Node e2e Makefile support for running remote tests against kubernetes-node-e2e-images.

Also includes other improvements:
- Makefile rule to run tests against remote instance using existing host or image
- Makefile will reuse an instance created from an image if it was not torn down
- Runner starts gce instances in parallel with building source
- Runner uses instance ip instead of hostname so that it doesn't need to resolve
- Runner supports cleaning up files and processes on an instance without stopping / deleting it
- Runner runs tests using `ginkgo` binary to support running tests in parallel

test/e2e_node/e2e_build.go

@@ -120,7 +120,7 @@ func getK8sNodeTestDir() (string, error) {
 func getKubeletServerBin() string {
 	bin, err := getK8sBin("kubelet")
 	if err != nil {
-		panic(fmt.Sprintf("Could not locate kubelet binary."))
+		glog.Fatalf("Could not locate kubelet binary %v.", err)
 	}
 	return bin
 }
@@ -128,7 +128,7 @@ func getKubeletServerBin() string {
 func getApiServerBin() string {
 	bin, err := getK8sBin("kube-apiserver")
 	if err != nil {
-		panic(fmt.Sprintf("Could not locate kube-apiserver binary."))
+		glog.Fatalf("Could not locate kube-apiserver binary %v.", err)
 	}
 	return bin
 }

test/e2e_node/e2e_remote.go

@@ -26,6 +26,7 @@ import (
 	"os/user"
 	"path/filepath"
 	"strings"
+	"sync"
 
 	"github.com/golang/glog"
 	utilerrors "k8s.io/kubernetes/pkg/util/errors"
@@ -41,6 +42,11 @@ var sshOptionsMap map[string]string
 
 const archiveName = "e2e_node_test.tar.gz"
 
+var hostnameIpOverrides = struct {
+	sync.RWMutex
+	m map[string]string
+}{m: make(map[string]string)}
+
 func init() {
 	usr, err := user.Current()
 	if err != nil {
@@ -51,9 +57,24 @@ func init() {
 	}
 }
 
+func AddHostnameIp(hostname, ip string) {
+	hostnameIpOverrides.Lock()
+	defer hostnameIpOverrides.Unlock()
+	hostnameIpOverrides.m[hostname] = ip
+}
+
+func GetHostnameOrIp(hostname string) string {
+	hostnameIpOverrides.RLock()
+	defer hostnameIpOverrides.RUnlock()
+	if ip, found := hostnameIpOverrides.m[hostname]; found {
+		return ip
+	}
+	return hostname
+}
+
 // CreateTestArchive builds the local source and creates a tar archive e2e_node_test.tar.gz containing
 // the binaries k8s required for node e2e tests
-func CreateTestArchive() string {
+func CreateTestArchive() (string, error) {
 	// Build the executables
 	buildGo()
 
@@ -65,50 +86,57 @@ func CreateTestArchive() string {
 
 	ginkgoTest := filepath.Join(buildOutputDir, "e2e_node.test")
 	if _, err := os.Stat(ginkgoTest); err != nil {
-		glog.Fatalf("Failed to locate test binary %s", ginkgoTest)
+		return "", fmt.Errorf("failed to locate test binary %s", ginkgoTest)
 	}
-
 	kubelet := filepath.Join(buildOutputDir, "kubelet")
 	if _, err := os.Stat(kubelet); err != nil {
-		glog.Fatalf("Failed to locate binary %s", kubelet)
+		return "", fmt.Errorf("failed to locate binary %s", kubelet)
 	}
 	apiserver := filepath.Join(buildOutputDir, "kube-apiserver")
 	if _, err := os.Stat(apiserver); err != nil {
-		glog.Fatalf("Failed to locate binary %s", apiserver)
+		return "", fmt.Errorf("failed to locate binary %s", apiserver)
+	}
+	ginkgo := filepath.Join(buildOutputDir, "ginkgo")
+	if _, err := os.Stat(apiserver); err != nil {
+		return "", fmt.Errorf("failed to locate binary %s", ginkgo)
 	}
 
 	glog.Infof("Building archive...")
 	tardir, err := ioutil.TempDir("", "node-e2e-archive")
 	if err != nil {
-		glog.Fatalf("Failed to create temporary directory %v.", err)
+		return "", fmt.Errorf("failed to create temporary directory %v.", err)
 	}
 	defer os.RemoveAll(tardir)
 
 	// Copy binaries
 	out, err := exec.Command("cp", ginkgoTest, filepath.Join(tardir, "e2e_node.test")).CombinedOutput()
 	if err != nil {
-		glog.Fatalf("Failed to copy e2e_node.test %v.", err)
+		return "", fmt.Errorf("failed to copy e2e_node.test %v.", err)
 	}
 	out, err = exec.Command("cp", kubelet, filepath.Join(tardir, "kubelet")).CombinedOutput()
 	if err != nil {
-		glog.Fatalf("Failed to copy kubelet %v.", err)
+		return "", fmt.Errorf("failed to copy kubelet %v.", err)
 	}
 	out, err = exec.Command("cp", apiserver, filepath.Join(tardir, "kube-apiserver")).CombinedOutput()
 	if err != nil {
-		glog.Fatalf("Failed to copy kube-apiserver %v.", err)
+		return "", fmt.Errorf("failed to copy kube-apiserver %v.", err)
+	}
+	out, err = exec.Command("cp", ginkgo, filepath.Join(tardir, "ginkgo")).CombinedOutput()
+	if err != nil {
+		return "", fmt.Errorf("failed to copy ginkgo %v.", err)
 	}
 
 	// Build the tar
 	out, err = exec.Command("tar", "-zcvf", archiveName, "-C", tardir, ".").CombinedOutput()
 	if err != nil {
-		glog.Fatalf("Failed to build tar %v.  Output:\n%s", err, out)
+		return "", fmt.Errorf("failed to build tar %v.  Output:\n%s", err, out)
 	}
 
 	dir, err := os.Getwd()
 	if err != nil {
-		glog.Fatalf("Failed to get working directory %v.", err)
+		return "", fmt.Errorf("failed to get working directory %v.", err)
 	}
-	return filepath.Join(dir, archiveName)
+	return filepath.Join(dir, archiveName), nil
 }
 
 // Returns the command output, whether the exit was ok, and any errors
@@ -118,31 +146,31 @@ func RunRemote(archive string, host string, cleanup bool, junitFileNumber int, s
 		if err != nil {
 			return "", false, fmt.Errorf("could not find username: %v", err)
 		}
-		output, err := RunSshCommand("ssh", host, "--", "sudo", "usermod", "-a", "-G", "docker", uname.Username)
+		output, err := RunSshCommand("ssh", GetHostnameOrIp(host), "--", "sudo", "usermod", "-a", "-G", "docker", uname.Username)
 		if err != nil {
-			return "", false, fmt.Errorf("Instance %s not running docker daemon - Command failed: %s", host, output)
+			return "", false, fmt.Errorf("instance %s not running docker daemon - Command failed: %s", host, output)
 		}
 	}
 
 	// Create the temp staging directory
 	glog.Infof("Staging test binaries on %s", host)
 	tmp := fmt.Sprintf("/tmp/gcloud-e2e-%d", rand.Int31())
-	_, err := RunSshCommand("ssh", host, "--", "mkdir", tmp)
+	_, err := RunSshCommand("ssh", GetHostnameOrIp(host), "--", "mkdir", tmp)
 	if err != nil {
 		// Exit failure with the error
 		return "", false, err
 	}
 	if cleanup {
 		defer func() {
-			output, err := RunSshCommand("ssh", host, "--", "rm", "-rf", tmp)
+			output, err := RunSshCommand("ssh", GetHostnameOrIp(host), "--", "rm", "-rf", tmp)
 			if err != nil {
-				glog.Errorf("Failed to cleanup tmp directory %s on host %v.  Output:\n%s", tmp, err, output)
+				glog.Errorf("failed to cleanup tmp directory %s on host %v.  Output:\n%s", tmp, err, output)
 			}
 		}()
 	}
 
 	// Copy the archive to the staging directory
-	_, err = RunSshCommand("scp", archive, fmt.Sprintf("%s:%s/", host, tmp))
+	_, err = RunSshCommand("scp", archive, fmt.Sprintf("%s:%s/", GetHostnameOrIp(host), tmp))
 	if err != nil {
 		// Exit failure with the error
 		return "", false, err
@@ -158,12 +186,12 @@ func RunRemote(archive string, host string, cleanup bool, junitFileNumber int, s
 	// If we are unable to stop existing running k8s processes, we should see messages in the kubelet/apiserver/etcd
 	// logs about failing to bind the required ports.
 	glog.Infof("Killing any existing node processes on %s", host)
-	RunSshCommand("ssh", host, "--", "sh", "-c", cmd)
+	RunSshCommand("ssh", GetHostnameOrIp(host), "--", "sh", "-c", cmd)
 
 	// Extract the archive
 	cmd = getSshCommand(" && ", fmt.Sprintf("cd %s", tmp), fmt.Sprintf("tar -xzvf ./%s", archiveName))
 	glog.Infof("Extracting tar on %s", host)
-	output, err := RunSshCommand("ssh", host, "--", "sh", "-c", cmd)
+	output, err := RunSshCommand("ssh", GetHostnameOrIp(host), "--", "sh", "-c", cmd)
 	if err != nil {
 		// Exit failure with the error
 		return "", false, err
@@ -172,12 +200,13 @@ func RunRemote(archive string, host string, cleanup bool, junitFileNumber int, s
 	// Run the tests
 	cmd = getSshCommand(" && ",
 		fmt.Sprintf("cd %s", tmp),
-		fmt.Sprintf("timeout -k 30s %ds ./e2e_node.test --logtostderr --v 2 --build-services=false --stop-services=%t --node-name=%s --report-dir=%s/results --junit-file-number=%d %s", *testTimeoutSeconds, cleanup, host, tmp, junitFileNumber, *ginkgoFlags),
+		fmt.Sprintf("timeout -k 30s %ds ./ginkgo %s ./e2e_node.test -- --logtostderr --v 2 --build-services=false --stop-services=%t --node-name=%s --report-dir=%s/results --junit-file-number=%d", *testTimeoutSeconds, *ginkgoFlags, cleanup, host, tmp, junitFileNumber),
 	)
 	aggErrs := []error{}
 
 	glog.Infof("Starting tests on %s", host)
-	output, err = RunSshCommand("ssh", host, "--", "sh", "-c", cmd)
+	output, err = RunSshCommand("ssh", GetHostnameOrIp(host), "--", "sh", "-c", cmd)
+
 	if err != nil {
 		aggErrs = append(aggErrs, err)
 	}
@@ -195,13 +224,13 @@ func RunRemote(archive string, host string, cleanup bool, junitFileNumber int, s
 }
 
 func getTestArtifacts(host, testDir string) error {
-	_, err := RunSshCommand("scp", "-r", fmt.Sprintf("%s:%s/results/", host, testDir), fmt.Sprintf("%s/%s", *resultsDir, host))
+	_, err := RunSshCommand("scp", "-r", fmt.Sprintf("%s:%s/results/", GetHostnameOrIp(host), testDir), fmt.Sprintf("%s/%s", *resultsDir, host))
 	if err != nil {
 		return err
 	}
 
 	// Copy junit to the top of artifacts
-	_, err = RunSshCommand("scp", fmt.Sprintf("%s:%s/results/junit*", host, testDir), fmt.Sprintf("%s/", *resultsDir))
+	_, err = RunSshCommand("scp", fmt.Sprintf("%s:%s/results/junit*", GetHostnameOrIp(host), testDir), fmt.Sprintf("%s/", *resultsDir))
 	if err != nil {
 		return err
 	}
@@ -223,7 +252,7 @@ func RunSshCommand(cmd string, args ...string) (string, error) {
 	}
 	output, err := exec.Command(cmd, args...).CombinedOutput()
 	if err != nil {
-		return fmt.Sprintf("%s", output), fmt.Errorf("Command [%s %s] failed with error: %v and output:\n%s", cmd, strings.Join(args, " "), err, output)
+		return fmt.Sprintf("%s", output), fmt.Errorf("command [%s %s] failed with error: %v and output:\n%s", cmd, strings.Join(args, " "), err, output)
 	}
 	return fmt.Sprintf("%s", output), nil
 }

test/e2e_node/jenkins/e2e-node-jenkins.sh

@@ -29,7 +29,10 @@ set -x
 . $1
 
 go build test/e2e_node/environment/conformance.go
+
+WORKSPACE=${WORKSPACE:-"/tmp/"}
 ARTIFACTS=${WORKSPACE}/_artifacts
+
 mkdir -p ${ARTIFACTS}
 go run test/e2e_node/runner/run_e2e.go  --logtostderr --vmodule=*=2 --ssh-env="gce" \
   --zone="$GCE_ZONE" --project="$GCE_PROJECT" --image-project="$GCE_IMAGE_PROJECT" \

test/e2e_node/jenkins/jenkins-ci.properties

@@ -11,6 +11,6 @@ GCE_ZONE=us-central1-f
 GCE_PROJECT=kubernetes-jenkins
 GCE_IMAGE_PROJECT=kubernetes-jenkins
 CLEANUP=true
-GINKGO_FLAGS=--ginkgo.skip=FLAKY
+GINKGO_FLAGS=--skip=FLAKY
 SETUP_NODE=false
 

test/e2e_node/jenkins/jenkins-pull.properties

@@ -11,5 +11,5 @@ GCE_ZONE=us-central1-f
 GCE_PROJECT=kubernetes-jenkins-pull
 GCE_IMAGE_PROJECT=kubernetes-jenkins-pull
 CLEANUP=true
-GINKGO_FLAGS=--ginkgo.skip=FLAKY
+GINKGO_FLAGS=--skip=FLAKY
 SETUP_NODE=false

test/e2e_node/runner/run_e2e.go

@@ -27,6 +27,7 @@ import (
 	"net/http"
 	"os"
 	"strings"
+	"sync"
 	"time"
 
 	"k8s.io/kubernetes/test/e2e_node"
@@ -45,11 +46,20 @@ var imageProject = flag.String("image-project", "", "gce project the hosts live
 var images = flag.String("images", "", "images to test")
 var hosts = flag.String("hosts", "", "hosts to test")
 var cleanup = flag.Bool("cleanup", true, "If true remove files from remote hosts and delete temporary instances")
+var deleteInstances = flag.Bool("delete-instances", true, "If true, delete any instances created")
 var buildOnly = flag.Bool("build-only", false, "If true, build e2e_node_test.tar.gz and exit.")
 var setupNode = flag.Bool("setup-node", false, "When true, current user will be added to docker group on the test machine")
 
 var computeService *compute.Service
 
+type Archive struct {
+	sync.Once
+	path string
+	err  error
+}
+
+var arc Archive
+
 type TestResult struct {
 	output string
 	err    error
@@ -94,35 +104,22 @@ func main() {
 		noColour = "\033[0m"
 	}
 
-	archive := e2e_node.CreateTestArchive()
-	defer os.Remove(archive)
+	go arc.getArchive()
+	defer arc.deleteArchive()
+
+	var err error
+	computeService, err = getComputeClient()
+	if err != nil {
+		glog.Fatalf("Unable to create gcloud compute service using defaults.  Make sure you are authenticated. %v", err)
+	}
 
 	results := make(chan *TestResult)
 	running := 0
 	if *images != "" {
-		// Setup the gce client for provisioning instances
-		// Getting credentials on gce jenkins is flaky, so try a couple times
-		var err error
-		for i := 0; i < 10; i++ {
-			var client *http.Client
-			client, err = google.DefaultClient(oauth2.NoContext, compute.ComputeScope)
-			if err != nil {
-				continue
-			}
-			computeService, err = compute.New(client)
-			if err != nil {
-				continue
-			}
-			time.Sleep(time.Second * 6)
-		}
-		if err != nil {
-			glog.Fatalf("Unable to create gcloud compute service using defaults.  Make sure you are authenticated. %v", err)
-		}
-
 		for _, image := range strings.Split(*images, ",") {
 			running++
 			fmt.Printf("Initializing e2e tests using image %s.\n", image)
-			go func(image string, junitFileNum int) { results <- testImage(image, archive, junitFileNum) }(image, running)
+			go func(image string, junitFileNum int) { results <- testImage(image, junitFileNum) }(image, running)
 		}
 	}
 	if *hosts != "" {
@@ -130,7 +127,7 @@ func main() {
 			fmt.Printf("Initializing e2e tests using host %s.\n", host)
 			running++
 			go func(host string, junitFileNum int) {
-				results <- testHost(host, archive, *cleanup, junitFileNum, *setupNode)
+				results <- testHost(host, *cleanup, junitFileNum, *setupNode)
 			}(host, running)
 		}
 	}
@@ -159,9 +156,51 @@ func main() {
 	}
 }
 
+func (a *Archive) getArchive() (string, error) {
+	a.Do(func() { a.path, a.err = e2e_node.CreateTestArchive() })
+	return a.path, a.err
+}
+
+func (a *Archive) deleteArchive() {
+	path, err := a.getArchive()
+	if err != nil {
+		return
+	}
+	os.Remove(path)
+}
+
 // Run tests in archive against host
-func testHost(host, archive string, deleteFiles bool, junitFileNum int, setupNode bool) *TestResult {
-	output, exitOk, err := e2e_node.RunRemote(archive, host, deleteFiles, junitFileNum, setupNode)
+func testHost(host string, deleteFiles bool, junitFileNum int, setupNode bool) *TestResult {
+	instance, err := computeService.Instances.Get(*project, *zone, host).Do()
+	if err != nil {
+		return &TestResult{
+			err:    err,
+			host:   host,
+			exitOk: false,
+		}
+	}
+	if strings.ToUpper(instance.Status) != "RUNNING" {
+		err = fmt.Errorf("instance %s not in state RUNNING, was %s.", host, instance.Status)
+		return &TestResult{
+			err:    err,
+			host:   host,
+			exitOk: false,
+		}
+	}
+	externalIp := getExternalIp(instance)
+	if len(externalIp) > 0 {
+		e2e_node.AddHostnameIp(host, externalIp)
+	}
+
+	path, err := arc.getArchive()
+	if err != nil {
+		// Don't log fatal because we need to do any needed cleanup contained in "defer" statements
+		return &TestResult{
+			err: fmt.Errorf("unable to create test archive %v.", err),
+		}
+	}
+
+	output, exitOk, err := e2e_node.RunRemote(path, host, deleteFiles, junitFileNum, setupNode)
 	return &TestResult{
 		output: output,
 		err:    err,
@@ -172,17 +211,21 @@ func testHost(host, archive string, deleteFiles bool, junitFileNum int, setupNod
 
 // Provision a gce instance using image and run the tests in archive against the instance.
 // Delete the instance afterward.
-func testImage(image, archive string, junitFileNum int) *TestResult {
+func testImage(image string, junitFileNum int) *TestResult {
 	host, err := createInstance(image)
-	if *cleanup {
+	if *deleteInstances {
 		defer deleteInstance(image)
 	}
 	if err != nil {
 		return &TestResult{
-			err: fmt.Errorf("Unable to create gce instance with running docker daemon for image %s.  %v", image, err),
+			err: fmt.Errorf("unable to create gce instance with running docker daemon for image %s.  %v", image, err),
 		}
 	}
-	return testHost(host, archive, false, junitFileNum, *setupNode)
+
+	// Only delete the files if we are keeping the instance and want it cleaned up.
+	// If we are going to delete the instance, don't bother with cleaning up the files
+	deleteFiles := !*deleteInstances && *cleanup
+	return testHost(host, deleteFiles, junitFileNum, *setupNode)
 }
 
 // Provision a gce instance using image
@@ -216,7 +259,7 @@ func createInstance(image string) (string, error) {
 		return "", err
 	}
 	if op.Error != nil {
-		return "", fmt.Errorf("Could not create instance %s: %+v", name, op.Error)
+		return "", fmt.Errorf("could not create instance %s: %+v", name, op.Error)
 	}
 
 	instanceRunning := false
@@ -230,17 +273,21 @@ func createInstance(image string) (string, error) {
 			continue
 		}
 		if strings.ToUpper(instance.Status) != "RUNNING" {
-			err = fmt.Errorf("Instance %s not in state RUNNING, was %s.", name, instance.Status)
+			err = fmt.Errorf("instance %s not in state RUNNING, was %s.", name, instance.Status)
 			continue
 		}
+		externalIp := getExternalIp(instance)
+		if len(externalIp) > 0 {
+			e2e_node.AddHostnameIp(name, externalIp)
+		}
 		var output string
-		output, err = e2e_node.RunSshCommand("ssh", name, "--", "sudo", "docker", "version")
+		output, err = e2e_node.RunSshCommand("ssh", e2e_node.GetHostnameOrIp(name), "--", "sudo", "docker", "version")
 		if err != nil {
-			err = fmt.Errorf("Instance %s not running docker daemon - Command failed: %s", name, output)
+			err = fmt.Errorf("instance %s not running docker daemon - Command failed: %s", name, output)
 			continue
 		}
 		if !strings.Contains(output, "Server") {
-			err = fmt.Errorf("Instance %s not running docker daemon - Server not found: %s", name, output)
+			err = fmt.Errorf("instance %s not running docker daemon - Server not found: %s", name, output)
 			continue
 		}
 		instanceRunning = true
@@ -248,6 +295,47 @@ func createInstance(image string) (string, error) {
 	return name, err
 }
 
+func getExternalIp(instance *compute.Instance) string {
+	for i := range instance.NetworkInterfaces {
+		ni := instance.NetworkInterfaces[i]
+		for j := range ni.AccessConfigs {
+			ac := ni.AccessConfigs[j]
+			if len(ac.NatIP) > 0 {
+				return ac.NatIP
+			}
+		}
+	}
+	return ""
+}
+
+func getComputeClient() (*compute.Service, error) {
+	const retries = 10
+	const backoff = time.Second * 6
+
+	// Setup the gce client for provisioning instances
+	// Getting credentials on gce jenkins is flaky, so try a couple times
+	var err error
+	var cs *compute.Service
+	for i := 0; i < retries; i++ {
+		if i > 0 {
+			time.Sleep(backoff)
+		}
+
+		var client *http.Client
+		client, err = google.DefaultClient(oauth2.NoContext, compute.ComputeScope)
+		if err != nil {
+			continue
+		}
+
+		cs, err = compute.New(client)
+		if err != nil {
+			continue
+		}
+		return cs, nil
+	}
+	return nil, err
+}
+
 func deleteInstance(image string) {
 	_, err := computeService.Instances.Delete(*project, *zone, imageToInstanceName(image)).Do()
 	if err != nil {