Mikhail Chusavitin
33d6eee9cf
Add NVLink port status (nvidia-smi nvlink -s), error counters (nvidia-smi nvlink -e), and dcgmi nvlink status to the support bundle, and enrich HardwarePCIeDevice entries with per-link telemetry. Replace the raw nv-hostengine pkill/restart dance in bee-nvidia-load with systemctl restart/start of nvidia-dcgm.service, and order bee-nvidia.service Before= nvidia-dcgm.service and nvidia-fabricmanager.service so modules/device nodes exist before those units start.
17 lines
552 B
Desktop File
17 lines
552 B
Desktop File
[Unit]
|
|
Description=Bee: load NVIDIA kernel modules and create device nodes
|
|
After=local-fs.target udev.service bee-blackbox.service
|
|
Before=bee-audit.service nvidia-dcgm.service nvidia-fabricmanager.service
|
|
# Skip silently if bee-nvidia-load is absent (non-nvidia builds).
|
|
ConditionPathExists=/usr/local/bin/bee-nvidia-load
|
|
|
|
[Service]
|
|
Type=oneshot
|
|
ExecStart=/usr/local/bin/bee-log-run /appdata/bee/export/bee-nvidia.log /usr/local/bin/bee-nvidia-load
|
|
StandardOutput=journal
|
|
StandardError=journal
|
|
RemainAfterExit=yes
|
|
|
|
[Install]
|
|
WantedBy=multi-user.target
|