├── kubernetes └── monitors │ ├── nodes-unschedulable │ ├── README.md │ └── nodes-unschedulable.json │ ├── pod-imagepullbackoff │ ├── README.md │ └── pod-imagepullbackoff.json │ ├── pod-crashloopbackoff │ ├── README.md │ └── pod-crashloopbackoff.json │ ├── data-missing.json │ ├── container-oomkilled.json │ ├── service-networkerrors.json │ ├── namespace-pods.json │ ├── container-memory-usage.json │ ├── container-cpu-usage.json │ ├── deployment-replicas-available.json │ └── statefulset-replicas-ready.json ├── scripts ├── AwesomeDatadog │ ├── AwesomeDatadog.psm1 │ ├── functions │ │ ├── New-Monitor.ps1 │ │ ├── Update-Monitor.ps1 │ │ ├── Test-Monitor.ps1 │ │ └── Search-Monitor.ps1 │ └── AwesomeDatadog.psd1 ├── Test-Monitors.ps1 └── Publish-Monitors.ps1 ├── .vscode └── extensions.json ├── .github └── workflows │ ├── ci.yaml │ └── publish.yaml ├── dotnet └── monitors │ ├── data-missing.json │ ├── gc-memoryload.json │ ├── aspnetcore-requests-queuelength.json │ └── exceptiontype-anomalies.json ├── azure └── monitors │ ├── datadog-integration-data-missing.json │ ├── sqlserverdatabases-storagepercent.json │ ├── sqlserverdatabases-logwritepercent.json │ ├── sqlserverdatabases-workerspercent.json │ ├── sqlserverdatabases-physicaldatareadpercent.json │ ├── containerservice-managedclusters-nodediskusagepercentage.json │ ├── rediscache-percentprocessortime.json │ ├── sqlserverdatabases-dtuconsumptionpercent.json │ ├── sqlserverdatabases-deadlocks.json │ ├── compute-quotusagepercentage.json │ ├── akscluster-unhealthy.json │ ├── sqlserverdatabases-connectionfailurerate.json │ ├── rediscache-usedmemorypercentage.json │ ├── loadbalancer-datapathavailability.json │ └── loadbalancer-healthprobestatusavailability.json ├── README.md └── LICENSE /kubernetes/monitors/nodes-unschedulable/README.md: -------------------------------------------------------------------------------- 1 | # Troubleshooting Guide: Kubernetes Nodes Unschedulable 2 | 3 | [Monitor](./nodes-unschedulable.json) 4 | 5 | - [How to Fix Kubernetes ‘Node Not Ready’ Error (Komodor)](https://komodor.com/learn/how-to-fix-kubernetes-node-not-ready-error/) 6 | -------------------------------------------------------------------------------- /scripts/AwesomeDatadog/AwesomeDatadog.psm1: -------------------------------------------------------------------------------- 1 | # Import all the functions 2 | $functionsFolder = Join-Path $PSScriptRoot "functions" 3 | . $functionsFolder/Search-Monitor.ps1 4 | . $functionsFolder/New-Monitor.ps1 5 | . $functionsFolder/Test-Monitor.ps1 6 | . $functionsFolder/Update-Monitor.ps1 7 | -------------------------------------------------------------------------------- /kubernetes/monitors/pod-imagepullbackoff/README.md: -------------------------------------------------------------------------------- 1 | # Troubleshooting Guide: Kubernetes Pod ImagePullBackoff 2 | 3 | [Monitor](./pod-imagepullbackoff.json) 4 | 5 | - [How to Fix ErrImagePull and ImagePullBackoff (Komodor)](https://komodor.com/learn/how-to-fix-errimagepull-and-imagepullbackoff/) 6 | -------------------------------------------------------------------------------- /kubernetes/monitors/pod-crashloopbackoff/README.md: -------------------------------------------------------------------------------- 1 | # Troubleshooting Guide: Kubernetes Pod CrashLoopBackOff 2 | 3 | [Monitor](./pod-crashloopbackoff.json) 4 | 5 | - [CrashLoopBackOff Error: Common Causes and Resolution (Komodor)](https://komodor.com/learn/how-to-fix-crashloopbackoff-kubernetes-error/) 6 | -------------------------------------------------------------------------------- /.vscode/extensions.json: -------------------------------------------------------------------------------- 1 | { 2 | // See https://go.microsoft.com/fwlink/?LinkId=827846 to learn about workspace recommendations. 3 | // Extension identifier format: ${publisher}.${name}. Example: vscode.csharp 4 | 5 | // List of extensions which should be recommended for users of this workspace. 6 | "recommendations": [ 7 | "yzhang.markdown-all-in-one" 8 | ], 9 | // List of extensions recommended by VS Code that should not be recommended for users of this workspace. 10 | "unwantedRecommendations": [ 11 | 12 | ] 13 | } -------------------------------------------------------------------------------- /.github/workflows/ci.yaml: -------------------------------------------------------------------------------- 1 | name: CI 2 | 3 | on: 4 | pull_request: 5 | branches: ["main"] 6 | workflow_dispatch: {} 7 | 8 | concurrency: 9 | group: ${{ github.workflow }}-${{ github.ref }} 10 | cancel-in-progress: true 11 | 12 | env: 13 | DD_API_KEY: ${{ secrets.DD_API_KEY }} 14 | DD_APP_KEY: ${{ secrets.DD_APP_KEY }} 15 | 16 | jobs: 17 | validate-monitors: 18 | name: Validate monitors 19 | runs-on: ubuntu-latest 20 | steps: 21 | - uses: actions/checkout@v3 22 | - name: Validate monitors 23 | run: scripts/Test-Monitors.ps1 24 | shell: pwsh 25 | -------------------------------------------------------------------------------- /.github/workflows/publish.yaml: -------------------------------------------------------------------------------- 1 | name: Publish 2 | 3 | on: 4 | push: 5 | branches: ["main"] 6 | workflow_dispatch: {} 7 | 8 | concurrency: 9 | group: ${{ github.workflow }}-${{ github.ref }} 10 | cancel-in-progress: true 11 | 12 | env: 13 | DD_API_KEY: ${{ secrets.DD_API_KEY }} 14 | DD_APP_KEY: ${{ secrets.DD_APP_KEY }} 15 | 16 | jobs: 17 | publish-monitors: 18 | name: Publish monitors 19 | runs-on: ubuntu-latest 20 | steps: 21 | - uses: actions/checkout@v3 22 | - name: Publish monitors 23 | run: scripts/Publish-Monitors.ps1 24 | shell: pwsh 25 | -------------------------------------------------------------------------------- /dotnet/monitors/data-missing.json: -------------------------------------------------------------------------------- 1 | { 2 | "name": "Dotnet Runtime Data is Missing on {{service.name}}", 3 | "type": "query alert", 4 | "query": "avg(last_5m):avg:runtime.dotnet.cpu.percent{service:*} by {subscription_id,service} < 0", 5 | "message": "Dotnet Runtime Data has not been seen in the last 10 minutes.", 6 | "tags": [], 7 | "options": { 8 | "thresholds": { 9 | "critical": 0 10 | }, 11 | "notify_audit": false, 12 | "require_full_window": false, 13 | "notify_no_data": true, 14 | "renotify_interval": 0, 15 | "include_tags": true, 16 | "new_group_delay": 60, 17 | "no_data_timeframe": 10, 18 | "silenced": {} 19 | }, 20 | "priority": null, 21 | "restricted_roles": null 22 | } 23 | -------------------------------------------------------------------------------- /kubernetes/monitors/data-missing.json: -------------------------------------------------------------------------------- 1 | { 2 | "name": "Kubernetes Datadog Agent Data is Missing on {{service.name}}", 3 | "type": "query alert", 4 | "query": "avg(last_5m):avg:kubernetes.cpu.usage.total{service:*} by {service,subscription_id} < 0", 5 | "message": "No Cluster agent data seen in the last 10 minutes.", 6 | "tags": [], 7 | "options": { 8 | "thresholds": { 9 | "critical": 0 10 | }, 11 | "notify_audit": false, 12 | "require_full_window": false, 13 | "notify_no_data": true, 14 | "renotify_interval": 0, 15 | "include_tags": true, 16 | "no_data_timeframe": 10, 17 | "new_group_delay": 60, 18 | "silenced": {} 19 | }, 20 | "priority": null, 21 | "restricted_roles": null 22 | } 23 | -------------------------------------------------------------------------------- /azure/monitors/datadog-integration-data-missing.json: -------------------------------------------------------------------------------- 1 | { 2 | "name": "Azure Datadog Integration Data is Missing on {{subscription_name.name}}", 3 | "type": "query alert", 4 | "query": "avg(last_1h):avg:azure.sql_servers.count{subscription_name:*} by {subscription_name,subscription_id} < 0", 5 | "message": "Azure Datadog Integration Data has not been seen in the last 10 minutes.", 6 | "tags": [], 7 | "options": { 8 | "thresholds": { 9 | "critical": 0 10 | }, 11 | "notify_audit": false, 12 | "require_full_window": false, 13 | "notify_no_data": true, 14 | "renotify_interval": 0, 15 | "include_tags": true, 16 | "evaluation_delay": 300, 17 | "new_group_delay": 60, 18 | "no_data_timeframe": 10, 19 | "silenced": {} 20 | }, 21 | "priority": null, 22 | "restricted_roles": null 23 | } 24 | -------------------------------------------------------------------------------- /azure/monitors/sqlserverdatabases-storagepercent.json: -------------------------------------------------------------------------------- 1 | { 2 | "name": "Azure SQL Server Database Storage Percent", 3 | "type": "query alert", 4 | "query": "avg(last_1h):avg:azure.sql_servers_databases.storage_percent{*} by {name,server_name} > 95", 5 | "message": "{{#is_alert}} The database {{name.name}} is more than {{threshold}}% full. {{/is_alert}}\n\n{{#is_recovery}} The database is no longer {{threshold}}% full. {{/is_recovery}}", 6 | "tags": [], 7 | "options": { 8 | "notify_audit": false, 9 | "locked": true, 10 | "timeout_h": 0, 11 | "silenced": {}, 12 | "include_tags": true, 13 | "thresholds": { 14 | "critical": 95, 15 | "critical_recovery": 80 16 | }, 17 | "new_host_delay": 300, 18 | "require_full_window": false, 19 | "notify_no_data": false, 20 | "renotify_interval": 0, 21 | "evaluation_delay": 300 22 | }, 23 | "priority": null, 24 | "restricted_roles": null 25 | } 26 | -------------------------------------------------------------------------------- /azure/monitors/sqlserverdatabases-logwritepercent.json: -------------------------------------------------------------------------------- 1 | { 2 | "name": "Azure SQL Server Database Log Write Percent", 3 | "type": "query alert", 4 | "query": "avg(last_1h):avg:azure.sql_servers_databases.log_write_percent{*} by {server_name,name} > 50", 5 | "message": "{{#is_alert}} The Log IO usage is greater than {{threshold}}% on database {{scope.name}}. {{/is_alert}}\n{{#is_recovery}} The Log IO percentage monitor has recovered. {{/is_recovery}}", 6 | "tags": [], 7 | "options": { 8 | "notify_audit": false, 9 | "locked": true, 10 | "timeout_h": 0, 11 | "silenced": {}, 12 | "include_tags": true, 13 | "thresholds": { 14 | "critical": 50, 15 | "critical_recovery": 30 16 | }, 17 | "new_host_delay": 300, 18 | "require_full_window": false, 19 | "notify_no_data": false, 20 | "renotify_interval": 0, 21 | "evaluation_delay": 300 22 | }, 23 | "priority": null, 24 | "restricted_roles": null 25 | } 26 | -------------------------------------------------------------------------------- /azure/monitors/sqlserverdatabases-workerspercent.json: -------------------------------------------------------------------------------- 1 | { 2 | "name": "Azure SQL Server Database Workers Percent", 3 | "type": "query alert", 4 | "query": "avg(last_1h):avg:azure.sql_servers_databases.workers_percent{*} by {name,server_name} > 20", 5 | "message": "{{#is_alert}} The database worker threads are greater than {{threshold}}% of the max for the last hour on {{name.name}} {{/is_alert}}\n\n{{#is_recovery}} The database workers percentage monitor has recovered. {{/is_recovery}}", 6 | "tags": [], 7 | "options": { 8 | "notify_audit": false, 9 | "locked": true, 10 | "timeout_h": 0, 11 | "silenced": {}, 12 | "include_tags": true, 13 | "thresholds": { 14 | "critical": 20, 15 | "critical_recovery": 10 16 | }, 17 | "new_host_delay": 300, 18 | "require_full_window": false, 19 | "notify_no_data": false, 20 | "renotify_interval": 0, 21 | "evaluation_delay": 300 22 | }, 23 | "priority": null, 24 | "restricted_roles": null 25 | } 26 | -------------------------------------------------------------------------------- /kubernetes/monitors/container-oomkilled.json: -------------------------------------------------------------------------------- 1 | { 2 | "name": "Kubernetes Container {{kube_container_name.name}} was OOM Killed", 3 | "type": "query alert", 4 | "query": "sum(last_5m):default_zero(sum:kubernetes.containers.state.terminated{reason:oomkilled,service:*} by {kube_cluster_name,kube_container_name}) >= 10", 5 | "message": "Container {{kube_container_name.name}} was OOM Killed {{value}} times.\n\nSee [dashboard](https://app.datadoghq.com/dash/integration/30322/kubernetes-pods-overview?tpl_var_cluster%5B0%5D={{kube_cluster_name.name}}&live=true&tile_focus=935123463493438).", 6 | "tags": [], 7 | "options": { 8 | "thresholds": { 9 | "critical": 10, 10 | "warning": 1 11 | }, 12 | "notify_audit": false, 13 | "require_full_window": false, 14 | "notify_no_data": false, 15 | "renotify_interval": 0, 16 | "include_tags": true, 17 | "new_group_delay": 60, 18 | "silenced": {} 19 | }, 20 | "priority": null, 21 | "restricted_roles": null 22 | } 23 | -------------------------------------------------------------------------------- /kubernetes/monitors/service-networkerrors.json: -------------------------------------------------------------------------------- 1 | { 2 | "name": "Kubernetes Service Network Errors on {{kube_service.name}}", 3 | "type": "query alert", 4 | "query": "sum(last_5m):exclude_null(sum:kubernetes.network.rx_errors{kube_service:*} by {kube_service,kube_cluster_name,subscription_id}) >= 1", 5 | "message": "The AT Kubernetes service {{kube_service.name}} is experiencing network errors. See [widget](https://app.datadoghq.com/screen/integration/30403/kubernetes-services-overview?tpl_var_kube_cluster_name%5B0%5D={{kube_cluster_name.name}}&live=true&tile_focus=33).", 6 | "tags": [], 7 | "options": { 8 | "thresholds": { 9 | "critical": 1, 10 | "critical_recovery": 0.1 11 | }, 12 | "notify_audit": false, 13 | "require_full_window": false, 14 | "notify_no_data": false, 15 | "renotify_interval": 0, 16 | "include_tags": true, 17 | "new_group_delay": 60, 18 | "silenced": {} 19 | }, 20 | "priority": null, 21 | "restricted_roles": null 22 | } 23 | -------------------------------------------------------------------------------- /dotnet/monitors/gc-memoryload.json: -------------------------------------------------------------------------------- 1 | { 2 | "name": "Dotnet GC Memory Load is High on {{name.name}}", 3 | "type": "query alert", 4 | "query": "avg(last_5m):avg:runtime.dotnet.gc.memory_load{service:*} by {subscription_id,subscription_name,name,aks-cluster-name,service} >= 90", 5 | "message": "The GC changes its behavior when its load gets above 85%. It is currently at {{value}}.\n\nSee [dashboard](https://app.datadoghq.com/dash/integration/30412/net-runtime-metrics?tpl_var_service%5B0%5D={{service.name}}&live=true).", 6 | "tags": [], 7 | "options": { 8 | "thresholds": { 9 | "critical": 90, 10 | "warning": 85, 11 | "warning_recovery": 80, 12 | "critical_recovery": 80 13 | }, 14 | "notify_audit": false, 15 | "require_full_window": false, 16 | "notify_no_data": false, 17 | "renotify_interval": 0, 18 | "include_tags": true, 19 | "new_group_delay": 60, 20 | "silenced": {} 21 | }, 22 | "priority": null, 23 | "restricted_roles": null 24 | } 25 | -------------------------------------------------------------------------------- /azure/monitors/sqlserverdatabases-physicaldatareadpercent.json: -------------------------------------------------------------------------------- 1 | { 2 | "name": "Azure SQL Server Database Physical Data Read Percent", 3 | "type": "query alert", 4 | "query": "avg(last_1h):avg:azure.sql_servers_databases.physical_data_read_percent{*} by {name,server_name} > 50", 5 | "message": "{{#is_alert}} The Data IO percentage has been greater than {{threshold}}% for the last 15 minutes on {{name.name}} {{/is_alert}}\n\n{{#is_recovery}} The Data IO percentage monitor has recovered. {{/is_recovery}}", 6 | "tags": [], 7 | "options": { 8 | "notify_audit": false, 9 | "locked": true, 10 | "timeout_h": 0, 11 | "silenced": {}, 12 | "include_tags": true, 13 | "thresholds": { 14 | "critical": 50, 15 | "critical_recovery": 30 16 | }, 17 | "new_host_delay": 300, 18 | "require_full_window": false, 19 | "notify_no_data": false, 20 | "renotify_interval": 0, 21 | "evaluation_delay": 300 22 | }, 23 | "priority": null, 24 | "restricted_roles": null 25 | } 26 | -------------------------------------------------------------------------------- /azure/monitors/containerservice-managedclusters-nodediskusagepercentage.json: -------------------------------------------------------------------------------- 1 | { 2 | "name": "Azure Container Service Managed Clusters Node Disk Usage Percentage", 3 | "type": "query alert", 4 | "query": "avg(last_1h):avg:azure.containerservice_managedclusters.node_disk_usage_percentage{*} by {subscription_name,node,name} > 80", 5 | "message": "{{#is_alert}} Disk usage on node {{node.name}} is greater than {{threshold}}% {{/is_alert}}\n\n{{#is_recovery}} The node disk usage monitor has recovered. {{/is_recovery}}", 6 | "tags": [], 7 | "options": { 8 | "notify_audit": false, 9 | "locked": true, 10 | "timeout_h": 0, 11 | "silenced": {}, 12 | "include_tags": true, 13 | "thresholds": { 14 | "critical": 80, 15 | "critical_recovery": 50 16 | }, 17 | "new_host_delay": 300, 18 | "require_full_window": false, 19 | "notify_no_data": false, 20 | "renotify_interval": 0, 21 | "evaluation_delay": 300 22 | }, 23 | "priority": null, 24 | "restricted_roles": null 25 | } 26 | -------------------------------------------------------------------------------- /azure/monitors/rediscache-percentprocessortime.json: -------------------------------------------------------------------------------- 1 | { 2 | "name": "Azure Redis Cache CPU Usage is High on {{name.name}}", 3 | "type": "query alert", 4 | "query": "avg(last_1h):avg:azure.cache_redis.percent_processor_time{subscription_name:*} by {name,subscription_id,subscription_name} > 90", 5 | "message": "{{name.name}} is using {{value}}% of its CPU.\n\nSee [dashboard](https://app.datadoghq.com/dash/integration/104/azure-redis-cache-overview?tpl_var_subscription_name%5B0%5D={{subscription_name.name}}&live=true).", 6 | "tags": [], 7 | "options": { 8 | "thresholds": { 9 | "critical": 90, 10 | "warning": 80, 11 | "critical_recovery": 80, 12 | "warning_recovery": 70 13 | }, 14 | "notify_audit": false, 15 | "require_full_window": false, 16 | "notify_no_data": false, 17 | "renotify_interval": 0, 18 | "include_tags": true, 19 | "evaluation_delay": 300, 20 | "new_group_delay": 60, 21 | "silenced": {} 22 | }, 23 | "priority": null, 24 | "restricted_roles": null 25 | } 26 | -------------------------------------------------------------------------------- /azure/monitors/sqlserverdatabases-dtuconsumptionpercent.json: -------------------------------------------------------------------------------- 1 | { 2 | "name": "Azure SQL Server Database DTU Consumption is High on {{name.name}}", 3 | "type": "query alert", 4 | "query": "avg(last_5m):avg:azure.sql_servers_databases.dtu_consumption_percent{subscription_name:*} by {name,resource_group,subscription_id,subscription_name} > 90", 5 | "message": "The DTU consumption on {{name.name}} is high. See [dashboard](https://app.datadoghq.com/dash/integration/93/azure-sql-databases-overview?tpl_var_resource_group%5B0%5D={{resource_group.name}}&live=true&tile_focus=3901420757560338).", 6 | "tags": [], 7 | "options": { 8 | "thresholds": { 9 | "critical": 90, 10 | "warning": 80, 11 | "critical_recovery": 70 12 | }, 13 | "notify_audit": false, 14 | "require_full_window": false, 15 | "notify_no_data": false, 16 | "renotify_interval": 0, 17 | "include_tags": true, 18 | "new_group_delay": 60, 19 | "silenced": {} 20 | }, 21 | "priority": null, 22 | "restricted_roles": null 23 | } 24 | -------------------------------------------------------------------------------- /dotnet/monitors/aspnetcore-requests-queuelength.json: -------------------------------------------------------------------------------- 1 | { 2 | "name": "ASP.NET Core Request Queue Length", 3 | "type": "query alert", 4 | "query": "avg(last_15m):max:runtime.dotnet.aspnetcore.requests.queue_length{*} by {kube_cluster_name} / diff(max:runtime.dotnet.aspnetcore.requests.total{*} by {kube_cluster_name}) * 100 > 70", 5 | "message": "{{#is_alert}} More than {{threshold}}% of ASP.NET requests are waiting in the queue. {{/is_alert}}\n\n{{#is_recovery}} The ASP.NET request queue monitor has recovered. {{/is_recovery}}", 6 | "tags": [], 7 | "options": { 8 | "notify_audit": false, 9 | "locked": true, 10 | "timeout_h": 0, 11 | "silenced": {}, 12 | "include_tags": true, 13 | "thresholds": { 14 | "critical": 70, 15 | "critical_recovery": 60 16 | }, 17 | "new_host_delay": 300, 18 | "require_full_window": false, 19 | "notify_no_data": false, 20 | "renotify_interval": 0, 21 | "evaluation_delay": 45 22 | }, 23 | "priority": null, 24 | "restricted_roles": null 25 | } 26 | -------------------------------------------------------------------------------- /azure/monitors/sqlserverdatabases-deadlocks.json: -------------------------------------------------------------------------------- 1 | { 2 | "name": "Azure SQL Server Database Deadlocks on {{name.name}}", 3 | "type": "query alert", 4 | "query": "avg(last_1h):avg:azure.sql_servers_databases.deadlock{subscription_name:*} by {name,subscription_name,server_name,resource_group} >= 10", 5 | "message": "This database has more than {{threshold}} deadlocks in the last 15 minutes. See [Deadlocks by Database](https://app.datadoghq.com/dash/integration/93/azure-sql-databases-overview?tpl_var_resource_group%5B0%5D={{resource_group.name}}&live=true&tile_focus=1159384921439762).", 6 | "tags": [], 7 | "options": { 8 | "thresholds": { 9 | "critical": 10, 10 | "critical_recovery": 0.1 11 | }, 12 | "notify_audit": false, 13 | "require_full_window": false, 14 | "notify_no_data": false, 15 | "renotify_interval": 0, 16 | "include_tags": true, 17 | "new_group_delay": 60, 18 | "evaluation_delay": 300, 19 | "silenced": {} 20 | }, 21 | "priority": null, 22 | "restricted_roles": null 23 | } 24 | -------------------------------------------------------------------------------- /azure/monitors/compute-quotusagepercentage.json: -------------------------------------------------------------------------------- 1 | { 2 | "name": "Azure Compute Quota Usage is High for {{usage_name.name}}", 3 | "type": "query alert", 4 | "query": "avg(last_1h):avg:azure.usage.percentage{usage_category:compute,subscription_name:*} by {region,usage_name,subscription_name} * 100 > 90", 5 | "message": "{{usage_name.name}} is at {{value}}% of it's quota limit. See [dashboard](https://app.datadoghq.com/dash/integration/30291/azure-resource-usage-and-quota-overview?tpl_var_subscription_name%5B0%5D={{subscription_name.name}}&live=true&tile_focus=157130772826574).", 6 | "tags": [], 7 | "options": { 8 | "thresholds": { 9 | "critical": 90, 10 | "warning": 75, 11 | "critical_recovery": 80, 12 | "warning_recovery": 70 13 | }, 14 | "notify_audit": false, 15 | "require_full_window": false, 16 | "notify_no_data": false, 17 | "renotify_interval": 0, 18 | "include_tags": true, 19 | "new_group_delay": 60, 20 | "evaluation_delay": 300, 21 | "silenced": {} 22 | }, 23 | "priority": null, 24 | "restricted_roles": null 25 | } 26 | -------------------------------------------------------------------------------- /kubernetes/monitors/namespace-pods.json: -------------------------------------------------------------------------------- 1 | { 2 | "name": "Kubernetes Namespace Status Failed", 3 | "type": "query alert", 4 | "query": "change(avg(last_5m),last_5m):sum:kubernetes_state.pod.status_phase{pod_phase:failed} by {kube_cluster_name,kube_namespace} >= 10", 5 | "message": "{{#is_alert}}\n{{value}} pods are failing in Cluster {{kube_cluster_name.name}} and namespace {{kube_namespace.name}}.\n\nThe threshold varies depending on your infrastructure. Change the threshold to suit your needs.\n{{/is_alert}}\n{{#is_recovery}}\nPods have stopped failing in Cluster {{kube_cluster_name.name}}.\n{{/is_recovery}}", 6 | "tags": [], 7 | "options": { 8 | "notify_audit": false, 9 | "locked": true, 10 | "timeout_h": 0, 11 | "silenced": {}, 12 | "include_tags": true, 13 | "thresholds": { 14 | "critical": 10, 15 | "critical_recovery": 0 16 | }, 17 | "new_host_delay": 300, 18 | "require_full_window": false, 19 | "notify_no_data": false, 20 | "renotify_interval": 0, 21 | "evaluation_delay": null 22 | }, 23 | "priority": null, 24 | "restricted_roles": null 25 | } 26 | -------------------------------------------------------------------------------- /kubernetes/monitors/container-memory-usage.json: -------------------------------------------------------------------------------- 1 | { 2 | "name": "Kubernetes Container Memory Usage", 3 | "type": "query alert", 4 | "query": "avg(last_5m):max:kubernetes.memory.usage{*} by {kube_container_name,kube_cluster_name} / max:kubernetes.memory.limits{*} by {kube_container_name,kube_cluster_name} * 100 >= 80", 5 | "message": "{{#is_alert}}\nOver the last five minutes, the {{kube_container_name.name}} container on the {{kube_cluster_name.name}} cluster used {{value}}% of its memory.\n{{/is_alert}}\n{{#is_recovery}}\nMemory usage has returned to normal for the {{kube_container_name.name}} container on the {{kube_cluster_name.name}} cluster.\n{{/is_recovery}}", 6 | "tags": [], 7 | "options": { 8 | "notify_audit": false, 9 | "locked": true, 10 | "timeout_h": 0, 11 | "silenced": {}, 12 | "include_tags": true, 13 | "thresholds": { 14 | "critical": 80, 15 | "critical_recovery": 50 16 | }, 17 | "new_host_delay": 300, 18 | "require_full_window": false, 19 | "notify_no_data": false, 20 | "renotify_interval": 0, 21 | "evaluation_delay": null 22 | }, 23 | "priority": null, 24 | "restricted_roles": null 25 | } 26 | -------------------------------------------------------------------------------- /kubernetes/monitors/nodes-unschedulable/nodes-unschedulable.json: -------------------------------------------------------------------------------- 1 | { 2 | "name": "Kubernetes Nodes Unschedulable", 3 | "type": "query alert", 4 | "query": "max(last_15m):sum:kubernetes_state.node.status{status:schedulable} by {kube_cluster_name} * 100 / sum:kubernetes_state.node.status{*} by {kube_cluster_name} <= 80", 5 | "message": "{{#is_alert}}\nLess than {{threshold}}% of nodes are schedulable on the {{kube_cluster_name.name}} cluster.\n\nThis may not be an issue, you may just need to cleanup old node resources in Azure that have been cordoned.\n{{/is_alert}}\n{{#is_recovery}}\nNodes have recovered and are schedulable on cluster {{kube_cluster_name.name}}.\n{{/is_recovery}}", 6 | "tags": [], 7 | "options": { 8 | "notify_audit": false, 9 | "locked": true, 10 | "timeout_h": 0, 11 | "silenced": {}, 12 | "include_tags": true, 13 | "thresholds": { 14 | "critical": 80, 15 | "critical_recovery": 100 16 | }, 17 | "new_host_delay": 300, 18 | "require_full_window": false, 19 | "notify_no_data": false, 20 | "renotify_interval": 0, 21 | "evaluation_delay": null 22 | }, 23 | "priority": null, 24 | "restricted_roles": null 25 | } 26 | -------------------------------------------------------------------------------- /azure/monitors/akscluster-unhealthy.json: -------------------------------------------------------------------------------- 1 | { 2 | "name": "Azure AKS Cluster {{name.name}} Reporting Unhealthy Status", 3 | "type": "query alert", 4 | "query": "avg(last_5m):default_zero(avg:azure.containerservice_managedclusters.count{subscription_name:*,!status:running} by {name,resource_group,subscription_name,status}) >= 1", 5 | "message": "The Azure resource health provider is reporting the AKS cluster {{name.name}} is in a {{status.name}} state.\n\nSee [AKS dashboard](https://app.datadoghq.com/dash/integration/30699/azure-kubernetes-service?tpl_var_resource_group%5B0%5D={{resource_group.name}}&live=true).\n\nMore information about [Azure Status and Count Metrics](https://docs.datadoghq.com/integrations/guide/azure-status-metric/).", 6 | "tags": [], 7 | "options": { 8 | "thresholds": { 9 | "critical": 1, 10 | "critical_recovery": 0.1 11 | }, 12 | "notify_audit": false, 13 | "require_full_window": false, 14 | "notify_no_data": false, 15 | "renotify_interval": 0, 16 | "include_tags": true, 17 | "new_group_delay": 60, 18 | "evaluation_delay": 60, 19 | "silenced": {} 20 | }, 21 | "priority": null, 22 | "restricted_roles": null 23 | } 24 | -------------------------------------------------------------------------------- /azure/monitors/sqlserverdatabases-connectionfailurerate.json: -------------------------------------------------------------------------------- 1 | { 2 | "name": "Azure SQL Server Database Connection Failure Rate on {{name.name}}", 3 | "type": "query alert", 4 | "query": "sum(last_1h):sum:azure.sql_servers_databases.connection_failed{subscription_name:*} by {resource_group,subscription_name,server_name,name}.as_count() / sum:azure.sql_servers_databases.connection_successful{subscription_name:*} by {resource_group,subscription_name,server_name,name}.as_count() * 100 >= 1", 5 | "message": "{{value}}% of connections to {{name.name}} are failing. See [dashboard](https://app.datadoghq.com/dash/integration/93/azure-sql-databases-overview?tpl_var_resource_group%5B0%5D={{resource_group.name}}&live=true&tile_focus=7111227358143092).", 6 | "tags": [], 7 | "options": { 8 | "thresholds": { 9 | "critical": 1, 10 | "critical_recovery": 0.1 11 | }, 12 | "notify_audit": false, 13 | "require_full_window": false, 14 | "notify_no_data": false, 15 | "renotify_interval": 0, 16 | "include_tags": true, 17 | "new_group_delay": 60, 18 | "evaluation_delay": 300, 19 | "silenced": {} 20 | }, 21 | "priority": null, 22 | "restricted_roles": null 23 | } 24 | -------------------------------------------------------------------------------- /kubernetes/monitors/pod-crashloopbackoff/pod-crashloopbackoff.json: -------------------------------------------------------------------------------- 1 | { 2 | "name": "Kubernetes Pod CrashloopBackOff", 3 | "type": "query alert", 4 | "query": "max(last_10m):sum:kubernetes_state.container.status_report.count.waiting{reason:crashloopbackoff} by {kube_cluster_name,kube_namespace} >= 4", 5 | "message": "{{#is_alert}}\nPod {{pod_name.name}} in cluster {{kube_cluster_name.name}} is in CrashloopBackOff on namespace {{kube_namespace.name}}.\n\nThis alert could generate several alerts for a bad deployment. Adjust the thresholds of the query to suit your infrastructure.\n{{/is_alert}}\n{{#is_recovery}}\nPod {{pod_name.name}} in cluster {{kube_cluster_name.name}} is no longer in CrashloopBackOff.\n{{/is_recovery}}", 6 | "tags": [], 7 | "options": { 8 | "notify_audit": false, 9 | "locked": true, 10 | "timeout_h": 0, 11 | "silenced": {}, 12 | "include_tags": true, 13 | "thresholds": { 14 | "critical": 4, 15 | "critical_recovery": 0 16 | }, 17 | "new_host_delay": 300, 18 | "require_full_window": false, 19 | "notify_no_data": false, 20 | "renotify_interval": 0, 21 | "evaluation_delay": null 22 | }, 23 | "priority": null, 24 | "restricted_roles": null 25 | } 26 | -------------------------------------------------------------------------------- /kubernetes/monitors/container-cpu-usage.json: -------------------------------------------------------------------------------- 1 | { 2 | "name": "Kubernetes Container CPU Usage is High on {{kube_container_name.name}}", 3 | "type": "query alert", 4 | "query": "avg(last_5m):(avg:kubernetes.cpu.usage.total{*} by {kube_cluster_name,kube_container_name} / (1000000000 * avg:kubernetes.cpu.limits{*} by {kube_cluster_name,kube_container_name})) * 100 >= 80", 5 | "message": "{{#is_alert}}\nOver the last five minutes, CPU usage has been high at {{value}}% on the {{kube_container_name.name}} container on the {{kube_cluster_name.name}} cluster.\n{{/is_alert}}\n{{#is_recovery}}\nCPU usage has returned to normal for the {{kube_container_name.name}} container on the {{kube_cluster_name.name}} cluster.\n{{/is_recovery}}", 6 | "tags": [], 7 | "options": { 8 | "notify_audit": false, 9 | "locked": true, 10 | "timeout_h": 0, 11 | "silenced": {}, 12 | "include_tags": true, 13 | "thresholds": { 14 | "critical": 80, 15 | "critical_recovery": 50 16 | }, 17 | "new_host_delay": 300, 18 | "require_full_window": false, 19 | "notify_no_data": false, 20 | "renotify_interval": 0, 21 | "evaluation_delay": null 22 | }, 23 | "priority": null, 24 | "restricted_roles": null 25 | } 26 | -------------------------------------------------------------------------------- /dotnet/monitors/exceptiontype-anomalies.json: -------------------------------------------------------------------------------- 1 | { 2 | "name": "Dotnet Runtime Exception Type Anomalies for {{exception_type.name}}", 3 | "type": "query alert", 4 | "query": "sum(last_4h):anomalies(sum:runtime.dotnet.exceptions.count{service:*} by {exception_type,service,subscription_id}.as_count(), 'agile', 2, direction='both', interval=60, alert_window='last_15m', seasonality='hourly', count_default_zero='true', timezone='utc') >= 1", 5 | "message": "There is an anomaly in the number of exceptions of type {{exception_type.name}} on {{service.name}}.\n\nSee [dashboard](https://app.datadoghq.com/dash/integration/30412/net-runtime-metrics?tpl_var_service%5B0%5D={{service.name}}&live=true).", 6 | "tags": [], 7 | "options": { 8 | "thresholds": { 9 | "critical": 1, 10 | "critical_recovery": 0 11 | }, 12 | "notify_audit": false, 13 | "require_full_window": false, 14 | "notify_no_data": false, 15 | "renotify_interval": 0, 16 | "threshold_windows": { 17 | "trigger_window": "last_15m", 18 | "recovery_window": "last_15m" 19 | }, 20 | "include_tags": true, 21 | "new_group_delay": 60, 22 | "silenced": {} 23 | }, 24 | "priority": null, 25 | "restricted_roles": null 26 | } 27 | -------------------------------------------------------------------------------- /kubernetes/monitors/pod-imagepullbackoff/pod-imagepullbackoff.json: -------------------------------------------------------------------------------- 1 | { 2 | "name": "Kubernetes Pod ImagePullBackOff", 3 | "type": "query alert", 4 | "query": "max(last_10m):max:kubernetes_state.container.status_report.count.waiting{reason:imagepullbackoff} by {kube_cluster_name,kube_namespace,pod_name} >= 1", 5 | "message": "{{#is_alert}}\nPod {{pod_name.name}} in cluster {{kube_cluster_name.name}} is in ImagePullBackOff on namespace {{kube_namespace.name}}.\n\nThis could happen for several reasons, for example a bad image path or tag or if the credentials for pulling images are not configured properly.\n{{/is_alert}}\n{{#is_recovery}}\nPod {{pod_name.name}} in cluster {{kube_cluster_name.name}} is back to normal.\n{{/is_recovery}}", 6 | "tags": [], 7 | "options": { 8 | "notify_audit": false, 9 | "locked": true, 10 | "timeout_h": 0, 11 | "silenced": {}, 12 | "include_tags": true, 13 | "thresholds": { 14 | "critical": 1, 15 | "critical_recovery": 0 16 | }, 17 | "new_host_delay": 300, 18 | "require_full_window": false, 19 | "notify_no_data": false, 20 | "renotify_interval": 0, 21 | "evaluation_delay": null 22 | }, 23 | "priority": null, 24 | "restricted_roles": null 25 | } 26 | -------------------------------------------------------------------------------- /scripts/AwesomeDatadog/functions/New-Monitor.ps1: -------------------------------------------------------------------------------- 1 | function New-Monitor { 2 | [CmdletBinding()] 3 | param ( 4 | [Parameter(Mandatory = $true, Position = 0)] 5 | [string]$MonitorFile, 6 | [Parameter(Mandatory = $false)] 7 | [string]$ApiKey = $env:DD_API_KEY, 8 | [Parameter(Mandatory = $false)] 9 | [string]$AppKey = $env:DD_APP_KEY 10 | ) 11 | 12 | $ErrorActionPreference = "Stop" 13 | 14 | # Test file path 15 | if (-not (Test-Path $MonitorFile)) { 16 | Write-Error "File not found: $MonitorFile" 17 | exit 1 18 | } 19 | 20 | # Import the monitor export file 21 | $monitor = Get-Content $MonitorFile | ConvertFrom-Json 22 | $monitor.tags += "managed_by:awesome-datadog" 23 | $monitorJson = $monitor | ConvertTo-Json -Depth 10 24 | 25 | Write-Debug "Monitor: $monitorJson" 26 | Write-Verbose "Creating monitor `"$($monitor.name)`"" 27 | 28 | $response = Invoke-WebRequest ` 29 | -Uri "https://api.datadoghq.com/api/v1/monitor" ` 30 | -ContentType "application/json" ` 31 | -Method Post ` 32 | -UseBasicParsing ` 33 | -Headers @{"DD-API-KEY" = $ApiKey; "DD-APPLICATION-KEY" = $AppKey } ` 34 | -Body $monitorJson 35 | Write-Debug $response 36 | Write-Verbose "Monitor created" 37 | } 38 | -------------------------------------------------------------------------------- /kubernetes/monitors/deployment-replicas-available.json: -------------------------------------------------------------------------------- 1 | { 2 | "name": "Kubernetes Deployments Replica Not Available", 3 | "type": "query alert", 4 | "query": "avg(last_15m):avg:kubernetes_state.deployment.replicas_desired{*} by {kube_namespace,kube_deployment,kube_cluster_name} - avg:kubernetes_state.deployment.replicas_available{*} by {kube_namespace,kube_deployment,kube_cluster_name} >= 2", 5 | "message": "{{#is_alert}}\n{{value}} Deployments Replica's pods are down on the {{kube_cluster_name.name}} cluster in Deployment {{kube_namespace.name}}/{{kube_deployment.name}}.\n{{/is_alert}}\n{{#is_recovery}}\nDeployments Replica's pods have recovered in Cluster {{kube_cluster_name.name}} and Deployment {{kube_namespace.name}}/{{kube_deployment.name}}.\n{{/is_recovery}}", 6 | "tags": [], 7 | "options": { 8 | "notify_audit": false, 9 | "locked": true, 10 | "timeout_h": 0, 11 | "silenced": {}, 12 | "include_tags": true, 13 | "thresholds": { 14 | "critical": 2, 15 | "critical_recovery": 0 16 | }, 17 | "new_host_delay": 300, 18 | "require_full_window": false, 19 | "notify_no_data": false, 20 | "renotify_interval": 0, 21 | "evaluation_delay": null 22 | }, 23 | "priority": null, 24 | "restricted_roles": null 25 | } 26 | -------------------------------------------------------------------------------- /azure/monitors/rediscache-usedmemorypercentage.json: -------------------------------------------------------------------------------- 1 | { 2 | "name": "Azure Redis Cache Memory Usage is High on {{name.name}}", 3 | "type": "query alert", 4 | "query": "avg(last_1h):avg:azure.cache_redis.usedmemorypercentage{subscription_name:*} by {name,subscription_id,subscription_name} > 90", 5 | "message": "{{name.name}} is using {{value}}% of its memory. Memory usage is a crucial performance factor. If `used_memory > total available system memory`, the OS will begin swapping old/unused sections of memory and writing them to disk. Writing or reading from disk is up to 100,000 times slower than writing or reading from memory.\n\nSee [dashboard](https://app.datadoghq.com/dash/integration/104/azure-redis-cache-overview?tpl_var_subscription_name%5B0%5D={{subscription_name.name}}&live=true).", 6 | "tags": [], 7 | "options": { 8 | "thresholds": { 9 | "critical": 90, 10 | "warning": 80, 11 | "critical_recovery": 80, 12 | "warning_recovery": 70 13 | }, 14 | "notify_audit": false, 15 | "require_full_window": false, 16 | "notify_no_data": false, 17 | "renotify_interval": 0, 18 | "include_tags": true, 19 | "evaluation_delay": 300, 20 | "new_group_delay": 60, 21 | "silenced": {} 22 | }, 23 | "priority": null, 24 | "restricted_roles": null 25 | } 26 | -------------------------------------------------------------------------------- /azure/monitors/loadbalancer-datapathavailability.json: -------------------------------------------------------------------------------- 1 | { 2 | "name": "Azure Load Balancer Data Path (VIP) Availability is Degraded on {{name.name}}", 3 | "type": "query alert", 4 | "query": "avg(last_1h):avg:azure.network_loadbalancers.data_path_availability{name:kubernetes,subscription_name:*} by {name,resource_group,region,subscription_name,subscription_id} <= 50", 5 | "message": "VIP is only {{value}}% available on Load Balancer {{name.name}}.\n\nVIP refers to data path availability. This measures availability from within a region to the load balancer front end, all the way to the SDN stack that supports your VM.\n\nSee [dashboard](https://app.datadoghq.com/dash/integration/71/azure-overview?tpl_var_subscription_name%5B0%5D={{subscription_name.name}}&live=true&tile_focus=8628618229855108).", 6 | "tags": [], 7 | "options": { 8 | "thresholds": { 9 | "critical": 50, 10 | "critical_recovery": 99, 11 | "warning": 80, 12 | "warning_recovery": 90 13 | }, 14 | "notify_audit": false, 15 | "require_full_window": false, 16 | "notify_no_data": false, 17 | "renotify_interval": 0, 18 | "include_tags": true, 19 | "new_group_delay": 60, 20 | "evaluation_delay": 300, 21 | "silenced": {} 22 | }, 23 | "priority": null, 24 | "restricted_roles": null 25 | } 26 | -------------------------------------------------------------------------------- /scripts/AwesomeDatadog/functions/Update-Monitor.ps1: -------------------------------------------------------------------------------- 1 | function Update-Monitor { 2 | [CmdletBinding()] 3 | param ( 4 | [Parameter(Mandatory = $true, Position = 0)] 5 | [string]$MonitorId, 6 | [Parameter(Mandatory = $true, Position = 1)] 7 | [string]$MonitorFile, 8 | [Parameter(Mandatory = $false)] 9 | [string]$ApiKey = $env:DD_API_KEY, 10 | [Parameter(Mandatory = $false)] 11 | [string]$AppKey = $env:DD_APP_KEY 12 | ) 13 | 14 | $ErrorActionPreference = "Stop" 15 | 16 | # Test file path 17 | if (-not (Test-Path $MonitorFile)) { 18 | Write-Error "File not found: $MonitorFile" 19 | exit 1 20 | } 21 | 22 | # Import the monitor export file 23 | $monitor = Get-Content $MonitorFile | ConvertFrom-Json 24 | $monitorJson = $monitor | ConvertTo-Json -Depth 10 25 | 26 | Write-Debug "Monitor: $monitorJson" 27 | Write-Debug "Updating monitor $MonitorId with $MonitorFile" 28 | 29 | $response = Invoke-WebRequest ` 30 | -Uri "https://api.datadoghq.com/api/v1/monitor/$MonitorId" ` 31 | -ContentType "application/json" ` 32 | -Method Put ` 33 | -UseBasicParsing ` 34 | -Headers @{"DD-API-KEY" = $ApiKey; "DD-APPLICATION-KEY" = $AppKey } ` 35 | -Body $monitorJson ` 36 | | ConvertFrom-Json 37 | 38 | Write-Debug $response 39 | Write-Verbose "Monitor updated" 40 | } 41 | -------------------------------------------------------------------------------- /kubernetes/monitors/statefulset-replicas-ready.json: -------------------------------------------------------------------------------- 1 | { 2 | "name": "Kubernetes Statefulset Replicas Ready", 3 | "type": "query alert", 4 | "query": "max(last_15m):sum:kubernetes_state.statefulset.replicas_desired{*} by {kube_namespace,kube_stateful_set,kube_cluster_name} - sum:kubernetes_state.statefulset.replicas_ready{*} by {kube_namespace,kube_stateful_set,kube_cluster_name} >= 2", 5 | "message": "{{#is_alert}}\n{{value}} Statefulset Replica's pods are down in Cluster {{kube_cluster_name.name}} and Statefulset {{kube_namespace.name}}/{{kube_stateful_set.name}}.\n\nThis might present an unsafe situation for any further manual operations, such as killing other pods.\n{{/is_alert}}\n{{#is_recovery}}\nStatefulset Replica's pods have recovered in Cluster {{kube_cluster_name.name}} and Statefulset {{kube_namespace.name}}/{{kube_stateful_set.name}}.\n{{/is_recovery}}", 6 | "tags": [], 7 | "options": { 8 | "notify_audit": false, 9 | "locked": true, 10 | "timeout_h": 0, 11 | "silenced": {}, 12 | "include_tags": true, 13 | "thresholds": { 14 | "critical": 2, 15 | "critical_recovery": 0 16 | }, 17 | "new_host_delay": 300, 18 | "require_full_window": false, 19 | "notify_no_data": false, 20 | "renotify_interval": 0, 21 | "evaluation_delay": null 22 | }, 23 | "priority": null, 24 | "restricted_roles": null 25 | } 26 | -------------------------------------------------------------------------------- /scripts/Test-Monitors.ps1: -------------------------------------------------------------------------------- 1 | [CmdletBinding()] 2 | param ( 3 | [Parameter(Mandatory = $false)] 4 | [string]$ApiKey = $env:DD_API_KEY, 5 | [Parameter(Mandatory = $false)] 6 | [string]$AppKey = $env:DD_APP_KEY 7 | ) 8 | 9 | $ErrorActionPreference = "Stop" 10 | 11 | Import-Module -Name $PSScriptRoot/AwesomeDatadog/AwesomeDatadog.psm1 -Force 12 | 13 | # Get all *.json files in the monitors directories 14 | Write-Host "Getting all monitors from the monitors directories" 15 | $monitorFiles = Get-ChildItem -Path $PSScriptRoot/../*/monitors/*.json -Recurse 16 | 17 | Write-Host "Found $($monitorFiles.Count) monitors" 18 | Write-Debug "Monitor files: $monitorFiles" 19 | 20 | $invalidMonitors = @() 21 | 22 | foreach ($monitorFile in $monitorFiles) { 23 | # Validate the monitor 24 | $isValid = Test-Monitor -MonitorFile $monitorFile.FullName -ApiKey $ApiKey -AppKey $AppKey -Debug:$DebugPreference -Verbose:$VerbosePreference 25 | if (!$isValid) { 26 | Write-Warning "Monitor `"$($monitorFile.FullName)`" is invalid" 27 | $invalidMonitors += $monitorFile.FullName 28 | } 29 | } 30 | 31 | $validMonitorCount = $monitorFiles.Count - $invalidMonitors.Count 32 | Write-Host "$validMonitorCount/$($monitorFiles.Count) monitors are valid" 33 | 34 | if ($invalidMonitors.Count -gt 0) { 35 | Write-Warning "Invalid monitors:`n$($invalidMonitors | Out-String)" 36 | exit 1 37 | } 38 | -------------------------------------------------------------------------------- /azure/monitors/loadbalancer-healthprobestatusavailability.json: -------------------------------------------------------------------------------- 1 | { 2 | "name": "Azure Load Balancer Health Probe Status (DIP) Availability is Degraded on {{name.name}}", 3 | "type": "query alert", 4 | "query": "avg(last_1h):avg:azure.network_loadbalancers.health_probe_status{name:kubernetes,subscription_name:*} by {name,resource_group,region,subscription_name,subscription_id} <= 50", 5 | "message": "DIP is only {{value}}% available on Load Balancer {{name.name}}.\n\nDIP refers to the health probe status, which indicates how Load Balancer views the health of your application, as indicated by your [health probe configuration](https://docs.microsoft.com/en-us/azure/load-balancer/load-balancer-custom-probe-overview).\n\nSee [dashboard](https://app.datadoghq.com/dash/integration/71/azure-overview?tpl_var_subscription_name%5B0%5D={{subscription_name.name}}&live=true&tile_focus=6188478116498776).", 6 | "tags": [], 7 | "options": { 8 | "thresholds": { 9 | "critical": 50, 10 | "critical_recovery": 99, 11 | "warning": 80, 12 | "warning_recovery": 90 13 | }, 14 | "notify_audit": false, 15 | "require_full_window": false, 16 | "notify_no_data": false, 17 | "renotify_interval": 0, 18 | "include_tags": true, 19 | "new_group_delay": 60, 20 | "evaluation_delay": 300, 21 | "silenced": {} 22 | }, 23 | "priority": null, 24 | "restricted_roles": null 25 | } 26 | -------------------------------------------------------------------------------- /scripts/AwesomeDatadog/functions/Test-Monitor.ps1: -------------------------------------------------------------------------------- 1 | function Test-Monitor { 2 | [CmdletBinding()] 3 | param ( 4 | [Parameter(Mandatory = $true, Position = 0)] 5 | [string]$MonitorFile, 6 | [Parameter(Mandatory = $false)] 7 | [string]$ApiKey = $env:DD_API_KEY, 8 | [Parameter(Mandatory = $false)] 9 | [string]$AppKey = $env:DD_APP_KEY 10 | ) 11 | 12 | $ErrorActionPreference = "Stop" 13 | 14 | # Test file path 15 | if (-not (Test-Path $MonitorFile)) { 16 | Write-Error "File not found: $MonitorFile" 17 | exit 1 18 | } 19 | 20 | # Import the monitor export file 21 | $monitor = Get-Content $MonitorFile | ConvertFrom-Json 22 | $monitor.tags += "managed_by:awesome-datadog" 23 | $monitorJson = $monitor | ConvertTo-Json -Depth 10 24 | 25 | Write-Debug "Monitor: $monitorJson" 26 | Write-Host "Validating monitor `"$($monitor.name)`"" 27 | 28 | try { 29 | Invoke-WebRequest ` 30 | -Uri "https://api.datadoghq.com/api/v1/monitor/validate" ` 31 | -ContentType "application/json" ` 32 | -Method Post ` 33 | -UseBasicParsing ` 34 | -Headers @{"DD-API-KEY" = $ApiKey; "DD-APPLICATION-KEY" = $AppKey } ` 35 | -Body $monitorJson 36 | $isValid = $true 37 | } 38 | catch { 39 | Write-Warning $_.Exception.Message 40 | $isValid = $false 41 | } 42 | 43 | if ($isValid) { Write-Verbose "Monitor is Valid" } else { Write-Warning "Monitor is Invalid" } 44 | 45 | return $isValid 46 | } -------------------------------------------------------------------------------- /scripts/AwesomeDatadog/functions/Search-Monitor.ps1: -------------------------------------------------------------------------------- 1 | function Search-Monitor { 2 | [CmdletBinding()] 3 | param ( 4 | [Parameter(Mandatory = $true, Position = 0)] 5 | [string]$MonitorFile, 6 | [Parameter(Mandatory = $false)] 7 | [string]$ApiKey = $env:DD_API_KEY, 8 | [Parameter(Mandatory = $false)] 9 | [string]$AppKey = $env:DD_APP_KEY 10 | ) 11 | 12 | $ErrorActionPreference = "Stop" 13 | 14 | # Test file path 15 | if (-not (Test-Path $MonitorFile)) { 16 | Write-Error "File not found: $MonitorFile" 17 | exit 1 18 | } 19 | 20 | # Import the monitor export file 21 | $monitor = Get-Content $MonitorFile | ConvertFrom-Json 22 | $monitorName = $monitor.name 23 | $monitorNameSanitized = $monitorName -replace "[^a-zA-Z0-9 ._]", "" 24 | $query = @{ 25 | query = $monitorNameSanitized 26 | } 27 | 28 | Write-Debug "Monitor: $monitorNameSanitized" 29 | Write-Debug "Query: $($query | Out-String)" 30 | Write-Host "Searching for monitor `"$monitorName`"" 31 | 32 | $monitorSearchResult = Invoke-WebRequest ` 33 | -Uri " https://api.datadoghq.com/api/v1/monitor/search" ` 34 | -Method Get ` 35 | -UseBasicParsing ` 36 | -Headers @{"DD-API-KEY" = $ApiKey; "DD-APPLICATION-KEY" = $AppKey } ` 37 | -Body $query ` 38 | | ConvertFrom-Json 39 | 40 | Write-Debug "Monitor search results: $($monitorSearchResult | ConvertTo-Json -Depth 10)" 41 | 42 | if ($monitorSearchResult.monitors.Count -ne 1) { 43 | Write-Host "Monitor not found: $monitorNameSanitized" 44 | return $null 45 | } 46 | 47 | $monitorId = $monitorSearchResult.monitors[0].id 48 | 49 | return $monitorId 50 | } -------------------------------------------------------------------------------- /scripts/Publish-Monitors.ps1: -------------------------------------------------------------------------------- 1 | [CmdletBinding()] 2 | param ( 3 | [Parameter(Mandatory = $false)] 4 | [string]$ApiKey = $env:DD_API_KEY, 5 | [Parameter(Mandatory = $false)] 6 | [string]$AppKey = $env:DD_APP_KEY 7 | ) 8 | 9 | $ErrorActionPreference = "Stop" 10 | 11 | Import-Module -Name $PSScriptRoot/AwesomeDatadog/AwesomeDatadog.psm1 -Force 12 | 13 | # Get all *.json files in the monitors directories 14 | Write-Host "Getting all monitors from the monitors directories" 15 | $monitorFiles = Get-ChildItem -Path $PSScriptRoot/../*/monitors/*.json -Recurse 16 | 17 | Write-Host "Found $($monitorFiles.Count) monitors" 18 | Write-Debug "Monitor files: $monitorFiles" 19 | 20 | $invalidMonitors = @() 21 | 22 | foreach ($monitorFile in $monitorFiles) { 23 | # Validate the monitor 24 | $isValid = Test-Monitor -MonitorFile $monitorFile.FullName -ApiKey $ApiKey -AppKey $AppKey -Debug:$DebugPreference -Verbose:$VerbosePreference 25 | if (!$isValid) { 26 | Write-Warning "Monitor `"$($monitorFile.FullName)`" is invalid" 27 | $invalidMonitors += $monitorFile.FullName 28 | continue 29 | } 30 | 31 | # Try to get the monitor 32 | $monitorId = Search-Monitor -MonitorFile $monitorFile.FullName -ApiKey $ApiKey -AppKey $AppKey -Debug:$DebugPreference -Verbose:$VerbosePreference 33 | 34 | if ($monitorId) { 35 | # If the monitor exists, update it 36 | Write-Host "Updating monitor $($monitorFile.Name)" 37 | Update-Monitor -MonitorId $monitorId -MonitorFile $monitorFile.FullName -ApiKey $ApiKey -AppKey $AppKey -Debug:$DebugPreference -Verbose:$VerbosePreference 38 | } 39 | else { 40 | # If the monitor does not exist, create it 41 | Write-Host "Creating monitor $($monitorFile.Name)" 42 | New-Monitor -MonitorFile $monitorFile.FullName -ApiKey $ApiKey -AppKey $AppKey -Debug:$DebugPreference -Verbose:$VerbosePreference 43 | } 44 | } 45 | 46 | $validMonitorCount = $monitorFiles.Count - $invalidMonitors.Count 47 | Write-Host "$validMonitorCount/$($monitorFiles.Count) monitors were published" 48 | Write-Host "Done publishing monitors 🎉" 49 | 50 | if ($invalidMonitors.Count -gt 0) { 51 | Write-Warning "Invalid monitors:`n$($invalidMonitors | Out-String)" 52 | exit 1 53 | } 54 | -------------------------------------------------------------------------------- /scripts/AwesomeDatadog/AwesomeDatadog.psd1: -------------------------------------------------------------------------------- 1 | # 2 | # Module manifest for module 'AwesomeDatadog' 3 | # 4 | # Generated by: philip-gai 5 | # 6 | # Generated on: 11/11/2022 7 | # 8 | 9 | @{ 10 | 11 | # Script module or binary module file associated with this manifest. 12 | # RootModule = '' 13 | 14 | # Version number of this module. 15 | ModuleVersion = '1.0' 16 | 17 | # Supported PSEditions 18 | # CompatiblePSEditions = @() 19 | 20 | # ID used to uniquely identify this module 21 | GUID = 'bd1ab391-109c-4aea-a018-d0ed9d1e98e6' 22 | 23 | # Author of this module 24 | Author = 'philip-gai' 25 | 26 | # Company or vendor of this module 27 | CompanyName = 'philip-gai' 28 | 29 | # Copyright statement for this module 30 | Copyright = '(c) philip-gai. All rights reserved.' 31 | 32 | # Description of the functionality provided by this module 33 | # Description = '' 34 | 35 | # Minimum version of the PowerShell engine required by this module 36 | # PowerShellVersion = '' 37 | 38 | # Name of the PowerShell host required by this module 39 | # PowerShellHostName = '' 40 | 41 | # Minimum version of the PowerShell host required by this module 42 | # PowerShellHostVersion = '' 43 | 44 | # Minimum version of Microsoft .NET Framework required by this module. This prerequisite is valid for the PowerShell Desktop edition only. 45 | # DotNetFrameworkVersion = '' 46 | 47 | # Minimum version of the common language runtime (CLR) required by this module. This prerequisite is valid for the PowerShell Desktop edition only. 48 | # ClrVersion = '' 49 | 50 | # Processor architecture (None, X86, Amd64) required by this module 51 | # ProcessorArchitecture = '' 52 | 53 | # Modules that must be imported into the global environment prior to importing this module 54 | # RequiredModules = @() 55 | 56 | # Assemblies that must be loaded prior to importing this module 57 | # RequiredAssemblies = @() 58 | 59 | # Script files (.ps1) that are run in the caller's environment prior to importing this module. 60 | # ScriptsToProcess = @() 61 | 62 | # Type files (.ps1xml) to be loaded when importing this module 63 | # TypesToProcess = @() 64 | 65 | # Format files (.ps1xml) to be loaded when importing this module 66 | # FormatsToProcess = @() 67 | 68 | # Modules to import as nested modules of the module specified in RootModule/ModuleToProcess 69 | # NestedModules = @() 70 | 71 | # Functions to export from this module, for best performance, do not use wildcards and do not delete the entry, use an empty array if there are no functions to export. 72 | FunctionsToExport = @( 73 | "Search-Monitor", 74 | "New-Monitor", 75 | "Test-Monitor", 76 | "Update-Monitor" 77 | ) 78 | 79 | # Cmdlets to export from this module, for best performance, do not use wildcards and do not delete the entry, use an empty array if there are no cmdlets to export. 80 | CmdletsToExport = @() 81 | 82 | # Variables to export from this module 83 | VariablesToExport = '*' 84 | 85 | # Aliases to export from this module, for best performance, do not use wildcards and do not delete the entry, use an empty array if there are no aliases to export. 86 | AliasesToExport = @() 87 | 88 | # DSC resources to export from this module 89 | # DscResourcesToExport = @() 90 | 91 | # List of all modules packaged with this module 92 | # ModuleList = @() 93 | 94 | # List of all files packaged with this module 95 | # FileList = @() 96 | 97 | # Private data to pass to the module specified in RootModule/ModuleToProcess. This may also contain a PSData hashtable with additional module metadata used by PowerShell. 98 | PrivateData = @{ 99 | 100 | PSData = @{ 101 | 102 | # Tags applied to this module. These help with module discovery in online galleries. 103 | # Tags = @() 104 | 105 | # A URL to the license for this module. 106 | # LicenseUri = '' 107 | 108 | # A URL to the main website for this project. 109 | # ProjectUri = '' 110 | 111 | # A URL to an icon representing this module. 112 | # IconUri = '' 113 | 114 | # ReleaseNotes of this module 115 | # ReleaseNotes = '' 116 | 117 | # Prerelease string of this module 118 | # Prerelease = '' 119 | 120 | # Flag to indicate whether the module requires explicit user acceptance for install/update/save 121 | # RequireLicenseAcceptance = $false 122 | 123 | # External dependent modules of this module 124 | # ExternalModuleDependencies = @() 125 | 126 | } # End of PSData hashtable 127 | 128 | } # End of PrivateData hashtable 129 | 130 | # HelpInfo URI of this module 131 | # HelpInfoURI = '' 132 | 133 | # Default prefix for commands exported from this module. Override the default prefix using Import-Module -Prefix. 134 | # DefaultCommandPrefix = '' 135 | 136 | } 137 | 138 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # awesome-datadog 2 | 3 | [![Awesome](https://awesome.re/badge-flat2.svg)](https://awesome.re) 4 | 5 | ![awesome-datadog-logo](https://user-images.githubusercontent.com/17363579/199892152-799ce2c9-cb98-40f1-aa0b-753120ad76f1.png) 6 | 7 | See Datadog docs for [exporting and importing monitors](https://docs.datadoghq.com/monitors/create/#exporting-and-importing-monitors). 8 | 9 | ## Monitors 10 | 11 | - [Azure](./azure/monitors/) 12 | - [Azure AKS Cluster Reporting Unhealthy Status](./azure/monitors/akscluster-unhealthy.json) 13 | - [Azure Compute Quota Usage is High](./azure/monitors/compute-quotusagepercentage.json) 14 | - [Azure Container Service Managed Clusters Node Disk Usage Percentage](./azure/monitors/containerservice-managedclusters-nodediskusagepercentage.json) 15 | - [Azure Datadog Integration Data is Missing](./azure/monitors/datadog-integration-data-missing.json) 16 | - [Azure Load Balancer Data Path (VIP) Availability is Degraded](./azure/monitors/loadbalancer-datapathavailability.json) 17 | - [Azure Load Balancer Health Probe Status (DIP) Availability is Degraded](./azure/monitors/loadbalancer-healthprobestatusavailability.json) 18 | - [Azure Redis Cache CPU Usage is High](./azure/monitors/rediscache-percentprocessortime.json) 19 | - [Azure Redis Cache Memory Usage is High](./azure/monitors/rediscache-usedmemorypercentage.json) 20 | - [Azure SQL Server Database Connection Failure Rate](./azure/monitors/sqlserverdatabases-connectionfailurerate.json) 21 | - [Azure SQL Server Database Deadlocks](./azure/monitors/sqlserverdatabases-deadlocks.json) 22 | - [Azure SQL Server Database DTU Consumption is High](./azure/monitors/sqlserverdatabases-dtuconsumptionpercent.json) 23 | - [Azure SQL Server Database Log Write Percent](./azure/monitors/sqlserverdatabases-logwritepercent.json) 24 | - [Azure SQL Server Database Physical Data Read Percent](./azure/monitors/sqlserverdatabases-physicaldatareadpercent.json) 25 | - [Azure SQL Server Database Storage Percent](./azure/monitors/sqlserverdatabases-storagepercent.json) 26 | - [Azure SQL Server Database Workers Percent](./azure/monitors/sqlserverdatabases-workerspercent.json) 27 | - [.NET](./dotnet/monitors/) 28 | - [ASP.NET Core Request Queue Length](./dotnet/monitors/aspnetcore-requests-queuelength.json) 29 | - [Dotnet Runtime Data is Missing](./dotnet/monitors/data-missing.json) 30 | - [Dotnet Runtime Exception Type Anomalies](./dotnet/monitors/exceptiontype-anomalies.json) 31 | - [Dotnet GC Memory Load is High](./dotnet/monitors/gc-memoryload.json) 32 | - [Kubernetes](./kubernetes/monitors/) 33 | - [Kubernetes Container CPU Usage](./kubernetes/monitors/container-cpu-usage.json) 34 | - [Kubernetes Container Memory Usage](./kubernetes/monitors/container-memory-usage.json) 35 | - [Kubernetes Container was OOM Killed](./kubernetes/monitors/container-oomkilled.json) 36 | - [Kubernetes Datadog Agent Data is Missing](./kubernetes/monitors/data-missing.json) 37 | - [Kubernetes Deployments Replica Not Available](./kubernetes/monitors/deployment-replicas-available.json) 38 | - [Kubernetes Namespace Status Failed](./kubernetes/monitors/namespace-pods.json) 39 | - [Kubernetes Nodes Unschedulable](./kubernetes/monitors/nodes-unschedulable/) 40 | - [Kubernetes Pod CrashloopBackOff](./kubernetes/monitors/pod-crashloopbackoff/) 41 | - [Kubernetes Pod ImagePullBackOff](./kubernetes/monitors/pod-imagepullbackoff/) 42 | - [Kubernetes Service Network Errors](./kubernetes/monitors/service-networkerrors.json) 43 | - [Kubernetes Statefulset Replicas Ready](./kubernetes/monitors/statefulset-replicas-ready.json) 44 | - Pull requests welcome 😊. See [contributing](#contributing). 45 | 46 | ## Dashboards 47 | 48 | - Pull requests welcome 😊. See [contributing](#contributing). 49 | 50 | ## Contributing 51 | 52 | Pull requests welcome! Please suggest improvements to the monitors, troubleshooting guides, etc. 53 | 54 | See Datadog docs for [exporting and importing monitors](https://docs.datadoghq.com/monitors/create/#exporting-and-importing-monitors). 55 | 56 | For monitors: 57 | 58 | 1. Export the monitor from Datadog and name the monitor file `.json`. 59 | 2. Create a folder or find an existing folder related to the service or technology you are monitoring. 60 | 3. If you are providing a troubleshooting guide (TSG), then create a folder `title-of-monitor` with a `README.md` and the monitor file `.json`. Put the TSG in the `README.md`. 61 | 4. Link to your monitor from this page. 62 | 63 | For dashboards: 64 | 65 | 1. Export the dashboard from Datadog and name the dashboard file `.json`. 66 | 2. Create a folder or find an existing folder related to the service or technology for your dashboard. 67 | 3. Create or find a `dashboards` folder in the service or technology folder. 68 | 4. Create a folder for your new dashboard named ``. 69 | 5. Add your dashboard template inside the `` folder. 70 | 6. Create a `README.md` inside the `` folder with pictures and an explanation of the dashboard. 71 | 7. Link to your dashboard folder from this page. 72 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | --------------------------------------------------------------------------------