Merge branch 'main' into tallaxes/expectations

hack/deploy/configure-values.sh

@@ -16,6 +16,9 @@ AZURE_RESOURCE_GROUP=$2
 KARPENTER_SERVICE_ACCOUNT_NAME=$3
 AZURE_KARPENTER_USER_ASSIGNED_IDENTITY_NAME=$4
 
+# Optional values through env vars:
+LOG_LEVEL=${LOG_LEVEL:-"info"}
+
 AKS_JSON=$(az aks show --name "$CLUSTER_NAME" --resource-group "$AZURE_RESOURCE_GROUP" -o json)
 AZURE_LOCATION=$(jq -r ".location" <<< "$AKS_JSON")
 AZURE_RESOURCE_GROUP_MC=$(jq -r ".nodeResourceGroup" <<< "$AKS_JSON")
@@ -47,7 +50,8 @@ NODE_IDENTITIES=$(jq -r ".identityProfile.kubeletidentity.resourceId" <<< "$AKS_
 KARPENTER_USER_ASSIGNED_CLIENT_ID=$(az identity show --resource-group "${AZURE_RESOURCE_GROUP}" --name "${AZURE_KARPENTER_USER_ASSIGNED_IDENTITY_NAME}" --query 'clientId' -otsv)
 
 export CLUSTER_NAME AZURE_LOCATION AZURE_RESOURCE_GROUP_MC KARPENTER_SERVICE_ACCOUNT_NAME \
-    CLUSTER_ENDPOINT BOOTSTRAP_TOKEN SSH_PUBLIC_KEY VNET_SUBNET_ID KARPENTER_USER_ASSIGNED_CLIENT_ID NODE_IDENTITIES AZURE_SUBSCRIPTION_ID NETWORK_PLUGIN NETWORK_PLUGIN_MODE NETWORK_POLICY
+    CLUSTER_ENDPOINT BOOTSTRAP_TOKEN SSH_PUBLIC_KEY VNET_SUBNET_ID KARPENTER_USER_ASSIGNED_CLIENT_ID NODE_IDENTITIES AZURE_SUBSCRIPTION_ID NETWORK_PLUGIN NETWORK_PLUGIN_MODE NETWORK_POLICY \
+    LOG_LEVEL
 
 # get karpenter-values-template.yaml, if not already present (e.g. outside of repo context)
 if [ ! -f karpenter-values-template.yaml ]; then

karpenter-values-template.yaml

@@ -43,3 +43,4 @@ serviceAccount:
     azure.workload.identity/client-id: ${KARPENTER_USER_ASSIGNED_CLIENT_ID}
 podLabels:
   azure.workload.identity/use: "true"
+logLevel: ${LOG_LEVEL}

test/suites/integration/expiration_test.go

@@ -18,15 +18,13 @@ package integration_test
 
 import (
 	. "github.com/onsi/ginkgo/v2"
-	. "github.com/onsi/gomega"
 	"github.com/samber/lo"
 	appsv1 "k8s.io/api/apps/v1"
 	corev1 "k8s.io/api/core/v1"
 	"k8s.io/apimachinery/pkg/api/resource"
 	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
 	"k8s.io/apimachinery/pkg/labels"
 	"k8s.io/apimachinery/pkg/util/intstr"
-	"sigs.k8s.io/controller-runtime/pkg/client"
 
 	karpv1 "sigs.k8s.io/karpenter/pkg/apis/v1"
 
@@ -53,7 +51,8 @@ var _ = Describe("Expiration", func() {
 		selector = labels.SelectorFromSet(dep.Spec.Selector.MatchLabels)
 	})
 	It("should expire the node after the expiration is reached", func() {
-		nodePool.Spec.Template.Spec.ExpireAfter = karpv1.MustParseNillableDuration("2m")
+		// Set expire after large enough to make sure the new nodes are not expired before workloads are moved over.
+		nodePool.Spec.Template.Spec.ExpireAfter = karpv1.MustParseNillableDuration("3m")
 		env.ExpectCreated(nodeClass, nodePool, dep)
 
 		nodeClaim := env.EventuallyExpectCreatedNodeClaimCount("==", 1)[0]
@@ -62,15 +61,8 @@ var _ = Describe("Expiration", func() {
 		env.Monitor.Reset() // Reset the monitor so that we can expect a single node to be spun up after expiration
 
 		// Eventually the node will be tainted, which means its actively being disrupted
-		Eventually(func(g Gomega) {
-			g.Expect(env.Client.Get(env.Context, client.ObjectKeyFromObject(node), node)).Should(Succeed())
-			_, ok := lo.Find(node.Spec.Taints, func(t corev1.Taint) bool {
-				return t.MatchTaint(&karpv1.DisruptedNoScheduleTaint)
-			})
-			g.Expect(ok).To(BeTrue())
-		}).Should(Succeed())
-
-		env.EventuallyExpectCreatedNodeCount("==", 2)
+		env.EventuallyExpectTaintedNodeCount("==", 1)
+		env.EventuallyExpectCreatedNodeCount("==", 1)
 		// Set the limit to 0 to make sure we don't continue to create nodeClaims.
 		// This is CRITICAL since it prevents leaking node resources into subsequent tests
 		nodePool.Spec.Limits = karpv1.Limits{
@@ -109,15 +101,8 @@ var _ = Describe("Expiration", func() {
 		env.Monitor.Reset() // Reset the monitor so that we can expect a single node to be spun up after expiration
 
 		// Eventually the node will be tainted, which means its actively being disrupted
-		Eventually(func(g Gomega) {
-			g.Expect(env.Client.Get(env.Context, client.ObjectKeyFromObject(node), node)).Should(Succeed())
-			_, ok := lo.Find(node.Spec.Taints, func(t corev1.Taint) bool {
-				return t.MatchTaint(&karpv1.DisruptedNoScheduleTaint)
-			})
-			g.Expect(ok).To(BeTrue())
-		}).Should(Succeed())
-
-		env.EventuallyExpectCreatedNodeCount("==", 2)
+		env.EventuallyExpectTaintedNodeCount("==", 1)
+		env.EventuallyExpectCreatedNodeCount("==", 1)
 		// Set the limit to 0 to make sure we don't continue to create nodeClaims.
 		// This is CRITICAL since it prevents leaking node resources into subsequent tests
 		nodePool.Spec.Limits = karpv1.Limits{