Skip to content

Fail loudly when renew-certificate --restart cannot restart the control plane; include scheduler #1670

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

Open
Mukuwul wants to merge 3 commits into
base: master
Choose a base branch
from
Open

Fail loudly when renew-certificate --restart cannot restart the control plane; include scheduler #1670

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
2efca88
Fail loudly when renew-certificate --restart cannot restart the contr…
Mukuwul Jul 18, 2026
339975f
Address review: constant format string and resource-agnostic restart …
Mukuwul Jul 18, 2026
dc167c6
Only treat NotFound as scheduler absence in restart probe
Mukuwul Jul 27, 2026
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
26 changes: 19 additions & 7 deletions cmd/renew_certificate.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -132,9 +132,8 @@ dapr mtls renew-cert -k --valid-until <no of days> --restart
"Certificate rotation is successful! Your new certicate is valid through "+expiry.Format(time.RFC1123))

if restartDaprServices {
restartControlPlaneService()
if err != nil {
print.FailureStatusEvent(os.Stdout, err.Error())
if err := restartControlPlaneService(); err != nil {
print.FailureStatusEvent(os.Stderr, "%s", err.Error())
os.Exit(1)
}
}
Expand Down Expand Up @@ -170,15 +169,28 @@ func logErrorAndExit(err error) {
}

func restartControlPlaneService() error {
namespace, err := kubernetes.GetDaprNamespace()
if err != nil {
return fmt.Errorf("failed to fetch Dapr namespace: %w", err)
}

controlPlaneServices := []string{
"deploy/dapr-sentry",
"deploy/dapr-sidecar-injector",
"deploy/dapr-operator",
"statefulsets/dapr-placement-server",
}
namespace, err := kubernetes.GetDaprNamespace()
// The scheduler control plane service only exists for runtime 1.14 onwards,
// so restart it only when it is present in the cluster. --ignore-not-found
// makes absence the only non-error outcome with empty output: any other
// probe failure (RBAC, transient API error) must fail the restart loudly
// rather than silently skipping the scheduler.
out, err := utils.RunCmdAndWait("kubectl", "get", "statefulsets/dapr-scheduler-server", "-n", namespace, "--ignore-not-found", "-o", "name")
if err != nil {
print.FailureStatusEvent(os.Stdout, "Failed to fetch Dapr namespace")
return fmt.Errorf("failed to check for dapr-scheduler-server statefulset: %w", err)
}
if strings.TrimSpace(out) != "" {
controlPlaneServices = append(controlPlaneServices, "statefulsets/dapr-scheduler-server")
}
Comment on lines +183 to 194

@Mukuwul Mukuwul Jul 18, 2026 •
edited
Loading

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

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

Done in 339975f - reworded both errors to be resource-agnostic since the list now includes statefulsets.


errs := make([]error, len(controlPlaneServices))
Expand All @@ -190,12 +202,12 @@ func restartControlPlaneService() error {
print.InfoStatusEvent(os.Stdout, fmt.Sprintf("Restarting %s..", name))
_, err := utils.RunCmdAndWait("kubectl", "rollout", "restart", "-n", namespace, name)
if err != nil {
errs[i] = fmt.Errorf("error in restarting deployment %s. Error is %w", name, err)
errs[i] = fmt.Errorf("error in restarting %s. Error is %w", name, err)
return
}
_, err = utils.RunCmdAndWait("kubectl", "rollout", "status", "-n", namespace, name)
if err != nil {
errs[i] = fmt.Errorf("error in checking status for deployment %s. Error is %w", name, err)
errs[i] = fmt.Errorf("error in checking rollout status for %s. Error is %w", name, err)
return
}
}(i, name)
Expand Down
Loading