feat: new nvme-exporter role

roles/nvme_exporter/README.md

@@ -0,0 +1,53 @@
+<p><img src="https://www.circonus.com/wp-content/uploads/2015/03/sol-icon-itOps.png" alt="graph logo" title="graph" align="right" height="60" /></p>
+
+# Ansible Role: NVMe exporter
+
+## Description
+
+Deploy prometheus [NVMe exporter](https://github.com/E4-Computer-Engineering/nvme-exporter) using ansible.
+
+## Requirements
+
+- gnu-tar on Mac deployer host (`brew install gnu-tar`)
+- The `nvme-cli` package (version 2.3 or above) and root privileges are recommended on the target host for full functionality. The exporter still starts without them, but scrapes will fail and increment the `nvme_exporter_scrape_failures_total` metric.
+
+## Role Variables
+
+All variables which can be overridden are stored in [defaults/main.yml](defaults/main.yml) file as well as in [meta/argument_specs.yml](meta/argument_specs.yml).
+Please refer to the [collection docs](https://prometheus-community.github.io/ansible/branch/main/nvme_exporter_role.html) for description and default values of the variables.
+
+## Example
+
+### Playbook
+
+Use it in a playbook as follows:
+
+```yaml
+- hosts: all
+  roles:
+    - prometheus.prometheus.nvme_exporter
+```
+
+### Demo site
+
+We provide an example site that demonstrates a full monitoring solution based on prometheus and grafana. The repository with code and links to running instances is [available on github](https://github.com/prometheus/demo-site) and the site is hosted on [DigitalOcean](https://digitalocean.com).
+
+## Local Testing
+
+The preferred way of locally testing the role is to use Docker and [molecule](https://github.com/ansible-community/molecule) (v3.x). You will have to install Docker on your system. See "Get started" for a Docker package suitable for your system. Running your tests is as simple as executing `molecule test`.
+
+## Continuous Integration
+
+Combining molecule and circle CI allows us to test how new PRs will behave when used with multiple ansible versions and multiple operating systems. This also allows use to create test scenarios for different role configurations. As a result we have quite a large test matrix which can take more time than local testing, so please be patient.
+
+## Contributing
+
+See [contributor guideline](CONTRIBUTING.md).
+
+## Troubleshooting
+
+See [troubleshooting](TROUBLESHOOTING.md).
+
+## License
+
+This project is licensed under MIT License. See [LICENSE](/LICENSE) for more details.

roles/nvme_exporter/defaults/main.yml

@@ -0,0 +1,23 @@
+---
+nvme_exporter_version: 3.0.0
+nvme_exporter_binary_url: "https://github.com/{{ _nvme_exporter_repo }}/releases/download/v{{ nvme_exporter_version }}/\
+                          nvme_exporter_{{ nvme_exporter_version }}_{{ ansible_facts['system'] | lower }}_{{ _nvme_exporter_go_ansible_arch }}.tar.gz"
+nvme_exporter_checksums_url: "https://github.com/{{ _nvme_exporter_repo }}/releases/download/v{{ nvme_exporter_version }}/checksums.txt"
+
+nvme_exporter_web_listen_address: "0.0.0.0:9998"
+nvme_exporter_web_telemetry_path: "/metrics"
+
+# Collector management. When nvme_exporter_disable_defaults is true only the
+# collectors listed in nvme_exporter_enabled_collectors are enabled. Collectors
+# in nvme_exporter_disabled_collectors are always disabled.
+nvme_exporter_disable_defaults: false
+nvme_exporter_enabled_collectors: []
+nvme_exporter_disabled_collectors: []
+
+nvme_exporter_binary_install_dir: "/usr/local/bin"
+nvme_exporter_system_group: "nvme-exp"
+nvme_exporter_system_user: "{{ nvme_exporter_system_group }}"
+
+nvme_exporter_config_dir: "/etc/nvme_exporter"
+# Local path to stash the archive and its extraction
+nvme_exporter_local_cache_path: "/tmp/nvme_exporter-{{ ansible_facts['system'] | lower }}-{{ _nvme_exporter_go_ansible_arch }}/{{ nvme_exporter_version }}"

roles/nvme_exporter/handlers/main.yml

@@ -0,0 +1,10 @@
+---
+- name: Restart nvme_exporter
+  listen: "restart nvme_exporter"
+  become: true
+  ansible.builtin.systemd:
+    daemon_reload: true
+    name: nvme_exporter
+    state: restarted
+  when:
+    - not ansible_check_mode

roles/nvme_exporter/meta/argument_specs.yml

@@ -0,0 +1,62 @@
+---
+# yamllint disable rule:line-length
+argument_specs:
+  main:
+    short_description: "Prometheus NVMe Exporter"
+    description:
+      - "Deploy prometheus L(NVMe exporter,https://github.com/E4-Computer-Engineering/nvme-exporter) using ansible"
+    author:
+      - "Prometheus Community"
+    options:
+      nvme_exporter_version:
+        description: "NVMe exporter package version. Also accepts latest as parameter."
+        default: "3.0.0"
+      nvme_exporter_binary_url:
+        description: "URL of the NVMe exporter binaries .tar.gz file"
+        default: "https://github.com/{{ _nvme_exporter_repo }}/releases/download/v{{ nvme_exporter_version }}/nvme_exporter_{{ nvme_exporter_version }}_{{ ansible_facts['system'] | lower }}_{{ _nvme_exporter_go_ansible_arch }}.tar.gz"
+      nvme_exporter_checksums_url:
+        description: "URL of the NVMe exporter checksums file"
+        default: "https://github.com/{{ _nvme_exporter_repo }}/releases/download/v{{ nvme_exporter_version }}/checksums.txt"
+      nvme_exporter_web_listen_address:
+        description: "Address on which NVMe exporter will listen"
+        default: "0.0.0.0:9998"
+      nvme_exporter_web_telemetry_path:
+        description: "Path under which to expose metrics"
+        default: "/metrics"
+      nvme_exporter_disable_defaults:
+        description: "Disable all default collectors. Only the collectors listed in O(nvme_exporter_enabled_collectors) will be enabled."
+        type: "bool"
+        default: false
+      nvme_exporter_enabled_collectors:
+        description:
+          - "List of collectors to enable explicitly (for example C(info), C(smart), C(ocp))."
+          - "Mostly useful in combination with O(nvme_exporter_disable_defaults)."
+        type: "list"
+        elements: "str"
+        default: []
+      nvme_exporter_disabled_collectors:
+        description: "List of collectors to disable explicitly (for example C(ocp))."
+        type: "list"
+        elements: "str"
+        default: []
+      nvme_exporter_binary_install_dir:
+        description:
+          - "I(Advanced)"
+          - "Directory to install nvme_exporter binary"
+        default: "/usr/local/bin"
+      nvme_exporter_system_group:
+        description:
+          - "I(Advanced)"
+          - "System group for NVMe exporter"
+        default: "nvme-exp"
+      nvme_exporter_system_user:
+        description:
+          - "I(Advanced)"
+          - "NVMe exporter user"
+        default: "nvme-exp"
+      nvme_exporter_local_cache_path:
+        description: "Local path to stash the archive and its extraction"
+        default: "/tmp/nvme_exporter-{{ ansible_facts['system'] | lower }}-{{ _nvme_exporter_go_ansible_arch }}/{{ nvme_exporter_version }}"
+      nvme_exporter_config_dir:
+        description: "Path to directory with nvme_exporter configuration"
+        default: "/etc/nvme_exporter"

roles/nvme_exporter/meta/main.yml

@@ -0,0 +1,27 @@
+---
+galaxy_info:
+  author: "Prometheus Community"
+  description: "NVMe exporter"
+  license: "Apache"
+  min_ansible_version: "2.14"
+  platforms:
+    - name: "Ubuntu"
+      versions:
+        - "jammy"
+        - "noble"
+    - name: "Debian"
+      versions:
+        - "bullseye"
+        - "bookworm"
+    - name: "EL"
+      versions:
+        - "9"
+        - "10"
+  galaxy_tags:
+    - "monitoring"
+    - "prometheus"
+    - "exporter"
+    - "metrics"
+    - "system"
+    - "nvme"
+    - "smart"

roles/nvme_exporter/molecule/alternative/molecule.yml

@@ -0,0 +1,19 @@
+---
+provisioner:
+  playbooks:
+    prepare: "${MOLECULE_PROJECT_DIRECTORY}/../../.config/molecule/alternative/prepare.yml"
+  inventory:
+    group_vars:
+      all:
+        nvme_exporter_local_cache_path: "/tmp/nvme_exporter-linux-amd64"
+        nvme_exporter_web_listen_address: "127.0.0.1:8080"
+        nvme_exporter_web_telemetry_path: "/nvme-metrics"
+        nvme_exporter_disable_defaults: true
+        nvme_exporter_enabled_collectors:
+          - "info"
+          - "smart"
+        nvme_exporter_disabled_collectors:
+          - "ocp"
+        nvme_exporter_version: 2.2.0
+        nvme_exporter_binary_url: "https://github.com/E4-Computer-Engineering/nvme-exporter/releases/download/v{{\
+                                  \ nvme_exporter_version }}/nvme_exporter_{{ nvme_exporter_version }}_linux_amd64.tar.gz"

roles/nvme_exporter/molecule/alternative/tests/test_alternative.py

@@ -0,0 +1,53 @@
+from __future__ import (absolute_import, division, print_function)
+__metaclass__ = type
+
+from testinfra_helpers import get_target_hosts
+
+testinfra_hosts = get_target_hosts()
+
+
+def test_directories(host):
+    dirs = [
+        "/etc/nvme_exporter"
+    ]
+    for dir in dirs:
+        d = host.file(dir)
+        assert d.is_directory
+        assert d.exists
+
+
+def test_service(host):
+    s = host.service("nvme_exporter")
+    try:
+        assert s.is_running
+    except AssertionError:
+        # Capture service logs
+        journal_output = host.run('journalctl -u nvme_exporter --since "1 hour ago"')
+        print("\n==== journalctl -u nvme_exporter Output ====\n")
+        print(journal_output)
+        print("\n============================================\n")
+        raise  # Re-raise the original assertion error
+
+
+def test_protecthome_property(host):
+    s = host.service("nvme_exporter")
+    p = s.systemd_properties
+    assert p.get("ProtectHome") == "yes"
+
+
+def test_collector_flags(host):
+    f = host.file("/etc/systemd/system/nvme_exporter.service")
+    assert f.contains("--collector.disable-defaults")
+    assert f.contains("--collector.info")
+    assert f.contains("--collector.smart")
+    assert f.contains("--no-collector.ocp")
+    assert f.contains("--web.telemetry-path=/nvme-metrics")
+
+
+def test_socket(host):
+    sockets = [
+        "tcp://127.0.0.1:8080"
+    ]
+    for socket in sockets:
+        s = host.socket(socket)
+        assert s.is_listening

roles/nvme_exporter/molecule/default/molecule.yml

@@ -0,0 +1,6 @@
+---
+provisioner:
+  inventory:
+    group_vars:
+      all:
+        nvme_exporter_web_listen_address: "127.0.0.1:9998"

roles/nvme_exporter/molecule/default/tests/test_default.py

@@ -0,0 +1,76 @@
+from __future__ import (absolute_import, division, print_function)
+__metaclass__ = type
+
+from testinfra_helpers import get_target_hosts
+
+testinfra_hosts = get_target_hosts()
+
+
+def test_directories(host):
+    dirs = [
+        "/etc/nvme_exporter"
+    ]
+    for dir in dirs:
+        d = host.file(dir)
+        assert d.is_directory
+        assert d.exists
+
+
+def test_files(host):
+    files = [
+        "/etc/systemd/system/nvme_exporter.service",
+        "/usr/local/bin/nvme_exporter"
+    ]
+    for file in files:
+        f = host.file(file)
+        assert f.exists
+        assert f.is_file
+
+
+def test_permissions_didnt_change(host):
+    dirs = [
+        "/etc",
+        "/root",
+        "/usr",
+        "/var"
+    ]
+    for file in dirs:
+        f = host.file(file)
+        assert f.exists
+        assert f.is_directory
+        assert f.user == "root"
+        assert f.group == "root"
+
+
+def test_user(host):
+    assert host.group("nvme-exp").exists
+    assert "nvme-exp" in host.user("nvme-exp").groups
+    assert host.user("nvme-exp").shell == "/usr/sbin/nologin"
+
+
+def test_service(host):
+    s = host.service("nvme_exporter")
+    try:
+        assert s.is_running
+    except AssertionError:
+        # Capture service logs
+        journal_output = host.run('journalctl -u nvme_exporter --since "1 hour ago"')
+        print("\n==== journalctl -u nvme_exporter Output ====\n")
+        print(journal_output)
+        print("\n============================================\n")
+        raise  # Re-raise the original assertion error
+
+
+def test_protecthome_property(host):
+    s = host.service("nvme_exporter")
+    p = s.systemd_properties
+    assert p.get("ProtectHome") == "yes"
+
+
+def test_socket(host):
+    sockets = [
+        "tcp://127.0.0.1:9998"
+    ]
+    for socket in sockets:
+        s = host.socket(socket)
+        assert s.is_listening

roles/nvme_exporter/molecule/latest/molecule.yml

@@ -0,0 +1,6 @@
+---
+provisioner:
+  inventory:
+    group_vars:
+      all:
+        nvme_exporter_version: latest

roles/nvme_exporter/molecule/latest/tests/test_latest.py

@@ -0,0 +1,41 @@
+from __future__ import (absolute_import, division, print_function)
+__metaclass__ = type
+
+from testinfra_helpers import get_target_hosts
+import pytest
+
+testinfra_hosts = get_target_hosts()
+
+
+@pytest.mark.parametrize("files", [
+    "/etc/systemd/system/nvme_exporter.service",
+    "/usr/local/bin/nvme_exporter"
+])
+def test_files(host, files):
+    f = host.file(files)
+    assert f.exists
+    assert f.is_file
+
+
+def test_service(host):
+    s = host.service("nvme_exporter")
+    try:
+        assert s.is_running
+    except AssertionError:
+        # Capture service logs
+        journal_output = host.run('journalctl -u nvme_exporter --since "1 hour ago"')
+        print("\n==== journalctl -u nvme_exporter Output ====\n")
+        print(journal_output)
+        print("\n============================================\n")
+        raise  # Re-raise the original assertion error
+
+
+def test_protecthome_property(host):
+    s = host.service("nvme_exporter")
+    p = s.systemd_properties
+    assert p.get("ProtectHome") == "yes"
+
+
+def test_socket(host):
+    s = host.socket("tcp://0.0.0.0:9998")
+    assert s.is_listening