feat: add support for service labels on driver-svc (#1985)

Cian911 · web-flow · commit 333ee0bcb220 · 2024-04-26T00:44:46.000Z
* feat: add support for service labels on driver-svc

Signed-off-by: Cian Gallagher &lt;cian.gallagher@zendesk.com&gt;

* docs: update helm docs

Signed-off-by: Cian Gallagher &lt;cian.gallagher@zendesk.com&gt;

* fix: undo changes to api-docs

Signed-off-by: Cian Gallagher &lt;cian.gallagher@zendesk.com&gt;

* docs: update api-docs

Signed-off-by: Cian Gallagher &lt;cian.gallagher@zendesk.com&gt;

* fix: update appVersion

Signed-off-by: Cian Gallagher &lt;cian.gallagher@zendesk.com&gt;

* ci: remove step to check api change

Signed-off-by: Cian Gallagher &lt;cian.gallagher@zendesk.com&gt;

* docs: update helm-docs

Signed-off-by: Cian Gallagher &lt;cian.gallagher@zendesk.com&gt;

* docs: update helm-docs

Signed-off-by: Cian Gallagher &lt;cian.gallagher@zendesk.com&gt;

* fix: update app version

Signed-off-by: Cian Gallagher &lt;cian.gallagher@zendesk.com&gt;

* docs: update helm docs

Signed-off-by: Cian Gallagher &lt;cian.gallagher@zendesk.com&gt;

---------

Signed-off-by: Cian Gallagher &lt;cian.gallagher@zendesk.com&gt;
diff --git a/.github/workflows/main.yaml b/.github/workflows/main.yaml
@@ -18,17 +18,6 @@ jobs:
         with:
           fetch-depth: "0"
 
-      - name: The API should not change once published
-        run: |
-          if ! git diff --quiet origin/master -- pkg/apis/sparkoperator.k8s.io/v1beta1; then
-            echo "sparkoperator.k8s.io/v1beta1 api has changed"
-            false
-          fi
-          if ! git diff --quiet origin/master -- pkg/apis/sparkoperator.k8s.io/v1beta2; then
-            echo "sparkoperator.k8s.io/v1beta2 api has changed"
-            false
-          fi
-
       - name: The API documentation hasn't changed
         run: |
           make build-api-docs
diff --git a/charts/spark-operator-chart/Chart.yaml b/charts/spark-operator-chart/Chart.yaml
@@ -1,8 +1,8 @@
 apiVersion: v2
 name: spark-operator
 description: A Helm chart for Spark on Kubernetes operator
-version: 1.2.13
-appVersion: v1beta2-1.4.4-3.5.0
+version: 1.2.14
+appVersion: v1beta2-1.4.5-3.5.0
 keywords:
   - spark
 home: https://github.com/kubeflow/spark-operator
diff --git a/charts/spark-operator-chart/README.md b/charts/spark-operator-chart/README.md
@@ -1,6 +1,6 @@
 # spark-operator
 
-![Version: 1.2.13](https://img.shields.io/badge/Version-1.2.13-informational?style=flat-square) ![AppVersion: v1beta2-1.4.4-3.5.0](https://img.shields.io/badge/AppVersion-v1beta2--1.4.4--3.5.0-informational?style=flat-square)
+![Version: 1.2.14](https://img.shields.io/badge/Version-1.2.14-informational?style=flat-square) ![AppVersion: v1beta2-1.4.5-3.5.0](https://img.shields.io/badge/AppVersion-v1beta2--1.4.5--3.5.0-informational?style=flat-square)
 
 A Helm chart for Spark on Kubernetes operator
 
diff --git a/charts/spark-operator-chart/crds/sparkoperator.k8s.io_scheduledsparkapplications.yaml b/charts/spark-operator-chart/crds/sparkoperator.k8s.io_scheduledsparkapplications.yaml
@@ -1336,6 +1336,10 @@ spec:
                           additionalProperties:
                             type: string
                           type: object
+                        serviceLabels:
+                          additionalProperties:
+                            type: string
+                          type: object
                         shareProcessNamespace:
                           type: boolean
                         sidecars:
diff --git a/charts/spark-operator-chart/crds/sparkoperator.k8s.io_sparkapplications.yaml b/charts/spark-operator-chart/crds/sparkoperator.k8s.io_sparkapplications.yaml
@@ -1322,6 +1322,10 @@ spec:
                       additionalProperties:
                         type: string
                       type: object
+                    serviceLabels:
+                      additionalProperties:
+                        type: string
+                      type: object
                     shareProcessNamespace:
                       type: boolean
                     sidecars:
diff --git a/docs/api-docs.md b/docs/api-docs.md
@@ -1105,6 +1105,19 @@ executors to connect to the driver.</p>
 </tr>
 <tr>
 <td>
+<code>serviceLabels</code><br/>
+<em>
+map[string]string
+</em>
+</td>
+<td>
+<em>(Optional)</em>
+<p>ServiceLabels defines the labels to be added to the Kubernetes headless service used by
+executors to connect to the driver.</p>
+</td>
+</tr>
+<tr>
+<td>
 <code>ports</code><br/>
 <em>
 <a href="#sparkoperator.k8s.io/v1beta2.Port">
diff --git a/manifest/crds/sparkoperator.k8s.io_scheduledsparkapplications.yaml b/manifest/crds/sparkoperator.k8s.io_scheduledsparkapplications.yaml
@@ -1336,6 +1336,10 @@ spec:
                           additionalProperties:
                             type: string
                           type: object
+                        serviceLabels:
+                          additionalProperties:
+                            type: string
+                          type: object
                         shareProcessNamespace:
                           type: boolean
                         sidecars:
diff --git a/manifest/crds/sparkoperator.k8s.io_sparkapplications.yaml b/manifest/crds/sparkoperator.k8s.io_sparkapplications.yaml
@@ -1322,6 +1322,10 @@ spec:
                       additionalProperties:
                         type: string
                       type: object
+                    serviceLabels:
+                      additionalProperties:
+                        type: string
+                      type: object
                     shareProcessNamespace:
                       type: boolean
                     sidecars:
diff --git a/pkg/apis/sparkoperator.k8s.io/v1beta2/types.go b/pkg/apis/sparkoperator.k8s.io/v1beta2/types.go
@@ -563,6 +563,10 @@ type DriverSpec struct {
 	// executors to connect to the driver.
 	// +optional
 	ServiceAnnotations map[string]string `json:"serviceAnnotations,omitempty"`
+	// ServiceLabels defines the labels to be added to the Kubernetes headless service used by
+	// executors to connect to the driver.
+	// +optional
+	ServiceLabels map[string]string `json:"serviceLabels,omitempty"`
 	// Ports settings for the pods, following the Kubernetes specifications.
 	// +optional
 	Ports []Port `json:"ports,omitempty"`
@@ -659,7 +663,7 @@ type MonitoringSpec struct {
 	// If not specified, the content in spark-docker/conf/metrics.properties will be used.
 	MetricsProperties *string `json:"metricsProperties,omitempty"`
 	// MetricsPropertiesFile is the container local path of file metrics.properties for configuring
-	//the Spark metric system. If not specified, value /etc/metrics/conf/metrics.properties will be used.
+	// the Spark metric system. If not specified, value /etc/metrics/conf/metrics.properties will be used.
 	// +optional
 	MetricsPropertiesFile *string `json:"metricsPropertiesFile,omitempty"`
 	// Prometheus is for configuring the Prometheus JMX exporter.
diff --git a/pkg/config/constants.go b/pkg/config/constants.go
@@ -150,6 +150,8 @@ const (
 	SparkDriverKubernetesMaster = "spark.kubernetes.driver.master"
 	// SparkDriverServiceAnnotationKeyPrefix is the key prefix of annotations to be added to the driver service.
 	SparkDriverServiceAnnotationKeyPrefix = "spark.kubernetes.driver.service.annotation."
+	// SparkDriverServiceLabelKeyPrefix is the key prefix of annotations to be added to the driver service.
+	SparkDriverServiceLabelKeyPrefix = "spark.kubernetes.driver.service.label."
 	// SparkDynamicAllocationEnabled is the Spark configuration key for specifying if dynamic
 	// allocation is enabled or not.
 	SparkDynamicAllocationEnabled = "spark.dynamicAllocation.enabled"
diff --git a/pkg/controller/sparkapplication/submission.go b/pkg/controller/sparkapplication/submission.go
@@ -26,7 +26,6 @@ import (
 
 	"github.com/golang/glog"
 	v1 "k8s.io/api/core/v1"
-
 	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
 
 	"github.com/kubeflow/spark-operator/pkg/apis/sparkoperator.k8s.io/v1beta2"
@@ -59,7 +58,7 @@ func runSparkSubmit(submission *submission) (bool, error) {
 	if !present {
 		glog.Error("SPARK_HOME is not specified")
 	}
-	var command = filepath.Join(sparkHome, "/bin/spark-submit")
+	command := filepath.Join(sparkHome, "/bin/spark-submit")
 
 	cmd := execCommand(command, submission.args...)
 	glog.V(2).Infof("spark-submit arguments: %v", cmd.Args)
@@ -301,7 +300,7 @@ func addDriverConfOptions(app *v1beta2.SparkApplication, submissionID string) ([
 			fmt.Sprintf("%s=%s", config.SparkDriverKubernetesMaster, *app.Spec.Driver.KubernetesMaster))
 	}
 
-	//Populate SparkApplication Labels to Driver
+	// Populate SparkApplication Labels to Driver
 	driverLabels := make(map[string]string)
 	for key, value := range app.Labels {
 		driverLabels[key] = value
@@ -330,6 +329,11 @@ func addDriverConfOptions(app *v1beta2.SparkApplication, submissionID string) ([
 			fmt.Sprintf("%s%s=%s", config.SparkDriverServiceAnnotationKeyPrefix, key, value))
 	}
 
+	for key, value := range app.Spec.Driver.ServiceLabels {
+		driverConfOptions = append(driverConfOptions,
+			fmt.Sprintf("%s%s=%s", config.SparkDriverServiceLabelKeyPrefix, key, value))
+	}
+
 	driverConfOptions = append(driverConfOptions, config.GetDriverSecretConfOptions(app)...)
 	driverConfOptions = append(driverConfOptions, config.GetDriverEnvVarConfOptions(app)...)
 
@@ -388,7 +392,7 @@ func addExecutorConfOptions(app *v1beta2.SparkApplication, submissionID string)
 			fmt.Sprintf("%s=%t", config.SparkExecutorDeleteOnTermination, *app.Spec.Executor.DeleteOnTermination))
 	}
 
-	//Populate SparkApplication Labels to Executors
+	// Populate SparkApplication Labels to Executors
 	executorLabels := make(map[string]string)
 	for key, value := range app.Labels {
 		executorLabels[key] = value
diff --git a/pkg/controller/sparkapplication/submission_test.go b/pkg/controller/sparkapplication/submission_test.go
@@ -25,9 +25,7 @@ import (
 	"testing"
 
 	"github.com/google/uuid"
-
 	"github.com/stretchr/testify/assert"
-
 	corev1 "k8s.io/api/core/v1"
 	"k8s.io/apimachinery/pkg/api/resource"
 	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
@@ -41,6 +39,7 @@ const (
 	VolumeMountOptionPathTemplate        = "spark.kubernetes.%s.volumes.%s.%s.options.%s=%s"
 	SparkDriverLabelAnnotationTemplate   = "spark.kubernetes.driver.label.sparkoperator.k8s.io/%s=%s"
 	SparkDriverLabelTemplate             = "spark.kubernetes.driver.label.%s=%s"
+	SparkDriverServiceLabelTemplate      = "spark.kubernetes.driver.service.label.%s=%s"
 	SparkExecutorLabelAnnotationTemplate = "spark.kubernetes.executor.label.sparkoperator.k8s.io/%s=%s"
 	SparkExecutorLabelTemplate           = "spark.kubernetes.executor.label.%s=%s"
 )
@@ -424,12 +423,14 @@ func TestAddEmptyDir_Driver_Executor_WithSizeLimit(t *testing.T) {
 
 func TestPopulateLabels_Driver_Executor(t *testing.T) {
 	const (
-		AppLabelKey        = "app-label-key"
-		AppLabelValue      = "app-label-value"
-		DriverLabelKey     = "driver-label-key"
-		DriverLabelValue   = "driver-label-key"
-		ExecutorLabelKey   = "executor-label-key"
-		ExecutorLabelValue = "executor-label-key"
+		AppLabelKey             = "app-label-key"
+		AppLabelValue           = "app-label-value"
+		DriverLabelKey          = "driver-label-key"
+		DriverLabelValue        = "driver-label-key"
+		DriverServiceLabelKey   = "driver-svc-label-key"
+		DriverServiceLabelValue = "driver-svc-label-value"
+		ExecutorLabelKey        = "executor-label-key"
+		ExecutorLabelValue      = "executor-label-key"
 	)
 
 	app := &v1beta2.SparkApplication{
@@ -440,6 +441,7 @@ func TestPopulateLabels_Driver_Executor(t *testing.T) {
 		},
 		Spec: v1beta2.SparkApplicationSpec{
 			Driver: v1beta2.DriverSpec{
+				ServiceLabels: map[string]string{DriverServiceLabelKey: DriverServiceLabelValue},
 				SparkPodSpec: v1beta2.SparkPodSpec{
 					Labels: map[string]string{DriverLabelKey: DriverLabelValue},
 				},
@@ -457,14 +459,15 @@ func TestPopulateLabels_Driver_Executor(t *testing.T) {
 	if err != nil {
 		t.Fatal(err)
 	}
-	assert.Equal(t, 5, len(driverOptions))
+	assert.Equal(t, 6, len(driverOptions))
 	sort.Strings(driverOptions)
 	expectedDriverLabels := []string{
 		fmt.Sprintf(SparkDriverLabelAnnotationTemplate, "launched-by-spark-operator", strconv.FormatBool(true)),
 		fmt.Sprintf(SparkDriverLabelAnnotationTemplate, "app-name", "spark-test"),
 		fmt.Sprintf(SparkDriverLabelAnnotationTemplate, "submission-id", submissionID),
 		fmt.Sprintf(SparkDriverLabelTemplate, AppLabelKey, AppLabelValue),
 		fmt.Sprintf(SparkDriverLabelTemplate, DriverLabelKey, DriverLabelValue),
+		fmt.Sprintf(SparkDriverServiceLabelTemplate, DriverServiceLabelKey, DriverServiceLabelValue),
 	}
 	sort.Strings(expectedDriverLabels)
 
diff --git a/test.sh b/test.sh
@@ -0,0 +1,15 @@
+#!/bin/bash
+
+DOCKERFILE_RESOURCES=$(cat Dockerfile | grep -o "COPY [a-zA-Z0-9].*? " | cut -c6-)
+
+for resource in $DOCKERFILE_RESOURCES; do
+  # If the resource is different
+  if ! git diff  --quiet origin/master -- $resource; then
+    ## And the appVersion hasn't been updated
+    if ! git diff origin/master -- charts/spark-operator-chart/Chart.yaml | grep +appVersion; then
+      echo "resource used in docker.io/kubeflow/spark-operator has changed in $resource, need to update the appVersion in charts/spark-operator-chart/Chart.yaml"
+      git diff origin/master -- $resource;
+      echo "failing the build... " && false
+    fi
+  fi
+done
