alexandre.pires
350650ecc2
- Create systemd service templates for llama_exporter, nvidia_exporter, and podman. - Add Prometheus configuration template for GPU metrics scraping. - Introduce variables for GPU monitoring role in main.yml. - Implement tasks for syncing llama models, including user setup and package installation. - Update podman tasks to ensure proper sudo access and lingering for the podman user. - Modify inventory to include gpu_monitoring group. - Add Terraform modules for deploying Vaultwarden, including ingress and service configurations. - Create Grafana dashboard for real-time GPU monitoring metrics. - Update secrets and environment files to include Vaultwarden admin token.
35 lines
832 B
Django/Jinja
35 lines
832 B
Django/Jinja
# nvidia_gpu_exporter - Prometheus exporter for NVIDIA GPUs via NVML
|
|
#
|
|
# Exposes GPU metrics at /metrics port {{ nvidia_exporter_port }}
|
|
|
|
[Unit]
|
|
Description=NVIDIA GPU Prometheus Exporter
|
|
After=network-online.target
|
|
Wants=network-online.target
|
|
|
|
[Service]
|
|
Type=simple
|
|
User={{ nvidia_exporter_user }}
|
|
Group={{ nvidia_exporter_user }}
|
|
WorkingDirectory={{ nvidia_exporter_install_dir }}
|
|
Environment="PYTHONUNBUFFERED=1"
|
|
ExecStart={{ nvidia_exporter_venv_path }}/bin/python3 {{ nvidia_exporter_script_path }}
|
|
Restart=on-failure
|
|
RestartSec=5
|
|
TimeoutStopSec=10
|
|
StandardOutput=journal
|
|
StandardError=journal
|
|
|
|
# Security hardening
|
|
NoNewPrivileges=true
|
|
ProtectSystem=strict
|
|
ProtectHome=true
|
|
ReadOnlyPaths=/sys
|
|
PrivateTmp=true
|
|
ProtectKernelTunables=true
|
|
ProtectKernelModules=true
|
|
ProtectControlGroups=true
|
|
|
|
[Install]
|
|
WantedBy=multi-user.target
|