feat: All prometheus_alert_group output and vars

CHANGELOG.md

@@ -1,4 +1,9 @@
 
+0.3.0 / 2020-03-06
+==================
+
+  * feat: All prometheus_alert_group output and vars
+
 0.2.0 / 2020-02-26
 ==================
 

README.md

@@ -31,6 +31,8 @@ Terraform module to deploy [cloudwatch_exporter](https://github.com/prometheus/c
 | image\_version | Tag of the docker image to use. | `string` | `"latest"` | no |
 | labels | Additionnal labels that will be merged on all resources. | `map` | `{}` | no |
 | namespace | Namespace in which the module will be deployed. | `string` | `"default"` | no |
+| prometheus\_alert\_groups\_rules\_annotations | Map of strings that will be merge on all prometheus alert groups rules annotations. | `map` | `{}` | no |
+| prometheus\_alert\_groups\_rules\_labels | Map of strings that will be merge on all prometheus alert groups rules labels. | `map` | `{}` | no |
 | replicas | Number of replicas to deploy. | `number` | `1` | no |
 | secret\_annotations | Additionnal annotations that will be merged for the secret. | `map` | `{}` | no |
 | secret\_key | Client secret that will be used by the cloudwatch-exporter. | `string` | n/a | yes |
@@ -56,6 +58,7 @@ Terraform module to deploy [cloudwatch_exporter](https://github.com/prometheus/c
 | image\_pull\_policy | Image pull policy defined on the cloudwatch-exporter container. |
 | image\_version | Tag of the docker image used for the cloudwatch-exporter container. |
 | namespace | Name of the namespace in which the resources have been deployed. |
+| prometheus\_alert\_groups | List of object representing prometheus alert groups you can import in prometheus to alert you in case of problems. |
 | secret\_annotations | Map of annotations that are configured on the secret. |
 | secret\_labels | Map of labels that are configured on the secret. |
 | secret\_name | Name of the secret created by the module. |

examples/default/outputs.tf

@@ -22,6 +22,11 @@ output "image_pull_policy" {
   value       = module.default.image_pull_policy
 }
 
+output "prometheus_alert_groups" {
+  description = "List of maps representing prometheus alert groups."
+  value       = module.default.prometheus_alert_groups
+}
+
 #####
 # Deployment
 #####

main.tf

@@ -13,6 +13,51 @@ locals {
   configuration = yamlencode(var.configuration)
   port          = 9106
   service_port  = 80
+  prometheus_alert_groups = [
+    {
+      "name" = "cloudwatch-exporter"
+      "rules" = [
+        {
+          "alert" = "CloudwatchExporterScrapeErrors"
+          "expr"  = "cloudwatch_exporter_scrape_error > 0"
+          "for"   = "1m"
+          "labels" = merge(
+            {
+              "severity" = "critical"
+              "urgency"  = "2"
+            },
+            var.prometheus_alert_groups_rules_labels
+          )
+          "annotations" = merge(
+            {
+              "summary"     = "Cloudwatch Exporter - Scrape Error on {{ $labels.instance }}",
+              "description" = "Cloudwatch Exporter: \n {{ $labels.instance }} scrape error.\nLabels:\n{{ $labels }}"
+            },
+            var.prometheus_alert_groups_rules_annotations
+          )
+        },
+        {
+          "alert" = "CloudwatchExporterScrapeDurationError"
+          "expr"  = "deriv(oracledb_exporter_last_scrape_duration_seconds[2m]) > 0.2 and oracledb_exporter_last_scrape_duration_seconds > 10"
+          "for"   = "5m"
+          "labels" = merge(
+            {
+              "severity" = "warning"
+              "urgency"  = "3"
+            },
+            var.prometheus_alert_groups_rules_labels
+          )
+          "annotations" = merge(
+            {
+              "summary"     = "Cloudwatch Exporter - Scrape Duration Error on {{ $labels.instance }}",
+              "description" = "Cloudwatch Exporter:\n {{ $labels.instance }} scrape duration is too high.\nLabels:\n{{ $labels }}"
+            },
+            var.prometheus_alert_groups_rules_annotations
+          )
+        }
+      ]
+    }
+  ]
 }
 
 #####

outputs.tf

@@ -22,6 +22,11 @@ output "image_pull_policy" {
   value       = var.enabled ? var.image_pull_policy : ""
 }
 
+output "prometheus_alert_groups" {
+  description = "List of object representing prometheus alert groups you can import in prometheus to alert you in case of problems."
+  value       = var.enabled ? local.prometheus_alert_groups : []
+}
+
 #####
 # Deployment
 #####

variables.tf

@@ -22,6 +22,20 @@ variable "namespace" {
   default     = "default"
 }
 
+#####
+# Prometheus
+#####
+
+variable "prometheus_alert_groups_rules_labels" {
+  description = "Map of strings that will be merge on all prometheus alert groups rules labels."
+  default     = {}
+}
+
+variable "prometheus_alert_groups_rules_annotations" {
+  description = "Map of strings that will be merge on all prometheus alert groups rules annotations."
+  default     = {}
+}
+
 #####
 # Application
 #####