# Systemd USER unit: gpu-exporter (both Dankclaw and Dankserver).
#
# Install path: ~/.config/systemd/user/gpu-exporter.service
# Installed and enabled by deploy_gpu_exporter in scripts/deploy-remote.sh.
#
# Per-GPU metrics (utilization / VRAM / temperature / power) for the mixed
# AMD + NVIDIA fleet, scraped by Prometheus. Like signal-relay it is a plain
# user unit, not a quadlet: it runs python3 straight from the checkout (a pull
# updates it with no copy step), a hand-written user unit can be enabled where
# the podman v1 generator's units cannot, and with Linger=yes for dank it starts
# at boot. It reads the host's own cgroup/drm sysfs and shells to nvidia-smi, so
# it must run on the host — a container would need GPU/DRM passthrough for
# nothing gained.
#
# BINDING. The base unit serves loopback only. deploy_gpu_exporter writes a
# drop-in adding THIS host's LAN address (the same two-address posture
# node-exporter and cadvisor use), so the endpoint is never a wildcard. It is
# unauthenticated metrics on the LAN, identical to node-exporter :9100 and
# cadvisor :8080 — Prometheus reaches same-host via host.containers.internal and
# the Dankserver instance over the LAN from Dankclaw.

[Unit]
Description=GPU metrics exporter (amdgpu sysfs + nvidia-smi)
After=network-online.target
Wants=network-online.target

[Service]
# Loopback by default; the deploy drop-in appends the host LAN address.
Environment=GPU_EXPORTER_BINDS=127.0.0.1
ExecStart=/usr/bin/python3 /home/dank/serverAppConfigs/scripts/gpu-exporter.py --serve
Restart=always
RestartSec=5

[Install]
WantedBy=default.target