Merge pull request #69008 from sjenning/better-pleg-msg

improve pleg error msg when it has never been successful

pkg/kubelet/pleg/generic.go

@@ -135,6 +135,9 @@ func (g *GenericPLEG) Start() {
 // relistThreshold is the maximum interval between two relist.
 func (g *GenericPLEG) Healthy() (bool, error) {
 	relistTime := g.getRelistTime()
+	if relistTime.IsZero() {
+		return false, fmt.Errorf("pleg has yet to be successful")
+	}
 	elapsed := g.clock.Since(relistTime)
 	if elapsed > relistThreshold {
 		return false, fmt.Errorf("pleg was last seen active %v ago; threshold is %v", elapsed, relistThreshold)

pkg/kubelet/pleg/generic_test.go

@@ -346,9 +346,11 @@ func TestRemoveCacheEntry(t *testing.T) {
 
 func TestHealthy(t *testing.T) {
 	testPleg := newTestGenericPLEG()
+
+	// pleg should initially be unhealthy
 	pleg, _, clock := testPleg.pleg, testPleg.runtime, testPleg.clock
 	ok, _ := pleg.Healthy()
-	assert.True(t, ok, "pleg should be healthy")
+	assert.False(t, ok, "pleg should be unhealthy")
 
 	// Advance the clock without any relisting.
 	clock.Step(time.Minute * 10)
@@ -361,6 +363,12 @@ func TestHealthy(t *testing.T) {
 	clock.Step(time.Minute * 1)
 	ok, _ = pleg.Healthy()
 	assert.True(t, ok, "pleg should be healthy")
+
+	// Advance by relistThreshold without any relisting. pleg should be unhealthy
+	// because it has been longer than relistThreshold since a relist occurred.
+	clock.Step(relistThreshold)
+	ok, _ = pleg.Healthy()
+	assert.False(t, ok, "pleg should be unhealthy")
 }
 
 func TestRelistWithReinspection(t *testing.T) {