MON-248 add 4xx monitor

caas/kubernetes/ingress/README.md

@@ -16,6 +16,7 @@ module "datadog-monitors-caas-kubernetes-ingress" {
 
 Creates DataDog monitors with the following checks:
 
+- Nginx Ingress 4xx errors
 - Nginx Ingress 5xx errors
 
 ## Inputs
@@ -27,12 +28,19 @@ Creates DataDog monitors with the following checks:
 | evaluation_delay | Delay in seconds for the metric evaluation | string | `15` | no |
 | filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no |
 | filter_tags_use_defaults | Use default filter tags convention | string | `true` | no |
+| ingress_4xx_enabled | Flag to enable Ingress 4xx errors monitor | string | `true` | no |
+| ingress_4xx_extra_tags | Extra tags for Ingress 4xx errors monitor | list | `<list>` | no |
+| ingress_4xx_message | Message sent when an alert is triggered | string | `` | no |
+| ingress_4xx_silenced | Groups to mute for Ingress 4xx errors monitor | map | `<map>` | no |
+| ingress_4xx_threshold_critical |  | string | `40` | no |
+| ingress_4xx_threshold_warning |  | string | `20` | no |
+| ingress_4xx_timeframe | Monitor timeframe for Ingress 4xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
 | ingress_5xx_enabled | Flag to enable Ingress 5xx errors monitor | string | `true` | no |
 | ingress_5xx_extra_tags | Extra tags for Ingress 5xx errors monitor | list | `<list>` | no |
 | ingress_5xx_message | Message sent when an alert is triggered | string | `` | no |
 | ingress_5xx_silenced | Groups to mute for Ingress 5xx errors monitor | map | `<map>` | no |
-| ingress_5xx_threshold_critical |  | string | `10` | no |
+| ingress_5xx_threshold_critical |  | string | `20` | no |
-| ingress_5xx_threshold_warning |  | string | `5` | no |
+| ingress_5xx_threshold_warning |  | string | `10` | no |
 | ingress_5xx_timeframe | Monitor timeframe for Ingress 5xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
 | message | Message sent when an alert is triggered | string | - | yes |
 | new_host_delay | Delay in seconds before monitor new resource | string | `300` | no |
@@ -41,7 +49,8 @@ Creates DataDog monitors with the following checks:
 
 | Name | Description |
 |------|-------------|
-| Nginx_ingress_too_many_5xx_id | id for monitor Nginx_ingress_too_many_5xx |
+| nginx_ingress_too_many_4xx_id | id for monitor nginx_ingress_too_many_4xx |
+| nginx_ingress_too_many_5xx_id | id for monitor nginx_ingress_too_many_5xx |
 
 Related documentation
 ---------------------

caas/kubernetes/ingress/inputs.tf

@@ -61,12 +61,51 @@ variable "ingress_5xx_timeframe" {
 
 variable "ingress_5xx_threshold_critical" {
   type    = "string"
-  default = "10"
+  default = "20"
 }
 
 variable "ingress_5xx_threshold_warning" {
   type    = "string"
-  default = "5"
+  default = "10"
+}
+
+variable "ingress_4xx_silenced" {
+  description = "Groups to mute for Ingress 4xx errors monitor"
+  type        = "map"
+  default     = {}
+}
+
+variable "ingress_4xx_enabled" {
+  description = "Flag to enable Ingress 4xx errors monitor"
+  type        = "string"
+  default     = "true"
+}
+
+variable "ingress_4xx_extra_tags" {
+  description = "Extra tags for Ingress 4xx errors monitor"
+  type        = "list"
+  default     = []
+}
+
+variable "ingress_4xx_message" {
+  description = "Message sent when an alert is triggered"
+  default     = ""
+}
+
+variable "ingress_4xx_timeframe" {
+  description = "Monitor timeframe for Ingress 4xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
+  type        = "string"
+  default     = "last_5m"
+}
+
+variable "ingress_4xx_threshold_critical" {
+  type    = "string"
+  default = "40"
+}
+
+variable "ingress_4xx_threshold_warning" {
+  type    = "string"
+  default = "20"
 }
 
 variable "artificial_requests_count" {

caas/kubernetes/ingress/modules.tf

@@ -17,3 +17,13 @@ module "filter-tags-5xx" {
   filter_tags_custom       = "${var.filter_tags_custom}"
   extra_tags               = ["!upstream:upstream-default-backend,status_code:5xx"]
 }
+
+module "filter-tags-4xx" {
+  source = "../../../common/filter-tags"
+
+  environment              = "${var.environment}"
+  resource                 = "ingress"
+  filter_tags_use_defaults = "${var.filter_tags_use_defaults}"
+  filter_tags_custom       = "${var.filter_tags_custom}"
+  extra_tags               = ["!upstream:upstream-default-backend,status_code:4xx"]
+}

caas/kubernetes/ingress/monitors-ingress.tf

@@ -1,4 +1,4 @@
-resource "datadog_monitor" "Nginx_ingress_too_many_5xx" {
+resource "datadog_monitor" "nginx_ingress_too_many_5xx" {
   count   = "${var.ingress_5xx_enabled ? 1 : 0}"
   name    = "[${var.environment}] Nginx Ingress 5xx errors {{#is_alert}}{{{comparator}}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
   message = "${coalesce(var.ingress_5xx_message, var.message)}"
@@ -33,3 +33,39 @@ resource "datadog_monitor" "Nginx_ingress_too_many_5xx" {
 
   tags = ["env:${var.environment}", "type:caas", "provider:prometheus", "resource:nginx-ingress-controller", "team:claranet", "created-by:terraform", "${var.ingress_5xx_extra_tags}"]
 }
+
+resource "datadog_monitor" "nginx_ingress_too_many_4xx" {
+  count   = "${var.ingress_4xx_enabled ? 1 : 0}"
+  name    = "[${var.environment}] Nginx Ingress 4xx errors {{#is_alert}}{{{comparator}}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
+  message = "${coalesce(var.ingress_4xx_message, var.message)}"
+
+  query = <<EOF
+    sum(${var.ingress_4xx_timeframe}): (
+      default(
+        avg:nginx_ingress.nginx_upstream_responses_total${module.filter-tags-4xx.query_alert} by {upstream,ingress_class} /
+        (avg:nginx_ingress.nginx_upstream_requests_total${module.filter-tags.query_alert} by {upstream,ingress_class} + ${var.artificial_requests_count}),
+      0) * 100
+    ) > ${var.ingress_4xx_threshold_critical}
+  EOF
+
+  type = "metric alert"
+
+  thresholds {
+    warning  = "${var.ingress_4xx_threshold_warning}"
+    critical = "${var.ingress_4xx_threshold_critical}"
+  }
+
+  notify_no_data      = false
+  evaluation_delay    = "${var.evaluation_delay}"
+  new_host_delay      = "${var.new_host_delay}"
+  renotify_interval   = 0
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = true
+
+  silenced = "${var.ingress_4xx_silenced}"
+
+  tags = ["env:${var.environment}", "type:caas", "provider:prometheus", "resource:nginx-ingress-controller", "team:claranet", "created-by:terraform", "${var.ingress_4xx_extra_tags}"]
+}

caas/kubernetes/ingress/outputs.tf

@@ -1,4 +1,9 @@
-output "Nginx_ingress_too_many_5xx_id" {
+output "nginx_ingress_too_many_5xx_id" {
-  description = "id for monitor Nginx_ingress_too_many_5xx"
+  description = "id for monitor nginx_ingress_too_many_5xx"
-  value       = "${datadog_monitor.Nginx_ingress_too_many_5xx.*.id}"
+  value       = "${datadog_monitor.nginx_ingress_too_many_5xx.*.id}"
+}
+
+output "nginx_ingress_too_many_4xx_id" {
+  description = "id for monitor nginx_ingress_too_many_4xx"
+  value       = "${datadog_monitor.nginx_ingress_too_many_4xx.*.id}"
 }