Merge branch 'MON-114_kubernetes_node_from_confluence' into 'master'

MON-114 kubernetes node monitors

Closes MON-114

See merge request claranet/pt-monitoring/projects/datadog/terraform/monitors!43

README.md

@@ -80,6 +80,7 @@ The `//` is very important, it's a terraform specific syntax used to separate gi
 		- [cluster](https://git.fr.clara.net/claranet/pt-monitoring/projects/datadog/terraform/monitors/tree/master/caas/kubernetes/cluster/)
 		- [ingress](https://git.fr.clara.net/claranet/pt-monitoring/projects/datadog/terraform/monitors/tree/master/caas/kubernetes/ingress/)
 			- [vts](https://git.fr.clara.net/claranet/pt-monitoring/projects/datadog/terraform/monitors/tree/master/caas/kubernetes/ingress/vts/)
+		- [node](https://git.fr.clara.net/claranet/pt-monitoring/projects/datadog/terraform/monitors/tree/master/caas/kubernetes/node/)
 		- [pod](https://git.fr.clara.net/claranet/pt-monitoring/projects/datadog/terraform/monitors/tree/master/caas/kubernetes/pod/)
 		- [workload](https://git.fr.clara.net/claranet/pt-monitoring/projects/datadog/terraform/monitors/tree/master/caas/kubernetes/workload/)
 - [cloud](https://git.fr.clara.net/claranet/pt-monitoring/projects/datadog/terraform/monitors/tree/master/cloud/)

caas/kubernetes/node/README.md

@@ -0,0 +1,100 @@
+# CAAS KUBERNETES NODE DataDog monitors
+
+## How to use this module
+
+```
+module "datadog-monitors-caas-kubernetes-node" {
+  source = "git::ssh://git@git.fr.clara.net/claranet/pt-monitoring/projects/datadog/terraform/monitors.git//caas/kubernetes/node?ref={revision}"
+
+  environment = "${var.environment}"
+  message     = "${module.datadog-message-alerting.alerting-message}"
+}
+
+```
+
+## Purpose
+
+Creates DataDog monitors with the following checks:
+
+- Kubernetes Node Disk pressure
+- Kubernetes Node Frequent unregister net device
+- Kubernetes Node Kubelet API does not respond
+- Kubernetes Node Kubelet sync loop that updates containers does not work
+- Kubernetes Node Memory pressure
+- Kubernetes Node not ready
+- Kubernetes Node Out of disk
+- Kubernetes Node unschedulable
+
+## Inputs
+
+| Name | Description | Type | Default | Required |
+|------|-------------|:----:|:-----:|:-----:|
+| disk\_out\_enabled | Flag to enable Out of disk monitor | string | `"true"` | no |
+| disk\_out\_extra\_tags | Extra tags for Out of disk monitor | list | `[]` | no |
+| disk\_out\_message | Custom message for Out of disk monitor | string | `""` | no |
+| disk\_out\_silenced | Groups to mute for Out of disk monitor | map | `{}` | no |
+| disk\_out\_threshold\_warning | Out of disk monitor (warning threshold) | string | `"3"` | no |
+| disk\_pressure\_enabled | Flag to enable Disk pressure monitor | string | `"true"` | no |
+| disk\_pressure\_extra\_tags | Extra tags for Disk pressure monitor | list | `[]` | no |
+| disk\_pressure\_message | Custom message for Disk pressure monitor | string | `""` | no |
+| disk\_pressure\_silenced | Groups to mute for Disk pressure monitor | map | `{}` | no |
+| disk\_pressure\_threshold\_warning | Disk pressure monitor (warning threshold) | string | `"3"` | no |
+| environment | Architecture environment | string | n/a | yes |
+| 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\_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 |
+| kubelet\_ping\_enabled | Flag to enable Kubelet ping monitor | string | `"true"` | no |
+| kubelet\_ping\_extra\_tags | Extra tags for Kubelet ping monitor | list | `[]` | no |
+| kubelet\_ping\_message | Custom message for Kubelet ping monitor | string | `""` | no |
+| kubelet\_ping\_silenced | Groups to mute for Kubelet ping monitor | map | `{}` | no |
+| kubelet\_ping\_threshold\_warning | Kubelet ping monitor (warning threshold) | string | `"3"` | no |
+| kubelet\_syncloop\_enabled | Flag to enable Kubelet sync loop monitor | string | `"true"` | no |
+| kubelet\_syncloop\_extra\_tags | Extra tags for Kubelet sync loop monitor | list | `[]` | no |
+| kubelet\_syncloop\_message | Custom message for Kubelet sync loop monitor | string | `""` | no |
+| kubelet\_syncloop\_silenced | Groups to mute for Kubelet sync loop monitor | map | `{}` | no |
+| kubelet\_syncloop\_threshold\_warning | Kubelet sync loop monitor (warning threshold) | string | `"3"` | no |
+| memory\_pressure\_enabled | Flag to enable Memory pressure monitor | string | `"true"` | no |
+| memory\_pressure\_extra\_tags | Extra tags for Memory pressure monitor | list | `[]` | no |
+| memory\_pressure\_message | Custom message for Memory pressure monitor | string | `""` | no |
+| memory\_pressure\_silenced | Groups to mute for Memory pressure monitor | map | `{}` | no |
+| memory\_pressure\_threshold\_warning | Memory pressure monitor (warning threshold) | string | `"3"` | 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 |
+| node\_unschedulable\_enabled | Flag to enable node unschedulable monitor | string | `"true"` | no |
+| node\_unschedulable\_extra\_tags | Extra tags for node unschedulable monitor | list | `[]` | no |
+| node\_unschedulable\_message | Custom message for node unschedulable monitor | string | `""` | no |
+| node\_unschedulable\_silenced | Groups to mute for node unschedulable monitor | map | `{}` | no |
+| node\_unschedulable\_time\_aggregator | Monitor aggregator for node unschedulable [available values: min, max or avg] | string | `"min"` | no |
+| node\_unschedulable\_timeframe | Monitor timeframe for node unschedulable [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `"last_1h"` | no |
+| ready\_enabled | Flag to enable Node ready monitor | string | `"true"` | no |
+| ready\_extra\_tags | Extra tags for Node ready monitor | list | `[]` | no |
+| ready\_message | Custom message for Node ready monitor | string | `""` | no |
+| ready\_silenced | Groups to mute for Node ready monitor | map | `{}` | no |
+| ready\_threshold\_warning | Node ready monitor (warning threshold) | string | `"3"` | no |
+| unregister\_net\_device\_enabled | Flag to enable Unregister net device monitor | string | `"true"` | no |
+| unregister\_net\_device\_extra\_tags | Extra tags for Unregister net device monitor | list | `[]` | no |
+| unregister\_net\_device\_message | Custom message for Unregister net device monitor | string | `""` | no |
+| unregister\_net\_device\_silenced | Groups to mute for Unregister net device monitor | map | `{}` | no |
+| unregister\_net\_device\_threshold\_critical | Unregister net device critical threshold | string | `"3"` | no |
+| unregister\_net\_device\_time\_aggregator | Monitor aggregator for Unregister net device [available values: min, max or avg] | string | `"min"` | no |
+| unregister\_net\_device\_timeframe | Monitor timeframe for Unregister net device [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `"15m"` | no |
+
+## Outputs
+
+| Name | Description |
+|------|-------------|
+| disk\_out\_id | id for monitor disk_out |
+| disk\_pressure\_id | id for monitor disk_pressure |
+| kubelet\_ping\_id | id for monitor kubelet_ping |
+| kubelet\_syncloop\_id | id for monitor kubelet_syncloop |
+| memory\_pressure\_id | id for monitor memory_pressure |
+| node\_unschedulable\_id | id for monitor node_unschedulable |
+| ready\_id | id for monitor ready |
+| unregister\_net\_device\_id | id for monitor unregister_net_device |
+
+## Related documentation
+
+* [Datadog metrics](https://docs.datadoghq.com/agent/kubernetes/metrics/)
+* [Datadog documentation](https://docs.datadoghq.com/integrations/kubernetes/)
+* [Datadog Blog](https://www.datadoghq.com/blog/monitor-kubernetes-docker/)

caas/kubernetes/node/inputs.tf

@@ -0,0 +1,293 @@
+# Datadog global variables
+
+variable "environment" {
+  description = "Architecture environment"
+}
+
+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     = 15
+}
+
+variable "new_host_delay" {
+  description = "Delay in seconds before monitor new resource"
+  default     = 300
+}
+
+# Datadog monitors variables
+
+variable "disk_pressure_silenced" {
+  description = "Groups to mute for Disk pressure monitor"
+  type        = "map"
+  default     = {}
+}
+
+variable "disk_pressure_enabled" {
+  description = "Flag to enable Disk pressure monitor"
+  type        = "string"
+  default     = "true"
+}
+
+variable "disk_pressure_extra_tags" {
+  description = "Extra tags for Disk pressure monitor"
+  type        = "list"
+  default     = []
+}
+
+variable "disk_pressure_message" {
+  description = "Custom message for Disk pressure monitor"
+  type        = "string"
+  default     = ""
+}
+
+variable "disk_pressure_threshold_warning" {
+  description = "Disk pressure monitor (warning threshold)"
+  type        = "string"
+  default     = 3
+}
+
+variable "disk_out_silenced" {
+  description = "Groups to mute for Out of disk monitor"
+  type        = "map"
+  default     = {}
+}
+
+variable "disk_out_enabled" {
+  description = "Flag to enable Out of disk monitor"
+  type        = "string"
+  default     = "true"
+}
+
+variable "disk_out_extra_tags" {
+  description = "Extra tags for Out of disk monitor"
+  type        = "list"
+  default     = []
+}
+
+variable "disk_out_message" {
+  description = "Custom message for Out of disk monitor"
+  type        = "string"
+  default     = ""
+}
+
+variable "disk_out_threshold_warning" {
+  description = "Out of disk monitor (warning threshold)"
+  type        = "string"
+  default     = 3
+}
+
+variable "memory_pressure_silenced" {
+  description = "Groups to mute for Memory pressure monitor"
+  type        = "map"
+  default     = {}
+}
+
+variable "memory_pressure_enabled" {
+  description = "Flag to enable Memory pressure monitor"
+  type        = "string"
+  default     = "true"
+}
+
+variable "memory_pressure_extra_tags" {
+  description = "Extra tags for Memory pressure monitor"
+  type        = "list"
+  default     = []
+}
+
+variable "memory_pressure_message" {
+  description = "Custom message for Memory pressure monitor"
+  type        = "string"
+  default     = ""
+}
+
+variable "memory_pressure_threshold_warning" {
+  description = "Memory pressure monitor (warning threshold)"
+  type        = "string"
+  default     = 3
+}
+
+variable "ready_silenced" {
+  description = "Groups to mute for Node ready monitor"
+  type        = "map"
+  default     = {}
+}
+
+variable "ready_enabled" {
+  description = "Flag to enable Node ready monitor"
+  type        = "string"
+  default     = "true"
+}
+
+variable "ready_extra_tags" {
+  description = "Extra tags for Node ready monitor"
+  type        = "list"
+  default     = []
+}
+
+variable "ready_message" {
+  description = "Custom message for Node ready monitor"
+  type        = "string"
+  default     = ""
+}
+
+variable "ready_threshold_warning" {
+  description = "Node ready monitor (warning threshold)"
+  type        = "string"
+  default     = 3
+}
+
+variable "kubelet_ping_silenced" {
+  description = "Groups to mute for Kubelet ping monitor"
+  type        = "map"
+  default     = {}
+}
+
+variable "kubelet_ping_enabled" {
+  description = "Flag to enable Kubelet ping monitor"
+  type        = "string"
+  default     = "true"
+}
+
+variable "kubelet_ping_extra_tags" {
+  description = "Extra tags for Kubelet ping monitor"
+  type        = "list"
+  default     = []
+}
+
+variable "kubelet_ping_message" {
+  description = "Custom message for Kubelet ping monitor"
+  type        = "string"
+  default     = ""
+}
+
+variable "kubelet_ping_threshold_warning" {
+  description = "Kubelet ping monitor (warning threshold)"
+  type        = "string"
+  default     = 3
+}
+
+variable "kubelet_syncloop_silenced" {
+  description = "Groups to mute for Kubelet sync loop monitor"
+  type        = "map"
+  default     = {}
+}
+
+variable "kubelet_syncloop_enabled" {
+  description = "Flag to enable Kubelet sync loop monitor"
+  type        = "string"
+  default     = "true"
+}
+
+variable "kubelet_syncloop_extra_tags" {
+  description = "Extra tags for Kubelet sync loop monitor"
+  type        = "list"
+  default     = []
+}
+
+variable "kubelet_syncloop_message" {
+  description = "Custom message for Kubelet sync loop monitor"
+  type        = "string"
+  default     = ""
+}
+
+variable "kubelet_syncloop_threshold_warning" {
+  description = "Kubelet sync loop monitor (warning threshold)"
+  type        = "string"
+  default     = 3
+}
+
+variable "unregister_net_device_silenced" {
+  description = "Groups to mute for Unregister net device monitor"
+  type        = "map"
+  default     = {}
+}
+
+variable "unregister_net_device_enabled" {
+  description = "Flag to enable Unregister net device monitor"
+  type        = "string"
+  default     = "true"
+}
+
+variable "unregister_net_device_extra_tags" {
+  description = "Extra tags for Unregister net device monitor"
+  type        = "list"
+  default     = []
+}
+
+variable "unregister_net_device_message" {
+  description = "Custom message for Unregister net device monitor"
+  type        = "string"
+  default     = ""
+}
+
+variable "unregister_net_device_time_aggregator" {
+  description = "Monitor aggregator for Unregister net device [available values: min, max or avg]"
+  type        = "string"
+  default     = "min"
+}
+
+variable "unregister_net_device_timeframe" {
+  description = "Monitor timeframe for Unregister net device [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
+  type        = "string"
+  default     = "15m"
+}
+
+variable "unregister_net_device_threshold_critical" {
+  default     = 3
+  description = "Unregister net device critical threshold"
+}
+
+variable "node_unschedulable_silenced" {
+  description = "Groups to mute for node unschedulable monitor"
+  type        = "map"
+  default     = {}
+}
+
+variable "node_unschedulable_enabled" {
+  description = "Flag to enable node unschedulable monitor"
+  type        = "string"
+  default     = "true"
+}
+
+variable "node_unschedulable_extra_tags" {
+  description = "Extra tags for node unschedulable monitor"
+  type        = "list"
+  default     = []
+}
+
+variable "node_unschedulable_message" {
+  description = "Custom message for node unschedulable monitor"
+  type        = "string"
+  default     = ""
+}
+
+variable "node_unschedulable_time_aggregator" {
+  description = "Monitor aggregator for node unschedulable [available values: min, max or avg]"
+  type        = "string"
+  default     = "min"
+}
+
+variable "node_unschedulable_timeframe" {
+  description = "Monitor timeframe for node unschedulable [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
+  type        = "string"
+  default     = "last_1h"
+}

caas/kubernetes/node/modules.tf

@@ -0,0 +1,20 @@
+module "filter-tags" {
+  source = "../../../common/filter-tags"
+
+  environment                 = "${var.environment}"
+  resource                    = "kubernetes"
+  filter_tags_use_defaults    = "${var.filter_tags_use_defaults}"
+  filter_tags_custom          = "${var.filter_tags_custom}"
+  filter_tags_custom_excluded = "${var.filter_tags_custom_excluded}"
+}
+
+module "filter-tags-unschedulable" {
+  source = "../../../common/filter-tags"
+
+  environment                 = "${var.environment}"
+  resource                    = "kubernetes"
+  filter_tags_use_defaults    = "${var.filter_tags_use_defaults}"
+  filter_tags_custom          = "${var.filter_tags_custom}"
+  filter_tags_custom_excluded = "${var.filter_tags_custom_excluded}"
+  extra_tags                  = ["status:unschedulable"]
+}

caas/kubernetes/node/monitors-k8s-node.tf

@@ -0,0 +1,233 @@
+resource "datadog_monitor" "disk_pressure" {
+  count   = "${var.disk_pressure_enabled == "true" ? 1 : 0}"
+  name    = "[${var.environment}] Kubernetes Node Disk pressure"
+  message = "${coalesce(var.disk_pressure_message, var.message)}"
+
+  type = "service check"
+
+  query = <<EOQ
+    "kubernetes_state.node.disk_pressure"${module.filter-tags.service_check}.by("kubernetescluster","node").last(6).count_by_status()
+  EOQ
+
+  thresholds = {
+    warning  = "${var.disk_pressure_threshold_warning}"
+    critical = 5
+  }
+
+  new_host_delay      = "${var.new_host_delay}"
+  notify_no_data      = false
+  renotify_interval   = 0
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = true
+
+  silenced = "${var.disk_pressure_silenced}"
+
+  tags = ["env:${var.environment}", "type:caas", "provider:kubernetes", "resource:kubernetes-node", "team:claranet", "created-by:terraform", "${var.disk_pressure_extra_tags}"]
+}
+
+resource "datadog_monitor" "disk_out" {
+  count   = "${var.disk_out_enabled == "true" ? 1 : 0}"
+  name    = "[${var.environment}] Kubernetes Node Out of disk"
+  message = "${coalesce(var.disk_out_message, var.message)}"
+
+  type = "service check"
+
+  query = <<EOQ
+    "kubernetes_state.node.out_of_disk"${module.filter-tags.service_check}.by("kubernetescluster","node").last(6).count_by_status()
+  EOQ
+
+  thresholds = {
+    warning  = "${var.disk_out_threshold_warning}"
+    critical = 5
+  }
+
+  new_host_delay      = "${var.new_host_delay}"
+  notify_no_data      = false
+  renotify_interval   = 0
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = true
+
+  silenced = "${var.disk_out_silenced}"
+
+  tags = ["env:${var.environment}", "type:caas", "provider:kubernetes", "resource:kubernetes-node", "team:claranet", "created-by:terraform", "${var.disk_out_extra_tags}"]
+}
+
+resource "datadog_monitor" "memory_pressure" {
+  count   = "${var.memory_pressure_enabled == "true" ? 1 : 0}"
+  name    = "[${var.environment}] Kubernetes Node Memory pressure"
+  message = "${coalesce(var.memory_pressure_message, var.message)}"
+
+  type = "service check"
+
+  query = <<EOQ
+    "kubernetes_state.node.memory_pressure"${module.filter-tags.service_check}.by("kubernetescluster","node").last(6).count_by_status()
+  EOQ
+
+  thresholds = {
+    warning  = "${var.memory_pressure_threshold_warning}"
+    critical = 5
+  }
+
+  new_host_delay      = "${var.new_host_delay}"
+  notify_no_data      = false
+  renotify_interval   = 0
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = true
+
+  silenced = "${var.memory_pressure_silenced}"
+
+  tags = ["env:${var.environment}", "type:caas", "provider:kubernetes", "resource:kubernetes-node", "team:claranet", "created-by:terraform", "${var.memory_pressure_extra_tags}"]
+}
+
+resource "datadog_monitor" "ready" {
+  count   = "${var.ready_enabled == "true" ? 1 : 0}"
+  name    = "[${var.environment}] Kubernetes Node not ready"
+  message = "${coalesce(var.ready_message, var.message)}"
+
+  type = "service check"
+
+  query = <<EOQ
+    "kubernetes_state.node.ready"${module.filter-tags.service_check}.by("kubernetescluster","node").last(6).count_by_status()
+  EOQ
+
+  thresholds = {
+    warning  = "${var.ready_threshold_warning}"
+    critical = 5
+  }
+
+  new_host_delay      = "${var.new_host_delay}"
+  notify_no_data      = false
+  renotify_interval   = 0
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = true
+
+  silenced = "${var.ready_silenced}"
+
+  tags = ["env:${var.environment}", "type:caas", "provider:kubernetes", "resource:kubernetes-node", "team:claranet", "created-by:terraform", "${var.ready_extra_tags}"]
+}
+
+resource "datadog_monitor" "kubelet_ping" {
+  count   = "${var.kubelet_ping_enabled == "true" ? 1 : 0}"
+  name    = "[${var.environment}] Kubernetes Node Kubelet API does not respond"
+  message = "${coalesce(var.kubelet_ping_message, var.message)}"
+
+  type = "service check"
+
+  query = <<EOQ
+    "kubernetes.kubelet.check.ping"${module.filter-tags.service_check}.by("kubernetescluster","name").last(6).count_by_status()
+  EOQ
+
+  thresholds = {
+    warning  = "${var.kubelet_ping_threshold_warning}"
+    critical = 5
+  }
+
+  new_host_delay      = "${var.new_host_delay}"
+  notify_no_data      = true
+  renotify_interval   = 0
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = true
+
+  silenced = "${var.kubelet_ping_silenced}"
+
+  tags = ["env:${var.environment}", "type:caas", "provider:kubernetes", "resource:kubernetes-node", "team:claranet", "created-by:terraform", "${var.kubelet_ping_extra_tags}"]
+}
+
+resource "datadog_monitor" "kubelet_syncloop" {
+  count   = "${var.kubelet_syncloop_enabled == "true" ? 1 : 0}"
+  name    = "[${var.environment}] Kubernetes Node Kubelet sync loop that updates containers does not work"
+  message = "${coalesce(var.kubelet_syncloop_message, var.message)}"
+
+  type = "service check"
+
+  query = <<EOQ
+    "kubernetes.kubelet.check.syncloop"${module.filter-tags.service_check}.by("kubernetescluster","name").last(6).count_by_status()
+  EOQ
+
+  thresholds = {
+    warning  = "${var.kubelet_syncloop_threshold_warning}"
+    critical = 5
+  }
+
+  new_host_delay      = "${var.new_host_delay}"
+  notify_no_data      = false
+  renotify_interval   = 0
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = true
+
+  silenced = "${var.kubelet_syncloop_silenced}"
+
+  tags = ["env:${var.environment}", "type:caas", "provider:kubernetes", "resource:kubernetes-node", "team:claranet", "created-by:terraform", "${var.kubelet_syncloop_extra_tags}"]
+}
+
+resource "datadog_monitor" "unregister_net_device" {
+  count   = "${var.unregister_net_device_enabled == "true" ? 1 : 0}"
+  name    = "[${var.environment}] Kubernetes Node Frequent unregister net device"
+  type    = "event alert"
+  message = "${coalesce(var.unregister_net_device_message, var.message)}"
+
+  query = <<EOQ
+    events('sources:kubernetes priority:all ${module.filter-tags.event_alert} \"UnregisterNetDevice\"').rollup('count').last('${var.unregister_net_device_timeframe}') > ${var.unregister_net_device_threshold_critical}
+  EOQ
+
+  new_host_delay = "${var.new_host_delay}"
+
+  notify_no_data    = false
+  renotify_interval = 0
+  notify_audit      = false
+  timeout_h         = 0
+  include_tags      = true
+  locked            = false
+
+  silenced = "${var.unregister_net_device_silenced}"
+  tags     = ["env:${var.environment}", "type:caas", "provider:kubernetes", "resource:kubernetes-node", "team:claranet", "created-by:terraform", "${var.unregister_net_device_extra_tags}"]
+}
+
+resource "datadog_monitor" "node_unschedulable" {
+  count   = "${var.node_unschedulable_enabled == "true" ? 1 : 0}"
+  name    = "[${var.environment}] Kubernetes Node unschedulable"
+  type    = "metric alert"
+  message = "${coalesce(var.node_unschedulable_message, var.message)}"
+
+  query = <<EOQ
+    ${var.node_unschedulable_time_aggregator}(${var.node_unschedulable_timeframe}):
+      sum:kubernetes_state.node.status${module.filter-tags-unschedulable.query_alert} by {kubernetescluster,node}
+    > 0
+  EOQ
+
+  thresholds {
+    critical = 0
+  }
+
+  evaluation_delay = "${var.evaluation_delay}"
+  new_host_delay   = "${var.new_host_delay}"
+
+  notify_no_data      = true
+  renotify_interval   = 0
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = true
+
+  silenced = "${var.node_unschedulable_silenced}"
+  tags     = ["env:${var.environment}", "type:caas", "provider:kubernetes", "resource:kubernetes-node", "team:claranet", "created-by:terraform", "${var.node_unschedulable_extra_tags}"]
+}

caas/kubernetes/node/outputs.tf

@@ -0,0 +1,39 @@
+output "disk_pressure_id" {
+  description = "id for monitor disk_pressure"
+  value       = "${datadog_monitor.disk_pressure.*.id}"
+}
+
+output "disk_out_id" {
+  description = "id for monitor disk_out"
+  value       = "${datadog_monitor.disk_out.*.id}"
+}
+
+output "memory_pressure_id" {
+  description = "id for monitor memory_pressure"
+  value       = "${datadog_monitor.memory_pressure.*.id}"
+}
+
+output "ready_id" {
+  description = "id for monitor ready"
+  value       = "${datadog_monitor.ready.*.id}"
+}
+
+output "kubelet_ping_id" {
+  description = "id for monitor kubelet_ping"
+  value       = "${datadog_monitor.kubelet_ping.*.id}"
+}
+
+output "kubelet_syncloop_id" {
+  description = "id for monitor kubelet_syncloop"
+  value       = "${datadog_monitor.kubelet_syncloop.*.id}"
+}
+
+output "unregister_net_device_id" {
+  description = "id for monitor unregister_net_device"
+  value       = "${datadog_monitor.unregister_net_device.*.id}"
+}
+
+output "node_unschedulable_id" {
+  description = "id for monitor node_unschedulable"
+  value       = "${datadog_monitor.node_unschedulable.*.id}"
+}