Onboard Managed Prometheus per stamp (#755)
* add prometheus * add missing provider * add missing provider block * add provider block * add a dependency * fix * adding dcra * add missing provider blocks * add missing provider block * export properties * rename and move rule * fix broken reference * fix * update * add monitor_metrics * update azurerm from 3.34 to 3.37 * change endpoint id * change dataCollectionRuleId * rename prometheus az mon workspace * automate monitoring data reader permissions * renaming components * rename state store (#774) (#775) * align version updates * bump * fix * test workload group * adding parent back * adding another rule * bump docs * add second rule group * bugfix * add diagram * Update `feature/managedprom` from `main` (#886) * Component updates 03.03.2023 (#882) * Bump azure/azapi in /src/testing/loadtest-azure/infra Bumps [azure/azapi](https://github.com/Azure/terraform-provider-azapi) from 1.3.0 to 1.4.0. - [Release notes](https://github.com/Azure/terraform-provider-azapi/releases) - [Changelog](https://github.com/Azure/terraform-provider-azapi/blob/main/CHANGELOG.md) - [Commits](https://github.com/Azure/terraform-provider-azapi/compare/v1.3.0...v1.4.0) --- updated-dependencies: - dependency-name: azure/azapi dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * Bump playwright-chromium Bumps [playwright-chromium](https://github.com/Microsoft/playwright) from 1.30.0 to 1.31.1. - [Release notes](https://github.com/Microsoft/playwright/releases) - [Commits](https://github.com/Microsoft/playwright/compare/v1.30.0...v1.31.1) --- updated-dependencies: - dependency-name: playwright-chromium dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * Bump hashicorp/azurerm in /src/testing/loadtest-azure/infra Bumps [hashicorp/azurerm](https://github.com/hashicorp/terraform-provider-azurerm) from 3.41.0 to 3.45.0. - [Release notes](https://github.com/hashicorp/terraform-provider-azurerm/releases) - [Changelog](https://github.com/hashicorp/terraform-provider-azurerm/blob/main/CHANGELOG.md) - [Commits](https://github.com/hashicorp/terraform-provider-azurerm/compare/v3.41.0...v3.45.0) --- updated-dependencies: - dependency-name: hashicorp/azurerm dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * Bump Azure.Storage.Blobs in /src/app/AlwaysOn.Tests Bumps [Azure.Storage.Blobs](https://github.com/Azure/azure-sdk-for-net) from 12.14.1 to 12.15.0. - [Release notes](https://github.com/Azure/azure-sdk-for-net/releases) - [Commits](https://github.com/Azure/azure-sdk-for-net/compare/Azure.Storage.Blobs_12.14.1...Azure.Storage.Blobs_12.15.0) --- updated-dependencies: - dependency-name: Azure.Storage.Blobs dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * Bump node from 19.5.0 to 19.7.0 in /src/app/AlwaysOn.UI Bumps node from 19.5.0 to 19.7.0. --- updated-dependencies: - dependency-name: node dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * Bump Azure.Data.Tables in /src/app/AlwaysOn.BackgroundProcessor Bumps [Azure.Data.Tables](https://github.com/Azure/azure-sdk-for-net) from 12.7.1 to 12.8.0. - [Release notes](https://github.com/Azure/azure-sdk-for-net/releases) - [Commits](https://github.com/Azure/azure-sdk-for-net/compare/Azure.Data.Tables_12.7.1...Azure.Data.Tables_12.8.0) --- updated-dependencies: - dependency-name: Azure.Data.Tables dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * Bump Microsoft.Azure.Cosmos in /src/app/AlwaysOn.Shared Bumps [Microsoft.Azure.Cosmos](https://github.com/Azure/azure-cosmos-dotnet-v3) from 3.31.2 to 3.32.0. - [Release notes](https://github.com/Azure/azure-cosmos-dotnet-v3/releases) - [Changelog](https://github.com/Azure/azure-cosmos-dotnet-v3/blob/master/changelog.md) - [Commits](https://github.com/Azure/azure-cosmos-dotnet-v3/compare/3.31.2...3.32.0) --- updated-dependencies: - dependency-name: Microsoft.Azure.Cosmos dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * Bump Azure.Identity in /src/app/AlwaysOn.HealthService Bumps [Azure.Identity](https://github.com/Azure/azure-sdk-for-net) from 1.8.1 to 1.8.2. - [Release notes](https://github.com/Azure/azure-sdk-for-net/releases) - [Commits](https://github.com/Azure/azure-sdk-for-net/compare/Azure.Identity_1.8.1...Azure.Identity_1.8.2) --- updated-dependencies: - dependency-name: Azure.Identity dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> * Bump hashicorp/azurerm Bumps [hashicorp/azurerm](https://github.com/hashicorp/terraform-provider-azurerm) from 3.41.0 to 3.46.0. - [Release notes](https://github.com/hashicorp/terraform-provider-azurerm/releases) - [Changelog](https://github.com/hashicorp/terraform-provider-azurerm/blob/main/CHANGELOG.md) - [Commits](https://github.com/hashicorp/terraform-provider-azurerm/compare/v3.41.0...v3.46.0) --- updated-dependencies: - dependency-name: hashicorp/azurerm dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * Bump Microsoft.Extensions.Hosting Bumps [Microsoft.Extensions.Hosting](https://github.com/dotnet/runtime) from 7.0.0 to 7.0.1. - [Release notes](https://github.com/dotnet/runtime/releases) - [Commits](https://github.com/dotnet/runtime/compare/v7.0.0...v7.0.1) --- updated-dependencies: - dependency-name: Microsoft.Extensions.Hosting dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> * Bump hashicorp/azurerm in /src/infra/monitoring/grafana/terraform/stamps Bumps [hashicorp/azurerm](https://github.com/hashicorp/terraform-provider-azurerm) from 3.41.0 to 3.46.0. - [Release notes](https://github.com/hashicorp/terraform-provider-azurerm/releases) - [Changelog](https://github.com/hashicorp/terraform-provider-azurerm/blob/main/CHANGELOG.md) - [Commits](https://github.com/hashicorp/terraform-provider-azurerm/compare/v3.41.0...v3.46.0) --- updated-dependencies: - dependency-name: hashicorp/azurerm dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * Bump vue from 3.2.45 to 3.2.47 in /src/app/AlwaysOn.UI Bumps [vue](https://github.com/vuejs/core) from 3.2.45 to 3.2.47. - [Release notes](https://github.com/vuejs/core/releases) - [Changelog](https://github.com/vuejs/core/blob/main/CHANGELOG.md) - [Commits](https://github.com/vuejs/core/compare/v3.2.45...v3.2.47) --- updated-dependencies: - dependency-name: vue dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> * Bump hashicorp/azurerm in /src/testing/userload-generator/infra Bumps [hashicorp/azurerm](https://github.com/hashicorp/terraform-provider-azurerm) from 3.41.0 to 3.46.0. - [Release notes](https://github.com/hashicorp/terraform-provider-azurerm/releases) - [Changelog](https://github.com/hashicorp/terraform-provider-azurerm/blob/main/CHANGELOG.md) - [Commits](https://github.com/hashicorp/terraform-provider-azurerm/compare/v3.41.0...v3.46.0) --- updated-dependencies: - dependency-name: hashicorp/azurerm dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * Bump hashicorp/azurerm in /src/testing/loadtest-locust/infra Bumps [hashicorp/azurerm](https://github.com/hashicorp/terraform-provider-azurerm) from 3.41.0 to 3.46.0. - [Release notes](https://github.com/hashicorp/terraform-provider-azurerm/releases) - [Changelog](https://github.com/hashicorp/terraform-provider-azurerm/blob/main/CHANGELOG.md) - [Commits](https://github.com/hashicorp/terraform-provider-azurerm/compare/v3.41.0...v3.46.0) --- updated-dependencies: - dependency-name: hashicorp/azurerm dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * Bump Microsoft.Azure.WebJobs.Extensions.DurableTask Bumps [Microsoft.Azure.WebJobs.Extensions.DurableTask](https://github.com/Azure/azure-functions-durable-extension) from 2.9.0 to 2.9.2. - [Release notes](https://github.com/Azure/azure-functions-durable-extension/releases) - [Changelog](https://github.com/Azure/azure-functions-durable-extension/blob/dev/azure-pipelines-release.yml) - [Commits](https://github.com/Azure/azure-functions-durable-extension/compare/v2.9.0...v2.9.2) --- updated-dependencies: - dependency-name: Microsoft.Azure.WebJobs.Extensions.DurableTask dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> * Bump actions/checkout from 2 to 3 Bumps [actions/checkout](https://github.com/actions/checkout) from 2 to 3. - [Release notes](https://github.com/actions/checkout/releases) - [Changelog](https://github.com/actions/checkout/blob/main/CHANGELOG.md) - [Commits](https://github.com/actions/checkout/compare/v2...v3) --- updated-dependencies: - dependency-name: actions/checkout dependency-type: direct:production update-type: version-update:semver-major ... Signed-off-by: dependabot[bot] <support@github.com> * Bump Microsoft.Extensions.Diagnostics.HealthChecks.Abstractions Bumps [Microsoft.Extensions.Diagnostics.HealthChecks.Abstractions](https://github.com/dotnet/aspnetcore) from 7.0.2 to 7.0.3. - [Release notes](https://github.com/dotnet/aspnetcore/releases) - [Changelog](https://github.com/dotnet/aspnetcore/blob/main/docs/ReleasePlanning.md) - [Commits](https://github.com/dotnet/aspnetcore/compare/v7.0.2...v7.0.3) --- updated-dependencies: - dependency-name: Microsoft.Extensions.Diagnostics.HealthChecks.Abstractions dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> * Bump Microsoft.Azure.Cosmos in /src/app/AlwaysOn.CatalogService Bumps [Microsoft.Azure.Cosmos](https://github.com/Azure/azure-cosmos-dotnet-v3) from 3.32.0 to 3.32.1. - [Release notes](https://github.com/Azure/azure-cosmos-dotnet-v3/releases) - [Changelog](https://github.com/Azure/azure-cosmos-dotnet-v3/blob/master/changelog.md) - [Commits](https://github.com/Azure/azure-cosmos-dotnet-v3/compare/3.32.0...3.32.1) --- updated-dependencies: - dependency-name: Microsoft.Azure.Cosmos dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> * Bump hashicorp/azurerm in /src/infra/workload/globalresources Bumps [hashicorp/azurerm](https://github.com/hashicorp/terraform-provider-azurerm) from 3.41.0 to 3.46.0. - [Release notes](https://github.com/hashicorp/terraform-provider-azurerm/releases) - [Changelog](https://github.com/hashicorp/terraform-provider-azurerm/blob/main/CHANGELOG.md) - [Commits](https://github.com/hashicorp/terraform-provider-azurerm/compare/v3.41.0...v3.46.0) --- updated-dependencies: - dependency-name: hashicorp/azurerm dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * Bump playwright-core Bumps [playwright-core](https://github.com/Microsoft/playwright) from 1.30.0 to 1.31.2. - [Release notes](https://github.com/Microsoft/playwright/releases) - [Commits](https://github.com/Microsoft/playwright/compare/v1.30.0...v1.31.2) --- updated-dependencies: - dependency-name: playwright-core dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * Bump Azure.Storage.Blobs in /src/app/AlwaysOn.HealthService Bumps [Azure.Storage.Blobs](https://github.com/Azure/azure-sdk-for-net) from 12.14.1 to 12.15.0. - [Release notes](https://github.com/Azure/azure-sdk-for-net/releases) - [Commits](https://github.com/Azure/azure-sdk-for-net/compare/Azure.Storage.Blobs_12.14.1...Azure.Storage.Blobs_12.15.0) --- updated-dependencies: - dependency-name: Azure.Storage.Blobs dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * Bump Azure.Identity from 1.8.1 to 1.8.2 in /src/app/AlwaysOn.Tests Bumps [Azure.Identity](https://github.com/Azure/azure-sdk-for-net) from 1.8.1 to 1.8.2. - [Release notes](https://github.com/Azure/azure-sdk-for-net/releases) - [Commits](https://github.com/Azure/azure-sdk-for-net/compare/Azure.Identity_1.8.1...Azure.Identity_1.8.2) --- updated-dependencies: - dependency-name: Azure.Identity dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> * Bump @microsoft/applicationinsights-web in /src/app/AlwaysOn.UI Bumps [@microsoft/applicationinsights-web](https://github.com/microsoft/ApplicationInsights-JS) from 2.8.9 to 2.8.10. - [Release notes](https://github.com/microsoft/ApplicationInsights-JS/releases) - [Changelog](https://github.com/microsoft/ApplicationInsights-JS/blob/master/RELEASES.md) - [Commits](https://github.com/microsoft/ApplicationInsights-JS/commits) --- updated-dependencies: - dependency-name: "@microsoft/applicationinsights-web" dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> * Bump Azure.Identity in /src/app/AlwaysOn.BackgroundProcessor Bumps [Azure.Identity](https://github.com/Azure/azure-sdk-for-net) from 1.8.1 to 1.8.2. - [Release notes](https://github.com/Azure/azure-sdk-for-net/releases) - [Commits](https://github.com/Azure/azure-sdk-for-net/compare/Azure.Identity_1.8.1...Azure.Identity_1.8.2) --- updated-dependencies: - dependency-name: Azure.Identity dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> * Bump NUnit3TestAdapter from 4.3.1 to 4.4.2 in /src/app/AlwaysOn.Tests Bumps [NUnit3TestAdapter](https://github.com/nunit/nunit3-vs-adapter) from 4.3.1 to 4.4.2. - [Release notes](https://github.com/nunit/nunit3-vs-adapter/releases) - [Commits](https://github.com/nunit/nunit3-vs-adapter/compare/V4.3.1...V4.4.2) --- updated-dependencies: - dependency-name: NUnit3TestAdapter dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * Bump hashicorp/azurerm in /src/infra/workload/releaseunit Bumps [hashicorp/azurerm](https://github.com/hashicorp/terraform-provider-azurerm) from 3.41.0 to 3.46.0. - [Release notes](https://github.com/hashicorp/terraform-provider-azurerm/releases) - [Changelog](https://github.com/hashicorp/terraform-provider-azurerm/blob/main/CHANGELOG.md) - [Commits](https://github.com/hashicorp/terraform-provider-azurerm/compare/v3.41.0...v3.46.0) --- updated-dependencies: - dependency-name: hashicorp/azurerm dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * Bump @playwright/test Bumps [@playwright/test](https://github.com/Microsoft/playwright) from 1.30.0 to 1.31.2. - [Release notes](https://github.com/Microsoft/playwright/releases) - [Commits](https://github.com/Microsoft/playwright/compare/v1.30.0...v1.31.2) --- updated-dependencies: - dependency-name: "@playwright/test" dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * Bump Microsoft.NET.Test.Sdk in /src/app/AlwaysOn.Tests Bumps [Microsoft.NET.Test.Sdk](https://github.com/microsoft/vstest) from 17.4.0 to 17.5.0. - [Release notes](https://github.com/microsoft/vstest/releases) - [Changelog](https://github.com/microsoft/vstest/blob/main/docs/releases.md) - [Commits](https://github.com/microsoft/vstest/compare/v17.4.0...v17.5.0) --- updated-dependencies: - dependency-name: Microsoft.NET.Test.Sdk dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * bump * Bump grafana/grafana in /src/infra/monitoring/grafana (#842) Bumps grafana/grafana from 9.3.6 to 9.4.1. --- updated-dependencies: - dependency-name: grafana/grafana dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Bump minimist (#883) Bumps [minimist](https://github.com/minimistjs/minimist) from 1.2.5 to 1.2.8. - [Release notes](https://github.com/minimistjs/minimist/releases) - [Changelog](https://github.com/minimistjs/minimist/blob/main/CHANGELOG.md) - [Commits](https://github.com/minimistjs/minimist/compare/v1.2.5...v1.2.8) --- updated-dependencies: - dependency-name: minimist dependency-type: indirect ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * workload identity note (#885) --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Hansjoerg Scherer <hjscherer@users.noreply.github.com> * bump tf versions * bump * update provider * add azapi to root module * update diag settings block * add azapi * drop enabled --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Hansjoerg Scherer <hjscherer@users.noreply.github.com>
This commit is contained in:
heoelri
GitHub
Родитель
bb028805e0
Коммит
34ad577333
Двоичный файл не отображается.
|
После Ширина: | Высота: | Размер: 187 KiB |
|
|
@ -0,0 +1,43 @@
|
|||
# Managed Prometheus in Azure Mission-critical
|
||||
|
||||
The Azure Mission-Critical reference implementation implements a wide variety of monitoring and observability capabilities and best practices. It uses regional and global Log Analytics workspaces to store logs and metrics, decoupled from the ephemeral nature and lifecycle of it's stamps, it contains an instrumented sample application workload using Application Insights for in-depth application metrics and distributed traces, uses a health service to evaluate and report the status of each of its deployed stamps and uses a self-hosted instance of Grafana to visualize the user and system flows and provide actionable insights into the overall health status of the workload. This is a good start, but might not be detailed enough for production workloads.
|
||||
|
||||
To further improve the observability capabilities of a mission-critical workload build based on top of a Azure Mission-Critical reference implementation, Prometheus can be used to gain more granular metrics from the infrastructure as well as from the workload.
|
||||
|
||||
> **Prometheus** is an open-source monitoring solution that enables you to collect metrics from various systems, applications, and services. It allows you to query and visualize your data, alert on critical conditions, and understand the performance and behavior of your infrastructure. It is built with a focus on scalability, reliability, and simplicity, making it a popular choice for monitoring large and complex systems.
|
||||
|
||||
## Why Prometheus?
|
||||
|
||||
Azure Mission-Critical follows a cloud-native-first, PaaS-first approach. Whenever possible should PaaS and cloud-native services be prioritized when designing, developing or modernizing a workload on Azure. These cloud-native, and several PaaS services have one thing in common, they provide prometheus metrics. To call out a few examples, AKS is using Kubernetes, Kubernetes provides Prometheus metrics on various levels like the control plane and the nodes (kubelet) but also its services like cert-manager, open service mesh and nginx (and of course many more) provide prometheus metric endpoints.
|
||||
|
||||
As the examples above show, Prometheus, Prometheus metrics and especially the Prometheus Query Language (PromQL) are well-established standards in the cloud native space. The existing Azure Monitor add-on for Azure Kubernetes Service already supported scraping prometheus metrics from endpoints within a cluster and stored them in Log Analytics. Azure Monitor Workspace now supports also PromQL which makes it easier to use across environments and platforms.
|
||||
|
||||
## Managed Prometheus
|
||||
|
||||
To use Prometheus you could already have deployed a Prometheus server on your own to scrape the metrics endpoints and provide the data to visualization tools like Grafana. But Prometheus is a beast by itself, you've to take care of the infrastructure, operations, maintenance and so on. This was now made easier with the availability of the **Azure Monitor managed service for Prometheus**. This managed service offering is compliant with the open-source project prometheus, but it abstracts the underlying infrastructure away. It consists of the following components:
|
||||
|
||||
- The 'ama-agent' is deployed on Kubernetes to gather the metrics.
|
||||
- An **Azure Monitor workspace** where the collected data is stored.
|
||||
- **Data collection rules** to determine what data to collect.
|
||||
- **Data collection endpoints** define the target to sent the data to for analysis and storage.
|
||||
- **Data collection rule associations** to link rules and resources they apply to.
|
||||
|
||||
This once set up provides you with a query endpoint that can be leveraged by for example Grafana to feed dashboards.
|
||||
|
||||
## How to fit Prometheus into Azure Mission-Critical?
|
||||
|
||||
You might wonder how these additional resources are getting deployed and where to put them. The answer is easy, the mission-critical architecture pattern separates between global and regional components as well as between stateful and stateless components.
|
||||
|
||||
The Azure Monitor workspace that stores the collected data is getting deployed into the `<prefix>-monitoring-rg`. One instance per region used.
|
||||
|
||||
The other resources, like the Data collection rule, endpoint and rule association is deployed alongside the regional stamps. They're ephemeral and share the same lifecycle as the stamp. When a new stamp is getting deployed, new rules, endpoints and associations are deployed and the old ones are getting destroyed.
|
||||
See [Data considerations in Azure Monitor workspace overview](https://learn.microsoft.com/azure/azure-monitor/essentials/azure-monitor-workspace-overview#data-considerations) for more information.
|
||||
|
||||
|
||||
## How to access the data?
|
||||
|
||||
The data can be visualized and queried via Grafana. The Azure Monitor workspace, deployed per-region, can be added as additional data sources to Grafana. When using the Grafana deployment in Azure Mission-Critical, the App Service instance used to host Grafana can be granted access to the Azure Monitor workspace via the built-in role "Monitoring Data Reader".
|
||||
|
||||
---
|
||||
|
||||
[Azure Mission-Critical - Full List of Documentation](/docs/README.md)
|
||||
|
|
@ -12,4 +12,12 @@ resource "azurerm_role_assignment" "loganalyticsreader_role" {
|
|||
scope = data.azurerm_subscription.current.id
|
||||
role_definition_name = "Log Analytics Reader"
|
||||
principal_id = azurerm_linux_web_app.appservice[each.key].identity[0].principal_id
|
||||
}
|
||||
|
||||
# Permission for Grafana to read from all Azure Monitor workspaces in the subscription
|
||||
resource "azurerm_role_assignment" "loganalyticsreader_role" {
|
||||
for_each = local.stamps
|
||||
scope = data.azurerm_subscription.current.id
|
||||
role_definition_name = "Monitoring Data Reader"
|
||||
principal_id = azurerm_linux_web_app.appservice[each.key].identity[0].principal_id
|
||||
}
|
||||
|
|
@ -31,13 +31,12 @@ resource "azurerm_monitor_diagnostic_setting" "acr" {
|
|||
target_resource_id = azurerm_container_registry.main.id
|
||||
log_analytics_workspace_id = azurerm_log_analytics_workspace.global.id
|
||||
|
||||
dynamic "log" {
|
||||
dynamic "enabled_log" {
|
||||
iterator = entry
|
||||
for_each = data.azurerm_monitor_diagnostic_categories.acr.log_category_types
|
||||
|
||||
content {
|
||||
category = entry.value
|
||||
enabled = true
|
||||
|
||||
retention_policy {
|
||||
enabled = true
|
||||
|
|
|
|||
|
|
@ -4,6 +4,10 @@ terraform {
|
|||
source = "hashicorp/azurerm"
|
||||
version = "3.61.0"
|
||||
}
|
||||
azapi = {
|
||||
source = "Azure/azapi"
|
||||
version = "1.5.0"
|
||||
}
|
||||
}
|
||||
|
||||
backend "azurerm" {
|
||||
|
|
@ -23,6 +27,8 @@ provider "azurerm" {
|
|||
}
|
||||
}
|
||||
|
||||
provider "azapi" {}
|
||||
|
||||
resource "azurerm_resource_group" "global" {
|
||||
name = "${local.prefix}-global-rg"
|
||||
location = local.location
|
||||
|
|
|
|||
|
|
@ -0,0 +1,12 @@
|
|||
terraform {
|
||||
required_providers {
|
||||
azurerm = {
|
||||
source = "hashicorp/azurerm"
|
||||
version = "3.61.0"
|
||||
}
|
||||
azapi = {
|
||||
source = "Azure/azapi"
|
||||
version = "1.5.0"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
|
@ -1,3 +1,7 @@
|
|||
output "log_analytics_workspace_id" {
|
||||
value = azurerm_log_analytics_workspace.stamp.workspace_id
|
||||
}
|
||||
}
|
||||
|
||||
output "azure_monitor_workspace_id" {
|
||||
value = azapi_resource.prometheus.id
|
||||
}
|
||||
|
|
|
|||
|
|
@ -0,0 +1,8 @@
|
|||
resource "azapi_resource" "prometheus" {
|
||||
type = "microsoft.monitor/accounts@2021-06-03-preview"
|
||||
name = "${local.prefix}-${local.location_short}-prometheus"
|
||||
parent_id = var.resource_group_id
|
||||
location = var.location
|
||||
|
||||
response_export_values = ["*"]
|
||||
}
|
||||
|
|
@ -13,6 +13,11 @@ variable "resource_group_name" {
|
|||
type = string
|
||||
}
|
||||
|
||||
variable "resource_group_id" {
|
||||
description = "Resource Group Id"
|
||||
type = string
|
||||
}
|
||||
|
||||
variable "azure_monitor_action_group_resource_id" {
|
||||
description = "Resource ID of a Azure Monitor action group to send alerts to"
|
||||
type = string
|
||||
|
|
|
|||
|
|
@ -11,6 +11,7 @@ module "stamp_monitoring" {
|
|||
|
||||
location = each.value
|
||||
prefix = local.prefix
|
||||
resource_group_id = azurerm_resource_group.monitoring.id
|
||||
resource_group_name = azurerm_resource_group.monitoring.name
|
||||
azure_monitor_action_group_resource_id = azurerm_monitor_action_group.main.id
|
||||
alerts_enabled = var.alerts_enabled
|
||||
|
|
|
|||
|
|
@ -4,6 +4,10 @@ terraform {
|
|||
source = "hashicorp/azurerm"
|
||||
version = "3.61.0"
|
||||
}
|
||||
azapi = {
|
||||
source = "Azure/azapi"
|
||||
version = "1.5.0"
|
||||
}
|
||||
}
|
||||
|
||||
backend "azurerm" {}
|
||||
|
|
@ -19,6 +23,8 @@ provider "azurerm" {
|
|||
}
|
||||
}
|
||||
|
||||
provider "azapi" {}
|
||||
|
||||
# Random API key which needs to be identical between all stamps
|
||||
resource "random_password" "api_key" {
|
||||
length = 32
|
||||
|
|
|
|||
|
|
@ -5,6 +5,18 @@ data "azurerm_cosmosdb_account" "global" {
|
|||
resource_group_name = var.global_resource_group_name
|
||||
}
|
||||
|
||||
data "azurerm_resource_group" "monitoring" {
|
||||
name = var.monitoring_resource_group_name
|
||||
}
|
||||
|
||||
data "azapi_resource" "prometheus" {
|
||||
name = "${local.prefix}-${local.location_short}-prometheus"
|
||||
type = "microsoft.monitor/accounts@2021-06-03-preview"
|
||||
parent_id = data.azurerm_resource_group.monitoring.id
|
||||
|
||||
response_export_values = ["*"]
|
||||
}
|
||||
|
||||
data "azurerm_container_registry" "global" {
|
||||
name = var.acr_name
|
||||
resource_group_name = var.global_resource_group_name
|
||||
|
|
|
|||
|
|
@ -10,6 +10,8 @@ resource "azurerm_kubernetes_cluster" "stamp" {
|
|||
|
||||
automatic_channel_upgrade = "node-image"
|
||||
|
||||
monitor_metrics {}
|
||||
|
||||
oidc_issuer_enabled = true
|
||||
workload_identity_enabled = true
|
||||
|
||||
|
|
|
|||
|
|
@ -1,3 +1,16 @@
|
|||
terraform {
|
||||
required_providers {
|
||||
azurerm = {
|
||||
source = "hashicorp/azurerm"
|
||||
version = "3.61.0"
|
||||
}
|
||||
azapi = {
|
||||
source = "Azure/azapi"
|
||||
version = "1.5.0"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
# Azure Resource Group used for all resources (per stamp)
|
||||
resource "azurerm_resource_group" "stamp" {
|
||||
name = "${var.prefix}-stamp-${var.location}-rg"
|
||||
|
|
|
|||
|
|
@ -0,0 +1,129 @@
|
|||
resource "azapi_resource" "dataCollectionRule" {
|
||||
schema_validation_enabled = false
|
||||
|
||||
type = "Microsoft.Insights/dataCollectionRules@2021-09-01-preview"
|
||||
name = "${local.prefix}-${local.location_short}-dcr"
|
||||
parent_id = azurerm_resource_group.stamp.id
|
||||
location = azurerm_resource_group.stamp.location
|
||||
|
||||
body = jsonencode({
|
||||
kind = "Linux"
|
||||
properties = {
|
||||
dataCollectionEndpointId = azapi_resource.dataCollectionEndpoint.id
|
||||
dataFlows = [
|
||||
{
|
||||
destinations = ["MonitoringAccount1"]
|
||||
streams = ["Microsoft-PrometheusMetrics"]
|
||||
}
|
||||
]
|
||||
dataSources = {
|
||||
prometheusForwarder = [
|
||||
{
|
||||
name = "PrometheusDataSource"
|
||||
streams = ["Microsoft-PrometheusMetrics"]
|
||||
labelIncludeFilter = {}
|
||||
}
|
||||
]
|
||||
}
|
||||
destinations = {
|
||||
monitoringAccounts = [
|
||||
{
|
||||
accountResourceId = data.azapi_resource.prometheus.id
|
||||
name = "MonitoringAccount1"
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
resource "azapi_resource" "dataCollectionEndpoint" {
|
||||
type = "Microsoft.Insights/dataCollectionEndpoints@2021-09-01-preview"
|
||||
name = "${local.prefix}-${local.location_short}-dce"
|
||||
parent_id = azurerm_resource_group.stamp.id
|
||||
location = azurerm_resource_group.stamp.location
|
||||
|
||||
body = jsonencode({
|
||||
kind = "Linux"
|
||||
properties = {}
|
||||
})
|
||||
}
|
||||
|
||||
resource "azapi_resource" "dataCollectionRuleAssociation" {
|
||||
schema_validation_enabled = false
|
||||
type = "Microsoft.Insights/dataCollectionRuleAssociations@2021-09-01-preview"
|
||||
name = "${local.prefix}-${local.location_short}-dcra"
|
||||
parent_id = azurerm_kubernetes_cluster.stamp.id
|
||||
#location = azurerm_resource_group.stamp.location
|
||||
|
||||
body = jsonencode({
|
||||
scope = azurerm_kubernetes_cluster.stamp.id
|
||||
properties = {
|
||||
dataCollectionRuleId = azapi_resource.dataCollectionRule.id
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
resource "azapi_resource" "prometheusK8sRuleGroup" {
|
||||
type = "Microsoft.AlertsManagement/prometheusRuleGroups@2021-07-22-preview"
|
||||
name = "${local.prefix}-${local.location_short}-k8sRuleGroup"
|
||||
parent_id = azurerm_resource_group.stamp.id
|
||||
location = azurerm_resource_group.stamp.location
|
||||
|
||||
body = jsonencode({
|
||||
properties = {
|
||||
description = "Prometheus Rule Group"
|
||||
scopes = [data.azapi_resource.prometheus.id]
|
||||
enabled = true
|
||||
clusterName = azurerm_kubernetes_cluster.stamp.name
|
||||
interval = "PT1M"
|
||||
|
||||
rules = [
|
||||
{
|
||||
record = "instance:node_cpu_utilisation:rate5m"
|
||||
expression = "1 - avg without (cpu) (sum without (mode)(rate(node_cpu_seconds_total{job=\"node\", mode=~\"idle|iowait|steal\"}[5m])))"
|
||||
labels = {
|
||||
workload_type = "job"
|
||||
}
|
||||
enabled = true
|
||||
},
|
||||
{
|
||||
record = "node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate"
|
||||
expression = "sum by (cluster, namespace, pod, container) ( irate(container_cpu_usage_seconds_total{job=\"cadvisor\", image!=\"\"}[5m])) * on (cluster, namespace, pod) group_left(node) topk by (cluster, namespace, pod) ( 1, max by(cluster, namespace, pod, node) (kube_pod_info{node!=\"\"}))"
|
||||
labels = {
|
||||
workload_type = "job"
|
||||
}
|
||||
enabled = true
|
||||
}
|
||||
]
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
resource "azapi_resource" "prometheusNodeRuleGroup" {
|
||||
type = "Microsoft.AlertsManagement/prometheusRuleGroups@2021-07-22-preview"
|
||||
name = "${local.prefix}-${local.location_short}-nodeRuleGroup"
|
||||
parent_id = azurerm_resource_group.stamp.id
|
||||
location = azurerm_resource_group.stamp.location
|
||||
|
||||
body = jsonencode({
|
||||
properties = {
|
||||
description = "Prometheus Rule Group"
|
||||
scopes = [data.azapi_resource.prometheus.id]
|
||||
enabled = true
|
||||
clusterName = azurerm_kubernetes_cluster.stamp.name
|
||||
interval = "PT1M"
|
||||
|
||||
rules = [
|
||||
{
|
||||
record = "instance:node_load1_per_cpu:ratio"
|
||||
expression = "( node_load1{job=\"node\"}/ instance:node_num_cpu:sum{job=\"node\"})"
|
||||
labels = {
|
||||
workload_type = "job"
|
||||
}
|
||||
enabled = true
|
||||
}
|
||||
]
|
||||
}
|
||||
})
|
||||
}
|
||||
|
|
@ -2,7 +2,7 @@ terraform {
|
|||
required_providers {
|
||||
azurerm = {
|
||||
source = "hashicorp/azurerm"
|
||||
version = "3.55.0"
|
||||
version = "3.61.0"
|
||||
}
|
||||
azapi = {
|
||||
source = "azure/azapi"
|
||||
|
|
|
|||
|
|
@ -163,6 +163,17 @@
|
|||
"node": ">=14"
|
||||
}
|
||||
},
|
||||
"node_modules/playwright-chromium/node_modules/playwright-core": {
|
||||
"version": "1.31.1",
|
||||
"resolved": "https://registry.npmjs.org/playwright-core/-/playwright-core-1.31.1.tgz",
|
||||
"integrity": "sha512-JTyX4kV3/LXsvpHkLzL2I36aCdml4zeE35x+G5aPc4bkLsiRiQshU5lWeVpHFAuC8xAcbI6FDcw/8z3q2xtJSQ==",
|
||||
"bin": {
|
||||
"playwright": "cli.js"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=14"
|
||||
}
|
||||
},
|
||||
"node_modules/playwright-core": {
|
||||
"version": "1.33.0",
|
||||
"resolved": "https://registry.npmjs.org/playwright-core/-/playwright-core-1.33.0.tgz",
|
||||
|
|
|
|||
Загрузка…
Ссылка в новой задаче