chore: Added end to end tests

Makefile

@@ -68,12 +68,17 @@ format: ## Format Go source files
 	@gofmt -l -w $(SRC)
 
 .PHONY: test
-test: test-unit
+test: test-unit test-e2e
 
 .PHONY: test-unit
 test-unit: download-tokenizer download-zmq
 	@printf "\033[33;1m==== Running Unit Tests ====\033[0m\n"
-	go test -ldflags="$(LDFLAGS)" -v ./...
+	go test -ldflags="$(LDFLAGS)" -v $$(echo $$(go list ./... | grep -v /test/))
+
+.PHONY: test-e2e
+test-e2e: image-build 
+	@printf "\033[33;1m==== Running End to End Tests ====\033[0m\n"
+	./test/scripts/run_e2e.sh
 
 .PHONY: test-integration
 test-integration: download-tokenizer download-zmq

go.mod

@@ -10,7 +10,13 @@ require (
 	github.com/google/go-cmp v0.7.0
 	github.com/jellydator/ttlcache/v3 v3.4.0
 	github.com/llm-d/llm-d-kv-cache-manager v0.2.1
+	github.com/onsi/ginkgo/v2 v2.23.4
+	github.com/onsi/gomega v1.37.0
+	github.com/openai/openai-go v1.12.0
 	github.com/stretchr/testify v1.11.0
+	google.golang.org/grpc v1.73.0
+	k8s.io/api v0.33.4
+	k8s.io/apiextensions-apiserver v0.33.2
 	k8s.io/apimachinery v0.33.4
 	k8s.io/client-go v0.33.4
 	sigs.k8s.io/controller-runtime v0.21.0
@@ -60,8 +66,6 @@ require (
 	github.com/modern-go/reflect2 v1.0.2 // indirect
 	github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect
 	github.com/mxk/go-flowrate v0.0.0-20140419014527-cca7078d478f // indirect
-	github.com/onsi/ginkgo/v2 v2.23.4 // indirect
-	github.com/onsi/gomega v1.37.0 // indirect
 	github.com/pebbe/zmq4 v1.4.0 // indirect
 	github.com/pkg/errors v0.9.1 // indirect
 	github.com/planetscale/vtprotobuf v0.6.1-0.20240319094008-0393e58bdf10 // indirect
@@ -74,6 +78,10 @@ require (
 	github.com/spf13/cobra v1.9.1 // indirect
 	github.com/spf13/pflag v1.0.6 // indirect
 	github.com/stoewer/go-strcase v1.3.0 // indirect
+	github.com/tidwall/gjson v1.14.4 // indirect
+	github.com/tidwall/match v1.1.1 // indirect
+	github.com/tidwall/pretty v1.2.1 // indirect
+	github.com/tidwall/sjson v1.2.5 // indirect
 	github.com/vmihailenco/msgpack/v5 v5.4.1 // indirect
 	github.com/vmihailenco/tagparser/v2 v2.0.0 // indirect
 	github.com/x448/float16 v0.8.4 // indirect
@@ -103,13 +111,10 @@ require (
 	gomodules.xyz/jsonpatch/v2 v2.4.0 // indirect
 	google.golang.org/genproto/googleapis/api v0.0.0-20250324211829-b45e905df463 // indirect
 	google.golang.org/genproto/googleapis/rpc v0.0.0-20250428153025-10db94c68c34 // indirect
-	google.golang.org/grpc v1.73.0 // indirect
 	google.golang.org/protobuf v1.36.6 // indirect
 	gopkg.in/evanphx/json-patch.v4 v4.12.0 // indirect
 	gopkg.in/inf.v0 v0.9.1 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
-	k8s.io/api v0.33.4 // indirect
-	k8s.io/apiextensions-apiserver v0.33.2 // indirect
 	k8s.io/apiserver v0.33.2 // indirect
 	k8s.io/component-base v0.33.2 // indirect
 	k8s.io/klog/v2 v2.130.1 // indirect

go.sum

@@ -123,6 +123,8 @@ github.com/onsi/ginkgo/v2 v2.23.4 h1:ktYTpKJAVZnDT4VjxSbiBenUjmlL/5QkBEocaWXiQus
 github.com/onsi/ginkgo/v2 v2.23.4/go.mod h1:Bt66ApGPBFzHyR+JO10Zbt0Gsp4uWxu5mIOTusL46e8=
 github.com/onsi/gomega v1.37.0 h1:CdEG8g0S133B4OswTDC/5XPSzE1OeP29QOioj2PID2Y=
 github.com/onsi/gomega v1.37.0/go.mod h1:8D9+Txp43QWKhM24yyOBEdpkzN8FvJyAwecBgsU4KU0=
+github.com/openai/openai-go v1.12.0 h1:NBQCnXzqOTv5wsgNC36PrFEiskGfO5wccfCWDo9S1U0=
+github.com/openai/openai-go v1.12.0/go.mod h1:g461MYGXEXBVdV5SaR/5tNzNbSfwTBBefwc+LlDCK0Y=
 github.com/pebbe/zmq4 v1.4.0 h1:gO5P92Ayl8GXpPZdYcD62Cwbq0slSBVVQRIXwGSJ6eQ=
 github.com/pebbe/zmq4 v1.4.0/go.mod h1:nqnPueOapVhE2wItZ0uOErngczsJdLOGkebMxaO8r48=
 github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
@@ -164,6 +166,16 @@ github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO
 github.com/stretchr/testify v1.8.1/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4=
 github.com/stretchr/testify v1.11.0 h1:ib4sjIrwZKxE5u/Japgo/7SJV3PvgjGiRNAvTVGqQl8=
 github.com/stretchr/testify v1.11.0/go.mod h1:wZwfW3scLgRK+23gO65QZefKpKQRnfz6sD981Nm4B6U=
+github.com/tidwall/gjson v1.14.2/go.mod h1:/wbyibRr2FHMks5tjHJ5F8dMZh3AcwJEMf5vlfC0lxk=
+github.com/tidwall/gjson v1.14.4 h1:uo0p8EbA09J7RQaflQ1aBRffTR7xedD2bcIVSYxLnkM=
+github.com/tidwall/gjson v1.14.4/go.mod h1:/wbyibRr2FHMks5tjHJ5F8dMZh3AcwJEMf5vlfC0lxk=
+github.com/tidwall/match v1.1.1 h1:+Ho715JplO36QYgwN9PGYNhgZvoUSc9X2c80KVTi+GA=
+github.com/tidwall/match v1.1.1/go.mod h1:eRSPERbgtNPcGhD8UCthc6PmLEQXEWd3PRB5JTxsfmM=
+github.com/tidwall/pretty v1.2.0/go.mod h1:ITEVvHYasfjBbM0u2Pg8T2nJnzm8xPwvNhhsoaGGjNU=
+github.com/tidwall/pretty v1.2.1 h1:qjsOFOWWQl+N3RsoF5/ssm1pHmJJwhjlSbZ51I6wMl4=
+github.com/tidwall/pretty v1.2.1/go.mod h1:ITEVvHYasfjBbM0u2Pg8T2nJnzm8xPwvNhhsoaGGjNU=
+github.com/tidwall/sjson v1.2.5 h1:kLy8mja+1c9jlljvWTlSazM7cKDRfJuR/bOJhcY5NcY=
+github.com/tidwall/sjson v1.2.5/go.mod h1:Fvgq9kS/6ociJEDnK0Fk1cpYF4FIW6ZF7LAe+6jwd28=
 github.com/vmihailenco/msgpack/v5 v5.4.1 h1:cQriyiUvjTwOHg8QZaPihLWeRAAVoCpE00IUPn0Bjt8=
 github.com/vmihailenco/msgpack/v5 v5.4.1/go.mod h1:GaZTsDaehaPpQVyxrf5mtQlH+pc21PIudVV/E3rRQok=
 github.com/vmihailenco/tagparser/v2 v2.0.0 h1:y09buUbR+b5aycVFQs/g70pqKVZNBmxwAhO7/IwNM9g=

test/e2e/e2e_suite_test.go

@@ -0,0 +1,183 @@
+package e2e
+
+import (
+	"context"
+	"io"
+	"os/exec"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/onsi/ginkgo/v2"
+	"github.com/onsi/gomega"
+	"github.com/onsi/gomega/gexec"
+	apiextv1 "k8s.io/apiextensions-apiserver/pkg/apis/apiextensions/v1"
+	"k8s.io/apimachinery/pkg/runtime"
+	clientgoscheme "k8s.io/client-go/kubernetes/scheme"
+	"sigs.k8s.io/controller-runtime/pkg/client"
+	"sigs.k8s.io/controller-runtime/pkg/client/config"
+	k8slog "sigs.k8s.io/controller-runtime/pkg/log"
+	infextv1a2 "sigs.k8s.io/gateway-api-inference-extension/api/v1alpha2"
+	"sigs.k8s.io/gateway-api-inference-extension/pkg/epp/util/env"
+)
+
+const (
+	// defaultExistsTimeout is the default timeout for a resource to exist in the api server.
+	defaultExistsTimeout = 30 * time.Second
+	// defaultReadyTimeout is the default timeout for a resource to report a ready state.
+	defaultReadyTimeout = 3 * time.Minute
+	// defaultModelReadyTimeout is the default timeout for the model server deployment to report a ready state.
+	defaultModelReadyTimeout = 10 * time.Minute
+	// defaultInterval is the default interval to check if a resource exists or ready conditions.
+	defaultInterval = time.Millisecond * 250
+	// xInferPoolManifest is the manifest for the inference pool CRD with 'inference.networking.x-k8s.io' group.
+	gieCrdsKustomize = "../../deploy/components/crds-gie"
+	// inferExtManifest is the manifest for the inference extension test resources.
+	inferExtManifest = "./yaml/inference-pools.yaml"
+	// modelName is the test model name.
+	modelName = "food-review"
+	// kvModelName is the model name used in KV tests.
+	kvModelName = "Qwen/Qwen2.5-1.5B-Instruct"
+	// safeKvModelName is the safe form of the model name used in KV tests
+	safeKvModelName = "qwen-qwen2-5-1-5b-instruct"
+	// envoyManifest is the manifest for the envoy proxy test resources.
+	envoyManifest = "./yaml/envoy.yaml"
+	// eppManifest is the manifest for the deployment of the EPP
+	eppManifest = "./yaml/deployments.yaml"
+	// rbacManifest is the manifest for the EPP's RBAC resources.
+	rbacManifest = "./yaml/rbac.yaml"
+	// serviceAccountManifest is the manifest for the EPP's service account resources.
+	serviceAccountManifest = "./yaml/service-accounts.yaml"
+	// servicesManifest is the manifest for the EPP's service resources.
+	servicesManifest = "./yaml/services.yaml"
+	// nsName is the namespace in which the K8S objects will be created
+	nsName = "default"
+)
+
+var (
+	ctx       = context.Background()
+	k8sClient client.Client
+	port      string
+	scheme    = runtime.NewScheme()
+
+	eppTag            = env.GetEnvString("EPP_TAG", "dev", ginkgo.GinkgoLogr)
+	vllmSimTag        = env.GetEnvString("VLLM_SIMULATOR_TAG", "dev", ginkgo.GinkgoLogr)
+	routingSideCarTag = env.GetEnvString("ROUTING_SIDECAR_TAG", "v0.2.0", ginkgo.GinkgoLogr)
+
+	existsTimeout     = env.GetEnvDuration("EXISTS_TIMEOUT", defaultExistsTimeout, ginkgo.GinkgoLogr)
+	readyTimeout      = env.GetEnvDuration("READY_TIMEOUT", defaultReadyTimeout, ginkgo.GinkgoLogr)
+	modelReadyTimeout = env.GetEnvDuration("MODEL_READY_TIMEOUT", defaultModelReadyTimeout, ginkgo.GinkgoLogr)
+	interval          = defaultInterval
+)
+
+func TestEndToEnd(t *testing.T) {
+	gomega.RegisterFailHandler(ginkgo.Fail)
+	ginkgo.RunSpecs(t,
+		"End To End Test Suite",
+	)
+}
+
+var _ = ginkgo.BeforeSuite(func() {
+	port = "30080"
+
+	setupK8sCluster()
+	setupK8sClient()
+	createCRDs()
+	createEnvoy()
+	applyYAMLFile(rbacManifest)
+	applyYAMLFile(serviceAccountManifest)
+	applyYAMLFile(servicesManifest)
+
+	infPoolYaml := readYaml(inferExtManifest)
+	infPoolYaml = substituteMany(infPoolYaml, map[string]string{"${POOL_NAME}": modelName + "-inference-pool"})
+	createObjsFromYaml(infPoolYaml)
+})
+
+var _ = ginkgo.AfterSuite(func() {
+	command := exec.Command("kind", "delete", "cluster", "--name", "e2e-tests")
+	session, err := gexec.Start(command, ginkgo.GinkgoWriter, ginkgo.GinkgoWriter)
+	gomega.Expect(err).ShouldNot(gomega.HaveOccurred())
+	gomega.Eventually(session).WithTimeout(600 * time.Second).Should(gexec.Exit(0))
+})
+
+// Create the Kubernetes cluster for the E2E tests and load the local images
+func setupK8sCluster() {
+	command := exec.Command("kind", "create", "cluster", "--name", "e2e-tests", "--config", "-")
+	stdin, err := command.StdinPipe()
+	gomega.Expect(err).ShouldNot(gomega.HaveOccurred())
+	go func() {
+		defer func() {
+			err := stdin.Close()
+			gomega.Expect(err).ShouldNot(gomega.HaveOccurred())
+		}()
+		clusterConfig := strings.ReplaceAll(kindClusterConfig, "${PORT}", port)
+		_, err := io.WriteString(stdin, clusterConfig)
+		gomega.Expect(err).ShouldNot(gomega.HaveOccurred())
+	}()
+	session, err := gexec.Start(command, ginkgo.GinkgoWriter, ginkgo.GinkgoWriter)
+	gomega.Expect(err).ShouldNot(gomega.HaveOccurred())
+	gomega.Eventually(session).WithTimeout(600 * time.Second).Should(gexec.Exit(0))
+
+	command = exec.Command("kind", "--name", "e2e-tests", "load", "docker-image",
+		"ghcr.io/llm-d/llm-d-inference-sim:"+vllmSimTag)
+	session, err = gexec.Start(command, ginkgo.GinkgoWriter, ginkgo.GinkgoWriter)
+	gomega.Expect(err).ShouldNot(gomega.HaveOccurred())
+	gomega.Eventually(session).WithTimeout(600 * time.Second).Should(gexec.Exit(0))
+
+	command = exec.Command("kind", "--name", "e2e-tests", "load", "docker-image",
+		"ghcr.io/llm-d/llm-d-inference-scheduler:"+eppTag)
+	session, err = gexec.Start(command, ginkgo.GinkgoWriter, ginkgo.GinkgoWriter)
+	gomega.Expect(err).ShouldNot(gomega.HaveOccurred())
+	gomega.Eventually(session).WithTimeout(600 * time.Second).Should(gexec.Exit(0))
+
+	command = exec.Command("kind", "--name", "e2e-tests", "load", "docker-image",
+		"ghcr.io/llm-d/llm-d-routing-sidecar:"+routingSideCarTag)
+	session, err = gexec.Start(command, ginkgo.GinkgoWriter, ginkgo.GinkgoWriter)
+	gomega.Expect(err).ShouldNot(gomega.HaveOccurred())
+	gomega.Eventually(session).WithTimeout(600 * time.Second).Should(gexec.Exit(0))
+}
+
+func setupK8sClient() {
+	k8sCfg := config.GetConfigOrDie()
+	gomega.ExpectWithOffset(1, k8sCfg).NotTo(gomega.BeNil())
+
+	err := clientgoscheme.AddToScheme(scheme)
+	gomega.Expect(err).NotTo(gomega.HaveOccurred())
+
+	err = apiextv1.AddToScheme(scheme)
+	gomega.Expect(err).NotTo(gomega.HaveOccurred())
+
+	err = infextv1a2.Install(scheme)
+	gomega.Expect(err).NotTo(gomega.HaveOccurred())
+
+	k8sClient, err = client.New(k8sCfg, client.Options{Scheme: scheme})
+	gomega.Expect(err).NotTo(gomega.HaveOccurred())
+	gomega.Expect(k8sClient).NotTo(gomega.BeNil())
+
+	k8slog.SetLogger(ginkgo.GinkgoLogr)
+}
+
+// createCRDs creates the Inference Extension CRDs used for testing.
+func createCRDs() {
+	crds := runKustomize(gieCrdsKustomize)
+	createObjsFromYaml(crds)
+}
+
+func createEnvoy() {
+	manifests := readYaml(envoyManifest)
+	ginkgo.By("Creating envoy proxy resources from manifest: " + envoyManifest)
+	createObjsFromYaml(manifests)
+}
+
+const kindClusterConfig = `
+kind: Cluster
+apiVersion: kind.x-k8s.io/v1alpha4
+nodes:
+- extraPortMappings:
+  - containerPort: 30080
+    hostPort: ${PORT}
+    protocol: TCP
+  - containerPort: 30081
+    hostPort: 30081
+    protocol: TCP
+`