tomasz-syn-grzegorza
359afb3a59
Infrastructure configs for GMKtec K11 (Docker, vLLM, LocalAI, ComfyUI, control-plane, gpu-fan agent, Server UI with CLI/file explorer/GPU fan curve). Co-authored-by: Cursor <cursoragent@cursor.com>
75 lines
2.3 KiB
Bash
Executable File
75 lines
2.3 KiB
Bash
Executable File
#!/usr/bin/env bash
|
||
# Diagnose gpu-fan port conflicts and running instances.
|
||
set -euo pipefail
|
||
|
||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||
STACK_DIR="$(cd "${SCRIPT_DIR}/.." && pwd)"
|
||
|
||
OPT_ENV="/opt/control-plane/.env"
|
||
REPO_ENV="${STACK_DIR}/../control-plane/.env"
|
||
|
||
echo "=== gpu-fan status ==="
|
||
echo ""
|
||
|
||
if systemctl list-unit-files gpu-fan.service &>/dev/null; then
|
||
echo "systemd:"
|
||
systemctl is-active gpu-fan 2>/dev/null && systemctl status gpu-fan --no-pager -l 2>/dev/null | head -8 || echo " inactive"
|
||
else
|
||
echo "systemd: gpu-fan.service not installed"
|
||
fi
|
||
echo ""
|
||
|
||
echo "Ports 8090–8099:"
|
||
if ss -tlnp 2>/dev/null | grep -E ':809[0-9]' ; then
|
||
:
|
||
elif ss -tln 2>/dev/null | grep -E ':809[0-9]' ; then
|
||
echo " (run as root for process names: sudo ss -tlnp)"
|
||
else
|
||
echo " (none listening)"
|
||
fi
|
||
echo ""
|
||
|
||
echo "gpu-fan processes:"
|
||
pgrep -af '/opt/gpu-fan/.venv/bin/python|stacks/gpu-fan/.venv/bin/python|gpu-fan/app.py' 2>/dev/null \
|
||
|| echo " (none)"
|
||
echo ""
|
||
|
||
echo "Shell suspended jobs (Ctrl+Z):"
|
||
if jobs -l 2>/dev/null | grep -q .; then
|
||
jobs -l
|
||
echo " Kill with: kill %<job-number>"
|
||
else
|
||
echo " (none in this shell)"
|
||
fi
|
||
echo ""
|
||
|
||
echo "GPU_FAN_API_PORT config:"
|
||
[[ -f "${OPT_ENV}" ]] && echo " /opt/control-plane/.env: $(grep '^GPU_FAN_API_PORT=' "${OPT_ENV}" || echo '(not set)')"
|
||
[[ -f "${REPO_ENV}" ]] && echo " repo control-plane: $(grep '^GPU_FAN_API_PORT=' "${REPO_ENV}" || echo '(not set)')"
|
||
echo " Note: production uses /opt/control-plane/.env (shared with Server UI)"
|
||
echo ""
|
||
|
||
if [[ "${1:-}" == "--cleanup" ]]; then
|
||
if [[ "${EUID}" -ne 0 ]]; then
|
||
echo "ERROR: --cleanup requires root: sudo ${SCRIPT_DIR}/status.sh --cleanup"
|
||
exit 1
|
||
fi
|
||
echo "=== cleanup ==="
|
||
systemctl stop gpu-fan 2>/dev/null || true
|
||
pkill -f '/opt/gpu-fan/.venv/bin/python /opt/gpu-fan/app.py' 2>/dev/null || true
|
||
pkill -f 'stacks/gpu-fan/.venv/bin/python app.py' 2>/dev/null || true
|
||
sleep 0.5
|
||
if ss -tln 2>/dev/null | grep -qE ':809[0-9]'; then
|
||
echo "WARNING: ports still in use:"
|
||
ss -tlnp 2>/dev/null | grep -E ':809[0-9]' || ss -tln | grep -E ':809[0-9]'
|
||
echo "Check suspended jobs in other shells: jobs -l"
|
||
else
|
||
echo "Ports 809x are free."
|
||
fi
|
||
echo ""
|
||
echo "Start production instance:"
|
||
echo " sudo systemctl start gpu-fan"
|
||
echo "Or foreground debug (systemd stopped):"
|
||
echo " sudo ${SCRIPT_DIR}/start.sh"
|
||
fi
|