Create Kubeflow Integration (#18391)

* inital set kubeflow

* set config file kubeflow

* implmentation

* metrics

* validation

* labeler

* dash

* monitor

* check

* test typo

* linter

* kubeflow assets

* add units

* fix unit

* fix labler

* fix labler

* fix labler

.codecov.yml

@@ -326,6 +326,10 @@ coverage:
         target: 75
         flags:
         - kube_metrics_server
+      Kubeflow:
+        target: 75
+        flags:
+        - kubeflow
       Kubelet:
         target: 75
         flags:
@@ -1138,6 +1142,11 @@ flags:
     paths:
     - kube_scheduler/datadog_checks/kube_scheduler
     - kube_scheduler/tests
+  kubeflow:
+    carryforward: true
+    paths:
+    - kubeflow/datadog_checks/kubeflow
+    - kubeflow/tests
   kubelet:
     carryforward: true
     paths:

.github/workflows/config/labeler.yml

@@ -279,6 +279,8 @@ integration/kube_proxy:
   - kube_proxy/**/*
 integration/kube_scheduler:
   - kube_scheduler/**/*
+integration/kubeflow:
+  - kubeflow/**/*
 integration/kubelet:
   - kubelet/**/*
 integration/kubernetes:

.github/workflows/test-all.yml

@@ -2094,6 +2094,26 @@ jobs:
       minimum-base-package: ${{ inputs.minimum-base-package }}
       pytest-args: ${{ inputs.pytest-args }}
     secrets: inherit
+  j89c297c:
+    uses: ./.github/workflows/test-target.yml
+    with:
+      job-name: Kubeflow
+      target: kubeflow
+      platform: linux
+      runner: '["ubuntu-22.04"]'
+      repo: "${{ inputs.repo }}"
+      python-version: "${{ inputs.python-version }}"
+      standard: ${{ inputs.standard }}
+      latest: ${{ inputs.latest }}
+      agent-image: "${{ inputs.agent-image }}"
+      agent-image-py2: "${{ inputs.agent-image-py2 }}"
+      agent-image-windows: "${{ inputs.agent-image-windows }}"
+      agent-image-windows-py2: "${{ inputs.agent-image-windows-py2 }}"
+      test-py2: ${{ inputs.test-py2 }}
+      test-py3: ${{ inputs.test-py3 }}
+      minimum-base-package: ${{ inputs.minimum-base-package }}
+      pytest-args: ${{ inputs.pytest-args }}
+    secrets: inherit
   j24a5cff:
     uses: ./.github/workflows/test-target.yml
     with:

kubeflow/CHANGELOG.md

@@ -0,0 +1,4 @@
+# CHANGELOG - Kubeflow
+
+<!-- towncrier release notes start -->
+

kubeflow/README.md

@@ -0,0 +1,92 @@
+# Agent Check: Kubeflow
+
+## Overview
+
+This check monitors [Kubeflow][1] through the Datadog Agent. 
+
+
+## Setup
+
+Follow the instructions below to install and configure this check for an Agent running on a host. For containerized environments, see the [Autodiscovery Integration Templates][3] for guidance on applying these instructions.
+
+### Installation
+
+The Kubeflow check is included in the [Datadog Agent][2] package.
+No additional installation is needed on your server.
+
+### Configuration
+
+1. Edit the `kubeflow.d/conf.yaml` file, in the `conf.d/` folder at the root of your Agent's configuration directory to start collecting your kubeflow performance data. See the [sample kubeflow.d/conf.yaml][4] for all available configuration options.
+
+2. [Restart the Agent][5].
+
+#### Metric collection
+
+Make sure that the Prometheus-formatted metrics are exposed for your `kubeflow` componenet. 
+For the Agent to start collecting metrics, the `kubeflow` pods need to be annotated.
+
+Kubeflow has metrics endpoints that can be accessed on port `9090`. 
+
+**Note**: The listed metrics can only be collected if they are available(depending on the version). Some metrics are generated only when certain actions are performed. 
+
+The only parameter required for configuring the `kubeflow` check is `openmetrics_endpoint`. This parameter should be set to the location where the Prometheus-formatted metrics are exposed. The default port is `9090`. In containerized environments, `%%host%%` should be used for [host autodetection][3]. 
+
+```yaml
+apiVersion: v1
+kind: Pod
+# (...)
+metadata:
+  name: '<POD_NAME>'
+  annotations:
+    ad.datadoghq.com/controller.checks: |
+      {
+        "kubeflow": {
+          "init_config": {},
+          "instances": [
+            {
+              "openmetrics_endpoint": "http://%%host%%:9090/metrics"
+            }
+          ]
+        }
+      }
+    # (...)
+spec:
+  containers:
+    - name: 'controller'
+# (...)
+```
+
+### Validation
+
+[Run the Agent's status subcommand][6] and look for `kubeflow` under the Checks section.
+
+## Data Collected
+
+### Metrics
+
+See [metadata.csv][7] for a list of metrics provided by this integration.
+
+### Events
+
+The Kubeflow integration does not include any events.
+
+### Service Checks
+
+The Kubeflow integration does not include any service checks.
+
+See [service_checks.json][8] for a list of service checks provided by this integration.
+
+## Troubleshooting
+
+Need help? Contact [Datadog support][9].
+
+
+[1]: **LINK_TO_INTEGRATION_SITE**
+[2]: https://app.datadoghq.com/account/settings/agent/latest
+[3]: https://docs.datadoghq.com/agent/kubernetes/integrations/
+[4]: https://github.com/DataDog/integrations-core/blob/master/kubeflow/datadog_checks/kubeflow/data/conf.yaml.example
+[5]: https://docs.datadoghq.com/agent/guide/agent-commands/#start-stop-and-restart-the-agent
+[6]: https://docs.datadoghq.com/agent/guide/agent-commands/#agent-status-and-information
+[7]: https://github.com/DataDog/integrations-core/blob/master/kubeflow/metadata.csv
+[8]: https://github.com/DataDog/integrations-core/blob/master/kubeflow/assets/service_checks.json
+[9]: https://docs.datadoghq.com/help/

kubeflow/assets/configuration/spec.yaml

@@ -0,0 +1,16 @@
+name: Kubeflow
+files:
+- name: kubeflow.yaml
+  options:
+    - template: init_config
+      options:
+        - template: init_config/openmetrics
+    - template: instances
+      options:
+        - template: instances/openmetrics
+          overrides:
+            openmetrics_endpoint.required: true
+            openmetrics_endpoint.value.example: http://<prometheus-service>:9090/metrics
+            openmetrics_endpoint.description: |
+              Endpoint exposing the Kubeflow's Prometheus metrics.
+