Sy/slurm integration

.codecov.yml

@@ -314,18 +314,18 @@ coverage:
         target: 75
         flags:
         - kong
-      KubeVirt_Handler:
+      KubeVirt_API:
         target: 75
         flags:
-        - kubevirt_handler
+        - kubevirt_api
       KubeVirt_Controller:
         target: 75
         flags:
         - kubevirt_controller
-      KubeVirt_API:
+      KubeVirt_Handler:
         target: 75
         flags:
-        - kubevirt_api
+        - kubevirt_handler
       Kube_DNS:
         target: 75
         flags:
@@ -550,6 +550,10 @@ coverage:
         target: 75
         flags:
         - singlestore
+      Slurm:
+        target: 75
+        flags:
+        - slurm
       Snowflake:
         target: 75
         flags:
@@ -1175,21 +1179,21 @@ flags:
     paths:
     - kubernetes_state/datadog_checks/kubernetes_state
     - kubernetes_state/tests
-  kubevirt_handler:
+  kubevirt_api:
     carryforward: true
     paths:
-    - kubevirt_handler/datadog_checks/kubevirt_handler
-    - kubevirt_handler/tests
+    - kubevirt_api/datadog_checks/kubevirt_api
+    - kubevirt_api/tests
   kubevirt_controller:
     carryforward: true
     paths:
     - kubevirt_controller/datadog_checks/kubevirt_controller
     - kubevirt_controller/tests
-  kubevirt_api:
+  kubevirt_handler:
     carryforward: true
     paths:
-    - kubevirt_api/datadog_checks/kubevirt_api
-    - kubevirt_api/tests
+    - kubevirt_handler/datadog_checks/kubevirt_handler
+    - kubevirt_handler/tests
   kyototycoon:
     carryforward: true
     paths:
@@ -1410,6 +1414,11 @@ flags:
     paths:
     - singlestore/datadog_checks/singlestore
     - singlestore/tests
+  slurm:
+    carryforward: true
+    paths:
+    - slurm/datadog_checks/slurm
+    - slurm/tests
   snmp:
     carryforward: true
     paths:

.github/workflows/test-all.yml

@@ -3154,6 +3154,26 @@ jobs:
       minimum-base-package: ${{ inputs.minimum-base-package }}
       pytest-args: ${{ inputs.pytest-args }}
     secrets: inherit
+  j1e78283:
+    uses: ./.github/workflows/test-target.yml
+    with:
+      job-name: Slurm
+      target: slurm
+      platform: linux
+      runner: '["ubuntu-22.04"]'
+      repo: "${{ 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
   j06ca546:
     uses: ./.github/workflows/test-target.yml
     with:

slurm/CHANGELOG.md

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

slurm/README.md

@@ -0,0 +1,60 @@
+# Agent Check: Slurm
+
+## Overview
+
+This check monitors [Slurm][1] through the Datadog Agent. 
+
+Include a high level overview of what this integration does:
+- What does your product do (in 1-2 sentences)?
+- What value will customers get from this integration, and why is it valuable to them?
+- What specific data will your integration monitor, and what's the value of that data?
+
+## 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 Slurm check is included in the [Datadog Agent][2] package.
+No additional installation is needed on your server.
+
+### Configuration
+
+1. Edit the `slurm.d/conf.yaml` file, in the `conf.d/` folder at the root of your Agent's configuration directory to start collecting your slurm performance data. See the [sample slurm.d/conf.yaml][4] for all available configuration options.
+
+2. [Restart the Agent][5].
+
+### Validation
+
+[Run the Agent's status subcommand][6] and look for `slurm` under the Checks section.
+
+## Data Collected
+
+### Metrics
+
+See [metadata.csv][7] for a list of metrics provided by this integration.
+
+### Events
+
+The Slurm integration does not include any events.
+
+### Service Checks
+
+The Slurm 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/slurm/datadog_checks/slurm/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/slurm/metadata.csv
+[8]: https://github.com/DataDog/integrations-core/blob/master/slurm/assets/service_checks.json
+[9]: https://docs.datadoghq.com/help/

slurm/assets/configuration/spec.yaml

@@ -0,0 +1,133 @@
+name: Slurm
+files:
+- name: slurm.yaml
+  options:
+  - template: init_config
+    options:
+      - name: slurm_binaries_dir
+        description: |
+          The directory at which all the Slurm binaries are located. These are mainly:
+          sinfo, sacct, sdiag, sshare and sdiag.
+        value:
+          type: string
+          example: /usr/bin/
+      - template: init_config/default
+  - template: instances
+    options:
+    - name: collect_sinfo_stats
+      description: Whether or not to collect statistics from the sinfo command.
+      value:
+        type: boolean
+        example: True
+    - name: collect_sdiag_stats
+      description: Whether or not to collect statistics from the sdiag command.
+      value:
+        type: boolean
+        example: True
+    - name: collect_squeue_stats
+      description: Whether or not to collect statistics from the squeue command.
+      value:
+        type: boolean
+        example: True
+    - name: collect_sacct_stats
+      description: Whether or not to collect statistics from the sacct command.
+      value:
+        type: boolean
+        example: True
+    - name: collect_sshare_stats
+      description: Whether or not to collect statistics from the sshare command.
+      value:
+        type: boolean
+        example: True
+    - name: collect_gpu_stats
+      description: Whether or not to collect GPU statistics when Slurm is configured to use GPUs.
+      value:
+        type: boolean
+        example: False
+    - name: sinfo_collection_level
+      description: |
+        The level of detail to collect from the sinfo command. The default is 'basic'. Available options are 1, 2 and
+        3. Level 1 collects data only for partitions. Level 2 collects data from individual nodes. Level 3 
+        collects data from from individual nodes as well but will be more verbose and include data such as CPU and 
+        memory usage as reported from the OS as well as additional tags.
+      value:
+        type: integer
+        example: 1
+    - name: sinfo_path
+      description: Full path to the sinfo binary.
+      value:
+        type: string
+        example: /usr/bin/sinfo
+    - name: sacct_path
+      description: Full path to the sacct binary.
+      value:
+        type: string
+        example: /usr/bin/sacct
+    - name: sdiag_path
+      description: Full path to the sdiag binary.
+      value:
+        type: string
+        example: /usr/bin/sdiag
+    - name: sshare_path
+      description: Full path to the sshare binary.
+      value:
+        type: string
+        example: /usr/bin/sshare
+    - name: squeue_path
+      description: Full path to the squeue binary.
+      value:
+        type: string
+        example: /usr/bin/squeue
+    - name: debug_sinfo_stats
+      description: |
+        Whether or not to enable debug logging for the sinfo command. This will log the output of the sinfo command
+        to the agent log.
+      value:
+        type: boolean
+        example: False
+      hidden: True
+    - name: debug_sdiag_stats
+      description: |
+        Whether or not to enable debug logging for the sdiag command. This will log the output of the sdiag command
+        to the agent log.
+      value:
+        type: boolean
+        example: False
+      hidden: True
+    - name: debug_squeue_stats
+      description: |
+        Whether or not to enable debug logging for the squeue command. This will log the output of the squeue command
+        to the agent log.
+      value:
+        type: boolean
+        example: False
+      hidden: True
+    - name: debug_sshare_stats
+      description: |
+        Whether or not to enable debug logging for the sshare command. This will log the output of the sshare command
+        to the agent log.
+      value:
+        type: boolean
+        example: False
+      hidden: True
+    - name: debug_sacct_stats
+      description: |
+        Whether or not to enable debug logging for the sacct command. This will log the output of the sacct command
+        to the agent log.
+      value:
+        type: boolean
+        example: False
+      hidden: True
+    - template: instances/default
+      overrides:
+        min_collection_interval.description: |
+          This changes the collection interval of the check. For more information, see:
+          https://docs.datadoghq.com/developers/write_agent_check/#collection-interval
+
+          Most Slurm metrics are collected from calling the different binaries. Depending on the size of the slurm cluster,
+          this can be a very expensive operation. It is recommended to set this to a higher value than the default 15 
+          seconds, but this can be adjusted based on the size of the cluster and the desired granularity of the metrics.
+        min_collection_interval.value.display_default: 15
+        min_collection_interval.value.default: 60
+        min_collection_interval.value.example: 60
+        min_collection_interval.enabled: true

slurm/assets/dashboards/slurm_overview.json

@@ -0,0 +1 @@
+{}

slurm/assets/service_checks.json

@@ -0,0 +1 @@
+[]

slurm/changelog.d/1.added

@@ -0,0 +1 @@
+Initial Release

slurm/datadog_checks/__init__.py

@@ -0,0 +1,4 @@
+# (C) Datadog, Inc. 2024-present
+# All rights reserved
+# Licensed under a 3-clause BSD style license (see LICENSE)
+__path__ = __import__('pkgutil').extend_path(__path__, __name__)  # type: ignore

slurm/datadog_checks/slurm/__about__.py

@@ -0,0 +1,4 @@
+# (C) Datadog, Inc. 2024-present
+# All rights reserved
+# Licensed under a 3-clause BSD style license (see LICENSE)
+__version__ = '0.0.1'

slurm/datadog_checks/slurm/__init__.py

@@ -0,0 +1,7 @@
+# (C) Datadog, Inc. 2024-present
+# All rights reserved
+# Licensed under a 3-clause BSD style license (see LICENSE)
+from .__about__ import __version__
+from .check import SlurmCheck
+
+__all__ = ['__version__', 'SlurmCheck']