philipp/uncloud
1
0
Fork 0
mirror of https://github.com/psviderski/uncloud.git synced 2026-08-26 19:13:34 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: add --skip-health flag to bypass health monitoring during container deployment

Browse Source
This commit is contained in:
Pasha Sviderski
2026-02-28 16:26:48 +10:00
parent e6705599b3
commit ce3cb8a34f
4 changed files with 80 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files
pkg/client/deploy/operation/container.go
+33 -23
View File
@@ -15,6 +15,8 @@ type RunContainerOperation struct {
ServiceID string
Spec api.ServiceSpec
MachineID string
// SkipHealthMonitor skips the monitoring period and health checks after starting a container.
SkipHealthMonitor bool
}
func (o *RunContainerOperation) Execute(ctx context.Context, cli Client) error {
@@ -26,6 +28,10 @@ func (o *RunContainerOperation) Execute(ctx context.Context, cli Client) error {
return fmt.Errorf("start container: %w", err)
}
if o.SkipHealthMonitor {
return nil
}
opts := api.WaitContainerHealthyOptions{MonitorPeriod: o.Spec.UpdateConfig.MonitorPeriod}
if err = cli.WaitContainerHealthy(ctx, o.ServiceID, resp.ID, opts); err != nil {
return fmt.Errorf("container '%s/%s' failed to become healthy: %w",
@@ -111,6 +117,8 @@ type ReplaceContainerOperation struct {
OldContainer api.ServiceContainer
// Order specifies the update order: "start-first" or "stop-first".
Order string
// SkipHealthMonitor skips the monitoring period and health checks after starting a new container.
SkipHealthMonitor bool
}
func (o *ReplaceContainerOperation) Execute(ctx context.Context, cli Client) error {
@@ -139,34 +147,36 @@ func (o *ReplaceContainerOperation) Execute(ctx context.Context, cli Client) err
return fmt.Errorf("start new container: %w", err)
}
opts := api.WaitContainerHealthyOptions{MonitorPeriod: o.Spec.UpdateConfig.MonitorPeriod}
if err = cli.WaitContainerHealthy(ctx, o.ServiceID, resp.ID, opts); err != nil {
// New container failed to become healthy. Stop it and roll back to the previous container.
// Don't remove the new stopped container to allow users to inspect logs and state.
// TODO: collect logs from the new container and include in the error message to speed up debugging.
if !o.SkipHealthMonitor {
opts := api.WaitContainerHealthyOptions{MonitorPeriod: o.Spec.UpdateConfig.MonitorPeriod}
if err = cli.WaitContainerHealthy(ctx, o.ServiceID, resp.ID, opts); err != nil {
// New container failed to become healthy. Stop it and roll back to the previous container.
// Don't remove the new stopped container to allow users to inspect logs and state.
// TODO: collect logs from the new container and include in the error message to speed up debugging.
// Use context without progress to not overwrite the container Unhealthy status with Stopped.
ctxWithoutProgress := progress.WithContextWriter(ctx, nil)
_ = cli.StopContainer(ctxWithoutProgress, o.ServiceID, resp.ID, container.StopOptions{})
// Use context without progress to not overwrite the container Unhealthy status with Stopped.
ctxWithoutProgress := progress.WithContextWriter(ctx, nil)
_ = cli.StopContainer(ctxWithoutProgress, o.ServiceID, resp.ID, container.StopOptions{})
newCtr := fmt.Sprintf("%s/%s", o.Spec.Name, stringid.TruncateID(resp.ID))
healthErr := fmt.Errorf(
"new container '%s' failed to become healthy: %w. "+
"It's stopped and available for inspection. Fetch logs with 'uc logs %s'",
newCtr, err, o.Spec.Name,
)
newCtr := fmt.Sprintf("%s/%s", o.Spec.Name, stringid.TruncateID(resp.ID))
healthErr := fmt.Errorf(
"new container '%s' failed to become healthy: %w. "+
"It's stopped and available for inspection. Fetch logs with 'uc logs %s'",
newCtr, err, o.Spec.Name,
)
if stopFirst && wasRunning {
// Restart the old container only if it was running before we stopped it.
oldCtr := fmt.Sprintf("%s/%s", o.OldContainer.ServiceSpec.Name, o.OldContainer.ShortID())
if rollbackErr := cli.StartContainer(ctx, o.ServiceID, o.OldContainer.ID); rollbackErr != nil {
return fmt.Errorf("%w. Rolled back to old container '%s' but failed to restart it: %w",
healthErr, oldCtr, rollbackErr)
if stopFirst && wasRunning {
// Restart the old container only if it was running before we stopped it.
oldCtr := fmt.Sprintf("%s/%s", o.OldContainer.ServiceSpec.Name, o.OldContainer.ShortID())
if rollbackErr := cli.StartContainer(ctx, o.ServiceID, o.OldContainer.ID); rollbackErr != nil {
return fmt.Errorf("%w. Rolled back to old container '%s' but failed to restart it: %w",
healthErr, oldCtr, rollbackErr)
}
return fmt.Errorf("%w. Rolled back to old container '%s'", healthErr, oldCtr)
}
return fmt.Errorf("%w. Rolled back to old container '%s'", healthErr, oldCtr)
}
return healthErr
return healthErr
}
}
// For start-first, we need to stop before removing.