Skip to content

enable auto-restarts of the NRI plugin server after the container runtime is restarted #1736

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

Draft
tariq1890 wants to merge 1 commit into
base: main
Choose a base branch
from
+18 −3
Draft

enable auto-restarts of the NRI plugin server after the container runtime is restarted #1736

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
21 changes: 18 additions & 3 deletions cmd/nvidia-ctk-installer/container/runtime/nri/plugin.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -113,13 +113,16 @@ func containerName(pod *api.PodSandbox, container *api.Container) string {
return container.Name
}

// Start starts the NRI plugin
// Start initializes the NRI plugin stub and starts the NRI plugin server
func (p *Plugin) Start(ctx context.Context, nriSocketPath, nriPluginIdx string) error {
pluginOpts := []stub.Option{
stub.WithPluginIdx(nriPluginIdx),
stub.WithLogger(toNriLogger{p.logger}),
stub.WithOnClose(func() {
p.logger.Infof("NRI ttrpc connection to %s is down. NRI plugin stopped.", nriSocketPath)
p.logger.Infof("NRI ttrpc connection to %s is down. NRI plugin stopped. Attempting to reconnect...", nriSocketPath)
if err := p.start(ctx); err != nil {
p.logger.Errorf("failed to restart NRI plugin: %v", err)
}
}),
}
if len(nriSocketPath) > 0 {
Expand All @@ -134,13 +137,25 @@ func (p *Plugin) Start(ctx context.Context, nriSocketPath, nriPluginIdx string)
if p.stub, err = stub.New(p, pluginOpts...); err != nil {
return fmt.Errorf("failed to initialise plugin at %s: %w", nriSocketPath, err)
}
err = p.stub.Start(ctx)
err = p.start(ctx)
if err != nil {
return fmt.Errorf("plugin exited with error: %w", err)
}
return nil
}

// start starts the NRI plugin server
func (p *Plugin) start(ctx context.Context) error {
if p != nil {
if p.stub == nil {
p.logger.Infof("NRI plugin not initialized. Skipping plugin start")
} else {
return p.stub.Start(ctx)
}
}
return nil
}

// Stop stops the NRI plugin
func (p *Plugin) Stop() {
if p == nil || p.stub == nil {
Expand Down
Loading