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

cmd/uncloud/deploy.go

@@ -21,12 +21,13 @@ import (
 type deployOptions struct {
 	cli.BuildServicesOptions
 
-	files    []string
-	profiles []string
-	services []string
-	noBuild  bool
-	recreate bool
-	yes      bool
+	files      []string
+	profiles   []string
+	services   []string
+	noBuild    bool
+	recreate   bool
+	skipHealth bool
+	yes        bool
 }
 
 // NewDeployCommand creates a new command to deploy services from a Compose file.
@@ -61,6 +62,10 @@ func NewDeployCommand() *cobra.Command {
 		"One or more Compose profiles to enable.")
 	cmd.Flags().BoolVar(&opts.recreate, "recreate", false,
 		"Recreate containers even if their configuration and image haven't changed.")
+	cmd.Flags().BoolVar(&opts.skipHealth, "skip-health", false,
+		"Skip the monitoring period and health checks after starting new containers. Useful for faster emergency "+
+			"deployments.\n"+
+			"Warning: This may cause downtime if new containers fail to start properly.")
 	cmd.Flags().BoolVarP(&opts.yes, "yes", "y", false,
 		"Auto-confirm deployment plan. Should be explicitly set when running non-interactively,\n"+
 			"e.g., in CI/CD pipelines. [$UNCLOUD_AUTO_CONFIRM]")
@@ -149,9 +154,9 @@ func runDeploy(ctx context.Context, uncli *cli.CLI, opts deployOptions) error {
 		fmt.Println()
 	}
 
-	var strategy deploy.Strategy
-	if opts.recreate {
-		strategy = &deploy.RollingStrategy{ForceRecreate: true}
+	strategy := &deploy.RollingStrategy{
+		ForceRecreate:     opts.recreate,
+		SkipHealthMonitor: opts.skipHealth,
 	}
 	composeDeploy, err := compose.NewDeploymentWithStrategy(ctx, clusterClient, project, strategy)
 	if err != nil {

pkg/client/deploy/operation/container.go

@@ -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.

pkg/client/deploy/strategy.go

@@ -29,6 +29,8 @@ type RollingStrategy struct {
 	// ForceRecreate indicates whether all containers should be recreated during the deployment,
 	// regardless of whether their specifications have changed.
 	ForceRecreate bool
+	// SkipHealthMonitor skips the monitoring period and health checks for faster emergency deployments.
+	SkipHealthMonitor bool
 
 	// state is the current and planned state of the cluster used for scheduling decisions.
 	state *scheduler.ClusterState
@@ -146,9 +148,10 @@ func (s *RollingStrategy) planReplicated(svc *api.Service, spec api.ServiceSpec)
 		if len(containers) == 0 {
 			// No more existing containers on this machine, create a new one.
 			plan.Operations = append(plan.Operations, &operation.RunContainerOperation{
-				ServiceID: plan.ServiceID,
-				Spec:      spec,
-				MachineID: m.Id,
+				ServiceID:         plan.ServiceID,
+				Spec:              spec,
+				MachineID:         m.Id,
+				SkipHealthMonitor: s.SkipHealthMonitor,
 			})
 			continue
 		}
@@ -166,11 +169,12 @@ func (s *RollingStrategy) planReplicated(svc *api.Service, spec api.ServiceSpec)
 		// Replace the old container with a new one.
 		order := determineUpdateOrder(ctr, spec)
 		plan.Operations = append(plan.Operations, &operation.ReplaceContainerOperation{
-			ServiceID:    plan.ServiceID,
-			Spec:         spec,
-			MachineID:    m.Id,
-			OldContainer: ctr,
-			Order:        order,
+			ServiceID:         plan.ServiceID,
+			Spec:              spec,
+			MachineID:         m.Id,
+			OldContainer:      ctr,
+			Order:             order,
+			SkipHealthMonitor: s.SkipHealthMonitor,
 		})
 	}
 
@@ -216,7 +220,8 @@ func (s *RollingStrategy) planGlobal(svc *api.Service, spec api.ServiceSpec) (Pl
 
 	for _, m := range availableMachines {
 		containers := containersOnMachine[m.Info.Id]
-		ops, err := reconcileGlobalContainer(containers, spec, plan.ServiceID, m.Info.Id, s.ForceRecreate)
+		ops, err := reconcileGlobalContainer(
+			containers, spec, plan.ServiceID, m.Info.Id, s.ForceRecreate, s.SkipHealthMonitor)
 		if err != nil {
 			return plan, err
 		}
@@ -242,16 +247,18 @@ func (s *RollingStrategy) planGlobal(svc *api.Service, spec api.ServiceSpec) (Pl
 // It ensures exactly one container with the desired spec is running on the machine by creating a new container and
 // removing old ones. If there is a host port conflict, it stops the old container before starting a new one.
 func reconcileGlobalContainer(
-	containers []api.MachineServiceContainer, spec api.ServiceSpec, serviceID, machineID string, forceRecreate bool,
+	containers []api.MachineServiceContainer, spec api.ServiceSpec, serviceID, machineID string,
+	forceRecreate, skipHealthCheck bool,
 ) ([]operation.Operation, error) {
 	var ops []operation.Operation
 
 	if len(containers) == 0 {
 		// No containers on this machine, create a new one.
 		ops = append(ops, &operation.RunContainerOperation{
-			ServiceID: serviceID,
-			Spec:      spec,
-			MachineID: machineID,
+			ServiceID:         serviceID,
+			Spec:              spec,
+			MachineID:         machineID,
+			SkipHealthMonitor: skipHealthCheck,
 		})
 		return ops, nil
 	}
@@ -322,11 +329,12 @@ func reconcileGlobalContainer(
 		// Replace the running container with a new one.
 		order := determineUpdateOrder(containerToReplace.Container, spec)
 		ops = append(ops, &operation.ReplaceContainerOperation{
-			ServiceID:    serviceID,
-			Spec:         spec,
-			MachineID:    machineID,
-			OldContainer: containerToReplace.Container,
-			Order:        order,
+			ServiceID:         serviceID,
+			Spec:              spec,
+			MachineID:         machineID,
+			OldContainer:      containerToReplace.Container,
+			Order:             order,
+			SkipHealthMonitor: skipHealthCheck,
 		})
 
 		// Remove any other containers (there shouldn't be any in normal operation).
@@ -342,9 +350,10 @@ func reconcileGlobalContainer(
 	} else {
 		// No running containers, create a new one and remove all stopped containers.
 		ops = append(ops, &operation.RunContainerOperation{
-			ServiceID: serviceID,
-			Spec:      spec,
-			MachineID: machineID,
+			ServiceID:         serviceID,
+			Spec:              spec,
+			MachineID:         machineID,
+			SkipHealthMonitor: skipHealthCheck,
 		})
 		for _, c := range containers {
 			ops = append(ops, &operation.RemoveContainerOperation{

pkg/client/deploy/strategy_test.go

@@ -401,7 +401,9 @@ func TestReconcileGlobalContainer(t *testing.T) {
 
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
-			ops, err := reconcileGlobalContainer(tt.containers, tt.spec, "service-1", "machine-1", tt.forceRecreate)
+			ops, err := reconcileGlobalContainer(
+				tt.containers, tt.spec, "service-1", "machine-1", tt.forceRecreate, false,
+			)
 			assert.NoError(t, err)
 			assertOperationsEqual(t, tt.expectedOps, ops)
 		})