Skip to content

fail fast when FabricManager fails to come up #908

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
tariq1890 merged 1 commit into from
Aug 10, 2026
Merged

fail fast when FabricManager fails to come up #908

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions rhel10/nvidia-driver
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -773,13 +773,13 @@ _start_daemons() {
--fm-config-file $fm_config_file \
--fm-pid-file $fm_pid_file \
--nvlsm-config-file $nvlsm_config_file \
--nvlsm-pid-file $nvlsm_pid_file
--nvlsm-pid-file $nvlsm_pid_file || return 1

# If not a NVLink5+ switch, check for the presence of NVLink4 (or below) switches
elif _assert_nvswitch_system; then
_configure_fabric_manager
echo "Starting NVIDIA fabric manager daemon..."
nv-fabricmanager -c /usr/share/nvidia/nvswitch/fabricmanager.cfg
nv-fabricmanager -c /usr/share/nvidia/nvswitch/fabricmanager.cfg || return 1
fi
}

Expand Down
4 changes: 2 additions & 2 deletions rhel10/precompiled/nvidia-driver
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -268,12 +268,12 @@ _load_driver() {
--fm-config-file $fm_config_file \
--fm-pid-file $fm_pid_file \
--nvlsm-config-file $nvlsm_config_file \
--nvlsm-pid-file $nvlsm_pid_file
--nvlsm-pid-file $nvlsm_pid_file || return 1

# If not a NVLink5+ switch, check for the presence of NVLink4 (or below) switches
elif _assert_nvswitch_system; then
echo "Starting NVIDIA fabric manager daemon..."
nv-fabricmanager -c /usr/share/nvidia/nvswitch/fabricmanager.cfg
nv-fabricmanager -c /usr/share/nvidia/nvswitch/fabricmanager.cfg || return 1
fi
}

Expand Down
4 changes: 2 additions & 2 deletions rhel8/nvidia-driver
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -750,13 +750,13 @@ _start_daemons() {
--fm-config-file $fm_config_file \
--fm-pid-file $fm_pid_file \
--nvlsm-config-file $nvlsm_config_file \
--nvlsm-pid-file $nvlsm_pid_file
--nvlsm-pid-file $nvlsm_pid_file || return 1

# If not a NVLink5+ switch, check for the presence of NVLink4 (or below) switches
elif _assert_nvswitch_system; then
_configure_fabric_manager
echo "Starting NVIDIA fabric manager daemon..."
nv-fabricmanager -c /usr/share/nvidia/nvswitch/fabricmanager.cfg
nv-fabricmanager -c /usr/share/nvidia/nvswitch/fabricmanager.cfg || return 1
fi
}

Expand Down
2 changes: 1 addition & 1 deletion rhel8/precompiled/nvidia-driver
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -210,7 +210,7 @@ _load_driver() {

if _assert_nvswitch_system; then
echo "Starting NVIDIA fabric manager daemon..."
nv-fabricmanager -c /usr/share/nvidia/nvswitch/fabricmanager.cfg
nv-fabricmanager -c /usr/share/nvidia/nvswitch/fabricmanager.cfg || return 1
fi
}

Expand Down
4 changes: 2 additions & 2 deletions rhel9/nvidia-driver
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -769,13 +769,13 @@ _start_daemons() {
--fm-config-file $fm_config_file \
--fm-pid-file $fm_pid_file \
--nvlsm-config-file $nvlsm_config_file \
--nvlsm-pid-file $nvlsm_pid_file
--nvlsm-pid-file $nvlsm_pid_file || return 1

# If not a NVLink5+ switch, check for the presence of NVLink4 (or below) switches
elif _assert_nvswitch_system; then
_configure_fabric_manager
echo "Starting NVIDIA fabric manager daemon..."
nv-fabricmanager -c /usr/share/nvidia/nvswitch/fabricmanager.cfg
nv-fabricmanager -c /usr/share/nvidia/nvswitch/fabricmanager.cfg || return 1
fi
}

Expand Down
4 changes: 2 additions & 2 deletions rhel9/precompiled/nvidia-driver
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -294,12 +294,12 @@ _load_driver() {
--fm-config-file $fm_config_file \
--fm-pid-file $fm_pid_file \
--nvlsm-config-file $nvlsm_config_file \
--nvlsm-pid-file $nvlsm_pid_file
--nvlsm-pid-file $nvlsm_pid_file || return 1

# If not a NVLink5+ switch, check for the presence of NVLink4 (or below) switches
elif _assert_nvswitch_system; then
echo "Starting NVIDIA fabric manager daemon..."
nv-fabricmanager -c /usr/share/nvidia/nvswitch/fabricmanager.cfg
nv-fabricmanager -c /usr/share/nvidia/nvswitch/fabricmanager.cfg || return 1
fi
}

Expand Down
8 changes: 3 additions & 5 deletions ubuntu22.04/nvidia-driver
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -377,9 +377,7 @@ _load_driver() {
set +o xtrace -o nounset
fi

_start_daemons

return 0
_start_daemons || return 1
}

# Stop persistenced and unload the kernel modules if they are currently loaded.
Expand Down Expand Up @@ -714,13 +712,13 @@ _start_daemons() {
--fm-config-file $fm_config_file \
--fm-pid-file $fm_pid_file \
--nvlsm-config-file $nvlsm_config_file \
--nvlsm-pid-file $nvlsm_pid_file
--nvlsm-pid-file $nvlsm_pid_file || return 1

# If not a NVLink5+ switch, check for the presence of NVLink4 (or below) switches
elif _assert_nvswitch_system; then
_configure_fabric_manager
echo "Starting NVIDIA fabric manager daemon..."
nv-fabricmanager -c /usr/share/nvidia/nvswitch/fabricmanager.cfg
nv-fabricmanager -c /usr/share/nvidia/nvswitch/fabricmanager.cfg || return 1
fi
}

Expand Down
8 changes: 3 additions & 5 deletions ubuntu22.04/precompiled/nvidia-driver
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -269,20 +269,18 @@ _load_driver() {
--fm-config-file $fm_config_file \
--fm-pid-file $fm_pid_file \
--nvlsm-config-file $nvlsm_config_file \
--nvlsm-pid-file $nvlsm_pid_file
--nvlsm-pid-file $nvlsm_pid_file || return 1

# If not a NVLink5+ switch, check for the presence of NVLink4 (or below) switches
elif _assert_nvswitch_system; then
echo "Installing NVIDIA fabric manager and libnvidia NSCQ packages..."
fabricmanager_install
nscq_install
imex_install

echo "Starting NVIDIA fabric manager daemon..."
nv-fabricmanager -c /usr/share/nvidia/nvswitch/fabricmanager.cfg
nv-fabricmanager -c /usr/share/nvidia/nvswitch/fabricmanager.cfg || return 1
fi

return 0
}

# Stop persistenced and unload the kernel modules if they are currently loaded.
Expand Down
8 changes: 3 additions & 5 deletions ubuntu24.04/nvidia-driver
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -318,9 +318,7 @@ _load_driver() {
set +o xtrace -o nounset
fi

_start_daemons

return 0
_start_daemons || return 1
}

# Stop persistenced and unload the kernel modules if they are currently loaded.
Expand Down Expand Up @@ -642,13 +640,13 @@ _start_daemons() {
--fm-config-file $fm_config_file \
--fm-pid-file $fm_pid_file \
--nvlsm-config-file $nvlsm_config_file \
--nvlsm-pid-file $nvlsm_pid_file
--nvlsm-pid-file $nvlsm_pid_file || return 1

# If not a NVLink5+ switch, check for the presence of NVLink4 (or below) switches
elif _assert_nvswitch_system; then
_configure_fabric_manager
echo "Starting NVIDIA fabric manager daemon..."
nv-fabricmanager -c /usr/share/nvidia/nvswitch/fabricmanager.cfg
nv-fabricmanager -c /usr/share/nvidia/nvswitch/fabricmanager.cfg || return 1
fi
}

Expand Down
8 changes: 3 additions & 5 deletions ubuntu24.04/precompiled/nvidia-driver
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -270,20 +270,18 @@ _load_driver() {
--fm-config-file $fm_config_file \
--fm-pid-file $fm_pid_file \
--nvlsm-config-file $nvlsm_config_file \
--nvlsm-pid-file $nvlsm_pid_file
--nvlsm-pid-file $nvlsm_pid_file || return 1

# If not a NVLink5+ switch, check for the presence of NVLink4 (or below) switches
elif _assert_nvswitch_system; then
echo "Installing NVIDIA fabric manager and libnvidia NSCQ packages..."
fabricmanager_install
nscq_install
imex_install

echo "Starting NVIDIA fabric manager daemon..."
nv-fabricmanager -c /usr/share/nvidia/nvswitch/fabricmanager.cfg
nv-fabricmanager -c /usr/share/nvidia/nvswitch/fabricmanager.cfg || return 1
fi

return 0
}

# Stop persistenced and unload the kernel modules if they are currently loaded.
Expand Down
8 changes: 3 additions & 5 deletions ubuntu26.04/nvidia-driver
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -330,9 +330,7 @@ _load_driver() {
set +o xtrace -o nounset
fi

_start_daemons

return 0
_start_daemons || return 1
}

# Stop persistenced and unload the kernel modules if they are currently loaded.
Expand Down Expand Up @@ -702,13 +700,13 @@ _start_daemons() {
--fm-config-file $fm_config_file \
--fm-pid-file $fm_pid_file \
--nvlsm-config-file $nvlsm_config_file \
--nvlsm-pid-file $nvlsm_pid_file
--nvlsm-pid-file $nvlsm_pid_file || return 1

# If not a NVLink5+ switch, check for the presence of NVLink4 (or below) switches
elif _assert_nvswitch_system; then
_configure_fabric_manager
echo "Starting NVIDIA fabric manager daemon..."
nv-fabricmanager -c /usr/share/nvidia/nvswitch/fabricmanager.cfg
nv-fabricmanager -c /usr/share/nvidia/nvswitch/fabricmanager.cfg || return 1
fi
}

Expand Down
8 changes: 3 additions & 5 deletions ubuntu26.04/precompiled/nvidia-driver
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -240,20 +240,18 @@ _load_driver() {
--fm-config-file $fm_config_file \
--fm-pid-file $fm_pid_file \
--nvlsm-config-file $nvlsm_config_file \
--nvlsm-pid-file $nvlsm_pid_file
--nvlsm-pid-file $nvlsm_pid_file || return 1

# If not a NVLink5+ switch, check for the presence of NVLink4 (or below) switches
elif _assert_nvswitch_system; then
echo "Installing NVIDIA fabric manager and libnvidia NSCQ packages..."
fabricmanager_install
nscq_install
imex_install

echo "Starting NVIDIA fabric manager daemon..."
nv-fabricmanager -c /usr/share/nvidia/nvswitch/fabricmanager.cfg
nv-fabricmanager -c /usr/share/nvidia/nvswitch/fabricmanager.cfg || return 1
fi

return 0
}

# Stop persistenced and unload the kernel modules if they are currently loaded.
Expand Down