Azure
/
prometheus-collector
зеркало из https://github.com/Azure/prometheus-collector.git
1
0
Форкнуть 0
Код Задачи Пакеты Проекты Релизы Вики Активность

Add terraform onboarding for prometheus addon (#469) 

* Add terraform onboarding for prometheus addon

* Add docs for terraform onboarding

* Rearrange folders

* Delete old folder structure

* update readme and other changes
This commit is contained in:
Sohamdg081992 2023-04-25 16:12:03 -07:00 коммит произвёл GitHub
Родитель 2eb2a81cbf
Коммит 3626f98957
Не найден ключ, соответствующий данной подписи
Идентификатор ключа GPG: 4AEE18F83AFDEB23
5 изменённых файлов: 566 добавлений и 0 удалений
Показать статистику Скачать Patch файл Скачать Diff файл Показать все файлы Свернуть все файлы

16
AddonTerraformTemplate/README.md Normal file
Просмотреть файл

@ -0,0 +1,16 @@
If you are deploying a new AKS cluster using Terraform with managed Prometheus addon enabled, follow the steps below.
1. Please download all files under AddonTerraformTemplate.
2. Run `terraform init -upgrade` to initialize the Terraform deployment.
3. Run `terraform plan -out main.tfplan` to initialize the Terraform deployment.
3. Run `terraform apply main.tfplan` to apply the execution plan to your cloud infrastructure.
Note: Pass the variables for `annotations_allowed` and `labels_allowed` keys only when those values exist. These are optional blocks.
**NOTE**
- Please edit the main.tf file appropriately before running the terraform template
- Please add in any existing azure_monitor_workspace_integrations values to the grafana resource before running the template otherwise the older values will get deleted and replaced with what is there in the template at the time of deployment
- Users with 'User Access Administrator' role in the subscription of the AKS cluster can be able to enable 'Monitoring Data Reader' role directly by deploying the template.
- Please edit the grafanaSku parameter if you are using a non standard SKU.
- Please run this template in the Grafana Resources RG.

445
AddonTerraformTemplate/main.tf Normal file
Просмотреть файл

@ -0,0 +1,445 @@
resource "azurerm_resource_group" "rg" {
location = var.resource_group_location
name = "defaultPrometheusOnboardingResourceGroup"
}
resource "azurerm_kubernetes_cluster" "k8s" {
location = azurerm_resource_group.rg.location
name = var.cluster_name
resource_group_name = azurerm_resource_group.rg.name
dns_prefix = var.dns_prefix
tags = {
Environment = "Development"
}
default_node_pool {
name = "agentpool"
vm_size = "Standard_D2_v2"
node_count = var.agent_count
}
monitor_metrics {
annotations_allowed = var.metric_annotations_allowlist
labels_allowed = var.metric_labels_allowlist
}
network_profile {
network_plugin = "kubenet"
load_balancer_sku = "standard"
}
identity {
type = "SystemAssigned"
}
}
resource "azurerm_monitor_data_collection_endpoint" "dce" {
name = "MSProm-${var.monitor_workspace_location}-${var.cluster_name}"
resource_group_name = azurerm_resource_group.rg.name
location = azurerm_resource_group.rg.location
kind = "Linux"
}
resource "azurerm_monitor_data_collection_rule" "dcr" {
name = "MSProm-${var.monitor_workspace_location}-${var.cluster_name}"
resource_group_name = azurerm_resource_group.rg.name
location = azurerm_resource_group.rg.location
data_collection_endpoint_id = azurerm_monitor_data_collection_endpoint.dce.id
kind = "Linux"
destinations {
monitor_account {
monitor_account_id = var.monitor_workspace_id
name = "MonitoringAccount1"
}
}
data_flow {
streams = ["Microsoft-PrometheusMetrics"]
destinations = ["MonitoringAccount1"]
}
data_sources {
prometheus_forwarder {
streams = ["Microsoft-PrometheusMetrics"]
name = "PrometheusDataSource"
}
}
description = "DCR for Azure Monitor Metrics Profile (Managed Prometheus)"
depends_on = [
azurerm_monitor_data_collection_endpoint.dce
]
}
resource "azurerm_monitor_data_collection_rule_association" "dcra" {
target_resource_id = azurerm_kubernetes_cluster.k8s.id
data_collection_endpoint_id = azurerm_monitor_data_collection_endpoint.dce.id
description = "Association of data collection rule. Deleting this association will break the data collection for this AKS Cluster."
}
resource "azurerm_dashboard_grafana" "grafana" {
name = "grafana-prometheus"
resource_group_name = azurerm_resource_group.rg.name
location = var.grafana_location
identity {
type = "SystemAssigned"
}
azure_monitor_workspace_integrations {
resource_id = var.monitor_workspace_id
}
}
resource "azurerm_role_assignment" "datareaderrole" {
scope = var.monitor_workspace_id
role_definition_id = "/subscriptions/${split("/",var.monitor_workspace_id)[2]}/providers/Microsoft.Authorization/roleDefinitions/b0d8363b-8ddd-447d-831f-62ca05bff136"
principal_id = azurerm_dashboard_grafana.grafana.identity.0.principal_id
}
resource "azapi_resource" "NodeRecordingRulesRuleGroup" {
type = "Microsoft.AlertsManagement/prometheusRuleGroups@2023-03-01"
name = "NodeRecordingRulesRuleGroup-${var.cluster_name}"
location = "eastus"
parent_id = azurerm_resource_group.rg.id
body = jsonencode({
"properties": {
"scopes": [
var.monitor_workspace_id
],
"clusterName": var.cluster_name,
"interval": "PT1M",
"rules": [
{
"record": "instance:node_num_cpu:sum",
"expression": "count without (cpu, mode) ( node_cpu_seconds_total{job=\"node\",mode=\"idle\"})"
},
{
"record": "instance:node_cpu_utilisation:rate5m",
"expression": "1 - avg without (cpu) ( sum without (mode) (rate(node_cpu_seconds_total{job=\"node\", mode=~\"idle|iowait|steal\"}[5m])))"
},
{
"record": "instance:node_load1_per_cpu:ratio",
"expression": "( node_load1{job=\"node\"}/ instance:node_num_cpu:sum{job=\"node\"})"
},
{
"record": "instance:node_memory_utilisation:ratio",
"expression": "1 - ( ( node_memory_MemAvailable_bytes{job=\"node\"} or ( node_memory_Buffers_bytes{job=\"node\"} + node_memory_Cached_bytes{job=\"node\"} + node_memory_MemFree_bytes{job=\"node\"} + node_memory_Slab_bytes{job=\"node\"} ) )/ node_memory_MemTotal_bytes{job=\"node\"})"
},
{
"record": "instance:node_vmstat_pgmajfault:rate5m",
"expression": "rate(node_vmstat_pgmajfault{job=\"node\"}[5m])"
},
{
"record": "instance_device:node_disk_io_time_seconds:rate5m",
"expression": "rate(node_disk_io_time_seconds_total{job=\"node\", device!=\"\"}[5m])"
},
{
"record": "instance_device:node_disk_io_time_weighted_seconds:rate5m",
"expression": "rate(node_disk_io_time_weighted_seconds_total{job=\"node\", device!=\"\"}[5m])"
},
{
"record": "instance:node_network_receive_bytes_excluding_lo:rate5m",
"expression": "sum without (device) ( rate(node_network_receive_bytes_total{job=\"node\", device!=\"lo\"}[5m]))"
},
{
"record": "instance:node_network_transmit_bytes_excluding_lo:rate5m",
"expression": "sum without (device) ( rate(node_network_transmit_bytes_total{job=\"node\", device!=\"lo\"}[5m]))"
},
{
"record": "instance:node_network_receive_drop_excluding_lo:rate5m",
"expression": "sum without (device) ( rate(node_network_receive_drop_total{job=\"node\", device!=\"lo\"}[5m]))"
},
{
"record": "instance:node_network_transmit_drop_excluding_lo:rate5m",
"expression": "sum without (device) ( rate(node_network_transmit_drop_total{job=\"node\", device!=\"lo\"}[5m]))"
}
]
}
})
schema_validation_enabled = false
ignore_missing_property = false
}
resource "azapi_resource" "KubernetesReccordingRulesRuleGroup" {
type = "Microsoft.AlertsManagement/prometheusRuleGroups@2023-03-01"
name = "KubernetesReccordingRulesRuleGroup-${var.cluster_name}"
location = azurerm_resource_group.rg.location
parent_id = azurerm_resource_group.rg.id
body = jsonencode({
"properties": {
"scopes": [
var.monitor_workspace_id
],
"clusterName": var.cluster_name,
"interval": "PT1M",
"rules": [
{
"record": "node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate",
"expression": "sum by (cluster, namespace, pod, container) ( irate(container_cpu_usage_seconds_total{job=\"cadvisor\", image!=\"\"}[5m])) * on (cluster, namespace, pod) group_left(node) topk by (cluster, namespace, pod) ( 1, max by(cluster, namespace, pod, node) (kube_pod_info{node!=\"\"}))"
},
{
"record": "node_namespace_pod_container:container_memory_working_set_bytes",
"expression": "container_memory_working_set_bytes{job=\"cadvisor\", image!=\"\"}* on (namespace, pod) group_left(node) topk by(namespace, pod) (1, max by(namespace, pod, node) (kube_pod_info{node!=\"\"}))"
},
{
"record": "node_namespace_pod_container:container_memory_rss",
"expression": "container_memory_rss{job=\"cadvisor\", image!=\"\"}* on (namespace, pod) group_left(node) topk by(namespace, pod) (1, max by(namespace, pod, node) (kube_pod_info{node!=\"\"}))"
},
{
"record": "node_namespace_pod_container:container_memory_cache",
"expression": "container_memory_cache{job=\"cadvisor\", image!=\"\"}* on (namespace, pod) group_left(node) topk by(namespace, pod) (1, max by(namespace, pod, node) (kube_pod_info{node!=\"\"}))"
},
{
"record": "node_namespace_pod_container:container_memory_swap",
"expression": "container_memory_swap{job=\"cadvisor\", image!=\"\"}* on (namespace, pod) group_left(node) topk by(namespace, pod) (1, max by(namespace, pod, node) (kube_pod_info{node!=\"\"}))"
},
{
"record": "cluster:namespace:pod_memory:active:kube_pod_container_resource_requests",
"expression": "kube_pod_container_resource_requests{resource=\"memory\",job=\"kube-state-metrics\"} * on (namespace, pod, cluster)group_left() max by (namespace, pod, cluster) ( (kube_pod_status_phase{phase=~\"Pending|Running\"} == 1))"
},
{
"record": "namespace_memory:kube_pod_container_resource_requests:sum",
"expression": "sum by (namespace, cluster) ( sum by (namespace, pod, cluster) ( max by (namespace, pod, container, cluster) ( kube_pod_container_resource_requests{resource=\"memory\",job=\"kube-state-metrics\"} ) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) ( kube_pod_status_phase{phase=~\"Pending|Running\"} == 1 ) ))"
},
{
"record": "cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests",
"expression": "kube_pod_container_resource_requests{resource=\"cpu\",job=\"kube-state-metrics\"} * on (namespace, pod, cluster)group_left() max by (namespace, pod, cluster) ( (kube_pod_status_phase{phase=~\"Pending|Running\"} == 1))"
},
{
"record": "namespace_cpu:kube_pod_container_resource_requests:sum",
"expression": "sum by (namespace, cluster) ( sum by (namespace, pod, cluster) ( max by (namespace, pod, container, cluster) ( kube_pod_container_resource_requests{resource=\"cpu\",job=\"kube-state-metrics\"} ) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) ( kube_pod_status_phase{phase=~\"Pending|Running\"} == 1 ) ))"
},
{
"record": "cluster:namespace:pod_memory:active:kube_pod_container_resource_limits",
"expression": "kube_pod_container_resource_limits{resource=\"memory\",job=\"kube-state-metrics\"} * on (namespace, pod, cluster)group_left() max by (namespace, pod, cluster) ( (kube_pod_status_phase{phase=~\"Pending|Running\"} == 1))"
},
{
"record": "namespace_memory:kube_pod_container_resource_limits:sum",
"expression": "sum by (namespace, cluster) ( sum by (namespace, pod, cluster) ( max by (namespace, pod, container, cluster) ( kube_pod_container_resource_limits{resource=\"memory\",job=\"kube-state-metrics\"} ) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) ( kube_pod_status_phase{phase=~\"Pending|Running\"} == 1 ) ))"
},
{
"record": "cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits",
"expression": "kube_pod_container_resource_limits{resource=\"cpu\",job=\"kube-state-metrics\"} * on (namespace, pod, cluster)group_left() max by (namespace, pod, cluster) ( (kube_pod_status_phase{phase=~\"Pending|Running\"} == 1) )"
},
{
"record": "namespace_cpu:kube_pod_container_resource_limits:sum",
"expression": "sum by (namespace, cluster) ( sum by (namespace, pod, cluster) ( max by (namespace, pod, container, cluster) ( kube_pod_container_resource_limits{resource=\"cpu\",job=\"kube-state-metrics\"} ) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) ( kube_pod_status_phase{phase=~\"Pending|Running\"} == 1 ) ))"
},
{
"record": "namespace_workload_pod:kube_pod_owner:relabel",
"expression": "max by (cluster, namespace, workload, pod) ( label_replace( label_replace( kube_pod_owner{job=\"kube-state-metrics\", owner_kind=\"ReplicaSet\"}, \"replicaset\", \"$1\", \"owner_name\", \"(.*)\" ) * on(replicaset, namespace) group_left(owner_name) topk by(replicaset, namespace) ( 1, max by (replicaset, namespace, owner_name) ( kube_replicaset_owner{job=\"kube-state-metrics\"} ) ), \"workload\", \"$1\", \"owner_name\", \"(.*)\" ))",
"labels": {
"workload_type": "deployment"
}
},
{
"record": "namespace_workload_pod:kube_pod_owner:relabel",
"expression": "max by (cluster, namespace, workload, pod) ( label_replace( kube_pod_owner{job=\"kube-state-metrics\", owner_kind=\"DaemonSet\"}, \"workload\", \"$1\", \"owner_name\", \"(.*)\" ))",
"labels": {
"workload_type": "daemonset"
}
},
{
"record": "namespace_workload_pod:kube_pod_owner:relabel",
"expression": "max by (cluster, namespace, workload, pod) ( label_replace( kube_pod_owner{job=\"kube-state-metrics\", owner_kind=\"StatefulSet\"}, \"workload\", \"$1\", \"owner_name\", \"(.*)\" ))",
"labels": {
"workload_type": "statefulset"
}
},
{
"record": "namespace_workload_pod:kube_pod_owner:relabel",
"expression": "max by (cluster, namespace, workload, pod) ( label_replace( kube_pod_owner{job=\"kube-state-metrics\", owner_kind=\"Job\"}, \"workload\", \"$1\", \"owner_name\", \"(.*)\" ))",
"labels": {
"workload_type": "job"
}
},
{
"record": ":node_memory_MemAvailable_bytes:sum",
"expression": "sum( node_memory_MemAvailable_bytes{job=\"node\"} or ( node_memory_Buffers_bytes{job=\"node\"} + node_memory_Cached_bytes{job=\"node\"} + node_memory_MemFree_bytes{job=\"node\"} + node_memory_Slab_bytes{job=\"node\"} )) by (cluster)"
},
{
"record": "cluster:node_cpu:ratio_rate5m",
"expression": "sum(rate(node_cpu_seconds_total{job=\"node\",mode!=\"idle\",mode!=\"iowait\",mode!=\"steal\"}[5m])) by (cluster) /count(sum(node_cpu_seconds_total{job=\"node\"}) by (cluster, instance, cpu)) by (cluster)"
}
]
}
})
schema_validation_enabled = false
ignore_missing_property = false
}
resource "azapi_resource" "NodeRecordingRulesRuleGroupWin" {
type = "Microsoft.AlertsManagement/prometheusRuleGroups@2023-03-01"
name = "NodeRecordingRulesRuleGroup-Win-${var.cluster_name}"
location = azurerm_resource_group.rg.location
parent_id = azurerm_resource_group.rg.id
body = jsonencode({
"properties": {
"scopes": [
var.monitor_workspace_id
],
"clusterName": var.cluster_name,
"interval": "PT1M",
"rules": [
{
"record": "node:windows_node:sum",
"expression": "count (windows_system_system_up_time{job=\"windows-exporter\"})"
},
{
"record": "node:windows_node_num_cpu:sum",
"expression": "count by (instance) (sum by (instance, core) (windows_cpu_time_total{job=\"windows-exporter\"}))"
},
{
"record": ":windows_node_cpu_utilisation:avg5m",
"expression": "1 - avg(rate(windows_cpu_time_total{job=\"windows-exporter\",mode=\"idle\"}[5m]))"
},
{
"record": "node:windows_node_cpu_utilisation:avg5m",
"expression": "1 - avg by (instance) (rate(windows_cpu_time_total{job=\"windows-exporter\",mode=\"idle\"}[5m]))"
},
{
"record": ":windows_node_memory_utilisation:",
"expression": "1 -sum(windows_memory_available_bytes{job=\"windows-exporter\"})/sum(windows_os_visible_memory_bytes{job=\"windows-exporter\"})"
},
{
"record": ":windows_node_memory_MemFreeCached_bytes:sum",
"expression": "sum(windows_memory_available_bytes{job=\"windows-exporter\"} + windows_memory_cache_bytes{job=\"windows-exporter\"})"
},
{
"record": "node:windows_node_memory_totalCached_bytes:sum",
"expression": "(windows_memory_cache_bytes{job=\"windows-exporter\"} + windows_memory_modified_page_list_bytes{job=\"windows-exporter\"} + windows_memory_standby_cache_core_bytes{job=\"windows-exporter\"} + windows_memory_standby_cache_normal_priority_bytes{job=\"windows-exporter\"} + windows_memory_standby_cache_reserve_bytes{job=\"windows-exporter\"})"
},
{
"record": ":windows_node_memory_MemTotal_bytes:sum",
"expression": "sum(windows_os_visible_memory_bytes{job=\"windows-exporter\"})"
},
{
"record": "node:windows_node_memory_bytes_available:sum",
"expression": "sum by (instance) ((windows_memory_available_bytes{job=\"windows-exporter\"}))"
},
{
"record": "node:windows_node_memory_bytes_total:sum",
"expression": "sum by (instance) (windows_os_visible_memory_bytes{job=\"windows-exporter\"})"
},
{
"record": "node:windows_node_memory_utilisation:ratio",
"expression": "(node:windows_node_memory_bytes_total:sum - node:windows_node_memory_bytes_available:sum) / scalar(sum(node:windows_node_memory_bytes_total:sum))"
},
{
"record": "node:windows_node_memory_utilisation:",
"expression": "1 - (node:windows_node_memory_bytes_available:sum / node:windows_node_memory_bytes_total:sum)"
},
{
"record": "node:windows_node_memory_swap_io_pages:irate",
"expression": "irate(windows_memory_swap_page_operations_total{job=\"windows-exporter\"}[5m])"
},
{
"record": ":windows_node_disk_utilisation:avg_irate",
"expression": "avg(irate(windows_logical_disk_read_seconds_total{job=\"windows-exporter\"}[5m]) + irate(windows_logical_disk_write_seconds_total{job=\"windows-exporter\"}[5m]))"
},
{
"record": "node:windows_node_disk_utilisation:avg_irate",
"expression": "avg by (instance) ((irate(windows_logical_disk_read_seconds_total{job=\"windows-exporter\"}[5m]) + irate(windows_logical_disk_write_seconds_total{job=\"windows-exporter\"}[5m])))"
}
]
}
})
schema_validation_enabled = false
ignore_missing_property = false
}
resource "azapi_resource" "NodeAndKubernetesRecordingRulesRuleGroupWin" {
type = "Microsoft.AlertsManagement/prometheusRuleGroups@2023-03-01"
name = "NodeAndKubernetesRecordingRulesRuleGroup-Win-${var.cluster_name}"
location = azurerm_resource_group.rg.location
parent_id = azurerm_resource_group.rg.id
body = jsonencode({
"properties": {
"scopes": [
var.monitor_workspace_id
],
"clusterName": "[variables('clusterName')]",
"interval": "PT1M",
"rules": [
{
"record": "node:windows_node_filesystem_usage:",
"expression": "max by (instance,volume)((windows_logical_disk_size_bytes{job=\"windows-exporter\"} - windows_logical_disk_free_bytes{job=\"windows-exporter\"}) / windows_logical_disk_size_bytes{job=\"windows-exporter\"})"
},
{
"record": "node:windows_node_filesystem_avail:",
"expression": "max by (instance, volume) (windows_logical_disk_free_bytes{job=\"windows-exporter\"} / windows_logical_disk_size_bytes{job=\"windows-exporter\"})"
},
{
"record": ":windows_node_net_utilisation:sum_irate",
"expression": "sum(irate(windows_net_bytes_total{job=\"windows-exporter\"}[5m]))"
},
{
"record": "node:windows_node_net_utilisation:sum_irate",
"expression": "sum by (instance) ((irate(windows_net_bytes_total{job=\"windows-exporter\"}[5m])))"
},
{
"record": ":windows_node_net_saturation:sum_irate",
"expression": "sum(irate(windows_net_packets_received_discarded_total{job=\"windows-exporter\"}[5m])) + sum(irate(windows_net_packets_outbound_discarded_total{job=\"windows-exporter\"}[5m]))"
},
{
"record": "node:windows_node_net_saturation:sum_irate",
"expression": "sum by (instance) ((irate(windows_net_packets_received_discarded_total{job=\"windows-exporter\"}[5m]) + irate(windows_net_packets_outbound_discarded_total{job=\"windows-exporter\"}[5m])))"
},
{
"record": "windows_pod_container_available",
"expression": "windows_container_available{job=\"windows-exporter\"} * on(container_id) group_left(container, pod, namespace) max(kube_pod_container_info{job=\"kube-state-metrics\"}) by(container, container_id, pod, namespace)"
},
{
"record": "windows_container_total_runtime",
"expression": "windows_container_cpu_usage_seconds_total{job=\"windows-exporter\"} * on(container_id) group_left(container, pod, namespace) max(kube_pod_container_info{job=\"kube-state-metrics\"}) by(container, container_id, pod, namespace)"
},
{
"record": "windows_container_memory_usage",
"expression": "windows_container_memory_usage_commit_bytes{job=\"windows-exporter\"} * on(container_id) group_left(container, pod, namespace) max(kube_pod_container_info{job=\"kube-state-metrics\"}) by(container, container_id, pod, namespace)"
},
{
"record": "windows_container_private_working_set_usage",
"expression": "windows_container_memory_usage_private_working_set_bytes{job=\"windows-exporter\"} * on(container_id) group_left(container, pod, namespace) max(kube_pod_container_info{job=\"kube-state-metrics\"}) by(container, container_id, pod, namespace)"
},
{
"record": "windows_container_network_received_bytes_total",
"expression": "windows_container_network_receive_bytes_total{job=\"windows-exporter\"} * on(container_id) group_left(container, pod, namespace) max(kube_pod_container_info{job=\"kube-state-metrics\"}) by(container, container_id, pod, namespace)"
},
{
"record": "windows_container_network_transmitted_bytes_total",
"expression": "windows_container_network_transmit_bytes_total{job=\"windows-exporter\"} * on(container_id) group_left(container, pod, namespace) max(kube_pod_container_info{job=\"kube-state-metrics\"}) by(container, container_id, pod, namespace)"
},
{
"record": "kube_pod_windows_container_resource_memory_request",
"expression": "max by (namespace, pod, container) (kube_pod_container_resource_requests{resource=\"memory\",job=\"kube-state-metrics\"}) * on(container,pod,namespace) (windows_pod_container_available)"
},
{
"record": "kube_pod_windows_container_resource_memory_limit",
"expression": "kube_pod_container_resource_limits{resource=\"memory\",job=\"kube-state-metrics\"} * on(container,pod,namespace) (windows_pod_container_available)"
},
{
"record": "kube_pod_windows_container_resource_cpu_cores_request",
"expression": "max by (namespace, pod, container) ( kube_pod_container_resource_requests{resource=\"cpu\",job=\"kube-state-metrics\"}) * on(container,pod,namespace) (windows_pod_container_available)"
},
{
"record": "kube_pod_windows_container_resource_cpu_cores_limit",
"expression": "kube_pod_container_resource_limits{resource=\"cpu\",job=\"kube-state-metrics\"} * on(container,pod,namespace) (windows_pod_container_available)"
},
{
"record": "namespace_pod_container:windows_container_cpu_usage_seconds_total:sum_rate",
"expression": "sum by (namespace, pod, container) (rate(windows_container_total_runtime{}[5m]))"
}
]
}
})
schema_validation_enabled = false
ignore_missing_property = false
}

38
AddonTerraformTemplate/outputs.tf Normal file
Просмотреть файл

@ -0,0 +1,38 @@
output "client_certificate" {
value = azurerm_kubernetes_cluster.k8s.kube_config[0].client_certificate
sensitive = true
}
output "client_key" {
value = azurerm_kubernetes_cluster.k8s.kube_config[0].client_key
sensitive = true
}
output "cluster_ca_certificate" {
value = azurerm_kubernetes_cluster.k8s.kube_config[0].cluster_ca_certificate
sensitive = true
}
output "cluster_password" {
value = azurerm_kubernetes_cluster.k8s.kube_config[0].password
sensitive = true
}
output "cluster_username" {
value = azurerm_kubernetes_cluster.k8s.kube_config[0].username
sensitive = true
}
output "host" {
value = azurerm_kubernetes_cluster.k8s.kube_config[0].host
sensitive = true
}
output "kube_config" {
value = azurerm_kubernetes_cluster.k8s.kube_config_raw
sensitive = true
}
output "resource_group_name" {
value = azurerm_resource_group.rg.name
}

24
AddonTerraformTemplate/providers.tf Normal file
Просмотреть файл

@ -0,0 +1,24 @@
terraform {
required_providers {
azapi = {
source = "azure/azapi"
version = "=0.1.0"
}
azurerm = {
source = "hashicorp/azurerm"
version = "~>3.0"
}
}
}
provider "azapi" {
default_location = "eastus"
default_tags = {
team = "Azure deployments"
}
}
provider "azurerm" {
features {}
}

43
AddonTerraformTemplate/variables.tf Normal file
Просмотреть файл

@ -0,0 +1,43 @@
variable "agent_count" {
default = 3
}
variable "cluster_name" {
default = "k8stest"
}
variable "cluster_location" {
default = "eastus"
}
variable "metric_labels_allowlist" {
default = "optional"
}
variable "metric_annotations_allowlist" {
default = "optional"
}
variable "dns_prefix" {
default = "k8stest"
}
variable "monitor_workspace_id" {
default = "/subscriptions/{sub_id}/resourceGroups/{rg_name}/providers/microsoft.monitor/accounts/{amw_name}"
}
variable "grafana_sku" {
default = "Standard"
}
variable "grafana_location" {
default = "eastus"
}
variable "monitor_workspace_location" {
default = "eastus"
}
variable "resource_group_location" {
default = "eastus"
description = "Location of the resource group."
}