Resolve MON-364 "Monitors for aws nlb"

README.md

@@ -151,6 +151,7 @@ The `//` is very important, it's a terraform specific syntax used to separate gi
 		- [elb](https://git.fr.clara.net/claranet/pt-monitoring/projects/datadog/terraform/monitors/tree/master/cloud/aws/elb/)
 		- [kinesis-firehose](https://git.fr.clara.net/claranet/pt-monitoring/projects/datadog/terraform/monitors/tree/master/cloud/aws/kinesis-firehose/)
 		- [lambda](https://git.fr.clara.net/claranet/pt-monitoring/projects/datadog/terraform/monitors/tree/master/cloud/aws/lambda/)
+		- [nlb](https://git.fr.clara.net/claranet/pt-monitoring/projects/datadog/terraform/monitors/tree/master/cloud/aws/nlb/)
 		- [rds](https://git.fr.clara.net/claranet/pt-monitoring/projects/datadog/terraform/monitors/tree/master/cloud/aws/rds/)
 			- [aurora](https://git.fr.clara.net/claranet/pt-monitoring/projects/datadog/terraform/monitors/tree/master/cloud/aws/rds/aurora/)
 				- [mysql](https://git.fr.clara.net/claranet/pt-monitoring/projects/datadog/terraform/monitors/tree/master/cloud/aws/rds/aurora/mysql/)

cloud/aws/nlb/README.md

@@ -0,0 +1,49 @@
+# CLOUD AWS NLB DataDog monitors
+
+## How to use this module
+
+```
+module "datadog-monitors-cloud-aws-nlb" {
+  source = "git::ssh://git@git.fr.clara.net/claranet/pt-monitoring/projects/datadog/terraform/monitors.git//cloud/aws/nlb?ref={revision}"
+
+  environment = var.environment
+  message     = module.datadog-message-alerting.alerting-message
+}
+
+```
+
+## Purpose
+
+Creates DataDog monitors with the following checks:
+
+- NLB healthy instances
+
+## Inputs
+
+| Name | Description | Type | Default | Required |
+|------|-------------|:----:|:-----:|:-----:|
+| environment | Architecture environment | string | n/a | yes |
+| evaluation\_delay | Delay in seconds for the metric evaluation | string | `"900"` | no |
+| filter\_tags\_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `"*"` | no |
+| filter\_tags\_custom\_excluded | Tags excluded for custom filtering when filter_tags_use_defaults is false | string | `""` | no |
+| filter\_tags\_use\_defaults | Use default filter tags convention | string | `"true"` | no |
+| message | Message sent when a monitor is triggered | string | n/a | yes |
+| new\_host\_delay | Delay in seconds before monitor new resource | string | `"300"` | no |
+| nlb\_no\_healthy\_instances\_enabled | Flag to enable NLB no healthy instances monitor | string | `"true"` | no |
+| nlb\_no\_healthy\_instances\_extra\_tags | Extra tags for NLB no healthy instances monitor | list(string) | `[]` | no |
+| nlb\_no\_healthy\_instances\_message | Custom message for NLB no healthy instances monitor | string | `""` | no |
+| nlb\_no\_healthy\_instances\_time\_aggregator | Monitor aggregator for NLB no healthy instances [available values: min, max or avg] | string | `"min"` | no |
+| nlb\_no\_healthy\_instances\_timeframe | Monitor timeframe for NLB no healthy instances [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `"last_5m"` | no |
+| prefix\_slug | Prefix string to prepend between brackets on every monitors names | string | `""` | no |
+
+## Outputs
+
+| Name | Description |
+|------|-------------|
+| NLB\_no\_healthy\_instances\_id | id for monitor NLB_no_healthy_instances |
+
+## Related documentation
+
+DataDog blog: [https://www.datadoghq.com/blog/monitor-aws-network-load-balancer/](https://www.datadoghq.com/blog/monitor-aws-network-load-balancer/)
+
+AWS NLB metrics documentation: [https://docs.aws.amazon.com/elasticloadbalancing/latest/network/load-balancer-cloudwatch-metrics.html](https://docs.aws.amazon.com/elasticloadbalancing/latest/network/load-balancer-cloudwatch-metrics.html)

cloud/aws/nlb/inputs.tf

@@ -0,0 +1,73 @@
+# Datadog global variables
+
+variable "environment" {
+  description = "Architecture environment"
+  type        = string
+}
+
+variable "filter_tags_use_defaults" {
+  description = "Use default filter tags convention"
+  default     = "true"
+}
+
+variable "filter_tags_custom" {
+  description = "Tags used for custom filtering when filter_tags_use_defaults is false"
+  default     = "*"
+}
+
+variable "filter_tags_custom_excluded" {
+  description = "Tags excluded for custom filtering when filter_tags_use_defaults is false"
+  default     = ""
+}
+
+variable "message" {
+  description = "Message sent when a monitor is triggered"
+}
+
+variable "evaluation_delay" {
+  description = "Delay in seconds for the metric evaluation"
+  default     = 900
+}
+
+variable "new_host_delay" {
+  description = "Delay in seconds before monitor new resource"
+  default     = 300
+}
+
+variable "prefix_slug" {
+  description = "Prefix string to prepend between brackets on every monitors names"
+  default     = ""
+}
+
+# Datadog monitors variables
+
+variable "nlb_no_healthy_instances_enabled" {
+  description = "Flag to enable NLB no healthy instances monitor"
+  type        = string
+  default     = "true"
+}
+
+variable "nlb_no_healthy_instances_extra_tags" {
+  description = "Extra tags for NLB no healthy instances monitor"
+  type        = list(string)
+  default     = []
+}
+
+variable "nlb_no_healthy_instances_message" {
+  description = "Custom message for NLB no healthy instances monitor"
+  type        = string
+  default     = ""
+}
+
+variable "nlb_no_healthy_instances_time_aggregator" {
+  description = "Monitor aggregator for NLB no healthy instances [available values: min, max or avg]"
+  type        = string
+  default     = "min"
+}
+
+variable "nlb_no_healthy_instances_timeframe" {
+  description = "Monitor timeframe for NLB no healthy instances [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
+  type        = string
+  default     = "last_5m"
+}
+

cloud/aws/nlb/modules.tf

@@ -0,0 +1,10 @@
+module "filter-tags" {
+  source = "../../../common/filter-tags"
+
+  environment                 = var.environment
+  resource                    = "aws_nlb"
+  filter_tags_use_defaults    = var.filter_tags_use_defaults
+  filter_tags_custom          = var.filter_tags_custom
+  filter_tags_custom_excluded = var.filter_tags_custom_excluded
+}
+

cloud/aws/nlb/monitors-nlb.tf

@@ -0,0 +1,34 @@
+resource "datadog_monitor" "NLB_no_healthy_instances" {
+  count   = var.nlb_no_healthy_instances_enabled == "true" ? 1 : 0
+  name    = "${var.prefix_slug == "" ? "" : "[${var.prefix_slug}]"}[${var.environment}] NLB healthy instances {{#is_alert}}is at 0{{/is_alert}}{{#is_warning}}is at {{value}}%%{{/is_warning}}"
+  message = coalesce(var.nlb_no_healthy_instances_message, var.message)
+  type    = "query alert"
+
+  query = <<EOQ
+    ${var.nlb_no_healthy_instances_time_aggregator}(${var.nlb_no_healthy_instances_timeframe}): (
+      sum:aws.networkelb.healthy_host_count.minimum${module.filter-tags.query_alert} by {region,loadbalancer} / (
+      sum:aws.networkelb.healthy_host_count.minimum${module.filter-tags.query_alert} by {region,loadbalancer} +
+      sum:aws.networkelb.un_healthy_host_count.maximum${module.filter-tags.query_alert} by {region,loadbalancer} )
+    ) * 100 < 1
+EOQ
+
+  thresholds = {
+    critical = 1
+    warning  = 100
+  }
+
+  evaluation_delay    = var.evaluation_delay
+  new_host_delay      = var.new_host_delay
+  notify_no_data      = true
+  renotify_interval   = 0
+  require_full_window = false
+  timeout_h           = 0
+  include_tags        = true
+
+  tags = concat(["env:${var.environment}", "type:cloud", "provider:aws", "resource:nlb", "team:claranet", "created-by:terraform"], var.nlb_no_healthy_instances_extra_tags)
+
+  lifecycle {
+    ignore_changes = ["silenced"]
+  }
+}
+

cloud/aws/nlb/outputs.tf

@@ -0,0 +1,5 @@
+output "NLB_no_healthy_instances_id" {
+  description = "id for monitor NLB_no_healthy_instances"
+  value       = datadog_monitor.NLB_no_healthy_instances.*.id
+}
+