+    # metrics_path defaults to '/metrics'
+    # scheme defaults to 'http'.
+
+    static_configs:
+         - targets: ['node-exporter:9100','localhost:9090', 'metrics:9171']