Add pre-create duplicate check and reduce sleep

pkg/cloudscale_ccm/loadbalancer.go

@@ -5,11 +5,13 @@ import (
 	"fmt"
 	"slices"
 	"strings"
+	"sync"
 
 	"github.com/cloudscale-ch/cloudscale-go-sdk/v6"
 	v1 "k8s.io/api/core/v1"
 	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
 	"k8s.io/apimachinery/pkg/labels"
+	"k8s.io/apimachinery/pkg/types"
 	"k8s.io/client-go/kubernetes"
 	"k8s.io/client-go/tools/record"
 	"k8s.io/klog/v2"
@@ -308,6 +310,19 @@ type loadbalancer struct {
 	srv      serverMapper
 	k8s      kubernetes.Interface
 	recorder record.EventRecorder
+	muMap    sync.Map
+}
+
+func (l *loadbalancer) lockForService(uid types.UID) func() {
+	rawMu, _ := l.muMap.LoadOrStore(string(uid), new(sync.Mutex))
+	mu := rawMu.(*sync.Mutex)
+	klog.V(4).InfoS("acquiring service lock", "uid", uid)
+	mu.Lock()
+
+	return func() {
+		klog.V(4).InfoS("releasing service lock", "uid", uid)
+		mu.Unlock()
+	}
 }
 
 // GetLoadBalancer returns whether the specified load balancer exists, and
@@ -391,6 +406,8 @@ func (l *loadbalancer) EnsureLoadBalancer(
 	service *v1.Service,
 	nodes []*v1.Node,
 ) (*v1.LoadBalancerStatus, error) {
+	unlock := l.lockForService(service.UID)
+	defer unlock()
 
 	// Detect configuration issues and abort if they are found
 	serviceInfo := newServiceInfo(service, clusterName)
@@ -497,6 +514,8 @@ func (l *loadbalancer) UpdateLoadBalancer(
 	service *v1.Service,
 	nodes []*v1.Node,
 ) error {
+	unlock := l.lockForService(service.UID)
+	defer unlock()
 
 	// Detect configuration issues and abort if they are found
 	serviceInfo := newServiceInfo(service, clusterName)
@@ -556,6 +575,8 @@ func (l *loadbalancer) EnsureLoadBalancerDeleted(
 	clusterName string,
 	service *v1.Service,
 ) error {
+	unlock := l.lockForService(service.UID)
+	defer unlock()
 
 	// Detect configuration issues and abort if they are found
 	serviceInfo := newServiceInfo(service, clusterName)

pkg/cloudscale_ccm/loadbalancer_test.go

@@ -1,7 +1,11 @@
 package cloudscale_ccm
 
 import (
+	"encoding/json"
+	"net/http"
+	"sync"
 	"testing"
+	"time"
 
 	"github.com/cloudscale-ch/cloudscale-go-sdk/v6"
 	"github.com/stretchr/testify/assert"
@@ -179,6 +183,130 @@ func TestLoadBalancer_EnsureLoadBalancer(t *testing.T) {
 	}
 }
 
+func TestLoadBalancer_ConcurrentCreate(t *testing.T) {
+	t.Parallel()
+
+	apiServer := testkit.NewMockAPIServer()
+
+	createCount := 0
+	var lbs []cloudscale.LoadBalancer
+	var mu sync.Mutex
+
+	// Custom handler for /v1/load-balancers to track creates.
+	// The sleep before appending to lbs increases the race window so that
+	// both goroutines can see an empty list before either creates.
+	apiServer.HandleFunc("/v1/load-balancers", func(w http.ResponseWriter, r *http.Request) {
+		switch r.Method {
+		case http.MethodPost:
+			time.Sleep(200 * time.Millisecond)
+
+			mu.Lock()
+			createCount++
+			lb := cloudscale.LoadBalancer{
+				HREF:   "/v1/load-balancers/lb-uuid-1",
+				UUID:   "lb-uuid-1",
+				Name:   "k8s-service-test-uid",
+				Status: "running",
+				ZonalResource: cloudscale.ZonalResource{
+					Zone: cloudscale.Zone{Slug: "rma1"},
+				},
+				Flavor: cloudscale.LoadBalancerFlavorStub{Slug: "lb-standard"},
+			}
+			lbs = append(lbs, lb)
+			mu.Unlock()
+
+			w.WriteHeader(http.StatusCreated)
+			_ = json.NewEncoder(w).Encode(lb)
+		case http.MethodGet:
+			mu.Lock()
+			defer mu.Unlock()
+			w.WriteHeader(http.StatusOK)
+			_ = json.NewEncoder(w).Encode(lbs)
+		}
+	})
+
+	// Mock server endpoint for node mapping.
+	serverUUID := "08d56bfe-40d0-4c68-a915-54f846c28c9e"
+	apiServer.WithServers([]cloudscale.Server{{
+		UUID: serverUUID,
+		Name: "node-1",
+		ZonalResource: cloudscale.ZonalResource{
+			Zone: cloudscale.Zone{Slug: "rma1"},
+		},
+		Interfaces: []cloudscale.Interface{{
+			Type: "private",
+			Addresses: []cloudscale.Address{{
+				Address: "10.0.0.1",
+				Subnet:  cloudscale.SubnetStub{UUID: "subnet-uuid-1"},
+			}},
+		}},
+	}})
+
+	// Mock the remaining LB endpoints so reconciliation can proceed.
+	apiServer.On("/v1/load-balancers/pools", 200, []cloudscale.LoadBalancerPool{})
+	apiServer.On("/v1/load-balancers/listeners", 200, []cloudscale.LoadBalancerListener{})
+	apiServer.On("/v1/load-balancers/health-monitors", 200, []cloudscale.LoadBalancerHealthMonitor{})
+	apiServer.On("/v1/floating-ips", 200, []cloudscale.FloatingIP{})
+
+	apiServer.Start()
+	defer apiServer.Close()
+
+	client := fake.NewSimpleClientset()
+	fakeDiscovery, ok := client.Discovery().(*fakediscovery.FakeDiscovery)
+	require.True(t, ok, "couldn't convert Discovery() to *FakeDiscovery")
+	fakeDiscovery.FakedServerVersion = &version.Info{
+		Major: "1",
+		Minor: "34",
+	}
+
+	l := &loadbalancer{
+		lbs:      lbMapper{client: apiServer.Client()},
+		srv:      serverMapper{client: apiServer.Client()},
+		k8s:      client,
+		recorder: record.NewFakeRecorder(10),
+	}
+
+	service := &v1.Service{
+		ObjectMeta: metav1.ObjectMeta{
+			Name:      "test-service",
+			Namespace: "default",
+			UID:       "test-uid",
+			Annotations: map[string]string{
+				LoadBalancerName:   "k8s-service-test-uid",
+				LoadBalancerFlavor: "lb-standard",
+				LoadBalancerZone:   "rma1",
+			},
+		},
+		Spec: v1.ServiceSpec{
+			Type: v1.ServiceTypeLoadBalancer,
+			Ports: []v1.ServicePort{
+				{Protocol: v1.ProtocolTCP, Port: 80, NodePort: 80},
+			},
+		},
+	}
+
+	_, _ = l.k8s.CoreV1().Services("default").Create(t.Context(), service, metav1.CreateOptions{})
+
+	nodes := []*v1.Node{{
+		ObjectMeta: metav1.ObjectMeta{Name: "node-1"},
+		Spec:       v1.NodeSpec{ProviderID: "cloudscale://" + serverUUID},
+	}}
+
+	var wg sync.WaitGroup
+	wg.Add(2)
+	go func() {
+		defer wg.Done()
+		_, _ = l.EnsureLoadBalancer(t.Context(), "test-cluster", service, nodes)
+	}()
+	go func() {
+		defer wg.Done()
+		_, _ = l.EnsureLoadBalancer(t.Context(), "test-cluster", service, nodes)
+	}()
+	wg.Wait()
+
+	assert.Equal(t, 1, createCount, "expected exactly one LB creation")
+}
+
 func TestFilterNodesBySelector(t *testing.T) {
 	t.Parallel()
 

pkg/cloudscale_ccm/reconcile.go

@@ -5,7 +5,6 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
-	"math/rand"
 	"slices"
 	"strings"
 	"time"
@@ -749,9 +748,7 @@ func reconcileLbState(
 			break
 		}
 
-		// Wait between 5-7.5 seconds between state fetches
-		// #nosec G404
-		wait := time.Duration(5000+rand.Intn(2500)) * time.Millisecond
+		wait := 500 * time.Millisecond
 
 		select {
 		case <-ctx.Done():

pkg/internal/actions/actions.go

@@ -9,6 +9,7 @@ import (
 	"time"
 
 	"github.com/cloudscale-ch/cloudscale-go-sdk/v6"
+	"k8s.io/klog/v2"
 )
 
 type Action interface {
@@ -50,6 +51,18 @@ func (a *CreateLbAction) Label() string {
 func (a *CreateLbAction) Run(
 	ctx context.Context, client *cloudscale.Client) (Control, error) {
 
+	existing, err := client.LoadBalancers.List(ctx)
+	if err == nil {
+		for _, lb := range existing {
+			if lb.Name == a.lb.Name {
+				klog.InfoS("lb already exists, skipping create",
+					"name", a.lb.Name, "uuid", lb.UUID)
+
+				return Refresh, nil
+			}
+		}
+	}
+
 	addrs := make([]cloudscale.VIPAddressRequest, 0, len(a.lb.VIPAddresses))
 	for _, addr := range a.lb.VIPAddresses {
 		addrs = append(addrs, cloudscale.VIPAddressRequest{
@@ -58,7 +71,7 @@ func (a *CreateLbAction) Run(
 		})
 	}
 
-	_, err := client.LoadBalancers.Create(ctx, &cloudscale.LoadBalancerRequest{
+	_, err = client.LoadBalancers.Create(ctx, &cloudscale.LoadBalancerRequest{
 		Name:         a.lb.Name,
 		Flavor:       a.lb.Flavor.Slug,
 		VIPAddresses: &addrs,

pkg/internal/testkit/api.go

@@ -138,6 +138,16 @@ func (m *MockAPIServer) Start() {
 	m.server = httptest.NewServer(m.mux)
 }
 
+// HandleFunc registers a custom handler for the given pattern.
+// This allows intercepting requests dynamically, e.g. to track invocations.
+func (m *MockAPIServer) HandleFunc(pattern string, handler http.HandlerFunc) {
+	if m.mux == nil {
+		m.mux = http.NewServeMux()
+		m.On("/", 404, "{}")
+	}
+	m.mux.HandleFunc(pattern, handler)
+}
+
 // Close stops/closes the server and resets it.
 func (m *MockAPIServer) Close() {
 	if m.server != nil {