feat: Scale storage support on IBM Cloud HPC "/mnt/lsf"<br>* Fix for Intermittent scale mount failures<br>* Custom VPC Share support on "/mnt/lsf"<br>* Test cases upgradation<br>* Tekton COS Integrate<br>* New custom images for PAC (#171)

nupurg-ibm · Nupur Goyal · web-flow · commit 3fc6a52eebfe · 2024-06-24T20:15:06.000+05:30
Co-authored-by: Nupur Goyal &lt;nupurgoyal@Nupurs-MacBook-Pro.local&gt;
diff --git a/modules/landing_zone_vsi/image_map.tf b/modules/landing_zone_vsi/image_map.tf
@@ -1,9 +1,9 @@
 locals {
   image_region_map = {
-    "hpcaas-lsf10-rhel88-v7" = {
-      "us-east"  = "r014-68a7ad8a-c513-418e-a30c-9a04ce0a144a"
-      "eu-de"    = "r010-b392ff76-fb8c-4b0f-9fef-fba89eb3ee5b"
-      "us-south" = "r006-86f207dd-7029-4705-9222-0f5499387734"
+    "hpcaas-lsf10-rhel88-v8" = {
+      "us-east"  = "r014-ee8b808f-e129-4d9e-965e-fed7003132e7"
+      "eu-de"    = "r010-bfad7737-77f9-4af7-9446-4783fb582258"
+      "us-south" = "r006-d314bc1d-e904-4124-9055-0862e1a56579"
     },
     "hpcaas-lsf10-rhel88-compute-v5" = {
       "us-east"  = "r014-deb34fb1-edbf-464c-9af3-7efa2efcff3f"
diff --git a/samples/configs/hpc_catalog_values.json b/samples/configs/hpc_catalog_values.json
@@ -20,7 +20,7 @@
     "enable_cos_integration"    : "false",
     "cos_instance_name"         : "__NULL__",
     "enable_fip"                : "true",
-    "management_image_name"     : "hpcaas-lsf10-rhel88-v7",
+    "management_image_name"     : "hpcaas-lsf10-rhel88-v8",
     "compute_image_name"        : "hpcaas-lsf10-rhel88-compute-v5",
     "login_image_name"          : "hpcaas-lsf10-rhel88-compute-v5",
     "login_node_instance_type"  : "bx2-2x8",
diff --git a/samples/configs/hpc_schematics_values.json b/samples/configs/hpc_schematics_values.json
@@ -197,7 +197,7 @@
         },
         {
           "name": "management_image_name",
-          "value": "hpcaas-lsf10-rhel88-v7",
+          "value": "hpcaas-lsf10-rhel88-v8",
           "type": "string",
           "secure": false,
           "description": "Name of the custom image that you want to use to create virtual server instances in your IBM Cloud account to deploy the IBM Cloud HPC cluster management nodes. By default, the solution uses a RHEL88 base image with additional software packages mentioned [here](https://cloud.ibm.com/docs/ibm-spectrum-lsf#create-custom-image). If you would like to include your application-specific binary files, follow the instructions in [ Planning for custom images ](https://cloud.ibm.com/docs/vpc?topic=vpc-planning-custom-images) to create your own custom image and use that to build the IBM Cloud HPC cluster through this offering."
diff --git a/solutions/hpc/variables.tf b/solutions/hpc/variables.tf
@@ -176,7 +176,7 @@ variable "login_node_instance_type" {
 }
 variable "management_image_name" {
   type        = string
-  default     = "hpcaas-lsf10-rhel88-v7"
+  default     = "hpcaas-lsf10-rhel88-v8"
   description = "Name of the custom image that you want to use to create virtual server instances in your IBM Cloud account to deploy the IBM Cloud HPC cluster management nodes. By default, the solution uses a RHEL88 base image with additional software packages mentioned [here](https://cloud.ibm.com/docs/ibm-spectrum-lsf#create-custom-image). If you would like to include your application-specific binary files, follow the instructions in [ Planning for custom images ](https://cloud.ibm.com/docs/vpc?topic=vpc-planning-custom-images) to create your own custom image and use that to build the IBM Cloud HPC cluster through this offering."
 
 }
diff --git a/tests/lsf/lsf_cluster_utils.go b/tests/lsf/lsf_cluster_utils.go
@@ -911,7 +911,7 @@ func GetOSNameOfNode(t *testing.T, sClient *ssh.Client, hostIP string, logger *u
 	return "", parseErr
 }
 
-// HPCCheckFileMount checks if essential LSF directories (conf, config_done, das_staging_area, gui-conf, gui-logs, log, repository-path and work) exist
+// HPCCheckFileMount checks if essential LSF directories (10.1, conf, config_done, das_staging_area, data, gui-conf, gui-logs, log, repository-path and work) exist
 // on remote machines identified by the provided list of IP addresses. It utilizes SSH to
 // query and validate the directories. Any missing directory triggers an error, and the
 // function logs the success message if all directories are found.
@@ -1022,15 +1022,15 @@ func verifyDirectories(t *testing.T, sClient *ssh.Client, ip string, logger *uti
 	// Split the output into directory names
 	actualDirs := strings.Fields(strings.TrimSpace(string(outputTwo)))
 	// Define expected directories
-	expectedDirs := []string{"conf", "config_done", "das_staging_area", "gui-conf", "gui-logs", "log", "repository-path", "work"}
+	expectedDirs := []string{"10.1", "conf", "config_done", "das_staging_area", "data", "gui-conf", "gui-logs", "log", "repository-path", "work"}
 
 	// Verify if all expected directories exist
 	if !utils.VerifyDataContains(t, actualDirs, expectedDirs, logger) {
 		return fmt.Errorf("actual directory '%v' does not match the expected directory '%v' for node IP '%s'", actualDirs, expectedDirs, ip)
 	}
 
 	// Log directories existence
-	logger.Info(t, fmt.Sprintf("Directories [conf, config_done, das_staging_area, gui-conf, gui-logs, log, repository-path and work] exist on %s", ip))
+	logger.Info(t, fmt.Sprintf("Directories [10.1, conf, config_done, das_staging_area, data, gui-conf, gui-logs, log, repository-path and work] exist on %s", ip))
 	return nil
 }
 
@@ -1321,7 +1321,7 @@ func LSFRunJobsAsLDAPUser(t *testing.T, sClient *ssh.Client, jobCmd, ldapUser st
 	return fmt.Errorf("job execution for ID %s exceeded the specified time", jobID)
 }
 
-// HPCCheckFileMountAsLDAPUser checks if essential LSF directories (conf, config_done, das_staging_area, gui-conf, gui-logs, log, repository-path and work) exist
+// HPCCheckFileMountAsLDAPUser checks if essential LSF directories (10.1, conf, config_done, das_staging_area, data, gui-conf, gui-logs, log, repository-path and work) exist
 // on remote machines It utilizes SSH to
 // query and validate the directories. Any missing directory triggers an error, and the
 // function logs the success message if all directories are found.
@@ -1408,15 +1408,15 @@ func verifyDirectoriesAsLdapUser(t *testing.T, sClient *ssh.Client, hostname str
 	// Split the output into directory names
 	actualDirs := strings.Fields(strings.TrimSpace(string(outputTwo)))
 	// Define expected directories
-	expectedDirs := []string{"conf", "config_done", "das_staging_area", "gui-conf", "gui-logs", "log", "repository-path", "work"}
+	expectedDirs := []string{"10.1", "conf", "config_done", "das_staging_area", "data", "gui-conf", "gui-logs", "log", "repository-path", "work"}
 
 	// Verify if all expected directories exist
 	if !utils.VerifyDataContains(t, actualDirs, expectedDirs, logger) {
 		return fmt.Errorf("actual directory '%v' does not match the expected directory '%v' for node IP '%s'", actualDirs, expectedDirs, hostname)
 	}
 
 	// Log directories existence
-	logger.Info(t, fmt.Sprintf("Directories [conf, config_done, das_staging_area, gui-conf, gui-logs, log, repository-path and work] exist on %s", hostname))
+	logger.Info(t, fmt.Sprintf("Directories [10.1, conf, config_done, das_staging_area, data, gui-conf, gui-logs, log, repository-path and work] exist on %s", hostname))
 	return nil
 }
 
diff --git a/tests/other_test.go b/tests/other_test.go
@@ -899,6 +899,7 @@ func TestRunInvalidLDAPServerIP(t *testing.T) {
 	if err != nil {
 		// Check if the error message contains specific keywords indicating LDAP server IP issues
 		result := utils.VerifyDataContains(t, err.Error(), "The connection to the existing LDAP server 10.10.10.10 failed", testLogger)
+		assert.True(t, result)
 		if result {
 			testLogger.PASS(t, "Validation succeeded: Invalid LDAP server IP")
 		} else {
@@ -984,6 +985,7 @@ func TestRunInvalidLDAPUsernamePassword(t *testing.T) {
 				userPasswordError := utils.VerifyDataContains(t, err.Error(), "ldap_usr_pwd", testLogger)
 				adminPasswordError := utils.VerifyDataContains(t, err.Error(), "ldap_adm_pwd", testLogger)
 				result := usernameError && userPasswordError && adminPasswordError
+
 				// Assert that the result is true if all mandatory fields are missing
 				assert.True(t, result)
 				if result {
@@ -1115,6 +1117,7 @@ func TestRunInvalidDomainName(t *testing.T) {
 	if err != nil {
 		// Check if the error message contains specific keywords indicating domain name issues
 		result := utils.VerifyDataContains(t, err.Error(), "The domain name provided for compute is not a fully qualified domain name", testLogger)
+		assert.True(t, result)
 		if result {
 			testLogger.PASS(t, "Validation succeeded: Invalid domain name")
 		} else {
@@ -1339,3 +1342,62 @@ func TestRunExistSubnetIDVpcNameAsNull(t *testing.T) {
 		testLogger.FAIL(t, "Expected error did not occur on Without VPC name and with valid cluster_subnet_ids and login_subnet_id")
 	}
 }
+
+// TestRunInvalidSshKeysAndRemoteAllowedIP validates cluster creation with invalid ssh keys and remote allowed IP.
+func TestRunInvalidSshKeysAndRemoteAllowedIP(t *testing.T) {
+	// Parallelize the test to run concurrently with others
+	t.Parallel()
+
+	// Setup test suite
+	setupTestSuite(t)
+
+	testLogger.Info(t, "Cluster creation process initiated for "+t.Name())
+
+	// HPC cluster prefix
+	hpcClusterPrefix := utils.GenerateTimestampedClusterPrefix(utils.GenerateRandomString())
+
+	// Retrieve cluster information from environment variables
+	envVars := GetEnvVars()
+
+	// Get the absolute path of solutions/hpc
+	abs, err := filepath.Abs("solutions/hpc")
+	require.NoError(t, err, "Unable to get absolute path")
+
+	terrPath := strings.ReplaceAll(abs, "tests/", "")
+
+	// Define Terraform options
+	terraformOptions := terraform.WithDefaultRetryableErrors(t, &terraform.Options{
+		TerraformDir: terrPath,
+		Vars: map[string]interface{}{
+			"cluster_prefix":     hpcClusterPrefix,
+			"bastion_ssh_keys":   []string{""},
+			"compute_ssh_keys":   []string{""},
+			"zones":              utils.SplitAndTrim(envVars.Zone, ","),
+			"remote_allowed_ips": []string{""},
+			"cluster_id":         envVars.ClusterID,
+			"reservation_id":     envVars.ReservationID,
+		},
+	})
+
+	// Apply the Terraform configuration
+	_, err = terraform.InitAndPlanE(t, terraformOptions)
+
+	// Check if an error occurred during apply
+	assert.Error(t, err, "Expected an error during apply")
+
+	if err != nil {
+		// Check if the error message contains specific keywords indicating domain name issues
+		result := utils.VerifyDataContains(t, err.Error(), "The provided IP address format is not valid", testLogger) &&
+			utils.VerifyDataContains(t, err.Error(), "No SSH Key found with name", testLogger)
+		assert.True(t, result)
+		if result {
+			testLogger.PASS(t, "Validation succeeded: Invalid ssh keys and remote allowed IP")
+		} else {
+			testLogger.FAIL(t, "Validation failed: Invalid ssh keys and remote allowed IP")
+		}
+	} else {
+		// Log an error if the expected error did not occur
+		t.Error("Expected error did not occur")
+		testLogger.FAIL(t, "Expected error did not occur on Invalid ssh keys and remote allowed IP")
+	}
+}
diff --git a/tests/pr_test.go b/tests/pr_test.go
@@ -35,6 +35,7 @@ var ignoreDestroys = []string{
 	"module.check_cluster_status.null_resource.remote_exec[0]",
 	"module.landing_zone_vsi.module.hpc.module.landing_zone_vsi.module.wait_management_candidate_vsi_booted.null_resource.remote_exec[0]",
 	"module.landing_zone_vsi.module.hpc.module.landing_zone_vsi.module.wait_management_vsi_booted.null_resource.remote_exec[0]",
+	"module.landing_zone_vsi.module.do_management_vsi_configuration.null_resource.remote_exec_script_cp_files[1]",
 }
 
 // EnvVars stores environment variable values.
diff --git a/tests/test_config.yml b/tests/test_config.yml
@@ -7,7 +7,7 @@ remote_allowed_ips:
 ssh_key: geretain-hpc
 login_node_instance_type: bx2-2x8
 login_image_name: hpcaas-lsf10-rhel88-compute-v5
-management_image_name: hpcaas-lsf10-rhel88-v7
+management_image_name: hpcaas-lsf10-rhel88-v8
 compute_image_name: hpcaas-lsf10-rhel88-compute-v5
 management_node_instance_type: bx2-2x8
 management_node_count: 2

Original file line number	Diff line number	Diff line change
`@@ -197,7 +197,7 @@`
`197`	`197`	`},`
`198`	`198`	`{`
`199`	`199`	`"name": "management_image_name",`
`200`		`- "value": "hpcaas-lsf10-rhel88-v7",`
	`200`	`+ "value": "hpcaas-lsf10-rhel88-v8",`
`201`	`201`	`"type": "string",`
`202`	`202`	`"secure": false,`
`203`	`203`	"description": "Name of the custom image that you want to use to create virtual server instances in your IBM Cloud account to deploy the IBM Cloud HPC cluster management nodes. By default, the solution uses a RHEL88 base image with additional software packages mentioned [here](https://cloud.ibm.com/docs/ibm-spectrum-lsf#create-custom-image). If you would like to include your application-specific binary files, follow the instructions in [ Planning for custom images ](https://cloud.ibm.com/docs/vpc?topic=vpc-planning-custom-images) to create your own custom image and use that to build the IBM Cloud HPC cluster through this offering."
Original file line number	Diff line number	Diff line change
`@@ -176,7 +176,7 @@ variable "login_node_instance_type" {`
`176`	`176`	`}`
`177`	`177`	`variable "management_image_name" {`
`178`	`178`	`type = string`
`179`		`- default = "hpcaas-lsf10-rhel88-v7"`
	`179`	`+ default = "hpcaas-lsf10-rhel88-v8"`
`180`	`180`	description = "Name of the custom image that you want to use to create virtual server instances in your IBM Cloud account to deploy the IBM Cloud HPC cluster management nodes. By default, the solution uses a RHEL88 base image with additional software packages mentioned [here](https://cloud.ibm.com/docs/ibm-spectrum-lsf#create-custom-image). If you would like to include your application-specific binary files, follow the instructions in [ Planning for custom images ](https://cloud.ibm.com/docs/vpc?topic=vpc-planning-custom-images) to create your own custom image and use that to build the IBM Cloud HPC cluster through this offering."
`181`	`181`
`182`	`182`	`}`
Original file line number	Diff line number	Diff line change
`@@ -35,6 +35,7 @@ var ignoreDestroys = []string{`
`35`	`35`	`"module.check_cluster_status.null_resource.remote_exec[0]",`
`36`	`36`	`"module.landing_zone_vsi.module.hpc.module.landing_zone_vsi.module.wait_management_candidate_vsi_booted.null_resource.remote_exec[0]",`
`37`	`37`	`"module.landing_zone_vsi.module.hpc.module.landing_zone_vsi.module.wait_management_vsi_booted.null_resource.remote_exec[0]",`
	`38`	`+ "module.landing_zone_vsi.module.do_management_vsi_configuration.null_resource.remote_exec_script_cp_files[1]",`
`38`	`39`	`}`
`39`	`40`
`40`	`41`	`// EnvVars stores environment variable values.`