Restructure project: Move AKS cluster to beispiel-k8s-cluster directory
Major improvements: - Import existing Azure AKS cluster with aztfexport - Optimize VM size from Standard_D4d_v4 to Standard_D2as_v6 (50% cost reduction) - Configure availability zones to [1, 2] - Add comprehensive monitoring setup: * New Log Analytics Workspace * OMS Agent integration * Data Collection Rule for Container Insights * Email alerts for CPU and Memory - Refactor configuration: * Extract all values to variables.tf * Rename resources with meaningful names * Add detailed outputs.tf - Add project documentation: * Comprehensive README.md * cluster-status-commands.md with useful Azure CLI commands * terraform.tfvars.example template * .gitignore for sensitive files Infrastructure changes: - Resource Group: trusted_ai_demo_rg (Germany West Central) - AKS Cluster: trai_k8s_cluster (Kubernetes 1.33) - Node Pool: 2-3 nodes with auto-scaling - Network: VNet 10.0.0.0/16, Subnet 10.0.0.0/24 - Monitoring: Full Container Insights with alerts Cost optimization: ~€75/month (down from ~€140/month) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
This commit is contained in:
cbazzaandClaude Sonnet 4.5 committed
1 parent
4fd1f14a3b
commit
dfff276de6
18 files changed
+702
-420
No files matched your search
@@ -0,0 +1,195 @@
|
||||
resource "azurerm_resource_group" "main" {
|
||||
location = var.location
|
||||
name = var.resource_group_name
|
||||
}
|
||||
|
||||
resource "azurerm_virtual_network" "main" {
|
||||
address_space = var.vnet_address_space
|
||||
location = var.location
|
||||
name = var.vnet_name
|
||||
resource_group_name = var.resource_group_name
|
||||
depends_on = [
|
||||
azurerm_resource_group.main
|
||||
]
|
||||
}
|
||||
|
||||
resource "azurerm_subnet" "default" {
|
||||
address_prefixes = var.subnet_address_prefixes
|
||||
name = var.subnet_name
|
||||
resource_group_name = var.resource_group_name
|
||||
virtual_network_name = var.vnet_name
|
||||
depends_on = [
|
||||
azurerm_virtual_network.main
|
||||
]
|
||||
}
|
||||
|
||||
resource "azurerm_log_analytics_workspace" "main" {
|
||||
name = "aksloganalytics${replace(var.aks_cluster_name, "_", "")}"
|
||||
location = var.location
|
||||
resource_group_name = var.resource_group_name
|
||||
sku = "PerGB2018"
|
||||
retention_in_days = 30
|
||||
depends_on = [
|
||||
azurerm_resource_group.main
|
||||
]
|
||||
}
|
||||
|
||||
resource "azurerm_kubernetes_cluster" "main" {
|
||||
automatic_upgrade_channel = "patch"
|
||||
dns_prefix = var.aks_dns_prefix
|
||||
image_cleaner_enabled = true
|
||||
image_cleaner_interval_hours = 168
|
||||
location = var.location
|
||||
name = var.aks_cluster_name
|
||||
oidc_issuer_enabled = true
|
||||
resource_group_name = var.resource_group_name
|
||||
workload_identity_enabled = true
|
||||
|
||||
default_node_pool {
|
||||
auto_scaling_enabled = true
|
||||
max_count = var.aks_node_pool_max_count
|
||||
min_count = var.aks_node_pool_min_count
|
||||
name = "agentpool"
|
||||
vm_size = var.aks_node_vm_size
|
||||
zones = var.aks_node_zones
|
||||
temporary_name_for_rotation = "temppool"
|
||||
upgrade_settings {
|
||||
max_surge = "10%"
|
||||
}
|
||||
}
|
||||
|
||||
identity {
|
||||
type = "SystemAssigned"
|
||||
}
|
||||
|
||||
maintenance_window_auto_upgrade {
|
||||
day_of_week = "Sunday"
|
||||
duration = 8
|
||||
frequency = "Weekly"
|
||||
interval = 1
|
||||
start_time = "00:00"
|
||||
utc_offset = "+00:00"
|
||||
}
|
||||
|
||||
maintenance_window_node_os {
|
||||
day_of_week = "Sunday"
|
||||
duration = 8
|
||||
frequency = "Weekly"
|
||||
interval = 1
|
||||
start_time = "00:00"
|
||||
utc_offset = "+00:00"
|
||||
}
|
||||
|
||||
oms_agent {
|
||||
log_analytics_workspace_id = azurerm_log_analytics_workspace.main.id
|
||||
msi_auth_for_monitoring_enabled = true
|
||||
}
|
||||
|
||||
depends_on = [
|
||||
azurerm_resource_group.main,
|
||||
azurerm_log_analytics_workspace.main
|
||||
]
|
||||
}
|
||||
|
||||
resource "azurerm_monitor_data_collection_rule" "aks_monitoring" {
|
||||
kind = "Linux"
|
||||
location = var.location
|
||||
name = "MSCI-${var.location}-${var.aks_cluster_name}"
|
||||
resource_group_name = var.resource_group_name
|
||||
|
||||
data_flow {
|
||||
destinations = ["ciworkspace"]
|
||||
streams = ["Microsoft-ContainerLog", "Microsoft-ContainerLogV2", "Microsoft-KubeEvents", "Microsoft-KubePodInventory"]
|
||||
}
|
||||
|
||||
data_sources {
|
||||
extension {
|
||||
extension_json = jsonencode({
|
||||
dataCollectionSettings = {
|
||||
enableContainerLogV2 = true
|
||||
interval = "1m"
|
||||
namespaceFilteringMode = "Off"
|
||||
}
|
||||
})
|
||||
extension_name = "ContainerInsights"
|
||||
name = "ContainerInsightsExtension"
|
||||
streams = ["Microsoft-ContainerLog", "Microsoft-ContainerLogV2", "Microsoft-KubeEvents", "Microsoft-KubePodInventory"]
|
||||
}
|
||||
}
|
||||
|
||||
destinations {
|
||||
log_analytics {
|
||||
name = "ciworkspace"
|
||||
workspace_resource_id = azurerm_log_analytics_workspace.main.id
|
||||
}
|
||||
}
|
||||
|
||||
depends_on = [
|
||||
azurerm_resource_group.main,
|
||||
azurerm_log_analytics_workspace.main
|
||||
]
|
||||
}
|
||||
|
||||
resource "azurerm_monitor_action_group" "alerts" {
|
||||
name = "RecommendedAlertRules-AG-c92012"
|
||||
resource_group_name = var.resource_group_name
|
||||
short_name = "alertc92012"
|
||||
|
||||
email_receiver {
|
||||
email_address = var.alert_email_address
|
||||
name = "Email_-EmailAction-"
|
||||
use_common_alert_schema = true
|
||||
}
|
||||
|
||||
depends_on = [
|
||||
azurerm_resource_group.main
|
||||
]
|
||||
}
|
||||
|
||||
resource "azurerm_monitor_metric_alert" "cpu_alert" {
|
||||
auto_mitigate = false
|
||||
frequency = "PT5M"
|
||||
name = "CPU Usage Percentage - ${var.aks_cluster_name}"
|
||||
resource_group_name = var.resource_group_name
|
||||
scopes = [azurerm_kubernetes_cluster.main.id]
|
||||
|
||||
action {
|
||||
action_group_id = azurerm_monitor_action_group.alerts.id
|
||||
}
|
||||
|
||||
criteria {
|
||||
aggregation = "Average"
|
||||
metric_name = "node_cpu_usage_percentage"
|
||||
metric_namespace = "Microsoft.ContainerService/managedClusters"
|
||||
operator = "GreaterThan"
|
||||
threshold = 95
|
||||
}
|
||||
|
||||
depends_on = [
|
||||
azurerm_resource_group.main
|
||||
]
|
||||
}
|
||||
|
||||
resource "azurerm_monitor_metric_alert" "memory_alert" {
|
||||
auto_mitigate = false
|
||||
frequency = "PT5M"
|
||||
name = "Memory Working Set Percentage - ${var.aks_cluster_name}"
|
||||
resource_group_name = var.resource_group_name
|
||||
scopes = [azurerm_kubernetes_cluster.main.id]
|
||||
|
||||
action {
|
||||
action_group_id = azurerm_monitor_action_group.alerts.id
|
||||
}
|
||||
|
||||
criteria {
|
||||
aggregation = "Average"
|
||||
metric_name = "node_memory_working_set_percentage"
|
||||
metric_namespace = "Microsoft.ContainerService/managedClusters"
|
||||
operator = "GreaterThan"
|
||||
threshold = 100
|
||||
}
|
||||
|
||||
depends_on = [
|
||||
azurerm_resource_group.main
|
||||
]
|
||||
}
|
||||
Reference in new issue
Block a user