AKS Service deployment done and can´t reach external IPs - azure

I've created a Kubernetes cluster in Azure using the following Terraform
# Locals block for hardcoded names
locals {
backend_address_pool_name = "appgateway-beap"
frontend_port_name = "appgateway-feport"
frontend_ip_configuration_name = "appgateway-feip"
http_setting_name = "appgateway-be-htst"
listener_name = "appgateway-httplstn"
request_routing_rule_name = "appgateway-rqrt"
app_gateway_subnet_name = "appgateway-subnet"
}
data "azurerm_subnet" "aks-subnet" {
name = "aks-subnet"
virtual_network_name = "np-dat-spoke-vnet"
resource_group_name = "ipz12-dat-np-connect-rg"
}
data "azurerm_subnet" "appgateway-subnet" {
name = "appgateway-subnet"
virtual_network_name = "np-dat-spoke-vnet"
resource_group_name = "ipz12-dat-np-connect-rg"
}
# Create Resource Group for Kubernetes Cluster
module "resource_group_kubernetes_cluster" {
source = "./modules/resource_group"
count = var.enable_kubernetes == true ? 1 : 0
#name_override = "rg-aks-spoke-dev-westus3-001"
app_or_service_name = "aks" # var.app_or_service_name
subscription_type = var.subscription_type # "spoke"
environment = var.environment # "dev"
location = var.location # "westus3"
instance_number = var.instance_number # "001"
tags = var.tags
}
resource "azurerm_user_assigned_identity" "identity_uami" {
location = var.location
name = "appgw-uami"
resource_group_name = module.resource_group_kubernetes_cluster[0].name
}
# Application Gateway Public Ip
resource "azurerm_public_ip" "test" {
name = "publicIp1"
location = var.location
resource_group_name = module.resource_group_kubernetes_cluster[0].name
allocation_method = "Static"
sku = "Standard"
}
resource "azurerm_application_gateway" "network" {
name = var.app_gateway_name
resource_group_name = module.resource_group_kubernetes_cluster[0].name
location = var.location
sku {
name = var.app_gateway_sku
tier = "Standard_v2"
capacity = 2
}
identity {
type = "UserAssigned"
identity_ids = [
azurerm_user_assigned_identity.identity_uami.id
]
}
gateway_ip_configuration {
name = "appGatewayIpConfig"
subnet_id = data.azurerm_subnet.appgateway-subnet.id
}
frontend_port {
name = local.frontend_port_name
port = 80
}
frontend_port {
name = "httpsPort"
port = 443
}
frontend_ip_configuration {
name = local.frontend_ip_configuration_name
public_ip_address_id = azurerm_public_ip.test.id
}
backend_address_pool {
name = local.backend_address_pool_name
}
backend_http_settings {
name = local.http_setting_name
cookie_based_affinity = "Disabled"
port = 80
protocol = "Http"
request_timeout = 1
}
http_listener {
name = local.listener_name
frontend_ip_configuration_name = local.frontend_ip_configuration_name
frontend_port_name = local.frontend_port_name
protocol = "Http"
}
request_routing_rule {
name = local.request_routing_rule_name
rule_type = "Basic"
http_listener_name = local.listener_name
backend_address_pool_name = local.backend_address_pool_name
backend_http_settings_name = local.http_setting_name
priority = 100
}
tags = var.tags
depends_on = [azurerm_public_ip.test]
lifecycle {
ignore_changes = [
backend_address_pool,
backend_http_settings,
request_routing_rule,
http_listener,
probe,
tags,
frontend_port
]
}
}
# Create the Azure Kubernetes Service (AKS) Cluster
resource "azurerm_kubernetes_cluster" "kubernetes_cluster" {
count = var.enable_kubernetes == true ? 1 : 0
name = "aks-prjx-${var.subscription_type}-${var.environment}-${var.location}-${var.instance_number}"
location = var.location
resource_group_name = module.resource_group_kubernetes_cluster[0].name # "rg-aks-spoke-dev-westus3-001"
dns_prefix = "dns-aks-prjx-${var.subscription_type}-${var.environment}-${var.location}-${var.instance_number}" #"dns-prjxcluster"
private_cluster_enabled = false
local_account_disabled = true
default_node_pool {
name = "npprjx${var.subscription_type}" #"prjxsyspool" # NOTE: "name must start with a lowercase letter, have max length of 12, and only have characters a-z0-9."
vm_size = "Standard_B8ms"
vnet_subnet_id = data.azurerm_subnet.aks-subnet.id
# zones = ["1", "2", "3"]
enable_auto_scaling = true
max_count = 3
min_count = 1
# node_count = 3
os_disk_size_gb = 50
type = "VirtualMachineScaleSets"
enable_node_public_ip = false
enable_host_encryption = false
node_labels = {
"node_pool_type" = "npprjx${var.subscription_type}"
"node_pool_os" = "linux"
"environment" = "${var.environment}"
"app" = "prjx_${var.subscription_type}_app"
}
tags = var.tags
}
ingress_application_gateway {
gateway_id = azurerm_application_gateway.network.id
}
# Enabled the cluster configuration to the Azure kubernets with RBAC
azure_active_directory_role_based_access_control {
managed = true
admin_group_object_ids = var.active_directory_role_based_access_control_admin_group_object_ids
azure_rbac_enabled = true #false
}
network_profile {
network_plugin = "azure"
network_policy = "azure"
outbound_type = "userDefinedRouting"
}
identity {
type = "SystemAssigned"
}
oms_agent {
log_analytics_workspace_id = module.log_analytics_workspace[0].id
}
timeouts {
create = "20m"
delete = "20m"
}
depends_on = [
azurerm_application_gateway.network
]
}
and provided the necessary permissions
# Get the AKS Agent Pool SystemAssigned Identity
data "azurerm_user_assigned_identity" "aks-identity" {
name = "${azurerm_kubernetes_cluster.kubernetes_cluster[0].name}-agentpool"
resource_group_name = "MC_${module.resource_group_kubernetes_cluster[0].name}_aks-prjx-spoke-dev-eastus-001_eastus"
}
# Get the AKS SystemAssigned Identity
data "azuread_service_principal" "aks-sp" {
display_name = azurerm_kubernetes_cluster.kubernetes_cluster[0].name
}
# Provide ACR Pull permission to AKS SystemAssigned Identity
resource "azurerm_role_assignment" "acrpull_role" {
scope = module.container_registry[0].id
role_definition_name = "AcrPull"
principal_id = data.azurerm_user_assigned_identity.aks-identity.principal_id
skip_service_principal_aad_check = true
depends_on = [
data.azurerm_user_assigned_identity.aks-identity
]
}
resource "azurerm_role_assignment" "aks_id_network_contributor_subnet" {
scope = data.azurerm_subnet.aks-subnet.id
role_definition_name = "Network Contributor"
principal_id = data.azurerm_user_assigned_identity.aks-identity.principal_id
depends_on = [data.azurerm_user_assigned_identity.aks-identity]
}
resource "azurerm_role_assignment" "akssp_network_contributor_subnet" {
scope = data.azurerm_subnet.aks-subnet.id
role_definition_name = "Network Contributor"
principal_id = data.azuread_service_principal.aks-sp.object_id
depends_on = [data.azuread_service_principal.aks-sp]
}
resource "azurerm_role_assignment" "aks_id_contributor_agw" {
scope = data.azurerm_subnet.appgateway-subnet.id
role_definition_name = "Network Contributor"
principal_id = data.azurerm_user_assigned_identity.aks-identity.principal_id
depends_on = [data.azurerm_user_assigned_identity.aks-identity]
}
resource "azurerm_role_assignment" "akssp_contributor_agw" {
scope = data.azurerm_subnet.appgateway-subnet.id
role_definition_name = "Network Contributor"
principal_id = data.azuread_service_principal.aks-sp.object_id
depends_on = [data.azuread_service_principal.aks-sp]
}
resource "azurerm_role_assignment" "aks_ingressid_contributor_on_agw" {
scope = azurerm_application_gateway.network.id
role_definition_name = "Contributor"
principal_id = azurerm_kubernetes_cluster.kubernetes_cluster[0].ingress_application_gateway[0].ingress_application_gateway_identity[0].object_id
depends_on = [azurerm_application_gateway.network,azurerm_kubernetes_cluster.kubernetes_cluster]
skip_service_principal_aad_check = true
}
resource "azurerm_role_assignment" "aks_ingressid_contributor_on_uami" {
scope = azurerm_user_assigned_identity.identity_uami.id
role_definition_name = "Contributor"
principal_id = azurerm_kubernetes_cluster.kubernetes_cluster[0].ingress_application_gateway[0].ingress_application_gateway_identity[0].object_id
depends_on = [azurerm_application_gateway.network,azurerm_kubernetes_cluster.kubernetes_cluster]
skip_service_principal_aad_check = true
}
resource "azurerm_role_assignment" "uami_contributor_on_agw" {
scope = azurerm_application_gateway.network.id
role_definition_name = "Contributor"
principal_id = azurerm_user_assigned_identity.identity_uami.principal_id
depends_on = [azurerm_application_gateway.network,azurerm_user_assigned_identity.identity_uami]
skip_service_principal_aad_check = true
}
and deployed the below mentioned application
apiVersion: apps/v1
kind: Deployment
metadata:
name: aks-helloworld
spec:
replicas: 1
selector:
matchLabels:
app: aks-helloworld-two
template:
metadata:
labels:
app: aks-helloworld-two
spec:
containers:
- name: aks-helloworld-two
image: mcr.microsoft.com/azuredocs/aks-helloworld:v1
ports:
- containerPort: 80
env:
- name: TITLE
value: "AKS Ingress Demo"
---
apiVersion: v1
kind: Service
metadata:
name: aks-helloworld
spec:
type: LoadBalancer
ports:
- port: 80
selector:
app: aks-helloworld-two
External IP got assigned
however I am not able to access the External IP
Note: I have not deployed any Ingress controller separately like mentioned in the Microsoft Article as I am not sure this is required

I tried to reproduce the same in my environment to create Kubernetes Service Cluster with Application Gateway:
Follow the Stack link to create Kubernetes Service Cluster with Ingress Application Gateway.
If you are unable to access your application using external Load balancer IP after deployment in Azure Kubernetes Service (AKS), Verify the below setting in AKS Cluster.
1.check the status of the load balancer using the below cmd.
kubectl get service <your service name>
Make sure that the External -IP field is not set to Pending state.
Verify the security group associated with the load balancer. Make sure that the security group allows traffic on the desired port.
Kindly follow the below steps to check NSG Security rules in AKS cluster.
Go to Azure Portal > Kubernetes services > Select your Kubernetes services> Properties > Select your resource group under Infrastructure resource group > overview > Select your NSG Group.
I have disabled inbound http rule in Network Security Group for testing, got the same error.
Application status, once disable the Port 80 in NSG.
check the routing rules on your virtual network. Make sure that traffic is being forwarded from the load balancer.

Related

What's the correct way to setup AKS cluster Static IP, Load Balancer and Ingress Controller?

It's now quite a few days that I'm trying to configure the cluster on AKS but I keep jumping between parts of the docs, various questions here on SO, articles on Medium.. all to keep failing at it.
The goal is get a static ip with a dns that I can use to connect my apps to the server deployed on AKS.
I have created via terraform the infrastructure which consists of a resource group in which I created a Public IP and the AKS cluster, so far so good.
After trying to use the ingress controller that gets installed when you use the option http_application_routing_enabled = true on cluster creation which the docs are discouraging for production https://learn.microsoft.com/en-us/azure/aks/http-application-routing, I'm trying the recommended way and install the ingress-nginx controller via Helm https://learn.microsoft.com/en-us/azure/aks/ingress-basic?tabs=azure-cli.
In terraform I'm installing it all like this
resource group and cluster
resource "azurerm_resource_group" "resource_group" {
name = var.resource_group_name
location = var.location
tags = {
Environment = "Test"
Team = "DevOps"
}
}
resource "azurerm_kubernetes_cluster" "server_cluster" {
name = "server_cluster"
location = azurerm_resource_group.resource_group.location
resource_group_name = azurerm_resource_group.resource_group.name
dns_prefix = "fixit"
kubernetes_version = var.kubernetes_version
# sku_tier = "Paid"
default_node_pool {
name = "default"
node_count = 1
min_count = 1
max_count = 3
# vm_size = "standard_b2s_v5"
# vm_size = "standard_e2bs_v5"
vm_size = "standard_b4ms"
type = "VirtualMachineScaleSets"
enable_auto_scaling = true
enable_host_encryption = false
# os_disk_size_gb = 30
# enable_node_public_ip = true
}
service_principal {
client_id = var.sp_client_id
client_secret = var.sp_client_secret
}
tags = {
Environment = "Production"
}
linux_profile {
admin_username = "azureuser"
ssh_key {
key_data = var.ssh_key
}
}
network_profile {
network_plugin = "kubenet"
load_balancer_sku = "standard"
# load_balancer_sku = "basic"
}
# http_application_routing_enabled = true
http_application_routing_enabled = false
}
public ip
resource "azurerm_public_ip" "public-ip" {
name = "fixit-public-ip"
location = var.location
resource_group_name = var.resource_group_name
allocation_method = "Static"
domain_name_label = "fixit"
sku = "Standard"
}
load balancer
resource "kubernetes_service" "cluster-ingress" {
metadata {
name = "cluster-ingress-svc"
annotations = {
"service.beta.kubernetes.io/azure-load-balancer-resource-group" = "fixit-resource-group"
# Warning SyncLoadBalancerFailed 2m38s (x8 over 12m) service-controller Error syncing load balancer:
# failed to ensure load balancer: findMatchedPIPByLoadBalancerIP: cannot find public IP with IP address 52.157.90.236
# in resource group MC_fixit-resource-group_server_cluster_westeurope
# "service.beta.kubernetes.io/azure-load-balancer-resource-group" = "MC_fixit-resource-group_server_cluster_westeurope"
# kubernetes.io/ingress.class: addon-http-application-routing
}
}
spec {
# type = "Ingress"
type = "LoadBalancer"
load_balancer_ip = var.public_ip_address
selector = {
name = "cluster-ingress-svc"
}
port {
name = "cluster-port"
protocol = "TCP"
port = 3000
target_port = "80"
}
}
}
ingress controller
resource "helm_release" "nginx" {
name = "ingress-nginx"
repository = "https://kubernetes.github.io/ingress-nginx"
chart = "ingress-nginx"
namespace = "default"
set {
name = "rbac.create"
value = "false"
}
set {
name = "controller.service.externalTrafficPolicy"
value = "Local"
}
set {
name = "controller.service.loadBalancerIP"
value = var.public_ip_address
}
set {
name = "controller.service.annotations.service.beta.kubernetes.io/azure-load-balancer-internal"
value = "true"
}
# --set controller.service.annotations."service\.beta\.kubernetes\.io/azure-load-balancer-health-probe-request-path"=/healthz
set {
name = "controller.service.annotations.service\\.beta\\.kubernetes\\.io/azure-load-balancer-health-probe-request-path"
value = "/healthz"
}
}
but the installation fails with this message from terraform
Warning: Helm release "ingress-nginx" was created but has a failed status. Use the `helm` command to investigate the error, correct it, then run Terraform again.
│
│ with module.ingress_controller.helm_release.nginx,
│ on modules/ingress_controller/controller.tf line 2, in resource "helm_release" "nginx":
│ 2: resource "helm_release" "nginx" {
│
╵
╷
│ Error: timed out waiting for the condition
│
│ with module.ingress_controller.helm_release.nginx,
│ on modules/ingress_controller/controller.tf line 2, in resource "helm_release" "nginx":
│ 2: resource "helm_release" "nginx" {
the controller print out
vincenzocalia#vincenzos-MacBook-Air helm_charts % kubectl describe svc ingress-nginx-controller
Name: ingress-nginx-controller
Namespace: default
Labels: app.kubernetes.io/component=controller
app.kubernetes.io/instance=ingress-nginx
app.kubernetes.io/managed-by=Helm
app.kubernetes.io/name=ingress-nginx
app.kubernetes.io/part-of=ingress-nginx
app.kubernetes.io/version=1.5.1
helm.sh/chart=ingress-nginx-4.4.2
Annotations: meta.helm.sh/release-name: ingress-nginx
meta.helm.sh/release-namespace: default
service: map[beta:map[kubernetes:map[io/azure-load-balancer-internal:true]]]
service.beta.kubernetes.io/azure-load-balancer-health-probe-request-path: /healthz
Selector: app.kubernetes.io/component=controller,app.kubernetes.io/instance=ingress-nginx,app.kubernetes.io/name=ingress-nginx
Type: LoadBalancer
IP Family Policy: SingleStack
IP Families: IPv4
IP: 10.0.173.243
IPs: 10.0.173.243
IP: 52.157.90.236
Port: http 80/TCP
TargetPort: http/TCP
NodePort: http 31709/TCP
Endpoints:
Port: https 443/TCP
TargetPort: https/TCP
NodePort: https 30045/TCP
Endpoints:
Session Affinity: None
External Traffic Policy: Local
HealthCheck NodePort: 32500
Events:
Type Reason Age From Message
---- ------ ---- ---- -------
Normal EnsuringLoadBalancer 32s (x5 over 108s) service-controller Ensuring load balancer
Warning SyncLoadBalancerFailed 31s (x5 over 107s) service-controller Error syncing load balancer: failed to ensure load balancer: findMatchedPIPByLoadBalancerIP: cannot find public IP with IP address 52.157.90.236 in resource group mc_fixit-resource-group_server_cluster_westeurope
vincenzocalia#vincenzos-MacBook-Air helm_charts % az aks show --resource-group fixit-resource-group --name server_cluster --query nodeResourceGroup -o tsv
MC_fixit-resource-group_server_cluster_westeurope
Why is it looking in the MC_fixit-resource-group_server_cluster_westeurope resource group and not in the fixit-resource-group I created for the Cluster, Public IP and Load Balancer?
If I change the controller load balancer ip to the public ip in MC_fixit-resource-group_server_cluster_westeurope then terraform still outputs the same error, but the controller prints out to be correctly assigned to the ip and load balancer
set {
name = "controller.service.loadBalancerIP"
value = "20.73.192.77" #var.public_ip_address
}
vincenzocalia#vincenzos-MacBook-Air helm_charts % kubectl get svc
NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE
cluster-ingress-svc LoadBalancer 10.0.110.114 52.157.90.236 3000:31863/TCP 104m
ingress-nginx-controller LoadBalancer 10.0.106.201 20.73.192.77 80:30714/TCP,443:32737/TCP 41m
ingress-nginx-controller-admission ClusterIP 10.0.23.188 <none> 443/TCP 41m
kubernetes ClusterIP 10.0.0.1 <none> 443/TCP 122m
vincenzocalia#vincenzos-MacBook-Air helm_charts % kubectl describe svc ingress-nginx-controller
Name: ingress-nginx-controller
Namespace: default
Labels: app.kubernetes.io/component=controller
app.kubernetes.io/instance=ingress-nginx
app.kubernetes.io/managed-by=Helm
app.kubernetes.io/name=ingress-nginx
app.kubernetes.io/part-of=ingress-nginx
app.kubernetes.io/version=1.5.1
helm.sh/chart=ingress-nginx-4.4.2
Annotations: meta.helm.sh/release-name: ingress-nginx
meta.helm.sh/release-namespace: default
service: map[beta:map[kubernetes:map[io/azure-load-balancer-internal:true]]]
service.beta.kubernetes.io/azure-load-balancer-health-probe-request-path: /healthz
Selector: app.kubernetes.io/component=controller,app.kubernetes.io/instance=ingress-nginx,app.kubernetes.io/name=ingress-nginx
Type: LoadBalancer
IP Family Policy: SingleStack
IP Families: IPv4
IP: 10.0.106.201
IPs: 10.0.106.201
IP: 20.73.192.77
LoadBalancer Ingress: 20.73.192.77
Port: http 80/TCP
TargetPort: http/TCP
NodePort: http 30714/TCP
Endpoints:
Port: https 443/TCP
TargetPort: https/TCP
NodePort: https 32737/TCP
Endpoints:
Session Affinity: None
External Traffic Policy: Local
HealthCheck NodePort: 32538
Events:
Type Reason Age From Message
---- ------ ---- ---- -------
Normal EnsuringLoadBalancer 39m (x2 over 41m) service-controller Ensuring load balancer
Normal EnsuredLoadBalancer 39m (x2 over 41m) service-controller Ensured load balancer
vincenzocalia#vincenzos-MacBook-Air helm_charts %
Reading here https://learn.microsoft.com/en-us/azure/aks/faq#why-are-two-resource-groups-created-with-aks
To enable this architecture, each AKS deployment spans two resource groups:
You create the first resource group. This group contains only the Kubernetes service resource. The AKS resource provider automatically creates the second resource group during deployment. An example of the second resource group is MC_myResourceGroup_myAKSCluster_eastus. For information on how to specify the name of this second resource group, see the next section.
The second resource group, known as the node resource group, contains all of the infrastructure resources associated with the cluster. These resources include the Kubernetes node VMs, virtual networking, and storage. By default, the node resource group has a name like MC_myResourceGroup_myAKSCluster_eastus. AKS automatically deletes the node resource group whenever the cluster is deleted, so it should only be used for resources that share the cluster's lifecycle.
Should I pass the first or the second group depending of what kind of resource I'm creating?
E.g. kubernetes_service needs 1st rg, while azurerm_public_ip needs the 2nd rg?
What is it that I'm missing out here?
Please explain it like I was 5 years old because I'm feeling like right now..
Many thanks
Finally found what the problem was.
Indeed the Public IP needs to be created in the node resource group because the ingress controller, with the loadBalancerIP assigned to the Public IP address, is going to look for it in the node resource group so if you create it in the resource group fails with the error I was getting.
The node resource group name is assigned at cluster creation eg. MC_myResourceGroup_myAKSCluster_eastus, but you can name it as you wish using the parameter node_resource_group = var.node_resource_group_name.
Also, the Public IP sku "Standard" (to be specified) or "Basic" ( default), and the cluster load_balancer_sku "standard" or "basic"(no default value her, it needs to be specified) have to match.
I also put the Public IP in the cluster module so it can depend on it, to avoid being created before it and failing as the node resource group has not been created yet, couldn't set that dependency correctly in main.tf file.
So the working configuration is now:
main
terraform {
required_version = ">=1.1.0"
required_providers {
azurerm = {
source = "hashicorp/azurerm"
version = "~> 3.0.2"
}
}
}
provider "azurerm" {
features {
resource_group {
prevent_deletion_if_contains_resources = false
}
}
subscription_id = var.azure_subscription_id
tenant_id = var.azure_subscription_tenant_id
client_id = var.service_principal_appid
client_secret = var.service_principal_password
}
provider "kubernetes" {
host = "${module.cluster.host}"
client_certificate = "${base64decode(module.cluster.client_certificate)}"
client_key = "${base64decode(module.cluster.client_key)}"
cluster_ca_certificate = "${base64decode(module.cluster.cluster_ca_certificate)}"
}
provider "helm" {
kubernetes {
host = "${module.cluster.host}"
client_certificate = "${base64decode(module.cluster.client_certificate)}"
client_key = "${base64decode(module.cluster.client_key)}"
cluster_ca_certificate = "${base64decode(module.cluster.cluster_ca_certificate)}"
}
}
module "cluster" {
source = "./modules/cluster"
location = var.location
vm_size = var.vm_size
resource_group_name = var.resource_group_name
node_resource_group_name = var.node_resource_group_name
kubernetes_version = var.kubernetes_version
ssh_key = var.ssh_key
sp_client_id = var.service_principal_appid
sp_client_secret = var.service_principal_password
}
module "ingress-controller" {
source = "./modules/ingress-controller"
public_ip_address = module.cluster.public_ip_address
depends_on = [
module.cluster.public_ip_address
]
}
cluster
resource "azurerm_resource_group" "resource_group" {
name = var.resource_group_name
location = var.location
tags = {
Environment = "test"
Team = "DevOps"
}
}
resource "azurerm_kubernetes_cluster" "server_cluster" {
name = "server_cluster"
### choose the resource goup to use for the cluster
location = azurerm_resource_group.resource_group.location
resource_group_name = azurerm_resource_group.resource_group.name
### decide the name of the cluster "node" resource group, if unset will be named automatically
node_resource_group = var.node_resource_group_name
dns_prefix = "fixit"
kubernetes_version = var.kubernetes_version
# sku_tier = "Paid"
default_node_pool {
name = "default"
node_count = 1
min_count = 1
max_count = 3
vm_size = var.vm_size
type = "VirtualMachineScaleSets"
enable_auto_scaling = true
enable_host_encryption = false
# os_disk_size_gb = 30
}
service_principal {
client_id = var.sp_client_id
client_secret = var.sp_client_secret
}
tags = {
Environment = "Production"
}
linux_profile {
admin_username = "azureuser"
ssh_key {
key_data = var.ssh_key
}
}
network_profile {
network_plugin = "kubenet"
load_balancer_sku = "basic"
}
http_application_routing_enabled = false
depends_on = [
azurerm_resource_group.resource_group
]
}
resource "azurerm_public_ip" "public-ip" {
name = "fixit-public-ip"
location = var.location
# resource_group_name = var.resource_group_name
resource_group_name = var.node_resource_group_name
allocation_method = "Static"
domain_name_label = "fixit"
# sku = "Standard"
depends_on = [
azurerm_kubernetes_cluster.server_cluster
]
}
ingress controller
resource "helm_release" "nginx" {
name = "ingress-nginx"
repository = "ingress-nginx"
chart = "ingress-nginx/ingress-nginx"
namespace = "default"
set {
name = "controller.service.externalTrafficPolicy"
value = "Local"
}
set {
name = "controller.service.annotations.service.beta.kubernetes.io/azure-load-balancer-internal"
value = "true"
}
set {
name = "controller.service.loadBalancerIP"
value = var.public_ip_address
}
set {
name = "controller.service.annotations.service.beta.kubernetes.io/azure-load-balancer-health-probe-request-path"
value = "/healthz"
}
}
ingress service
apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
name: ingress-service
# namespace: default
annotations:
nginx.ingress.kubernetes.io/ssl-redirect: "false"
nginx.ingress.kubernetes.io/use-regex: "true"
nginx.ingress.kubernetes.io/rewrite-target: /$2$3$4
spec:
ingressClassName: nginx
rules:
# - host: fixit.westeurope.cloudapp.azure.com #dns from Azure PublicIP
### Node.js server
- http:
paths:
- path: /(/|$)(.*)
pathType: Prefix
backend:
service:
name: server-clusterip-service
port:
number: 80
- http:
paths:
- path: /server(/|$)(.*)
pathType: Prefix
backend:
service:
name: server-clusterip-service
port:
number: 80
...
other services omitted
Hope this can help others having difficulties in getting the setup right.
Cheers.

Terraform azurerm_storage_share_directory does not work with file share 'NFS'

We created an Azure storage account with the intention of creating an 'Azure File' to be mounted using NFS (default is SMB). Below is the Terraform code which creates a storage account, a file share and a private endpoint to the file share so that it can be mounted using NFS.
resource "azurerm_storage_account" "az_file_sa" {
name = "abcdxxxyyyzzz"
resource_group_name = local.resource_group_name
location = var.v_region
account_tier = "Premium"
account_kind = "FileStorage"
account_replication_type = "LRS"
enable_https_traffic_only = false
}
resource "azurerm_storage_share" "file_share" {
name = "fileshare"
storage_account_name = azurerm_storage_account.az_file_sa.name
quota = 100
enabled_protocol = "NFS"
depends_on = [ azurerm_storage_account.az_file_sa ]
}
resource "azurerm_private_endpoint" "fileshare-endpoint" {
name = "fileshare-endpoint"
location = var.v_region
resource_group_name = local.resource_group_name
subnet_id = azurerm_subnet.subnet2.id
private_service_connection {
name = "fileshare-endpoint-connection"
private_connection_resource_id = azurerm_storage_account.az_file_sa.id
is_manual_connection = false
subresource_names = [ "file" ]
}
depends_on = [ azurerm_storage_share.file_share ]
}
This works fine. Now, if we try to create a directory on this file share using below Terraform code
resource "azurerm_storage_share_directory" "xxx" {
name = "dev"
share_name = "fileshare"
storage_account_name = "abcdxxxyyyzzz"
}
error we get is,
│ Error: checking for presence of existing Directory "dev" (File Share "fileshare" / Storage Account "abcdxxxyyyzzz" / Resource Group "RG_XXX_YO"): directories.Client#Get: Failure sending request: StatusCode=0 -- Original Error: Get "https://abcdxxxyyyzzz.file.core.windows.net/fileshare/dev?restype=directory": read tcp 192.168.1.3:61175->20.60.179.37:443: read: connection reset by peer
Clearly, this share is not accessible over public https endpoint.
Is there a way to create a directory using 'azurerm_storage_share_directory' when file share is of type 'NFS'?
We were able to mount NFS on a Linux VM (in the same virtual network) using below code where 10.10.2.4 is private IP of the NFS fileshare endpoint.
sudo mkdir -p /mount/abcdxxxyyyzzz/fileshare
sudo mount -t nfs 10.10.2.4:/abcdxxxyyyzzz/fileshare /mount/abcdxxxyyyzzz/fileshare -o vers=4,minorversion=1,sec=sys
regards, Yogesh
full Terraform files
vnet.tf
resource "azurerm_virtual_network" "vnet" {
name = "yogimogi-vnet"
address_space = ["10.10.0.0/16"]
location = local.region
resource_group_name = local.resource_group_name
depends_on = [ azurerm_resource_group.rg ]
}
resource "azurerm_subnet" "subnet1" {
name = "yogimogi-vnet-subnet1"
resource_group_name = local.resource_group_name
virtual_network_name = azurerm_virtual_network.vnet.name
address_prefixes = ["10.10.1.0/24"]
service_endpoints = ["Microsoft.Storage"]
}
resource "azurerm_subnet" "subnet2" {
name = "yogimogi-vnet-subnet2"
resource_group_name = local.resource_group_name
virtual_network_name = azurerm_virtual_network.vnet.name
address_prefixes = ["10.10.2.0/24"]
service_endpoints = ["Microsoft.Storage"]
}
main.tf
resource "azurerm_resource_group" "rg" {
name = local.resource_group_name
location = local.region
tags = {
description = "Resource group for some testing, Yogesh KETKAR"
createdBy = "AutomationEdge"
createDate = "UTC time: ${timestamp()}"
}
}
resource "azurerm_storage_account" "sa" {
name = local.storage_account_name
resource_group_name = local.resource_group_name
location = local.region
account_tier = "Premium"
account_kind = "FileStorage"
account_replication_type = "LRS"
enable_https_traffic_only = false
depends_on = [ azurerm_resource_group.rg ]
}
resource "azurerm_storage_share" "file_share" {
name = "fileshare"
storage_account_name = azurerm_storage_account.sa.name
quota = 100
enabled_protocol = "NFS"
depends_on = [ azurerm_storage_account.sa ]
}
resource "azurerm_storage_account_network_rules" "network_rule" {
storage_account_id = azurerm_storage_account.sa.id
default_action = "Allow"
ip_rules = ["127.0.0.1"]
virtual_network_subnet_ids = [azurerm_subnet.subnet2.id, azurerm_subnet.subnet1.id]
bypass = ["Metrics"]
}
resource "azurerm_private_endpoint" "fileshare-endpoint" {
name = "fileshare-endpoint"
location = local.region
resource_group_name = local.resource_group_name
subnet_id = azurerm_subnet.subnet2.id
private_service_connection {
name = "fileshare-endpoint-connection"
private_connection_resource_id = azurerm_storage_account.sa.id
is_manual_connection = false
subresource_names = [ "file" ]
}
depends_on = [ azurerm_storage_share.file_share ]
}
resource "azurerm_storage_share_directory" "d1" {
name = "d1"
share_name = azurerm_storage_share.file_share.name
storage_account_name = azurerm_storage_account.sa.name
depends_on = [ azurerm_storage_share.file_share, azurerm_private_endpoint.fileshare-endpoint ]
}
error is
╷
│ Error: checking for presence of existing Directory "d1" (File Share "fileshare" / Storage Account "22xdkkdkdkdkdkdkdx22" / Resource Group "RG_Central_US_YOGIMOGI"): directories.Client#Get: Failure sending request: StatusCode=0 -- Original Error: Get
"https://22xdkkdkdkdkdkdkdx22.file.core.windows.net/fileshare/d1?restype=directory": read tcp 10.41.7.110:54240->20.209.18.37:443: read: connection reset by peer
│
│ with azurerm_storage_share_directory.d1,
│ on main.tf line 60, in resource "azurerm_storage_share_directory" "d1":
│ 60: resource "azurerm_storage_share_directory" "d1" {
│
╵
I tried to reproduce the same having private endpoint ,having NFS enabled
and got errors as network rule is not created when NFS enabled.
As virtual network provides access control for NFS , after vnet creation you must configure a virtual network rule,for file share to be accessed.
resource "azurerm_virtual_network" "example" {
name = "ka-vnet"
address_space = ["10.0.0.0/16"]
location = data.azurerm_resource_group.example.location
resource_group_name = data.azurerm_resource_group.example.name
// tags = local.common_tags
}
resource "azurerm_subnet" "storage" {
name = "ka-subnet"
resource_group_name = data.azurerm_resource_group.example.name
virtual_network_name = azurerm_virtual_network.example.name
address_prefixes = ["10.0.2.0/24"]
}
resource "azurerm_storage_account" "az_file_sa" {
name = "kaabdx"
resource_group_name = data.azurerm_resource_group.example.name
location = data.azurerm_resource_group.example.location
account_tier = "Premium"
account_kind = "FileStorage"
account_replication_type = "LRS"
enable_https_traffic_only = false
//provide network rules
network_rules {
default_action = "Allow"
ip_rules = ["127.0.0.1/24"]
//23.45.1.0/24
virtual_network_subnet_ids = ["${azurerm_subnet.storage.id }"]
}
}
resource "azurerm_private_endpoint" "fileshare-endpoint" {
name = "fileshare-endpoint"
location = data.azurerm_resource_group.example.location
resource_group_name = data.azurerm_resource_group.example.name
subnet_id = azurerm_subnet.storage.id
private_service_connection {
name = "fileshare-endpoint-connection"
private_connection_resource_id = azurerm_storage_account.az_file_sa.id
is_manual_connection = false
subresource_names = [ "file" ]
}
depends_on = [ azurerm_storage_share.file_share ]
}
resource "azurerm_storage_share" "file_share" {
name = "fileshare"
storage_account_name = azurerm_storage_account.az_file_sa.name
quota = 100
enabled_protocol = "NFS"
depends_on = [ azurerm_storage_account.az_file_sa ]
}
resource "azurerm_storage_share_directory" "mynewfileshare" {
name = "kadev"
share_name = azurerm_storage_share.file_share.name
storage_account_name = azurerm_storage_account.az_file_sa.name
}
regarding the error that you got :
Error: checking for presence of existing Directory ... directories.Client#Get: Failure sending request: StatusCode=0 -- Original Error: Get "https://abcdxxxyyyzzz.file.core.windows.net/fileshare/dev?restype=directory": read tcp 192.168.1.3:61175->20.60.179.37:443: read: connection reset by peer
Please note that :
VNet peering will not be able to give access to file share. Virtual
network peering with virtual networks hosted in the private endpoint
give NFS share access to the clients in peered virtual networks .Each
of virtual network or subnet must be individually added to the
allowlist.
A checking for presence of existing Directory occurs if the terraform is not initiated .Run Terraform init and then try to Terraform plan and terraform apply.
References:
Cannot create azurerm_storage_container in azurerm_storage_account that uses network_rules · GitHub
NFS Azure file share problems | learn.microsoft.com

Providing access to EFS from ECS task

I am struggling to get an ECS task to be able to see an EFS volume.
The terraform config is:
EFS DEFINITION
resource "aws_efs_file_system" "persistent" {
encrypted = true
}
resource "aws_efs_access_point" "access" {
file_system_id = aws_efs_file_system.persistent.id
}
resource "aws_efs_mount_target" "mount" {
for_each = {for net in aws_subnet.private : net.id => {id = net.id}}
file_system_id = aws_efs_file_system.persistent.id
subnet_id = each.value.id
security_groups = [aws_security_group.efs.id]
}
TASK DEFINITION
resource "aws_ecs_task_definition" "app" {
family = "backend-app-task"
execution_role_arn = aws_iam_role.ecs_task_execution_role.arn
task_role_arn = aws_iam_role.ecs_task_role.arn
network_mode = "awsvpc"
requires_compatibilities = ["FARGATE"]
cpu = var.fargate_cpu
memory = var.fargate_memory
container_definitions = data.template_file.backendapp.rendered
volume {
name = "persistent"
efs_volume_configuration {
file_system_id = aws_efs_file_system.persistent.id
root_directory = "/opt/data"
transit_encryption = "ENABLED"
transit_encryption_port = 2999
authorization_config {
access_point_id = aws_efs_access_point.access.id
iam = "ENABLED"
}
}
}
}
SECURITY GROUP
resource "aws_security_group" "efs" {
name = "efs-security-group"
vpc_id = aws_vpc.main.id
ingress {
protocol = "tcp"
from_port = 2999
to_port = 2999
security_groups = [aws_security_group.ecs_tasks.id]
cidr_blocks = [for net in aws_subnet.private : net.cidr_block]
}
}
TASK ROLE
resource "aws_iam_role" "ecs_task_role" {
name = "ecsTaskRole"
assume_role_policy = data.aws_iam_policy_document.ecs_task_execution_role_base.json
managed_policy_arns = ["arn:aws:iam::aws:policy/AmazonElasticFileSystemFullAccess","arn:aws:iam::aws:policy/service-role/AmazonECSTaskExecutionRolePolicy", aws_iam_policy.ecs_exec_policy.arn]
}
As I understand the AWS docs, the IAM role should have access, and the security group should be passing traffic, but the error suggests that the task cannot resolve the EFS instance.
The error message is:
ResourceInitializationError: failed to invoke EFS utils commands to set up EFS volumes: stderr: Failed to resolve "fs-0000000000000.efs.eu-west-2.amazonaws.com" - check that your file system ID is correct.
I've manually confirmed in the console that the EFS id is correct, so I can only conclude that it cannot resolve due to a network/permissions issue.
-- EDIT --
ECS SERVICE DEFINITION
resource "aws_ecs_service" "main" {
name = "backendservice"
cluster = aws_ecs_cluster.main.id
task_definition = aws_ecs_task_definition.app.arn
desired_count = var.app_count
launch_type = "FARGATE"
enable_execute_command = true
network_configuration {
security_groups = [aws_security_group.ecs_tasks.id]
subnets = aws_subnet.private.*.id
assign_public_ip = true
}
load_balancer {
target_group_arn = aws_alb_target_group.app.id
container_name = "server"
container_port = var.app_port
}
depends_on = [aws_alb_listener.backend]
}
ECS TASK SECURITY GROUP
resource "aws_security_group" "ecs_tasks" {
name = "backend-ecs-tasks-security-group"
description = "allow inbound access from the ALB only"
vpc_id = aws_vpc.main.id
ingress {
protocol = "tcp"
from_port = var.app_port
to_port = var.app_port
security_groups = [aws_security_group.lb.id]
}
egress {
protocol = "-1"
from_port = 0
to_port = 0
cidr_blocks = ["0.0.0.0/0"]
}
}
VPC DEFINITION (minus internet gateway)
data "aws_availability_zones" "available" {
}
resource "aws_vpc" "main" {
cidr_block = "172.17.0.0/16"
}
# Create var.az_count private subnets, each in a different AZ
resource "aws_subnet" "private" {
count = var.az_count
cidr_block = cidrsubnet(aws_vpc.main.cidr_block, 8, count.index)
availability_zone = data.aws_availability_zones.available.names[count.index]
vpc_id = aws_vpc.main.id
}
resource "aws_subnet" "public" {
count = var.az_count
cidr_block = cidrsubnet(aws_vpc.main.cidr_block, 8, var.az_count + count.index)
availability_zone = data.aws_availability_zones.available.names[count.index]
vpc_id = aws_vpc.main.id
map_public_ip_on_launch = true
}
EDIT
It turned out the mountPoints block was missing from the container template. I have now added it, but the outcome is the same.
Run into this problem, this is what I did to resolve:
platform_version = "1.4.0" on the aws_ecs_service, its possible its no longer relevant but was in this blog post I used as a starting point https://medium.com/#ilia.lazebnik/attaching-an-efs-file-system-to-an-ecs-task-7bd15b76a6ef
Made sure aws_efs_mount_target has subnet_id and security_groups set to same ones used by the service. Since I use multiple subnets for multiple availability zones I created mount target for each of them.
Added standard EFS port 2049 to ingress as without that mount operation was failing with timeout error.

not able to deploy application gateway using terraform as resource is taking too long to deploy

Hi I am trying to deploy the application gateway and it's taking lot of time to deploy. Its taking more than 28mins.
module.app-gateway.azurerm_application_gateway.agw: Still creating... [28m38s elapsed]
module.app-gateway.azurerm_application_gateway.agw: Still creating... [28m48s elapsed]
Here is the terraform code I am using
resource "azurerm_public_ip" "agw" {
name = "${var.env}-hub-agw1-pip1"
location = var.region
resource_group_name = var.rg_name
allocation_method = "Dynamic"
domain_name_label = "${var.env}-ag-frontend-ip"
tags = var.tag
}
resource "azurerm_application_gateway" "agw" {
name = "${var.env}-hub-agw1"
location = var.region
resource_group_name = var.rg_name
enable_http2 = true
tags = var.tag
sku {
name = "Standard_Small"
tier = "Standard"
capacity = 1
}
gateway_ip_configuration {
name = "${var.env}-hub-agw1-ip-configuration"
subnet_id = var.subnet_id
}
frontend_ip_configuration {
name = "${var.env}-frontend_ip_configuration_name-public"
public_ip_address_id = azurerm_public_ip.agw.id
}
frontend_port {
name = "${var.env}-frontend_port_name-80"
port = 80
}
frontend_port {
name = "${var.env}-frontend_port_name-443"
port = 443
}
backend_address_pool {
name = var.backend_pool
ip_addresses = [var.vm_priv_address]
}
ssl_certificate {
name = var.cert_name
data = filebase64("certificate.pfx")
password = "jrcszmnadminstrator#2021"
}
backend_http_settings {
name = var.http_setting_name
cookie_based_affinity = "Disabled"
port = 80
protocol = "Http"
request_timeout = 1
}
http_listener {
name = "${var.ag_listener_name}-http"
frontend_ip_configuration_name = "${var.env}-frontend_ip_configuration_name-public"
frontend_port_name = "${var.env}-frontend_port_name-80"
protocol = "Http"
}
http_listener {
name = "${var.ag_listener_name}-https"
frontend_ip_configuration_name = "${var.env}-frontend_ip_configuration_name-public"
frontend_port_name = "${var.env}-frontend_port_name-443"
protocol = "Https"
ssl_certificate_name = "certificate"
}
request_routing_rule {
name = "request_routing_rule_name-https"
rule_type = "Basic"
http_listener_name = "${var.ag_listener_name}-https"
backend_address_pool_name = var.backend_pool
backend_http_settings_name = var.http_setting_name
}
request_routing_rule {
name = "${var.request_routing_rule_name}-http"
rule_type = "Basic"
http_listener_name = "${var.ag_listener_name}-http"
backend_address_pool_name = var.backend_pool
backend_http_settings_name = var.http_setting_name
}
Depending on the App gateway sku and other configurations in the resource , the creation time may range from 15 min to 25 min using Terraform azurerm Provider.
Sometimes when using an old azurerm provider / terraform version might create some latency as they might be using old Azure API's which will result in the creation time taking a bit long than usual. Or If there is an ongoing issue on Azure Resource Manager then at that time too we may face issues like timeouts/ latency in creating or updating a resource which will be intermittent and later resolved from Azure side.
So, Its recommended to use the latest Terraform version and latest azurerm provider to avoid such issues.
I used your code to create the application and it took normal time to complete the creation as below :

Terraform 403 error when creating function app and storage account with private endpoint

I am getting a 403 forbidden when creating a function app that connects to its storage account via private endpoint inside a vnet. Storage account has firewall default action of 'Deny', and of course if I set it to 'Allow' it will work. I want this as 'Deny', however. Following this microsoft link if the function app and storage account are created in the same region with vnet, subnets, and private endpoints then it's supposed to work so I must be doing something wrong. I also tried changing the region for the storage account and it still resulted in a 403.
Error:
Error: web.AppsClient#CreateOrUpdate: Failure sending request: StatusCode=0 -- Original Error: Code="BadRequest" Message="There was a conflict. The remote server returned an error: (403) Forbidden." Details=[{"Message":"There was a conflict. The remote server returned an error: (403) Forbidden."},{"Code":"BadRequest"},{"ErrorEntity":{"Code":"BadRequest","ExtendedCode":"01020","Message":"There was a conflict. The remote server returned an error: (403) Forbidden.","MessageTemplate":"There was a conflict. {0}","Parameters":["The remote server returned an error: (403) Forbidden."]}}]
Here is my terraform code
resource "azurerm_function_app" "func" {
name = "${var.func_basics.name}-func"
location = var.func_basics.location
resource_group_name = var.func_basics.resource_group_name
app_service_plan_id = azurerm_app_service_plan.svc_plan.id
storage_account_name = azurerm_storage_account.func_sa.name
storage_account_access_key = azurerm_storage_account.func_sa.primary_access_key
version = var.runtime_version
https_only = true
depends_on = [
azurerm_storage_account.func_sa,
azurerm_app_service_plan.svc_plan,
azurerm_application_insights.func_ai,
azurerm_virtual_network.func_vnet
]
app_settings = merge(var.app_settings, local.additional_app_settings)
}
resource "azurerm_app_service_plan" "svc_plan" {
name = "${var.func_basics.name}-func-plan"
location = var.func_basics.location
resource_group_name = var.func_basics.resource_group_name
kind = "elastic"
sku {
tier = "ElasticPremium"
size = "EP1"
}
}
resource "azurerm_application_insights" "func_ai" {
name = "${var.func_basics.name}-func-appi"
location = var.func_basics.location
resource_group_name = var.func_basics.resource_group_name
application_type = var.ai_app_type
}
resource "azurerm_storage_account" "func_sa" {
name = "st${lower(replace(var.func_basics.name, "/[-_]*/", ""))}"
resource_group_name = var.func_basics.resource_group_name
location = var.func_basics.location
account_tier = var.sa_settings.tier
account_replication_type = var.sa_settings.replication_type
account_kind = "StorageV2"
enable_https_traffic_only = true
min_tls_version = "TLS1_2"
depends_on = [
azurerm_virtual_network.func_vnet
]
network_rules {
default_action = "Deny"
virtual_network_subnet_ids = [azurerm_subnet.func_endpoint_subnet.id]
bypass = [
"Metrics",
"Logging",
"AzureServices"
]
}
}
resource "azurerm_virtual_network" "func_vnet" {
name = "${var.func_basics.name}-func-vnet"
resource_group_name = var.func_basics.resource_group_name
location = var.func_basics.location
address_space = ["10.0.0.0/16"]
}
resource "azurerm_subnet" "func_service_subnet" {
name = "${var.func_basics.name}-func-svc-snet"
resource_group_name = var.func_basics.resource_group_name
virtual_network_name = azurerm_virtual_network.func_vnet.name
address_prefixes = ["10.0.1.0/24"]
enforce_private_link_service_network_policies = true
service_endpoints = ["Microsoft.Storage"]
delegation {
name = "${var.func_basics.name}-func-del"
service_delegation {
name = "Microsoft.Web/serverFarms"
actions = ["Microsoft.Network/virtualNetworks/subnets/action"]
}
}
}
resource "azurerm_subnet" "func_endpoint_subnet" {
name = "${var.func_basics.name}-func-end-snet"
resource_group_name = var.func_basics.resource_group_name
virtual_network_name = azurerm_virtual_network.func_vnet.name
address_prefixes = ["10.0.2.0/24"]
enforce_private_link_endpoint_network_policies = true
}
resource "azurerm_private_endpoint" "func_req_sa_blob_endpoint" {
name = "${var.func_basics.name}-func-req-sa-blob-end"
resource_group_name = var.func_basics.resource_group_name
location = var.func_basics.location
subnet_id = azurerm_subnet.func_endpoint_subnet.id
private_service_connection {
name = "${var.func_basics.name}-func-req-sa-blob-pscon"
private_connection_resource_id = azurerm_storage_account.func_sa.id
is_manual_connection = false
subresource_names = ["blob"]
}
}
resource "azurerm_private_endpoint" "func_req_sa_file_endpoint" {
name = "${var.func_basics.name}-func-req-sa-file-end"
resource_group_name = var.func_basics.resource_group_name
location = var.func_basics.location
subnet_id = azurerm_subnet.func_endpoint_subnet.id
private_service_connection {
name = "${var.func_basics.name}-func-req-sa-file-pscon"
private_connection_resource_id = azurerm_storage_account.func_sa.id
is_manual_connection = false
subresource_names = ["file"]
}
}
resource "azurerm_app_service_virtual_network_swift_connection" "func_vnet_swift" {
app_service_id = azurerm_function_app.func.id
subnet_id = azurerm_subnet.func_service_subnet.id
}
locals {
additional_app_settings = {
"APPINSIGHTS_INSTRUMENTATIONKEY" = azurerm_application_insights.func_ai.instrumentation_key
"WEBSITE_CONTENTAZUREFILECONNECTIONSTRING" = azurerm_storage_account.func_sa.primary_connection_string
"AzureWebJobsStorage" = azurerm_storage_account.func_sa.primary_connection_string
"WEBSITE_VNET_ROUTE_ALL" = "1"
"WEBSITE_CONTENTOVERVNET" = "1"
"WEBSITE_DNS_SERVER" = "168.63.129.16"
}
}
It seems that it's a common error message when you create an Azure function where the storage account of the function is added to the Virtual Network, read here for more details.
To resolve it, you can use the local-exec Provisioner to invoke the az CLI command to deny the traffic after all of the provisions are finished.
az storage account update --name storage_account_name --resource-group reource_group_name --default-action 'Deny' --bypass 'AzureServices', 'Logging', 'Metrics'
Alternatively, you can separately configure the storage account network rules. You may need to allow your client's IP to access the storage account.
resource "azurerm_storage_account_network_rules" "test" {
resource_group_name = var.resourceGroupName
storage_account_name = azurerm_storage_account.func_sa.name
default_action = "Deny"
bypass = [
"Metrics",
"Logging",
"AzureServices"
]
ip_rules = ["x.x.x.x"]
depends_on = [
azurerm_storage_account.func_sa,
azurerm_app_service_plan.svc_plan,
azurerm_application_insights.func_ai,
azurerm_virtual_network.func_vnet,
azurerm_function_app.func
]
}
In addition, there is a possible solution for this similar case on Github.
I've had this issue in the past and found that it can be resolved as follows. I've tested this on v3.3.0 of the provider using the azurerm_windows_function_app resource. I think currently this is an Azure problem, in that it if you don't supply a share it will try and create one but will be denied. You'd expect this to work if Allow Azure services on the trusted services list to access this storage account is enabled, but webapps aren't trusted.
Create your storage account with IP rules and deny
Create a share within this for your function app content
within the function set the following configuration settings
WEBSITE_CONTENTAZUREFILECONNECTIONSTRING = <storage_account.primary_connection_string>
WEBSITE_CONTENTSHARE = <your share>
WEBSITE_CONTENTOVERVNET = 1
In the functions site configuration set the attribute vnet_route_all_enabled = true

Resources