check that StartTransientUnit succeeds

Signed-off-by: lifubang <[email protected]>

libcontainer/cgroups/systemd/common.go

@@ -11,6 +11,26 @@ import (
 	"github.com/opencontainers/runc/libcontainer/configs"
 )
 
+// Refer to https://github.com/coreos/go-systemd/blob/5a0db84d3dc459ccdc6ffcc44b1c452bf9f171cb/dbus/methods.go#L78-L101
+// or https://godoc.org/github.com/coreos/go-systemd/dbus#Conn.StartUnit
+// job completion: one of done, canceled, timeout, failed, dependency, skipped.
+// done indicates successful execution of a job. canceled indicates that a job
+// has been canceled  before it finished execution. timeout indicates that the
+// job timeout was reached. failed indicates that the job failed. dependency
+// indicates that a job this job has been depending on failed and the job hence
+// has been removed too. skipped indicates that a job was skipped because it
+// didn't apply to the units current state.
+type DbusJobCompletionResultType string
+
+const (
+	DbusJobDone       DbusJobCompletionResultType = "done"
+	DbusJobCanceled   DbusJobCompletionResultType = "canceled"
+	DbusJobTimeout    DbusJobCompletionResultType = "timeout"
+	DbusJobFailed     DbusJobCompletionResultType = "failed"
+	DbusJobDependency DbusJobCompletionResultType = "dependency"
+	DbusJobSkipped    DbusJobCompletionResultType = "skipped"
+)
+
 var (
 	connOnce sync.Once
 	connDbus *systemdDbus.Conn

libcontainer/cgroups/systemd/v2.go

@@ -15,6 +15,7 @@ import (
 	"github.com/opencontainers/runc/libcontainer/cgroups"
 	"github.com/opencontainers/runc/libcontainer/cgroups/fs2"
 	"github.com/opencontainers/runc/libcontainer/configs"
+	"github.com/pkg/errors"
 	"github.com/sirupsen/logrus"
 )
 
@@ -139,7 +140,11 @@ func (m *unifiedManager) Apply(pid int) error {
 	statusChan := make(chan string, 1)
 	if _, err := dbusConnection.StartTransientUnit(unitName, "replace", properties, statusChan); err == nil {
 		select {
-		case <-statusChan:
+		case s := <-statusChan:
+			if DbusJobCompletionResultType(s) != DbusJobDone {
+				dbusConnection.ResetFailedUnit(unitName)
+				return errors.Errorf("error creating systemd unit `%s`: got `%s`", unitName, s)
+			}
 		case <-time.After(time.Second):
 			logrus.Warnf("Timed out while waiting for StartTransientUnit(%s) completion signal from dbus. Continuing...", unitName)
 		}
@@ -168,7 +173,18 @@ func (m *unifiedManager) Destroy() error {
 	if err != nil {
 		return err
 	}
-	dbusConnection.StopUnit(getUnitName(m.cgroups), "replace", nil)
+	unitName := getUnitName(m.cgroups)
+	statusChan := make(chan string, 1)
+	if _, err := dbusConnection.StopUnit(unitName, "replace", statusChan); err == nil {
+		select {
+		case s := <-statusChan:
+			if DbusJobCompletionResultType(s) != DbusJobDone {
+				logrus.Warnf("error stopping unit `%s`: got `%s`. Continuing...", unitName, s)
+			}
+		case <-time.After(time.Second):
+			logrus.Warnf("Timed out while waiting for StopUnit(%s) completion signal from dbus. Continuing...", unitName)
+		}
+	}
 
 	// XXX this is probably not needed, systemd should handle it
 	err = os.Remove(m.path)