podman health check phase3

podman will not start a transient service and timer for healthchecks.
this handles the tracking of the timing for health checks.

added the 'started' status which represents the time that a container is
in its start-period.

the systemd timing can be disabled with an env variable of
DISABLE_HC_SYSTEMD="true".

added filter for ps where --filter health=[starting, healthy, unhealthy]
can now be used.

Signed-off-by: baude <bbaude@redhat.com>

1 files changed, 22 insertions, 0 deletions

diff --git a/libpod/container_internal.go b/libpod/container_internal.go
index 13e660dc3..7a90bc7d4 100644
--- a/libpod/container_internal.go
+++ b/libpod/container_internal.go
@@ -833,6 +833,12 @@ func (c *Container) init(ctx context.Context) error {
 	if err := c.save(); err != nil {
 		return err
 	}
+	if c.config.HealthCheckConfig != nil {
+		if err := c.createTimer(); err != nil {
+			logrus.Error(err)
+		}
+	}
+
 	defer c.newContainerEvent(events.Init)
 	return c.completeNetworkSetup()
 }
@@ -956,6 +962,15 @@ func (c *Container) start() error {
 
 	c.state.State = ContainerStateRunning
 
+	if c.config.HealthCheckConfig != nil {
+		if err := c.updateHealthStatus(HealthCheckStarting); err != nil {
+			logrus.Error(err)
+		}
+		if err := c.startTimer(); err != nil {
+			logrus.Error(err)
+		}
+	}
+
 	defer c.newContainerEvent(events.Start)
 
 	return c.save()
@@ -1123,6 +1138,13 @@ func (c *Container) cleanup(ctx context.Context) error {
 
 	logrus.Debugf("Cleaning up container %s", c.ID())
 
+	// Remove healthcheck unit/timer file if it execs
+	if c.config.HealthCheckConfig != nil {
+		if err := c.removeTimer(); err != nil {
+			logrus.Error(err)
+		}
+	}
+
 	// Clean up network namespace, if present
 	if err := c.cleanupNetwork(); err != nil {
 		lastError = err