Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[SPARK-49598][K8S] Support user-defined labels for OnDemand PVCs #48079

Closed
wants to merge 10 commits into from
Closed

[SPARK-49598][K8S] Support user-defined labels for OnDemand PVCs #48079

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
945f9af
[SPARK-49598] Added support to create custom user-defined labels for …
prathit06 Sep 11, 2024
12c1f30
Merge branch 'apache:master' into ondemand-pvc-labels
prathit06 Sep 11, 2024
98e12ae
Merge branch 'apache:master' into ondemand-pvc-labels
prathit06 Sep 12, 2024
3a4b210
using standard way to pick labels for volumes & applied suggested cha…
prathit06 Sep 12, 2024
cf7ccfe
added label properties in docs
prathit06 Sep 12, 2024
3c974f5
removed todo comment
prathit06 Sep 12, 2024
04070c1
minor refactoring
prathit06 Sep 12, 2024
7edb8ff
changed pattern for volume labels & change in docs for the same
prathit06 Sep 12, 2024
d017e41
added volume label key in configs & addressed comments
prathit06 Sep 12, 2024
740b47e
fix test case failure
prathit06 Sep 12, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions resource-managers/kubernetes/core/src/main/scala/org/apache/spark/deploy/k8s/Config.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -776,6 +776,7 @@ private[spark] object Config extends Logging {
val KUBERNETES_VOLUMES_OPTIONS_MEDIUM_KEY = "options.medium"
val KUBERNETES_VOLUMES_OPTIONS_SIZE_LIMIT_KEY = "options.sizeLimit"
val KUBERNETES_VOLUMES_OPTIONS_SERVER_KEY = "options.server"
val KUBERNETES_VOLUMES_OPTIONS_LABELS_KEY = "options.labels"

val KUBERNETES_DRIVER_ENV_PREFIX = "spark.kubernetes.driverEnv."

Expand Down
3 changes: 2 additions & 1 deletion ...ers/kubernetes/core/src/main/scala/org/apache/spark/deploy/k8s/KubernetesVolumeSpec.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,8 @@ private[spark] case class KubernetesHostPathVolumeConf(hostPath: String)
private[spark] case class KubernetesPVCVolumeConf(
claimName: String,
storageClass: Option[String] = None,
size: Option[String] = None)
size: Option[String] = None,
labels: Map[String, String] = Map())
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please follow the existing semantic of Option.

- labels: Map[String, String] = Map())
+ labels: Option[Map[String, String]] = None)

extends KubernetesVolumeSpecificConf

private[spark] case class KubernetesEmptyDirVolumeConf(
Expand Down
20 changes: 19 additions & 1 deletion ...rs/kubernetes/core/src/main/scala/org/apache/spark/deploy/k8s/KubernetesVolumeUtils.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -86,12 +86,14 @@ object KubernetesVolumeUtils {
val storageClassKey =
s"$volumeType.$volumeName.$KUBERNETES_VOLUMES_OPTIONS_CLAIM_STORAGE_CLASS_KEY"
val sizeLimitKey = s"$volumeType.$volumeName.$KUBERNETES_VOLUMES_OPTIONS_SIZE_LIMIT_KEY"
val labelsKey = s"$volumeType.$volumeName.$KUBERNETES_VOLUMES_OPTIONS_LABELS_KEY"
verifyOptionKey(options, claimNameKey, KUBERNETES_VOLUMES_PVC_TYPE)
verifySize(options.get(sizeLimitKey))
KubernetesPVCVolumeConf(
options(claimNameKey),
options.get(storageClassKey),
options.get(sizeLimitKey))
options.get(sizeLimitKey),
convertStringLabelsToMap(options.get(labelsKey)))

case KUBERNETES_VOLUMES_EMPTYDIR_TYPE =>
val mediumKey = s"$volumeType.$volumeName.$KUBERNETES_VOLUMES_OPTIONS_MEDIUM_KEY"
Expand Down Expand Up @@ -127,4 +129,20 @@ object KubernetesVolumeUtils {
}
}
}

/**
* Converts string of labels to consumable java Map
*
* @param labels labels in format : k1=v1,k2=v2
* @return Map[k1->v1, k2->v2]
*/
private def convertStringLabelsToMap(labels: Option[String]): Map[String, String] = {
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I believe we don't need this helper.

labels match {
case Some(value) =>
value.split(",").map(_.split("=")).collect {
case Array(k, v) => k -> v
}.toMap
case None => Map()
}
}
}
4 changes: 2 additions & 2 deletions ...es/core/src/main/scala/org/apache/spark/deploy/k8s/features/MountVolumesFeatureStep.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -74,7 +74,7 @@ private[spark] class MountVolumesFeatureStep(conf: KubernetesConf)
new VolumeBuilder()
.withHostPath(new HostPathVolumeSource(hostPath, ""))

case KubernetesPVCVolumeConf(claimNameTemplate, storageClass, size) =>
case KubernetesPVCVolumeConf(claimNameTemplate, storageClass, size, labels) =>
val claimName = conf match {
case c: KubernetesExecutorConf =>
claimNameTemplate
Expand All @@ -91,7 +91,7 @@ private[spark] class MountVolumesFeatureStep(conf: KubernetesConf)
.withApiVersion("v1")
.withNewMetadata()
.withName(claimName)
.addToLabels(SPARK_APP_ID_LABEL, conf.appId)
.addToLabels((labels ++ Map(SPARK_APP_ID_LABEL -> conf.appId)).asJava)
.endMetadata()
.withNewSpec()
.withStorageClassName(storageClass.get)
Expand Down
2 changes: 1 addition & 1 deletion ...agers/kubernetes/core/src/test/scala/org/apache/spark/deploy/k8s/KubernetesTestConf.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -117,7 +117,7 @@ object KubernetesTestConf {
(KUBERNETES_VOLUMES_HOSTPATH_TYPE,
Map(KUBERNETES_VOLUMES_OPTIONS_PATH_KEY -> path))

case KubernetesPVCVolumeConf(claimName, storageClass, sizeLimit) =>
case KubernetesPVCVolumeConf(claimName, storageClass, sizeLimit, labels) =>
val sconf = storageClass
.map { s => (KUBERNETES_VOLUMES_OPTIONS_CLAIM_STORAGE_CLASS_KEY, s) }.toMap
val lconf = sizeLimit.map { l => (KUBERNETES_VOLUMES_OPTIONS_SIZE_LIMIT_KEY, l) }.toMap
Expand Down
19 changes: 18 additions & 1 deletion ...bernetes/core/src/test/scala/org/apache/spark/deploy/k8s/KubernetesVolumeUtilsSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,13 +50,30 @@ class KubernetesVolumeUtilsSuite extends SparkFunSuite {
sparkConf.set("test.persistentVolumeClaim.volumeName.mount.path", "/path")
sparkConf.set("test.persistentVolumeClaim.volumeName.mount.readOnly", "true")
sparkConf.set("test.persistentVolumeClaim.volumeName.options.claimName", "claimName")
sparkConf.set("test.persistentVolumeClaim.volumeName.options.labels", "env=test,name=pvc-name")

val volumeSpec = KubernetesVolumeUtils.parseVolumesWithPrefix(sparkConf, "test.").head
assert(volumeSpec.volumeName === "volumeName")
assert(volumeSpec.mountPath === "/path")
assert(volumeSpec.mountReadOnly)
assert(volumeSpec.volumeConf.asInstanceOf[KubernetesPVCVolumeConf] ===
KubernetesPVCVolumeConf("claimName"))
KubernetesPVCVolumeConf(claimName = "claimName",
labels = Map("env" -> "test", "name" -> "pvc-name")))
}

test("Parses persistentVolumeClaim volumes & puts labels as empty Map if not in correct format") {
val sparkConf = new SparkConf(false)
sparkConf.set("test.persistentVolumeClaim.volumeName.mount.path", "/path")
sparkConf.set("test.persistentVolumeClaim.volumeName.mount.readOnly", "true")
sparkConf.set("test.persistentVolumeClaim.volumeName.options.claimName", "claimName")
sparkConf.set("test.persistentVolumeClaim.volumeName.options.labels", "env:test,name:pvc-name")

val volumeSpec = KubernetesVolumeUtils.parseVolumesWithPrefix(sparkConf, "test.").head
assert(volumeSpec.volumeName === "volumeName")
assert(volumeSpec.mountPath === "/path")
assert(volumeSpec.mountReadOnly)
assert(volumeSpec.volumeConf.asInstanceOf[KubernetesPVCVolumeConf] ===
KubernetesPVCVolumeConf(claimName = "claimName", labels = Map()))
}

test("Parses emptyDir volumes correctly") {
Expand Down
5 changes: 3 additions & 2 deletions ...re/src/test/scala/org/apache/spark/deploy/k8s/features/MountVolumesFeatureStepSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,7 +48,8 @@ class MountVolumesFeatureStepSuite extends SparkFunSuite {
"/tmp",
"",
true,
KubernetesPVCVolumeConf("pvcClaim")
KubernetesPVCVolumeConf(claimName = "pvcClaim",
labels = Map("env" -> "test", "name" -> "pvc-name"))
)
val kubernetesConf = KubernetesTestConf.createDriverConf(volumes = Seq(volumeConf))
val step = new MountVolumesFeatureStep(kubernetesConf)
Expand Down Expand Up @@ -120,7 +121,7 @@ class MountVolumesFeatureStepSuite extends SparkFunSuite {
"/tmp",
"",
true,
KubernetesPVCVolumeConf("OnDemand")
KubernetesPVCVolumeConf(MountVolumesFeatureStep.PVC_ON_DEMAND)
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please don't touch irrelevant line.

)
val kubernetesConf = KubernetesTestConf.createDriverConf(volumes = Seq(volumeConf))
val step = new MountVolumesFeatureStep(kubernetesConf)
Expand Down