UPSTREAM: <carry>: disable etcd readiness checks by default

Explicitly exclude etcd and etcd-readiness checks (OCPBUGS-48177)
and have etcd operator take responsibility for properly reporting etcd readiness.
Justification: kube-apiserver instances get removed from a load balancer when etcd starts
to report not ready (as will KA's /readyz). Client connections can withstand etcd unreadiness
longer than the readiness timeout is. Thus, it is not necessary to drop connections
in case etcd resumes its readiness before a client connection times out naturally.
This is a downstream patch only as OpenShift's way of using etcd is unique.

Author: ingvagabund

staging/src/k8s.io/apiserver/pkg/server/config.go

@@ -586,13 +586,27 @@ type CompletedConfig struct {
 func (c *Config) AddHealthChecks(healthChecks ...healthz.HealthChecker) {
 	c.HealthzChecks = append(c.HealthzChecks, healthChecks...)
 	c.LivezChecks = append(c.LivezChecks, healthChecks...)
-	c.ReadyzChecks = append(c.ReadyzChecks, healthChecks...)
+	c.AddReadyzChecks(healthChecks...)
 }
 
 // AddReadyzChecks adds a health check to our config to be exposed by the readyz endpoint
 // of our configured apiserver.
 func (c *Config) AddReadyzChecks(healthChecks ...healthz.HealthChecker) {
-	c.ReadyzChecks = append(c.ReadyzChecks, healthChecks...)
+	// Info(ingvagabund): Explicitly exclude etcd and etcd-readiness checks (OCPBUGS-48177)
+	// and have etcd operator take responsibility for properly reporting etcd readiness.
+	// Justification: kube-apiserver instances get removed from a load balancer when etcd starts
+	// to report not ready (as will KA's /readyz). Client connections can withstand etcd unreadiness
+	// longer than the readiness timeout is. Thus, it is not necessary to drop connections
+	// in case etcd resumes its readiness before a client connection times out naturally.
+	// This is a downstream patch only as OpenShift's way of using etcd is unique.
+	readyzChecks := []healthz.HealthChecker{}
+	for _, check := range healthChecks {
+		if check.Name() == "etcd" || check.Name() == "etcd-readiness" {
+			continue
+		}
+		readyzChecks = append(readyzChecks, check)
+	}
+	c.ReadyzChecks = append(c.ReadyzChecks, readyzChecks...)
 }
 
 // AddPostStartHook allows you to add a PostStartHook that will later be added to the server itself in a New call.

staging/src/k8s.io/apiserver/pkg/server/options/etcd.go

@@ -355,7 +355,7 @@ func (s *EtcdOptions) maybeApplyResourceTransformers(c *server.Config) (err erro
 
 func addHealthChecksWithoutLivez(c *server.Config, healthChecks ...healthz.HealthChecker) {
 	c.HealthzChecks = append(c.HealthzChecks, healthChecks...)
-	c.ReadyzChecks = append(c.ReadyzChecks, healthChecks...)
+	c.AddReadyzChecks(healthChecks...)
 }
 
 func (s *EtcdOptions) addEtcdHealthEndpoint(c *server.Config) error {

staging/src/k8s.io/apiserver/pkg/server/options/etcd_test.go

@@ -262,6 +262,17 @@ func TestParseWatchCacheSizes(t *testing.T) {
 	}
 }
 
+func excludeEtcdReadyzChecks(readyzChecks []string) []string {
+	includedReadyzChecks := []string{}
+	for _, checkName := range readyzChecks {
+		if checkName == "etcd" || checkName == "etcd-readiness" {
+			continue
+		}
+		includedReadyzChecks = append(includedReadyzChecks, checkName)
+	}
+	return includedReadyzChecks
+}
+
 func TestKMSHealthzEndpoint(t *testing.T) {
 	featuregatetesting.SetFeatureGateDuringTest(t, utilfeature.DefaultFeatureGate, features.KMSv1, true)
 
@@ -367,7 +378,9 @@ func TestKMSHealthzEndpoint(t *testing.T) {
 			}
 
 			healthChecksAreEqual(t, tc.wantHealthzChecks, serverConfig.HealthzChecks, "healthz")
-			healthChecksAreEqual(t, tc.wantReadyzChecks, serverConfig.ReadyzChecks, "readyz")
+			// Remove the excluded checks here to reduce the carry patch changes in case
+			// the changes drifts too much during rebases and similar scope-like changes.
+			healthChecksAreEqual(t, excludeEtcdReadyzChecks(tc.wantReadyzChecks), serverConfig.ReadyzChecks, "readyz")
 			healthChecksAreEqual(t, tc.wantLivezChecks, serverConfig.LivezChecks, "livez")
 		})
 	}
@@ -407,7 +420,9 @@ func TestReadinessCheck(t *testing.T) {
 				t.Fatalf("Failed to add healthz error: %v", err)
 			}
 
-			healthChecksAreEqual(t, tc.wantReadyzChecks, serverConfig.ReadyzChecks, "readyz")
+			// Remove the excluded checks here to reduce the carry patch changes in case
+			// the changes drifts too much during rebases and similar scope-like changes.
+			healthChecksAreEqual(t, excludeEtcdReadyzChecks(tc.wantReadyzChecks), serverConfig.ReadyzChecks, "readyz")
 			healthChecksAreEqual(t, tc.wantHealthzChecks, serverConfig.HealthzChecks, "healthz")
 			healthChecksAreEqual(t, tc.wantLivezChecks, serverConfig.LivezChecks, "livez")
 		})

test/e2e/apimachinery/health_handlers.go

@@ -82,7 +82,6 @@ var (
 	requiredReadyzChecks = sets.NewString(
 		"[+]ping ok",
 		"[+]log ok",
-		"[+]etcd ok",
 		"[+]informer-sync ok",
 		"[+]poststarthook/start-apiserver-admission-initializer ok",
 		"[+]poststarthook/generic-apiserver-start-informers ok",