Handle Jobs with ttl_seconds_after_finished = 0 correctly

Author: jaylonmcshan19-x

kubernetes/resource_kubernetes_job_v1.go

@@ -28,6 +28,7 @@ func resourceKubernetesJobV1() *schema.Resource {
 		ReadContext:   resourceKubernetesJobV1Read,
 		UpdateContext: resourceKubernetesJobV1Update,
 		DeleteContext: resourceKubernetesJobV1Delete,
+		CustomizeDiff: resourceKubernetesJobV1CustomizeDiff,
 		Importer: &schema.ResourceImporter{
 			StateContext: schema.ImportStatePassthroughContext,
 		},
@@ -48,6 +49,42 @@ func resourceKubernetesJobV1() *schema.Resource {
 	}
 }
 
+func resourceKubernetesJobV1CustomizeDiff(ctx context.Context, d *schema.ResourceDiff, meta interface{}) error {
+	if d.Id() == "" {
+		log.Printf("[DEBUG] Resource ID is empty, resource not created yet.")
+		return nil
+	}
+
+	conn, err := meta.(KubeClientsets).MainClientset()
+	if err != nil {
+		return err
+	}
+
+	namespace, name, err := idParts(d.Id())
+	if err != nil {
+		return err
+	}
+
+	ttlAttr := d.Get("spec.0.ttl_seconds_after_finished")
+	ttlSeconds, ok := ttlAttr.(int)
+	if !ok || ttlSeconds != 0 {
+		return nil
+	}
+
+	// getting the job
+	_, err = conn.BatchV1().Jobs(namespace).Get(ctx, name, metav1.GetOptions{})
+	if err != nil {
+		if errors.IsNotFound(err) {
+			// Suppress diff
+			d.Clear("spec")
+			d.Clear("metadata")
+			return nil
+		}
+		return err
+	}
+	return nil
+}
+
 func resourceKubernetesJobV1Schema() map[string]*schema.Schema {
 	return map[string]*schema.Schema{
 		"metadata": jobMetadataSchema(),
@@ -118,8 +155,17 @@ func resourceKubernetesJobV1Read(ctx context.Context, d *schema.ResourceData, me
 		return diag.FromErr(err)
 	}
 	if !exists {
-		d.SetId("")
-		return diag.Diagnostics{}
+		// Check if ttl_seconds_after_finished is set
+		if ttl, ok := d.GetOk("spec.0.ttl_seconds_after_finished"); ok {
+			// ttl_seconds_after_finished is set, Job is deleted due to TTL
+			// We don't need to remove the resource from the state
+			log.Printf("[INFO] Job %s has been deleted by Kubernetes due to TTL (ttl_seconds_after_finished = %v), keeping resource in state", d.Id(), ttl)
+			return diag.Diagnostics{}
+		} else {
+			// ttl_seconds_after_finished is not set, remove the resource from the state
+			d.SetId("")
+			return diag.Diagnostics{}
+		}
 	}
 	conn, err := meta.(KubeClientsets).MainClientset()
 	if err != nil {

kubernetes/resource_kubernetes_job_v1_test.go

@@ -237,6 +237,40 @@ func TestAccKubernetesJobV1_ttl_seconds_after_finished(t *testing.T) {
 	})
 }
 
+func TestAccKubernetesJobV1_customizeDiff_ttlZero(t *testing.T) {
+	var conf batchv1.Job
+	name := fmt.Sprintf("tf-acc-test-%s", acctest.RandString(10))
+	imageName := busyboxImage
+	resourceName := "kubernetes_job_v1.test"
+
+	resource.ParallelTest(t, resource.TestCase{
+		PreCheck: func() {
+			testAccPreCheck(t)
+			skipIfClusterVersionLessThan(t, "1.21.0")
+		},
+		ProviderFactories: testAccProviderFactories,
+		Steps: []resource.TestStep{
+			// Step 1: Create the Job
+			{
+				Config: testAccKubernetesJobV1Config_customizeDiff_ttlZero(name, imageName),
+				Check: resource.ComposeAggregateTestCheckFunc(
+					testAccCheckKubernetesJobV1Exists(resourceName, &conf),
+					resource.TestCheckResourceAttr(resourceName, "spec.0.ttl_seconds_after_finished", "0"),
+				),
+			},
+			// Step 2: Wait for the Job to complete and be deleted
+			{
+				PreConfig: func() {
+					time.Sleep(70 * time.Second)
+				},
+				Config:             testAccKubernetesJobV1Config_customizeDiff_ttlZero(name, imageName),
+				PlanOnly:           true,
+				ExpectNonEmptyPlan: false,
+			},
+		},
+	})
+}
+
 func testAccCheckJobV1Waited(minDuration time.Duration) func(*terraform.State) error {
 	// NOTE this works because this function is called when setting up the test
 	// and the function it returns is called after the resource has been created
@@ -516,3 +550,28 @@ func testAccKubernetesJobV1Config_modified(name, imageName string) string {
   wait_for_completion = false
 }`, name, imageName)
 }
+
+func testAccKubernetesJobV1Config_customizeDiff_ttlZero(name, imageName string) string {
+	return fmt.Sprintf(`
+resource "kubernetes_job_v1" "test" {
+  metadata {
+    name = "%s"
+  }
+  spec {
+    ttl_seconds_after_finished = 0
+    template {
+      metadata {}
+      spec {
+        container {
+          name    = "wait-test"
+          image   = "%s"
+          command = ["sleep", "60"]
+        }
+        restart_policy = "Never"
+      }
+    }
+  }
+  wait_for_completion = false
+}
+`, name, imageName)
+}