[SPARK-25960][k8s] Support subpath mounting with Kubernetes

docs/running-on-kubernetes.md

@@ -219,6 +219,7 @@ To mount a volume of any of the types above into the driver pod, use the followi
 ```
 --conf spark.kubernetes.driver.volumes.[VolumeType].[VolumeName].mount.path=<mount path>
 --conf spark.kubernetes.driver.volumes.[VolumeType].[VolumeName].mount.readOnly=<true|false>
+--conf spark.kubernetes.driver.volumes.[VolumeType].[VolumeName].mount.subPath=<mount subPath>
 ``` 
 
 Specifically, `VolumeType` can be one of the following values: `hostPath`, `emptyDir`, and `persistentVolumeClaim`. `VolumeName` is the name you want to use for the volume under the `volumes` field in the pod specification.
@@ -780,6 +781,14 @@ specific to Spark on Kubernetes.
    <code>spark.kubernetes.driver.volumes.persistentVolumeClaim.checkpointpvc.mount.path=/checkpoint</code>.
   </td>
 </tr>
+<tr>
+  <td><code>spark.kubernetes.driver.volumes.[VolumeType].[VolumeName].mount.subPath</code></td>
+  <td>(none)</td>
+  <td>
+   Specifies a <a href="https://kubernetes.io/docs/concepts/storage/volumes/#using-subpath">subpath</a> to be mounted from the volume into the driver pod.
+   <code>spark.kubernetes.driver.volumes.persistentVolumeClaim.checkpointpvc.mount.subPath=checkpoint</code>.
+  </td>
+</tr>
 <tr>
   <td><code>spark.kubernetes.driver.volumes.[VolumeType].[VolumeName].mount.readOnly</code></td>
   <td>(none)</td>
@@ -804,6 +813,14 @@ specific to Spark on Kubernetes.
    <code>spark.kubernetes.executor.volumes.persistentVolumeClaim.checkpointpvc.mount.path=/checkpoint</code>.
   </td>
 </tr>
+<tr>
+  <td><code>spark.kubernetes.executor.volumes.[VolumeType].[VolumeName].mount.subPath</code></td>
+  <td>(none)</td>
+  <td>
+   Specifies a <a href="https://kubernetes.io/docs/concepts/storage/volumes/#using-subpath">subpath</a> to be mounted from the volume into the executor pod.
+   <code>spark.kubernetes.executor.volumes.persistentVolumeClaim.checkpointpvc.mount.subPath=checkpoint</code>.
+  </td>
+</tr>
 <tr>
   <td><code>spark.kubernetes.executor.volumes.[VolumeType].[VolumeName].mount.readOnly</code></td>
   <td>false</td>

resource-managers/kubernetes/core/src/main/scala/org/apache/spark/deploy/k8s/Config.scala

@@ -297,6 +297,7 @@ private[spark] object Config extends Logging {
   val KUBERNETES_VOLUMES_PVC_TYPE = "persistentVolumeClaim"
   val KUBERNETES_VOLUMES_EMPTYDIR_TYPE = "emptyDir"
   val KUBERNETES_VOLUMES_MOUNT_PATH_KEY = "mount.path"
+  val KUBERNETES_VOLUMES_MOUNT_SUBPATH_KEY = "mount.subPath"
   val KUBERNETES_VOLUMES_MOUNT_READONLY_KEY = "mount.readOnly"
   val KUBERNETES_VOLUMES_OPTIONS_PATH_KEY = "options.path"
   val KUBERNETES_VOLUMES_OPTIONS_CLAIM_NAME_KEY = "options.claimName"

resource-managers/kubernetes/core/src/main/scala/org/apache/spark/deploy/k8s/KubernetesVolumeSpec.scala

@@ -34,5 +34,6 @@ private[spark] case class KubernetesEmptyDirVolumeConf(
 private[spark] case class KubernetesVolumeSpec[T <: KubernetesVolumeSpecificConf](
     volumeName: String,
     mountPath: String,
+    mountSubPath: String,
     mountReadOnly: Boolean,
     volumeConf: T)

resource-managers/kubernetes/core/src/main/scala/org/apache/spark/deploy/k8s/KubernetesVolumeUtils.scala

@@ -39,13 +39,15 @@ private[spark] object KubernetesVolumeUtils {
     getVolumeTypesAndNames(properties).map { case (volumeType, volumeName) =>
       val pathKey = s"$volumeType.$volumeName.$KUBERNETES_VOLUMES_MOUNT_PATH_KEY"
       val readOnlyKey = s"$volumeType.$volumeName.$KUBERNETES_VOLUMES_MOUNT_READONLY_KEY"
+      val subPathKey = s"$volumeType.$volumeName.$KUBERNETES_VOLUMES_MOUNT_SUBPATH_KEY"
 
       for {
         path <- properties.getTry(pathKey)
         volumeConf <- parseVolumeSpecificConf(properties, volumeType, volumeName)
       } yield KubernetesVolumeSpec(
         volumeName = volumeName,
         mountPath = path,
+        mountSubPath = properties.get(subPathKey).getOrElse(""),
         mountReadOnly = properties.get(readOnlyKey).exists(_.toBoolean),
         volumeConf = volumeConf
       )

resource-managers/kubernetes/core/src/main/scala/org/apache/spark/deploy/k8s/features/MountVolumesFeatureStep.scala

@@ -51,6 +51,7 @@ private[spark] class MountVolumesFeatureStep(
       val volumeMount = new VolumeMountBuilder()
         .withMountPath(spec.mountPath)
         .withReadOnly(spec.mountReadOnly)
+        .withSubPath(spec.mountSubPath)
         .withName(spec.volumeName)
         .build()
 

resource-managers/kubernetes/core/src/test/scala/org/apache/spark/deploy/k8s/KubernetesVolumeUtilsSuite.scala

@@ -33,6 +33,18 @@ class KubernetesVolumeUtilsSuite extends SparkFunSuite {
       KubernetesHostPathVolumeConf("/hostPath"))
   }
 
+  test("Parses subPath correctly") {
+    val sparkConf = new SparkConf(false)
+    sparkConf.set("test.emptyDir.volumeName.mount.path", "/path")
+    sparkConf.set("test.emptyDir.volumeName.mount.readOnly", "true")
+    sparkConf.set("test.emptyDir.volumeName.mount.subPath", "subPath")
+
+    val volumeSpec = KubernetesVolumeUtils.parseVolumesWithPrefix(sparkConf, "test.").head.get
+    assert(volumeSpec.volumeName === "volumeName")
+    assert(volumeSpec.mountPath === "/path")
+    assert(volumeSpec.mountSubPath === "subPath")
+  }
+
   test("Parses persistentVolumeClaim volumes correctly") {
     val sparkConf = new SparkConf(false)
     sparkConf.set("test.persistentVolumeClaim.volumeName.mount.path", "/path")

resource-managers/kubernetes/core/src/test/scala/org/apache/spark/deploy/k8s/features/MountVolumesFeatureStepSuite.scala

@@ -43,6 +43,7 @@ class MountVolumesFeatureStepSuite extends SparkFunSuite {
     val volumeConf = KubernetesVolumeSpec(
       "testVolume",
       "/tmp",
+      "",
       false,
       KubernetesHostPathVolumeConf("/hostPath/tmp")
     )
@@ -62,6 +63,7 @@ class MountVolumesFeatureStepSuite extends SparkFunSuite {
     val volumeConf = KubernetesVolumeSpec(
       "testVolume",
       "/tmp",
+      "",
       true,
       KubernetesPVCVolumeConf("pvcClaim")
     )
@@ -83,6 +85,7 @@ class MountVolumesFeatureStepSuite extends SparkFunSuite {
     val volumeConf = KubernetesVolumeSpec(
       "testVolume",
       "/tmp",
+      "",
       false,
       KubernetesEmptyDirVolumeConf(Some("Memory"), Some("6G"))
     )
@@ -104,6 +107,7 @@ class MountVolumesFeatureStepSuite extends SparkFunSuite {
     val volumeConf = KubernetesVolumeSpec(
       "testVolume",
       "/tmp",
+      "",
       false,
       KubernetesEmptyDirVolumeConf(None, None)
     )
@@ -125,12 +129,14 @@ class MountVolumesFeatureStepSuite extends SparkFunSuite {
     val hpVolumeConf = KubernetesVolumeSpec(
       "hpVolume",
       "/tmp",
+      "",
       false,
       KubernetesHostPathVolumeConf("/hostPath/tmp")
     )
     val pvcVolumeConf = KubernetesVolumeSpec(
       "checkpointVolume",
       "/checkpoints",
+      "",
       true,
       KubernetesPVCVolumeConf("pvcClaim")
     )
@@ -142,4 +148,77 @@ class MountVolumesFeatureStepSuite extends SparkFunSuite {
     assert(configuredPod.pod.getSpec.getVolumes.size() === 2)
     assert(configuredPod.container.getVolumeMounts.size() === 2)
   }
+
+  test("Mounts subpath on emptyDir") {
+    val volumeConf = KubernetesVolumeSpec(
+      "testVolume",
+      "/tmp",
+      "foo",
+      false,
+      KubernetesEmptyDirVolumeConf(None, None)
+    )
+    val kubernetesConf = emptyKubernetesConf.copy(roleVolumes = volumeConf :: Nil)
+    val step = new MountVolumesFeatureStep(kubernetesConf)
+    val configuredPod = step.configurePod(SparkPod.initialPod())
+
+    assert(configuredPod.pod.getSpec.getVolumes.size() === 1)
+    val emptyDirMount = configuredPod.container.getVolumeMounts.get(0)
+    assert(emptyDirMount.getMountPath === "/tmp")
+    assert(emptyDirMount.getName === "testVolume")
+    assert(emptyDirMount.getSubPath === "foo")
+  }
+
+  test("Mounts subpath on persistentVolumeClaims") {
+    val volumeConf = KubernetesVolumeSpec(
+      "testVolume",
+      "/tmp",
+      "bar",
+      true,
+      KubernetesPVCVolumeConf("pvcClaim")
+    )
+    val kubernetesConf = emptyKubernetesConf.copy(roleVolumes = volumeConf :: Nil)
+    val step = new MountVolumesFeatureStep(kubernetesConf)
+    val configuredPod = step.configurePod(SparkPod.initialPod())
+
+    assert(configuredPod.pod.getSpec.getVolumes.size() === 1)
+    val pvcClaim = configuredPod.pod.getSpec.getVolumes.get(0).getPersistentVolumeClaim
+    assert(pvcClaim.getClaimName === "pvcClaim")
+    assert(configuredPod.container.getVolumeMounts.size() === 1)
+    val pvcMount = configuredPod.container.getVolumeMounts.get(0)
+    assert(pvcMount.getMountPath === "/tmp")
+    assert(pvcMount.getName === "testVolume")
+    assert(pvcMount.getSubPath === "bar")
+  }
+
+  test("Mounts multiple subpaths") {
+    val volumeConf = KubernetesEmptyDirVolumeConf(None, None)
+    val emptyDirSpec = KubernetesVolumeSpec(
+      "testEmptyDir",
+      "/tmp/foo",
+      "foo",
+      true,
+      KubernetesEmptyDirVolumeConf(None, None)
+    )
+    val pvcSpec = KubernetesVolumeSpec(
+      "testPVC",
+      "/tmp/bar",
+      "bar",
+      true,
+      KubernetesEmptyDirVolumeConf(None, None)
+    )
+    val kubernetesConf = emptyKubernetesConf.copy(
+      roleVolumes = emptyDirSpec :: pvcSpec :: Nil)
+    val step = new MountVolumesFeatureStep(kubernetesConf)
+    val configuredPod = step.configurePod(SparkPod.initialPod())
+
+    assert(configuredPod.pod.getSpec.getVolumes.size() === 2)
+    val mounts = configuredPod.container.getVolumeMounts
+    assert(mounts.size() === 2)
+    assert(mounts.get(0).getName === "testEmptyDir")
+    assert(mounts.get(0).getMountPath === "/tmp/foo")
+    assert(mounts.get(0).getSubPath === "foo")
+    assert(mounts.get(1).getName === "testPVC")
+    assert(mounts.get(1).getMountPath === "/tmp/bar")
+    assert(mounts.get(1).getSubPath === "bar")
+  }
 }

resource-managers/kubernetes/core/src/test/scala/org/apache/spark/deploy/k8s/submit/KubernetesDriverBuilderSuite.scala

@@ -140,6 +140,40 @@ class KubernetesDriverBuilderSuite extends SparkFunSuite {
     val volumeSpec = KubernetesVolumeSpec(
       "volume",
       "/tmp",
+      "",
+      false,
+      KubernetesHostPathVolumeConf("/path"))
+    val conf = KubernetesConf(
+      new SparkConf(false),
+      KubernetesDriverSpecificConf(
+        JavaMainAppResource(None),
+        "test-app",
+        "main",
+        Seq.empty),
+      "prefix",
+      "appId",
+      Map.empty,
+      Map.empty,
+      Map.empty,
+      Map.empty,
+      Map.empty,
+      volumeSpec :: Nil,
+      hadoopConfSpec = None)
+    validateStepTypesApplied(
+      builderUnderTest.buildFromFeatures(conf),
+      BASIC_STEP_TYPE,
+      CREDENTIALS_STEP_TYPE,
+      SERVICE_STEP_TYPE,
+      LOCAL_DIRS_STEP_TYPE,
+      MOUNT_VOLUMES_STEP_TYPE,
+      DRIVER_CMD_STEP_TYPE)
+  }
+
+  test("Apply volumes step if a mount subpath is present.") {
+    val volumeSpec = KubernetesVolumeSpec(
+      "volume",
+      "/tmp",
+      "foo",
       false,
       KubernetesHostPathVolumeConf("/path"))
     val conf = KubernetesConf(

resource-managers/kubernetes/core/src/test/scala/org/apache/spark/scheduler/cluster/k8s/KubernetesExecutorBuilderSuite.scala

@@ -107,6 +107,7 @@ class KubernetesExecutorBuilderSuite extends SparkFunSuite {
     val volumeSpec = KubernetesVolumeSpec(
       "volume",
       "/tmp",
+      "",
       false,
       KubernetesHostPathVolumeConf("/checkpoint"))
     val conf = KubernetesConf(