health check: add on-failure actions

For systems that have extreme robustness requirements (edge devices,
particularly those in difficult to access environments), it is important
that applications continue running in all circumstances. When the
application fails, Podman must restart it automatically to provide this
robustness. Otherwise, these devices may require customer IT to
physically gain access to restart, which can be prohibitively difficult.

Add a new `--on-failure` flag that supports four actions:

- **none**: Take no action.

- **kill**: Kill the container.

- **restart**: Restart the container.  Do not combine the `restart`
               action with the `--restart` flag.  When running inside of
               a systemd unit, consider using the `kill` or `stop`
               action instead to make use of systemd's restart policy.

- **stop**: Stop the container.

To remain backwards compatible, **none** is the default action.

Signed-off-by: Valentin Rothberg <vrothberg@redhat.com>

4 files changed, 15 insertions, 1 deletions

diff --git a/pkg/domain/entities/pods.go b/pkg/domain/entities/pods.go
index 55e2fd574..a059cd7b5 100644
--- a/pkg/domain/entities/pods.go
+++ b/pkg/domain/entities/pods.go
@@ -212,6 +212,7 @@ type ContainerCreateOptions struct {
 	HealthRetries     uint
 	HealthStartPeriod string
 	HealthTimeout     string
+	HealthOnFailure   string
 	Hostname          string `json:"hostname,omitempty"`
 	HTTPProxy         bool
 	HostUsers         []string
diff --git a/pkg/specgen/generate/container_create.go b/pkg/specgen/generate/container_create.go
index 4d5ac22ad..8900d2e5d 100644
--- a/pkg/specgen/generate/container_create.go
+++ b/pkg/specgen/generate/container_create.go
@@ -515,6 +515,10 @@ func createContainerOptions(rt *libpod.Runtime, s *specgen.SpecGenerator, pod *l
 		logrus.Debugf("New container has a health check")
 	}
 
+	if s.ContainerHealthCheckConfig.HealthCheckOnFailureAction != define.HealthCheckOnFailureActionNone {
+		options = append(options, libpod.WithHealthCheckOnFailureAction(s.ContainerHealthCheckConfig.HealthCheckOnFailureAction))
+	}
+
 	if len(s.Secrets) != 0 {
 		manager, err := rt.SecretsManager()
 		if err != nil {
diff --git a/pkg/specgen/specgen.go b/pkg/specgen/specgen.go
index 51b6736a9..34418c132 100644
--- a/pkg/specgen/specgen.go
+++ b/pkg/specgen/specgen.go
@@ -9,6 +9,7 @@ import (
 	"github.com/containers/common/libimage"
 	nettypes "github.com/containers/common/libnetwork/types"
 	"github.com/containers/image/v5/manifest"
+	"github.com/containers/podman/v4/libpod/define"
 	"github.com/containers/storage/types"
 	spec "github.com/opencontainers/runtime-spec/specs-go"
 )
@@ -533,7 +534,8 @@ type ContainerResourceConfig struct {
 // ContainerHealthCheckConfig describes a container healthcheck with attributes
 // like command, retries, interval, start period, and timeout.
 type ContainerHealthCheckConfig struct {
-	HealthConfig *manifest.Schema2HealthConfig `json:"healthconfig,omitempty"`
+	HealthConfig               *manifest.Schema2HealthConfig     `json:"healthconfig,omitempty"`
+	HealthCheckOnFailureAction define.HealthCheckOnFailureAction `json:"health_check_on_failure_action,omitempty"`
 }
 
 // SpecGenerator creates an OCI spec and Libpod configuration options to create
diff --git a/pkg/specgenutil/specgen.go b/pkg/specgenutil/specgen.go
index 439a13385..3189926b2 100644
--- a/pkg/specgenutil/specgen.go
+++ b/pkg/specgenutil/specgen.go
@@ -265,6 +265,13 @@ func FillOutSpecGen(s *specgen.SpecGenerator, c *entities.ContainerCreateOptions
 			Test: []string{"NONE"},
 		}
 	}
+
+	onFailureAction, err := define.ParseHealthCheckOnFailureAction(c.HealthOnFailure)
+	if err != nil {
+		return err
+	}
+	s.HealthCheckOnFailureAction = onFailureAction
+
 	if err := setNamespaces(s, c); err != nil {
 		return err
 	}