Merge remote-tracking branch 'upstream/main'

Author: dchourasia

go.mod

@@ -7,7 +7,7 @@ toolchain go1.21.5
 require (
 	github.com/kubeflow/training-operator v1.7.0
 	github.com/onsi/gomega v1.31.1
-	github.com/project-codeflare/codeflare-common v0.0.0-20240905061421-272c8b361325
+	github.com/project-codeflare/codeflare-common v0.0.0-20240913125822-2f60dc7b588c
 	github.com/prometheus/client_golang v1.18.0
 	github.com/prometheus/common v0.45.0
 	github.com/ray-project/kuberay/ray-operator v1.1.0-alpha.0

go.sum

@@ -363,10 +363,8 @@ github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZb
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
 github.com/project-codeflare/appwrapper v0.8.0 h1:vWHNtXUtHutN2EzYb6rryLdESnb8iDXsCokXOuNYXvg=
 github.com/project-codeflare/appwrapper v0.8.0/go.mod h1:FMQ2lI3fz6LakUVXgN1FTdpsc3BBkNIZZgtMmM9J5UM=
-github.com/project-codeflare/codeflare-common v0.0.0-20240829135229-4225111c401e h1:ozVW0icXLDJcKigc3Bi/4Fc4UMXMxESO53msCLameWw=
-github.com/project-codeflare/codeflare-common v0.0.0-20240829135229-4225111c401e/go.mod h1:unKTw+XoMANTES3WieG016im7rxZ7IR2/ph++L5Vp1Y=
-github.com/project-codeflare/codeflare-common v0.0.0-20240905061421-272c8b361325 h1:77e1P1PFUizHP9V/DiIa19Mp/ITPH8z4d4zirAcnFY8=
-github.com/project-codeflare/codeflare-common v0.0.0-20240905061421-272c8b361325/go.mod h1:unKTw+XoMANTES3WieG016im7rxZ7IR2/ph++L5Vp1Y=
+github.com/project-codeflare/codeflare-common v0.0.0-20240913125822-2f60dc7b588c h1:dtALMViz1KkOqHXNWy7fEXgX8CsT1YfopexQGkEzg/Q=
+github.com/project-codeflare/codeflare-common v0.0.0-20240913125822-2f60dc7b588c/go.mod h1:unKTw+XoMANTES3WieG016im7rxZ7IR2/ph++L5Vp1Y=
 github.com/prometheus/client_golang v0.9.1/go.mod h1:7SWBe2y4D6OKWSNQJUaRYU/AaXPKyh/dDVn+NZz0KFw=
 github.com/prometheus/client_golang v1.0.0/go.mod h1:db9x61etRT2tGnBNRi70OPL5FsnadC4Ky3P0J6CfImo=
 github.com/prometheus/client_golang v1.7.1/go.mod h1:PY5Wy2awLA44sXw4AOSfFBetzPP4j5+D6mVACh+pe2M=

tests/odh/mnist_ray_test.go

@@ -169,21 +169,15 @@ func mnistRay(test Test, numGpus int, namespace *corev1.Namespace, rayImage stri
 
 	// Initialise raycluster client to interact with raycluster to get rayjob details using REST-API
 	dashboardUrl := GetDashboardUrl(test, namespace, rayCluster)
-	rayClusterClientConfig := RayClusterClientConfig{Address: dashboardUrl.String(), Client: nil, InsecureSkipVerify: true}
-	rayClient, err := NewRayClusterClient(rayClusterClientConfig, test.Config().BearerToken)
-	test.Expect(err).ToNot(HaveOccurred(), fmt.Sprintf("Failed to create new raycluster client: %s", err))
+	rayClient := GetRayClusterClient(test, dashboardUrl, test.Config().BearerToken)
 
 	// wait until rayjob exists
 	test.Eventually(func() ([]RayJobDetailsResponse, error) {
-		rayJobs, err := rayClient.GetJobs()
-		if err != nil {
-			return *rayJobs, err
-		}
-		return *rayJobs, nil
+		return rayClient.ListJobs()
 	}, TestTimeoutMedium, 1*time.Second).Should(HaveLen(1), "Ray job not found")
 
 	// Get test job-id
-	jobID := GetTestJobId(test, rayClient, dashboardUrl.Host)
+	jobID := GetTestJobId(test, rayClient)
 	test.Expect(jobID).ToNot(BeEmpty())
 
 	// Wait for the job to be succeeded or failed

tests/odh/mnist_raytune_hpo_test.go

@@ -140,21 +140,15 @@ func mnistRayTuneHpo(t *testing.T, numGpus int) {
 
 	// Initialise raycluster client to interact with raycluster to get rayjob details using REST-API
 	dashboardUrl := GetDashboardUrl(test, namespace, rayCluster)
-	rayClusterClientConfig := RayClusterClientConfig{Address: dashboardUrl.String(), Client: nil, InsecureSkipVerify: true}
-	rayClient, err := NewRayClusterClient(rayClusterClientConfig, test.Config().BearerToken)
-	test.Expect(err).ToNot(HaveOccurred(), fmt.Sprintf("Failed to create new raycluster client: %s", err))
+	rayClient := GetRayClusterClient(test, dashboardUrl, test.Config().BearerToken)
 
 	// wait until rayjob exists
 	test.Eventually(func() ([]RayJobDetailsResponse, error) {
-		rayJobs, err := rayClient.GetJobs()
-		if err != nil {
-			return *rayJobs, err
-		}
-		return *rayJobs, nil
+		return rayClient.ListJobs()
 	}, TestTimeoutMedium, 1*time.Second).Should(HaveLen(1), "Ray job not found")
 
 	// Get rayjob-ID
-	jobID := GetTestJobId(test, rayClient, dashboardUrl.Host)
+	jobID := GetTestJobId(test, rayClient)
 	test.Expect(jobID).ToNot(BeEmpty())
 
 	// Wait for the job to either succeed or fail

tests/odh/ray_finetune_llm_deepspeed_test.go

@@ -127,21 +127,15 @@ func rayFinetuneLlmDeepspeed(t *testing.T, numGpus int, modelName string, modelC
 
 	// Initialise raycluster client to interact with raycluster to get rayjob details using REST-API
 	dashboardUrl := GetDashboardUrl(test, namespace, rayCluster)
-	rayClusterClientConfig := RayClusterClientConfig{Address: dashboardUrl.String(), Client: nil, InsecureSkipVerify: true}
-	rayClient, err := NewRayClusterClient(rayClusterClientConfig, test.Config().BearerToken)
-	test.Expect(err).ToNot(HaveOccurred(), fmt.Sprintf("Failed to create new raycluster client: %s", err))
+	rayClient := GetRayClusterClient(test, dashboardUrl, test.Config().BearerToken)
 
 	// wait until rayjob exists
 	test.Eventually(func() ([]RayJobDetailsResponse, error) {
-		rayJobs, err := rayClient.GetJobs()
-		if err != nil {
-			return *rayJobs, err
-		}
-		return *rayJobs, nil
+		return rayClient.ListJobs()
 	}, TestTimeoutMedium, 1*time.Second).Should(HaveLen(1), "Ray job not found")
 
 	// Get test job-id
-	jobID := GetTestJobId(test, rayClient, dashboardUrl.Host)
+	jobID := GetTestJobId(test, rayClient)
 	test.Expect(jobID).ToNot(BeEmpty())
 
 	// Wait for the job to be succeeded or failed

tests/odh/support.go

@@ -44,23 +44,23 @@ func ReadFileExt(t support.Test, fileName string) []byte {
 	return file
 }
 
-func GetDashboardUrl(test support.Test, namespace *v1.Namespace, rayCluster *rayv1.RayCluster) *url.URL {
+func GetDashboardUrl(test support.Test, namespace *v1.Namespace, rayCluster *rayv1.RayCluster) string {
 	dashboardName := "ray-dashboard-" + rayCluster.Name
 	route := support.GetRoute(test, namespace.Name, dashboardName)
 	hostname := route.Status.Ingress[0].Host
 	dashboardUrl, _ := url.Parse("https://" + hostname)
 	test.T().Logf("Ray-dashboard route : %s\n", dashboardUrl.String())
 
-	return dashboardUrl
+	return dashboardUrl.String()
 }
 
-func GetTestJobId(test support.Test, rayClient support.RayClusterClient, hostName string) string {
-	allJobsData, err := rayClient.GetJobs()
+func GetTestJobId(test support.Test, rayClient support.RayClusterClient) string {
+	allJobsData, err := rayClient.ListJobs()
 	test.Expect(err).ToNot(gomega.HaveOccurred())
+	test.Expect(allJobsData).NotTo(gomega.BeEmpty())
+
+	jobID := allJobsData[0].SubmissionID
+	test.T().Logf("Ray job has been successfully submitted to the raycluster with Submission-ID : %s\n", jobID)
 
-	jobID := (*allJobsData)[0].SubmissionID
-	if len(*allJobsData) > 0 {
-		test.T().Logf("Ray job has been successfully submitted to the raycluster with Submission-ID : %s\n", jobID)
-	}
 	return jobID
 }