summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--inventory/host_vars/ch-mon.yml3
-rw-r--r--roles/monitoring/alerta/tasks/main.yml6
-rw-r--r--roles/monitoring/prometheus/server/defaults/main/rules_node.yml2
3 files changed, 8 insertions, 3 deletions
diff --git a/inventory/host_vars/ch-mon.yml b/inventory/host_vars/ch-mon.yml
index bd952fc8..684cc722 100644
--- a/inventory/host_vars/ch-mon.yml
+++ b/inventory/host_vars/ch-mon.yml
@@ -145,6 +145,7 @@ prometheus_alertmanager_web_external_url: "http://{{ network.primary.address | i
prometheus_alertmanager_auth_users:
server: "{{ vault_prometheus_alertmanager_auth_user_passwords['server'] }}"
admin: "{{ vault_prometheus_alertmanager_auth_user_passwords['admin'] }}"
+ alerta: "alerta" ## TODO: move this to vault
prometheus_alertmanager_route:
receiver: alerta
@@ -161,7 +162,7 @@ prometheus_alertmanager_receivers:
http_config:
basic_auth:
username: admin
- password: alerta
+ password: alerta ## TODO: move this to vault
grafana_secret_key: "{{ vault_grafana_secret_key }}"
diff --git a/roles/monitoring/alerta/tasks/main.yml b/roles/monitoring/alerta/tasks/main.yml
index af7530d8..a4fd3df9 100644
--- a/roles/monitoring/alerta/tasks/main.yml
+++ b/roles/monitoring/alerta/tasks/main.yml
@@ -12,10 +12,14 @@
content: |
DEBUG = {{ '{{' }} 'True' if env.DEBUG else 'False' {{ '}}' }}
SECRET = "{{ '{{' }} env.SECRET_KEY {{ '}}' }}"
- PLUGINS = ['reject', 'blackout', 'heartbeat']
+ PLUGINS = ['reject', 'blackout', 'heartbeat', 'prometheus']
DEFAULT_ENVIRONMENT = 'unknown'
ALLOWED_ENVIRONMENTS = ['unknown', 'chaos-at-.*']
HEARTBEAT_EVENTS = ['PrometheusAlertmanagerE2eDeadManSwitch']
+ ALERTMANAGER_USERNAME = 'alerta'
+ ALERTMANAGER_PASSWORD = 'alerta'
+ ALERTMANAGER_SILENCE_FROM_ACK = True
+ ALERTMANAGER_USE_EXTERNALURL_FOR_SILENCES = True
dest: "{{ alerta_base_path }}/config/alertad.conf.j2"
- name: install pod manifest
diff --git a/roles/monitoring/prometheus/server/defaults/main/rules_node.yml b/roles/monitoring/prometheus/server/defaults/main/rules_node.yml
index 525355d5..75e96bca 100644
--- a/roles/monitoring/prometheus/server/defaults/main/rules_node.yml
+++ b/roles/monitoring/prometheus/server/defaults/main/rules_node.yml
@@ -206,7 +206,7 @@ prometheus_server_rules_node:
severity: warning
annotations:
summary: Host Network Interface Saturated (instance {{ '{{' }} $labels.instance {{ '}}' }})
- description: "The network interface \"{{ '{{' }} $labels.interface {{ '}}' }}\" on \"{{ '{{' }} $labels.instance {{ '}}' }}\" is getting overloaded.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
+ description: "The network interface \"{{ '{{' }} $labels.device {{ '}}' }}\" on \"{{ '{{' }} $labels.instance {{ '}}' }}\" is getting overloaded.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: HostConntrackLimit
expr: node_nf_conntrack_entries / node_nf_conntrack_entries_limit > 0.8