prometheus: connect server to alertmanager if configured

3 files changed, 64 insertions, 1 deletions

diff --git a/roles/monitoring/prometheus/server/defaults/main/main.yml b/roles/monitoring/prometheus/server/defaults/main/main.yml
index b10d6f17..8e7fea4b 100644
--- a/roles/monitoring/prometheus/server/defaults/main/main.yml
+++ b/roles/monitoring/prometheus/server/defaults/main/main.yml
@@ -9,5 +9,8 @@ prometheus_server_jobs:
   - node
 
 prometheus_server_rules:
-  prometheus: "{{ prometheus_server_rules_prometheus + prometheus_server_rules_prometheus_extra }}"
+  prometheus: "{{ prometheus_server_rules_prometheus + ((prometheus_server_alertmanager is defined) | ternary(prometheus_server_rules_prometheus_alertmanager, [])) + prometheus_server_rules_prometheus_extra }}"
   node: "{{ prometheus_server_rules_node + prometheus_server_rules_prometheus_extra }}"
+
+# prometheus_server_alertmanager:
+#   url: "127.0.0.1:9093"
diff --git a/roles/monitoring/prometheus/server/defaults/main/rules_prometheus.yml b/roles/monitoring/prometheus/server/defaults/main/rules_prometheus.yml
index 6d84efa4..8d4672b1 100644
--- a/roles/monitoring/prometheus/server/defaults/main/rules_prometheus.yml
+++ b/roles/monitoring/prometheus/server/defaults/main/rules_prometheus.yml
@@ -190,3 +190,50 @@ prometheus_server_rules_prometheus:
     annotations:
       summary: Prometheus TSDB WAL truncations failed (instance {{ '{{' }} $labels.instance {{ '}}' }})
       description: "Prometheus encountered {{ '{{' }} $value {{ '}}' }} TSDB WAL truncation failures\n  VALUE = {{ '{{' }} $value {{ '}}' }}\n  LABELS = {{ '{{' }} $labels {{ '}}' }}"
+
+
+prometheus_server_rules_prometheus_alertmanager:
+  - alert: PrometheusAlertmanagerConfigurationReloadFailure
+    expr: alertmanager_config_last_reload_successful != 1
+    for: 0m
+    labels:
+      severity: warning
+    annotations:
+      summary: Prometheus AlertManager configuration reload failure (instance {{ '{{' }} $labels.instance {{ '}}' }})
+      description: "AlertManager configuration reload error\n  VALUE = {{ '{{' }} $value {{ '}}' }}\n  LABELS = {{ '{{' }} $labels {{ '}}' }}"
+
+  - alert: PrometheusAlertmanagerConfigNotSynced
+    expr: count(count_values("config_hash", alertmanager_config_hash)) > 1
+    for: 0m
+    labels:
+      severity: warning
+    annotations:
+      summary: Prometheus AlertManager config not synced (instance {{ '{{' }} $labels.instance {{ '}}' }})
+      description: "Configurations of AlertManager cluster instances are out of sync\n  VALUE = {{ '{{' }} $value {{ '}}' }}\n  LABELS = {{ '{{' }} $labels {{ '}}' }}"
+
+  - alert: PrometheusAlertmanagerE2eDeadManSwitch
+    expr: vector(1)
+    for: 0m
+    labels:
+      severity: critical
+    annotations:
+      summary: Prometheus AlertManager E2E dead man switch (instance {{ '{{' }} $labels.instance {{ '}}' }})
+      description: "Prometheus DeadManSwitch is an always-firing alert. It's used as an end-to-end test of Prometheus through the Alertmanager.\n  VALUE = {{ '{{' }} $value {{ '}}' }}\n  LABELS = {{ '{{' }} $labels {{ '}}' }}"
+
+  - alert: PrometheusNotConnectedToAlertmanager
+    expr: prometheus_notifications_alertmanagers_discovered < 1
+    for: 0m
+    labels:
+      severity: critical
+    annotations:
+      summary: Prometheus not connected to alertmanager (instance {{ '{{' }} $labels.instance {{ '}}' }})
+      description: "Prometheus cannot connect the alertmanager\n  VALUE = {{ '{{' }} $value {{ '}}' }}\n  LABELS = {{ '{{' }} $labels {{ '}}' }}"
+
+  - alert: PrometheusAlertmanagerNotificationFailing
+    expr: rate(alertmanager_notifications_failed_total[1m]) > 0
+    for: 0m
+    labels:
+      severity: critical
+    annotations:
+      summary: Prometheus AlertManager notification failing (instance {{ '{{' }} $labels.instance {{ '}}' }})
+      description: "Alertmanager is failing sending notifications\n  VALUE = {{ '{{' }} $value {{ '}}' }}\n  LABELS = {{ '{{' }} $labels {{ '}}' }}"
diff --git a/roles/monitoring/prometheus/server/templates/prometheus.yml.j2 b/roles/monitoring/prometheus/server/templates/prometheus.yml.j2
index 3975c74d..c76990f4 100644
--- a/roles/monitoring/prometheus/server/templates/prometheus.yml.j2
+++ b/roles/monitoring/prometheus/server/templates/prometheus.yml.j2
@@ -6,6 +6,13 @@ global:
 
 rule_files:
   - /etc/prometheus/rules/*.yml
+{% if prometheus_server_alertmanager is defined %}
+
+alerting:
+  alertmanagers:
+  - static_configs:
+    - targets: ['{{ prometheus_server_alertmanager.url }}']
+{% endif %}
 
 scrape_configs:
   - job_name: 'prometheus'
@@ -13,6 +20,12 @@ scrape_configs:
     - targets: ['localhost:9090']
       labels:
         instance: "{{ inventory_hostname }}"
+{% if prometheus_server_alertmanager is defined %}
+
+  - job_name: 'alertmanager'
+    static_configs:
+    - targets: ['{{ prometheus_server_alertmanager.url }}']
+{% endif %}
 {% for job in prometheus_server_jobs %}
 
   - job_name: '{{ job }}'