Skip to content
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.

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

Kit changes for Nvidia settings APIs #48

Merged
merged 1 commit into from
Aug 1, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
Original file line number Diff line number Diff line change
@@ -0,0 +1,14 @@
[required-extensions]
nvidia-container-runtime = "v1"
std = { version = "v1", helpers = ["default"] }

+++
### generated from the template file ###
accept-nvidia-visible-devices-as-volume-mounts = {{default true settings.nvidia-container-runtime.visible-devices-as-volume-mounts}}
accept-nvidia-visible-devices-envvar-when-unprivileged = {{default false settings.nvidia-container-runtime.visible-devices-envvar-when-unprivileged}}

[nvidia-container-cli]
root = "/"
path = "/usr/bin/nvidia-container-cli"
environment = []
ldconfig = "@/sbin/ldconfig"
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,7 @@ Source3: nvidia-oci-hooks-json
Source4: nvidia-gpu-devices.rules
Source5: nvidia-container-toolkit-tmpfiles-ecs.conf
Source6: nvidia-container-toolkit-tmpfiles-k8s.conf
Source7: nvidia-container-toolkit-config-k8s

BuildRequires: %{_cross_os}glibc-devel
Requires: %{_cross_os}libnvidia-container
Expand Down Expand Up @@ -59,13 +60,16 @@ install -d %{buildroot}%{_cross_templatedir}
install -d %{buildroot}%{_cross_udevrulesdir}
install -d %{buildroot}%{_cross_datadir}/nvidia-container-toolkit
install -d %{buildroot}%{_cross_factorydir}/nvidia-container-runtime
install -d %{buildroot}%{_cross_templatedir}/nvidia-container-runtime
install -p -m 0755 nvidia-container-runtime-hook %{buildroot}%{_cross_bindir}/
install -p -m 0755 nvidia-ctk %{buildroot}%{_cross_bindir}/
install -m 0644 %{S:1} %{S:2} %{buildroot}%{_cross_factorydir}/nvidia-container-runtime/
install -m 0644 %{S:1} %{buildroot}%{_cross_factorydir}/nvidia-container-runtime/
install -m 0644 %{S:2} %{buildroot}%{_cross_factorydir}/nvidia-container-runtime/
install -m 0644 %{S:3} %{buildroot}%{_cross_templatedir}/nvidia-oci-hooks-json
install -p -m 0644 %{S:4} %{buildroot}%{_cross_udevrulesdir}/90-nvidia-gpu-devices.rules
install -m 0644 %{S:5} %{buildroot}%{_cross_tmpfilesdir}/nvidia-container-toolkit-ecs.conf
install -m 0644 %{S:6} %{buildroot}%{_cross_tmpfilesdir}/nvidia-container-toolkit-k8s.conf
install -m 0644 %{S:7} %{buildroot}%{_cross_templatedir}/nvidia-container-runtime/
ln -s shimpei %{buildroot}%{_cross_bindir}/nvidia-oci

%files
Expand All @@ -83,4 +87,5 @@ ln -s shimpei %{buildroot}%{_cross_bindir}/nvidia-oci

%files k8s
%{_cross_factorydir}/nvidia-container-runtime/nvidia-container-toolkit-config-k8s.toml
%{_cross_templatedir}/nvidia-container-runtime/nvidia-container-toolkit-config-k8s
%{_cross_tmpfilesdir}/nvidia-container-toolkit-k8s.conf
13 changes: 13 additions & 0 deletions packages/nvidia-k8s-device-plugin/nvidia-k8s-device-plugin-conf
Original file line number Diff line number Diff line change
@@ -0,0 +1,13 @@
[required-extensions]
kubernetes = "v1"
std = { version = "v1", helpers = ["default"] }

+++
version: v1
flags:
migStrategy: "none"
failOnInitError: true
plugin:
passDeviceSpecs: {{default true settings.kubernetes.device-plugins.nvidia.pass-device-specs}}
deviceListStrategy: {{default "volume-mounts" settings.kubernetes.device-plugins.nvidia.device-list-strategy}}
deviceIDStrategy: {{default "index" settings.kubernetes.device-plugins.nvidia.device-id-strategy}}
Original file line number Diff line number Diff line change
@@ -0,0 +1,8 @@
[required-extensions]
kubernetes = "v1"
+++
[Service]
{{#if settings.kubernetes.device-plugins.nvidia}}
Comment on lines +4 to +5
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Did you test that this works correctly on instances without an nvidia device plugin set?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes. I tested it if settings.kubernetes.device-plugins.nvidia is not defined then this file is rendered as

[Service]

which are kind of ignored as there is no overriding settings. It works as expected.

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This feels weird and to someone just seeing this on the system would appear to be a failure? Can we add a comment in an else statement to say deliberately left this way or something? Is it not better to just remove the [Service] as well?

ExecStart=
ExecStart=/usr/bin/nvidia-device-plugin --config-file=/etc/nvidia-k8s-device-plugin/settings.yaml
{{/if}}
Original file line number Diff line number Diff line change
@@ -1,7 +1,5 @@
[Unit]
Description=Start NVIDIA kubernetes device plugin
RefuseManualStart=true
RefuseManualStop=true
yeazelm marked this conversation as resolved.
Show resolved Hide resolved
After=kubelet.service
Wants=kubelet.service

Expand Down
10 changes: 10 additions & 0 deletions packages/nvidia-k8s-device-plugin/nvidia-k8s-device-plugin.spec
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,9 @@ License: Apache-2.0
URL: https://github.com/NVIDIA/k8s-device-plugin
Source0: https://%{goimport}/archive/v%{gover}/v%{gover}.tar.gz#/k8s-device-plugin-%{gover}.tar.gz
Source1: nvidia-k8s-device-plugin.service
Source2: nvidia-k8s-device-plugin-conf
Source3: nvidia-k8s-device-plugin-exec-start-conf


BuildRequires: %{_cross_os}glibc-devel
Requires: %{name}(binaries)
Expand Down Expand Up @@ -61,11 +64,18 @@ install -p -m 0755 fips/nvidia-device-plugin %{buildroot}%{_cross_fips_bindir}

install -d %{buildroot}%{_cross_unitdir}
install -p -m 0644 %{S:1} %{buildroot}%{_cross_unitdir}
install -d %{buildroot}%{_cross_unitdir}/nvidia-k8s-device-plugin.service.d
install -D -m 0644 %{S:2} %{buildroot}%{_cross_templatedir}/nvidia-k8s-device-plugin-conf
install -D -m 0644 %{S:3} %{buildroot}%{_cross_templatedir}/nvidia-k8s-device-plugin-exec-start-conf


%files
%license LICENSE
%{_cross_attribution_file}
%{_cross_unitdir}/nvidia-k8s-device-plugin.service
%dir %{_cross_unitdir}/nvidia-k8s-device-plugin.service.d
%{_cross_templatedir}/nvidia-k8s-device-plugin-conf
%{_cross_templatedir}/nvidia-k8s-device-plugin-exec-start-conf

%files bin
%{_cross_bindir}/nvidia-device-plugin
Expand Down