add vars on titles

claranet · Jan 23, 2025 · 6e4bbc5 · 6e4bbc5
1 parent 6e66038
commit 6e4bbc5
Show file tree

Hide file tree

Showing 4 changed files with 22 additions and 22 deletions.
diff --git a/caas/kubernetes/node/README.md b/caas/kubernetes/node/README.md
@@ -17,15 +17,15 @@ module "datadog-monitors-caas-kubernetes-node" {
 
 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 unschedulable
-- Kubernetes Node volume inodes usage
-- Kubernetes Node volume space usage
+- Kubernetes Node {{kube_node}} disk pressure on {{kube_cluster_name}}
+- Kubernetes Node {{kube_node}} frequent unregister net device
+- Kubernetes Node {{kube_node}} Kubelet API does not respond on {{kube_cluster_name}}
+- Kubernetes Node {{kube_node}} Kubelet sync loop that updates containers does not work on {{kube_cluster_name}}
+- Kubernetes Node {{kube_node}} memory pressure on {{kube_cluster_name}}
+- Kubernetes Node {{kube_node}} not ready on {{kube_cluster_name}}
+- Kubernetes Node {{kube_node}} unschedulable on {{kube_cluster_name}}
+- Kubernetes Node volume {{persistentvolumeclaim}} inodes usage
+- Kubernetes Node volume {{persistentvolumeclaim}} space usage
 
 <!-- BEGIN_TF_DOCS -->
 ## Requirements

diff --git a/caas/kubernetes/node/monitors-k8s-node.tf b/caas/kubernetes/node/monitors-k8s-node.tf
@@ -1,6 +1,6 @@
 resource "datadog_monitor" "disk_pressure" {
   count   = var.disk_pressure_enabled == "true" ? 1 : 0
-  name    = "${var.prefix_slug == "" ? "" : "[${var.prefix_slug}]"}[${var.environment}] Kubernetes Node Disk pressure"
+  name    = "${var.prefix_slug == "" ? "" : "[${var.prefix_slug}]"}[${var.environment}] Kubernetes Node {{kube_node}} disk pressure on {{kube_cluster_name}}"
   message = coalesce(var.disk_pressure_message, var.message)
   type    = "service check"
 
@@ -27,7 +27,7 @@ EOQ
 
 resource "datadog_monitor" "memory_pressure" {
   count   = var.memory_pressure_enabled == "true" ? 1 : 0
-  name    = "${var.prefix_slug == "" ? "" : "[${var.prefix_slug}]"}[${var.environment}] Kubernetes Node Memory pressure"
+  name    = "${var.prefix_slug == "" ? "" : "[${var.prefix_slug}]"}[${var.environment}] Kubernetes Node {{kube_node}} memory pressure on {{kube_cluster_name}}"
   message = coalesce(var.memory_pressure_message, var.message)
   type    = "service check"
 
@@ -54,7 +54,7 @@ EOQ
 
 resource "datadog_monitor" "ready" {
   count   = var.ready_enabled == "true" ? 1 : 0
-  name    = "${var.prefix_slug == "" ? "" : "[${var.prefix_slug}]"}[${var.environment}] Kubernetes Node not ready"
+  name    = "${var.prefix_slug == "" ? "" : "[${var.prefix_slug}]"}[${var.environment}] Kubernetes Node {{kube_node}} not ready on {{kube_cluster_name}}"
   message = coalesce(var.ready_message, var.message)
   type    = "service check"
 
@@ -81,12 +81,12 @@ EOQ
 
 resource "datadog_monitor" "kubelet_ping" {
   count   = var.kubelet_ping_enabled == "true" ? 1 : 0
-  name    = "${var.prefix_slug == "" ? "" : "[${var.prefix_slug}]"}[${var.environment}] Kubernetes Node Kubelet API does not respond"
+  name    = "${var.prefix_slug == "" ? "" : "[${var.prefix_slug}]"}[${var.environment}] Kubernetes Node {{kube_node}} Kubelet API does not respond on {{kube_cluster_name}}"
   message = coalesce(var.kubelet_ping_message, var.message)
   type    = "service check"
 
   query = <<EOQ
-    "kubernetes.kubelet.check.ping"${module.filter-tags.service_check}.by("name","kube_cluster_name").last(6).count_by_status()
+    "kubernetes.kubelet.check.ping"${module.filter-tags.service_check}.by("kube_node","kube_cluster_name").last(6).count_by_status()
 EOQ
 
   monitor_thresholds {
@@ -109,12 +109,12 @@ EOQ
 
 resource "datadog_monitor" "kubelet_syncloop" {
   count   = var.kubelet_syncloop_enabled == "true" ? 1 : 0
-  name    = "${var.prefix_slug == "" ? "" : "[${var.prefix_slug}]"}[${var.environment}] Kubernetes Node Kubelet sync loop that updates containers does not work"
+  name    = "${var.prefix_slug == "" ? "" : "[${var.prefix_slug}]"}[${var.environment}] Kubernetes Node {{kube_node}} Kubelet sync loop that updates containers does not work on {{kube_cluster_name}}"
   message = coalesce(var.kubelet_syncloop_message, var.message)
   type    = "service check"
 
   query = <<EOQ
-    "kubernetes.kubelet.check.syncloop"${module.filter-tags.service_check}.by("name","kube_cluster_name").last(6).count_by_status()
+    "kubernetes.kubelet.check.syncloop"${module.filter-tags.service_check}.by("kube_node","kube_cluster_name").last(6).count_by_status()
 EOQ
 
   monitor_thresholds {
@@ -136,7 +136,7 @@ EOQ
 
 resource "datadog_monitor" "unregister_net_device" {
   count   = var.unregister_net_device_enabled == "true" ? 1 : 0
-  name    = "${var.prefix_slug == "" ? "" : "[${var.prefix_slug}]"}[${var.environment}] Kubernetes Node Frequent unregister net device"
+  name    = "${var.prefix_slug == "" ? "" : "[${var.prefix_slug}]"}[${var.environment}] Kubernetes Node {{kube_node}} frequent unregister net device"
   message = coalesce(var.unregister_net_device_message, var.message)
   type    = "event-v2 alert"
 
@@ -154,7 +154,7 @@ resource "datadog_monitor" "unregister_net_device" {
 
 resource "datadog_monitor" "node_unschedulable" {
   count   = var.node_unschedulable_enabled == "true" ? 1 : 0
-  name    = "${var.prefix_slug == "" ? "" : "[${var.prefix_slug}]"}[${var.environment}] Kubernetes Node unschedulable"
+  name    = "${var.prefix_slug == "" ? "" : "[${var.prefix_slug}]"}[${var.environment}] Kubernetes Node {{kube_node}} unschedulable on {{kube_cluster_name}}"
   message = coalesce(var.node_unschedulable_message, var.message)
   type    = "metric alert"
 
@@ -183,7 +183,7 @@ EOQ
 
 resource "datadog_monitor" "volume_space" {
   count   = var.volume_space_enabled == "true" ? 1 : 0
-  name    = "${var.prefix_slug == "" ? "" : "[${var.prefix_slug}]"}[${var.environment}] Kubernetes Node volume space usage {{#is_alert}}{{{comparator}}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
+  name    = "${var.prefix_slug == "" ? "" : "[${var.prefix_slug}]"}[${var.environment}] Kubernetes Node volume {{persistentvolumeclaim}} space usage {{#is_alert}}{{{comparator}}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}% ({{value}}%){{/is_warning}} on {{kube_cluster_name}}"
   message = coalesce(var.volume_space_message, var.message)
   type    = "query alert"
 
@@ -214,7 +214,7 @@ EOQ
 
 resource "datadog_monitor" "volume_inodes" {
   count   = var.volume_inodes_enabled == "true" ? 1 : 0
-  name    = "${var.prefix_slug == "" ? "" : "[${var.prefix_slug}]"}[${var.environment}] Kubernetes Node volume inodes usage {{#is_alert}}{{{comparator}}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
+  name    = "${var.prefix_slug == "" ? "" : "[${var.prefix_slug}]"}[${var.environment}] Kubernetes Node volume {{persistentvolumeclaim}} inodes usage {{#is_alert}}{{{comparator}}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}% ({{value}}%){{/is_warning}} on {{kube_cluster_name}}"
   message = coalesce(var.volume_inodes_message, var.message)
   type    = "query alert"
 

diff --git a/caas/kubernetes/pod/README.md b/caas/kubernetes/pod/README.md
@@ -21,7 +21,7 @@ Creates DataDog monitors with the following checks:
 - Kubernetes Pod {{pod_name}} container {{kube_container_name}} killed by OOM on {{kube_cluster_name}}
 - Kubernetes Pod terminated abnormally
 - Kubernetes Pod waiting errors
-- Kubernetes pods in {{kube_replica_set}} frequently restarted on {{kube_cluster_name}}
+- Kubernetes Pods in {{kube_replica_set}} frequently restarted on {{kube_cluster_name}}
 
 <!-- BEGIN_TF_DOCS -->
 ## Requirements

diff --git a/caas/kubernetes/pod/monitors-k8s-pod.tf b/caas/kubernetes/pod/monitors-k8s-pod.tf
@@ -119,7 +119,7 @@ EOQ
 
 resource "datadog_monitor" "pod_frequently_restarted" {
   count   = var.pod_frequently_restarted_enabled == "true" ? 1 : 0
-  name    = "${var.prefix_slug == "" ? "" : "[${var.prefix_slug}]"}[${var.environment}] Kubernetes pods in {{kube_replica_set}} frequently restarted on {{kube_cluster_name}}"
+  name    = "${var.prefix_slug == "" ? "" : "[${var.prefix_slug}]"}[${var.environment}] Kubernetes Pods in {{kube_replica_set}} frequently restarted on {{kube_cluster_name}}"
   message = coalesce(var.pod_frequently_restarted_message, var.message)
   type    = "metric alert"