Order nvidia-fabricmanager after bee-nvidia to fix boot race

bee-nvidia.service loads NVIDIA kernel modules; without After=bee-nvidia.service
fabricmanager starts before /dev/nvidiactl is ready, fails, and relies on
systemd restart to recover (~38s delay on affected systems).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Mikhail Chusavitin
2026-06-18 10:11:52 +03:00
parent 966944d6d8
commit 20766ccc76

View File

@@ -1,3 +1,8 @@
[Unit]
# bee-nvidia.service loads the NVIDIA kernel modules; fabricmanager must wait
# for them to be fully initialized before attempting to open /dev/nvidiactl.
After=bee-nvidia.service
[Service]
# Skip fabricmanager on systems without NVSwitch hardware.
# ExecCondition exits 1-254 → unit is silently skipped (inactive, not failed).