Add Azure IoT Edge integration

.azure-pipelines/changes.yml

@@ -27,7 +27,7 @@ jobs:
 - template: './templates/test-single-windows.yml'
   parameters:
     job_name: Changed
-    check: '--changed datadog_checks_base datadog_checks_dev active_directory aspdotnet disk dns_check dotnetclr exchange_server iis pdh_check sqlserver tcp_check win32_event_log windows_service wmi_check'
+    check: '--changed datadog_checks_base datadog_checks_dev active_directory aspdotnet azure_iot_edge disk dns_check dotnetclr exchange_server iis pdh_check sqlserver tcp_check win32_event_log windows_service wmi_check'
     display: Windows
     pip_cache_config:
       key: 'pip | $(Agent.OS) | datadog_checks_base/datadog_checks/base/data/agent_requirements.in'

.azure-pipelines/templates/test-all-checks.yml

@@ -49,6 +49,12 @@ jobs:
     - checkName: aspdotnet
       displayName: ASP.NET
       os: windows
+    - checkName: azure_iot_edge
+      displayName: Azure IoT Edge
+      os: linux
+    - checkName: azure_iot_edge
+      displayName: Azure IoT Edge
+      os: windows
     - checkName: btrfs
       displayName: Btrfs
       os: linux

.codecov.yml

@@ -51,6 +51,10 @@ coverage:
         target: 75
         flags:
         - apache
+      Azure IoT Edge:
+        target: 75
+        flags:
+        - azure_iot_edge
       Btrfs:
         target: 75
         flags:
@@ -565,6 +569,11 @@ flags:
     paths:
     - aspdotnet/datadog_checks/aspdotnet
     - aspdotnet/tests
+  azure_iot_edge:
+    carryforward: true
+    paths:
+    - azure_iot_edge/datadog_checks/azure_iot_edge
+    - azure_iot_edge/tests
   btrfs:
     carryforward: true
     paths:

azure_iot_edge/CHANGELOG.md

@@ -0,0 +1,2 @@
+# CHANGELOG - Azure IoT Edge
+

azure_iot_edge/MANIFEST.in

@@ -0,0 +1,10 @@
+graft datadog_checks
+graft tests
+
+include MANIFEST.in
+include README.md
+include requirements.in
+include requirements-dev.txt
+include manifest.json
+
+global-exclude *.py[cod] __pycache__

azure_iot_edge/README.md

@@ -0,0 +1,114 @@
+# Agent Check: Azure IoT Edge
+
+## Overview
+
+[Azure IoT Edge][1] is a fully managed service to deploy Cloud workloads to run on Internet of Things (IoT) edge devices via standard containers.
+
+Use the Datadog-Azure IoT Edge integration to collect metrics and health status from IoT Edge devices.
+
+**Note**: this integration requires IoT Edge runtime version 1.0.10 or above.
+
+## Setup
+
+Follow the instructions below to install and configure this check for an IoT Edge device running on a device host.
+
+### Installation
+
+The Azure IoT Edge check is included in the [Datadog Agent][2] package.
+
+No additional installation is needed on your device.
+
+### Configuration
+
+It is recommended to configure the IoT Edge device so that the Agent runs as a custom module. Follow the official Microsoft documentation on [deploying Azure IoT Edge modules][3] for general information on installing and working with custom modules for Azure IoT Edge.
+
+Follow the steps below to configure the IoT Edge device, runtime modules, and the Datadog Agent to start collecting IoT Edge metrics.
+
+1. Configure the **Edge Agent** runtime module as follows:
+    - Image version must be `1.0.10` or above.
+    - Under "Create Options", add the following `Labels`. Edit the `com.datadoghq.ad.instances` label as appropriate. See the [sample azure_iot_edge.d/conf.yaml][5] for all available configuration options. See the documentation on [Docker Integrations Autodiscovery][6] for more information on labels-based integration configuration.
+
+        ```json
+        "Labels": {
+            "com.datadoghq.ad.check_names": "[\"azure_iot_edge\"]",
+            "com.datadoghq.ad.init_configs": "[{}]",
+            "com.datadoghq.ad.instances": "[{\"edge_hub_prometheus_url\": \"http://edgeHub:9600/metrics\", \"edge_agent_prometheus_url\": \"http://edgeAgent:9600/metrics\"}]"
+        }
+        ```
+
+    - Under "Environment Variables", experimental metrics must be enabled by adding these environment variables (note the double underscores):
+        - `ExperimentalFeatures__Enabled`: `true`
+        - `ExperimentalFeatures__EnableMetrics`: `true`
+
+1. Configure the **Edge Hub** runtime module as follows:
+    - Image version must be `1.0.10` or above.
+    - Under "Environment Variables", experimental metrics must be enabled by adding these environment variables (note the double underscores):
+        - `ExperimentalFeatures__Enabled`: `true`
+        - `ExperimentalFeatures__EnableMetrics`: `true`
+
+1. Install and configure the Datadog Agent as a **custom module**:
+    - Set the module name. For example: `datadog-agent`.
+    - Set the Agent image URI. For example: `datadog/agent:7`.
+    - Under "Environment Variables", configure your `DD_API_KEY`. You may also set extra Agent configuration here (see [Agent Environment Variables][4]).
+    - Under "Container Create Options", enter the following configuration based on your device OS. **Note**: `NetworkId` must correspond to the network name set in the device `config.yaml` file.
+
+        - Linux:
+            ```json
+            {
+                "HostConfig": {
+                    "NetworkMode": "default",
+                    "Env": ["NetworkId=azure-iot-edge"],
+                    "Binds": ["/var/run/docker.sock:/var/run/docker.sock"]
+                }
+            }
+            ```
+        - Windows:
+            ```json
+            {
+                "HostConfig": {
+                    "NetworkMode": "default",
+                    "Env": ["NetworkId=nat"],
+                    "Binds": ["//./pipe/iotedge_moby_engine:/./pipe/docker_engine"]
+                }
+            }
+            ```
+
+    - Save the Datadog Agent custom module.
+
+1. Save and deploy changes to your device configuration.
+
+### Validation
+
+Once the Agent has been deployed to the device, [run the Agent's status subcommand][7] and look for `azure_iot_edge` under the Checks section.
+
+## Data Collected
+
+### Metrics
+
+See [metadata.csv][8] for a list of metrics provided by this check.
+
+### Service Checks
+
+**azure.iot_edge.edge_agent.prometheus.health**:
+Returns `CRITICAL` if the Agent is unable to reach the Edge Agent metrics Prometheus endpoint. Returns `OK` otherwise.
+
+**azure.iot_edge.edge_hub.prometheus.health**:
+Returns `CRITICAL` if the Agent is unable to reach the Edge Hub metrics Prometheus endpoint. Returns `OK` otherwise.
+
+### Events
+
+Azure IoT Edge does not include any events.
+
+## Troubleshooting
+
+Need help? Contact [Datadog support][9].
+
+[1]: https://azure.microsoft.com/en-us/services/iot-edge/
+[2]: https://docs.datadoghq.com/agent/
+[3]: https://docs.microsoft.com/en-us/azure/iot-edge/how-to-deploy-modules-portal
+[4]: https://docs.datadoghq.com/agent/guide/environment-variables/
+[5]: https://github.com/DataDog/integrations-core/blob/master/azure_iot_edge/datadog_checks/azure_iot_edge/data/conf.yaml.example
+[6]: https://docs.datadoghq.com/agent/docker/integrations/
+[7]: https://docs.datadoghq.com/agent/guide/agent-commands/#agent-status-and-information
+[8]: https://github.com/DataDog/integrations-core/blob/master/azure_iot_edge/metadata.csv
+[9]: https://docs.datadoghq.com/help/

azure_iot_edge/assets/configuration/spec.yaml

@@ -0,0 +1,24 @@
+name: Azure IoT Edge
+files:
+  - name: azure_iot_edge.yaml
+    options:
+      - template: init_config
+        options:
+          - template: init_config/default
+      - template: instances
+        options:
+          - name: edge_hub_prometheus_url
+            description: |
+              The URL where Edge Hub metrics are exposed via Prometheus.
+            required: true
+            value:
+              type: string
+              example: http://edgeHub:9600/metrics
+          - name: edge_agent_prometheus_url
+            description: |
+              The URL where Edge Agent metrics are exposed via Prometheus.
+            required: true
+            value:
+              type: string
+              example: http://edgeAgent:9600/metrics
+          - template: instances/default

azure_iot_edge/assets/monitors/disk_usage.json

@@ -0,0 +1,31 @@
+{
+	"name": "[Azure IoT Edge] IoT Edge device {{host}} is running out of available disk space",
+	"type": "query alert",
+	"query": "max(last_1h):avg:azure.iot_edge.edge_agent.available_disk_space_bytes{*} by {host} / avg:azure.iot_edge.edge_agent.total_disk_space_bytes{*} by {host}.rollup(max, 60) * 100 < 10",
+	"message": "Please check device {{host}}, as Edge Agent reports that available disk space has dropped below {{threshold}}%.",
+	"tags": [
+		"integration:azure_iot_edge"
+	],
+	"options": {
+		"notify_audit": false,
+		"locked": false,
+		"timeout_h": 0,
+		"silenced": {},
+		"include_tags": true,
+		"no_data_timeframe": null,
+		"require_full_window": true,
+		"new_host_delay": 300,
+		"notify_no_data": false,
+		"renotify_interval": 0,
+		"escalation_message": "",
+		"thresholds": {
+			"critical": 10,
+			"warning": 25,
+			"critical_recovery": 11,
+			"warning_recovery": 26
+		}
+	},
+	"recommended_monitor_metadata": {
+		"description": "Triggers an alert when an IoT Edge device is running out of available disk space"
+	}
+}

azure_iot_edge/assets/monitors/edgehub_retries.json

@@ -0,0 +1,32 @@
+{
+	"name": "[Azure IoT Edge] Rate of Edge Hub operations retries is higher than usual on device device {{host}}",
+	"type": "query alert",
+	"query": "avg(last_1h):anomalies(per_minute(avg:azure.iot_edge.edge_hub.operation_retry_total{*} by {host}), 'basic', 2, direction='above', alert_window='last_15m', interval=60, count_default_zero='true') >= 1",
+	"message": "Please check device {{host}}, as Edge Hub reports a rate of operation retries of {{value}} per minute, which is higher than usual.",
+	"tags": [
+		"integration:azure_iot_edge"
+	],
+	"options": {
+		"notify_audit": false,
+		"locked": false,
+		"timeout_h": 0,
+		"new_host_delay": 300,
+		"require_full_window": false,
+		"notify_no_data": false,
+		"renotify_interval": "0",
+		"escalation_message": "",
+		"no_data_timeframe": null,
+		"include_tags": true,
+		"thresholds": {
+			"critical": 1,
+			"critical_recovery": 0
+		},
+		"threshold_windows": {
+			"trigger_window": "last_15m",
+			"recovery_window": "last_15m"
+		}
+	},
+	"recommended_monitor_metadata": {
+		"description": "Notifies when rate of Edge Hub operation retries is higher than usual"
+	}
+}

azure_iot_edge/assets/monitors/iothub_syncs.json

@@ -0,0 +1,32 @@
+{
+	"name": "[Azure IoT Edge] Rate of unsuccessful syncs with IoT Hub is higher than usual on device {{host}}",
+	"type": "query alert",
+	"query": "avg(last_1h):anomalies(per_minute(avg:azure.iot_edge.edge_agent.unsuccessful_iothub_syncs_total{*} by {host}), 'basic', 2, direction='above', alert_window='last_15m', interval=60, count_default_zero='true') >= 1",
+	"message": "Number of unsuccessful syncs between Edge Agent and IoT Hub on device {{host}} is at {{value}} per minute, which is higher than usual.",
+	"tags": [
+		"integration:azure_iot_edge"
+	],
+	"options": {
+		"notify_audit": false,
+		"locked": false,
+		"timeout_h": 0,
+		"new_host_delay": 300,
+		"require_full_window": false,
+		"notify_no_data": false,
+		"renotify_interval": "0",
+		"escalation_message": "",
+		"no_data_timeframe": null,
+		"include_tags": true,
+		"thresholds": {
+			"critical": 1,
+			"critical_recovery": 0
+		},
+		"threshold_windows": {
+			"trigger_window": "last_15m",
+			"recovery_window": "last_15m"
+		}
+	},
+	"recommended_monitor_metadata": {
+		"description": "Notifies when unsuccessful syncs between Edge Agent and IoT Hub are higher than usual"
+	}
+}

azure_iot_edge/assets/monitors/memory_usage.json

@@ -0,0 +1,31 @@
+{
+	"name": "[Azure IoT Edge] IoT Edge device {{host}} is running out of memory",
+	"type": "query alert",
+	"query": "max(last_1h):avg:azure.iot_edge.edge_agent.used_memory_bytes{*} by {host} / avg:azure.iot_edge.edge_agent.total_memory_bytes{*} by {host}.rollup(max, 60) * 100 > 80",
+	"message": "Please check device {{host}}, as Edge Agent reports usage of more than {{threshold}}% of available RAM for the last hour.",
+	"tags": [
+		"integration:azure_iot_edge"
+	],
+	"options": {
+		"notify_audit": false,
+		"locked": false,
+		"timeout_h": 0,
+		"silenced": {},
+		"include_tags": true,
+		"no_data_timeframe": null,
+		"require_full_window": true,
+		"new_host_delay": 300,
+		"notify_no_data": false,
+		"renotify_interval": 0,
+		"escalation_message": "",
+		"thresholds": {
+			"critical": 80,
+			"warning": 65,
+			"critical_recovery": 79,
+			"warning_recovery": 64
+		}
+	},
+	"recommended_monitor_metadata": {
+		"description": "Triggers an alert when an IoT Edge device is running out of memory"
+	}
+}

azure_iot_edge/assets/service_checks.json

@@ -0,0 +1,32 @@
+[
+    {
+        "agent_version": "6.24.0",
+        "integration": "Azure IoT Edge",
+        "groups": [
+            "host",
+            "endpoint"
+        ],
+        "check": "azure.iot_edge.edge_agent.prometheus.health",
+        "statuses": [
+            "ok",
+            "critical"
+        ],
+        "name": "Edge Agent health",
+        "description": "Returns `CRITICAL` if the Agent is unable to reach the Edge Agent metrics Prometheus endpoint. Returns `OK` otherwise."
+    },
+    {
+        "agent_version": "6.24.0",
+        "integration": "Azure IoT Edge",
+        "groups": [
+            "host",
+            "endpoint"
+        ],
+        "check": "azure.iot_edge.edge_hub.prometheus.health",
+        "statuses": [
+            "ok",
+            "critical"
+        ],
+        "name": "Edge Hub health",
+        "description": "Returns `CRITICAL` if the Agent is unable to reach the Edge Hub metrics Prometheus endpoint. Returns `OK` otherwise."
+    }
+]

azure_iot_edge/datadog_checks/__init__.py

@@ -0,0 +1,4 @@
+# (C) Datadog, Inc. 2020-present
+# All rights reserved
+# Licensed under a 3-clause BSD style license (see LICENSE)
+__path__ = __import__('pkgutil').extend_path(__path__, __name__)  # type: ignore

azure_iot_edge/datadog_checks/azure_iot_edge/__about__.py

@@ -0,0 +1,4 @@
+# (C) Datadog, Inc. 2020-present
+# All rights reserved
+# Licensed under a 3-clause BSD style license (see LICENSE)
+__version__ = '0.0.1'

azure_iot_edge/datadog_checks/azure_iot_edge/__init__.py

@@ -0,0 +1,7 @@
+# (C) Datadog, Inc. 2020-present
+# All rights reserved
+# Licensed under a 3-clause BSD style license (see LICENSE)
+from .__about__ import __version__
+from .check import AzureIoTEdgeCheck
+
+__all__ = ['__version__', 'AzureIoTEdgeCheck']