From 0ce697eefa72091181e81f2e656d84ff54083c39 Mon Sep 17 00:00:00 2001 From: hezhao2 Date: Mon, 13 Nov 2023 10:21:05 +0800 Subject: [PATCH] [KYUUBI #5654] Introduce new config to forcibly rewrite pod name ### _Why are the changes needed?_ close #5654 This pr is to introduce a config for rewriting pod name, which can help users forcibly rewrite driver or executor pod name prefix. ### _How was this patch tested?_ - [ ] Add some test cases that check the changes thoroughly including negative and positive cases if possible - [ ] Add screenshots for manual tests if appropriate - [ ] [Run test](https://kyuubi.readthedocs.io/en/master/contributing/code/testing.html#running-tests) locally before make a pull request ### _Was this patch authored or co-authored using generative AI tooling?_ No. Closes #5672 from zhaohehuhu/dev-1111. Closes #5654 6a450e444 [hezhao2] introduce new config to force rewrite pod name Authored-by: hezhao2 Signed-off-by: Cheng Pan --- docs/configuration/settings.md | 30 ++++++++++--------- .../org/apache/kyuubi/config/KyuubiConf.scala | 20 +++++++++++++ .../engine/spark/SparkProcessBuilder.scala | 16 ++++++++-- .../apache/kyuubi/util/KubernetesUtils.scala | 24 +++++++++------ .../spark/SparkProcessBuilderSuite.scala | 21 ++++++++++++- 5 files changed, 85 insertions(+), 26 deletions(-) diff --git a/docs/configuration/settings.md b/docs/configuration/settings.md index 2673a6903ae..0fa6d8e5a4d 100644 --- a/docs/configuration/settings.md +++ b/docs/configuration/settings.md @@ -309,20 +309,22 @@ You can configure the Kyuubi properties in `$KYUUBI_HOME/conf/kyuubi-defaults.co ### Kubernetes -| Key | Default | Meaning | Type | Since | -|-----------------------------------------------------|-------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------|-------| -| kyuubi.kubernetes.authenticate.caCertFile | <undefined> | Path to the CA cert file for connecting to the Kubernetes API server over TLS from the kyuubi. Specify this as a path as opposed to a URI (i.e. do not provide a scheme) | string | 1.7.0 | -| kyuubi.kubernetes.authenticate.clientCertFile | <undefined> | Path to the client cert file for connecting to the Kubernetes API server over TLS from the kyuubi. Specify this as a path as opposed to a URI (i.e. do not provide a scheme) | string | 1.7.0 | -| kyuubi.kubernetes.authenticate.clientKeyFile | <undefined> | Path to the client key file for connecting to the Kubernetes API server over TLS from the kyuubi. Specify this as a path as opposed to a URI (i.e. do not provide a scheme) | string | 1.7.0 | -| kyuubi.kubernetes.authenticate.oauthToken | <undefined> | The OAuth token to use when authenticating against the Kubernetes API server. Note that unlike, the other authentication options, this must be the exact string value of the token to use for the authentication. | string | 1.7.0 | -| kyuubi.kubernetes.authenticate.oauthTokenFile | <undefined> | Path to the file containing the OAuth token to use when authenticating against the Kubernetes API server. Specify this as a path as opposed to a URI (i.e. do not provide a scheme) | string | 1.7.0 | -| kyuubi.kubernetes.context | <undefined> | The desired context from your kubernetes config file used to configure the K8s client for interacting with the cluster. | string | 1.6.0 | -| kyuubi.kubernetes.context.allow.list || The allowed kubernetes context list, if it is empty, there is no kubernetes context limitation. | set | 1.8.0 | -| kyuubi.kubernetes.master.address | <undefined> | The internal Kubernetes master (API server) address to be used for kyuubi. | string | 1.7.0 | -| kyuubi.kubernetes.namespace | default | The namespace that will be used for running the kyuubi pods and find engines. | string | 1.7.0 | -| kyuubi.kubernetes.namespace.allow.list || The allowed kubernetes namespace list, if it is empty, there is no kubernetes namespace limitation. | set | 1.8.0 | -| kyuubi.kubernetes.terminatedApplicationRetainPeriod | PT5M | The period for which the Kyuubi server retains application information after the application terminates. | duration | 1.7.1 | -| kyuubi.kubernetes.trust.certificates | false | If set to true then client can submit to kubernetes cluster only with token | boolean | 1.7.0 | +| Key | Default | Meaning | Type | Since | +|----------------------------------------------------------------------|-------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------|-------| +| kyuubi.kubernetes.authenticate.caCertFile | <undefined> | Path to the CA cert file for connecting to the Kubernetes API server over TLS from the kyuubi. Specify this as a path as opposed to a URI (i.e. do not provide a scheme) | string | 1.7.0 | +| kyuubi.kubernetes.authenticate.clientCertFile | <undefined> | Path to the client cert file for connecting to the Kubernetes API server over TLS from the kyuubi. Specify this as a path as opposed to a URI (i.e. do not provide a scheme) | string | 1.7.0 | +| kyuubi.kubernetes.authenticate.clientKeyFile | <undefined> | Path to the client key file for connecting to the Kubernetes API server over TLS from the kyuubi. Specify this as a path as opposed to a URI (i.e. do not provide a scheme) | string | 1.7.0 | +| kyuubi.kubernetes.authenticate.oauthToken | <undefined> | The OAuth token to use when authenticating against the Kubernetes API server. Note that unlike, the other authentication options, this must be the exact string value of the token to use for the authentication. | string | 1.7.0 | +| kyuubi.kubernetes.authenticate.oauthTokenFile | <undefined> | Path to the file containing the OAuth token to use when authenticating against the Kubernetes API server. Specify this as a path as opposed to a URI (i.e. do not provide a scheme) | string | 1.7.0 | +| kyuubi.kubernetes.context | <undefined> | The desired context from your kubernetes config file used to configure the K8s client for interacting with the cluster. | string | 1.6.0 | +| kyuubi.kubernetes.context.allow.list || The allowed kubernetes context list, if it is empty, there is no kubernetes context limitation. | set | 1.8.0 | +| kyuubi.kubernetes.master.address | <undefined> | The internal Kubernetes master (API server) address to be used for kyuubi. | string | 1.7.0 | +| kyuubi.kubernetes.namespace | default | The namespace that will be used for running the kyuubi pods and find engines. | string | 1.7.0 | +| kyuubi.kubernetes.namespace.allow.list || The allowed kubernetes namespace list, if it is empty, there is no kubernetes namespace limitation. | set | 1.8.0 | +| kyuubi.kubernetes.spark.forciblyRewriteDriverPodName.enabled | false | Whether to forcibly rewrite Spark driver pod name with 'kyuubi--driver'. If disabled, Kyuubi will try to preserve the application name while satisfying K8s' pod name policy, but some vendors may have stricter pod name policies, thus the generated name may become illegal. | boolean | 1.8.1 | +| kyuubi.kubernetes.spark.forciblyRewriteExecutorPodNamePrefix.enabled | false | Whether to forcibly rewrite Spark executor pod name prefix with 'kyuubi-'. If disabled, Kyuubi will try to preserve the application name while satisfying K8s' pod name policy, but some vendors may have stricter Pod name policies, thus the generated name may become illegal. | boolean | 1.8.1 | +| kyuubi.kubernetes.terminatedApplicationRetainPeriod | PT5M | The period for which the Kyuubi server retains application information after the application terminates. | duration | 1.7.1 | +| kyuubi.kubernetes.trust.certificates | false | If set to true then client can submit to kubernetes cluster only with token | boolean | 1.7.0 | ### Lineage diff --git a/kyuubi-common/src/main/scala/org/apache/kyuubi/config/KyuubiConf.scala b/kyuubi-common/src/main/scala/org/apache/kyuubi/config/KyuubiConf.scala index c06672ad27a..042a211a2bf 100644 --- a/kyuubi-common/src/main/scala/org/apache/kyuubi/config/KyuubiConf.scala +++ b/kyuubi-common/src/main/scala/org/apache/kyuubi/config/KyuubiConf.scala @@ -3153,4 +3153,24 @@ object KyuubiConf { .serverOnly .intConf .createOptional + + val KUBERNETES_FORCIBLY_REWRITE_DRIVER_POD_NAME: ConfigEntry[Boolean] = + buildConf("kyuubi.kubernetes.spark.forciblyRewriteDriverPodName.enabled") + .doc("Whether to forcibly rewrite Spark driver pod name with 'kyuubi--driver'. " + + "If disabled, Kyuubi will try to preserve the application name while satisfying K8s' " + + "pod name policy, but some vendors may have stricter pod name policies, thus the " + + "generated name may become illegal.") + .version("1.8.1") + .booleanConf + .createWithDefault(false) + + val KUBERNETES_FORCIBLY_REWRITE_EXEC_POD_NAME_PREFIX: ConfigEntry[Boolean] = + buildConf("kyuubi.kubernetes.spark.forciblyRewriteExecutorPodNamePrefix.enabled") + .doc("Whether to forcibly rewrite Spark executor pod name prefix with 'kyuubi-'. " + + "If disabled, Kyuubi will try to preserve the application name while satisfying K8s' " + + "pod name policy, but some vendors may have stricter Pod name policies, thus the " + + "generated name may become illegal.") + .version("1.8.1") + .booleanConf + .createWithDefault(false) } diff --git a/kyuubi-server/src/main/scala/org/apache/kyuubi/engine/spark/SparkProcessBuilder.scala b/kyuubi-server/src/main/scala/org/apache/kyuubi/engine/spark/SparkProcessBuilder.scala index afc96fb5ea0..086ca057de8 100644 --- a/kyuubi-server/src/main/scala/org/apache/kyuubi/engine/spark/SparkProcessBuilder.scala +++ b/kyuubi-server/src/main/scala/org/apache/kyuubi/engine/spark/SparkProcessBuilder.scala @@ -30,6 +30,7 @@ import org.apache.hadoop.security.UserGroupInformation import org.apache.kyuubi._ import org.apache.kyuubi.config.KyuubiConf +import org.apache.kyuubi.config.KyuubiConf._ import org.apache.kyuubi.engine.{ApplicationManagerInfo, KyuubiApplicationManager, ProcBuilder} import org.apache.kyuubi.engine.KubernetesApplicationOperation.{KUBERNETES_SERVICE_HOST, KUBERNETES_SERVICE_PORT} import org.apache.kyuubi.engine.ProcBuilder.KYUUBI_ENGINE_LOG_PATH_KEY @@ -229,17 +230,28 @@ class SparkProcessBuilder( kubernetesNamespace()) } + private val forciblyRewriteDriverPodName: Boolean = + conf.get(KUBERNETES_FORCIBLY_REWRITE_DRIVER_POD_NAME) + private val forciblyRewriteExecPodNamePrefix: Boolean = + conf.get(KUBERNETES_FORCIBLY_REWRITE_EXEC_POD_NAME_PREFIX) + def appendPodNameConf(conf: Map[String, String]): Map[String, String] = { val appName = conf.getOrElse(APP_KEY, "spark") val map = mutable.Map.newBuilder[String, String] if (clusterManager().exists(cm => cm.toLowerCase(Locale.ROOT).startsWith("k8s"))) { if (!conf.contains(KUBERNETES_EXECUTOR_POD_NAME_PREFIX)) { - val prefix = KubernetesUtils.generateExecutorPodNamePrefix(appName, engineRefId) + val prefix = KubernetesUtils.generateExecutorPodNamePrefix( + appName, + engineRefId, + forciblyRewriteExecPodNamePrefix) map += (KUBERNETES_EXECUTOR_POD_NAME_PREFIX -> prefix) } if (deployMode().exists(_.toLowerCase(Locale.ROOT) == "cluster")) { if (!conf.contains(KUBERNETES_DRIVER_POD_NAME)) { - val name = KubernetesUtils.generateDriverPodName(appName, engineRefId) + val name = KubernetesUtils.generateDriverPodName( + appName, + engineRefId, + forciblyRewriteDriverPodName) map += (KUBERNETES_DRIVER_POD_NAME -> name) } } diff --git a/kyuubi-server/src/main/scala/org/apache/kyuubi/util/KubernetesUtils.scala b/kyuubi-server/src/main/scala/org/apache/kyuubi/util/KubernetesUtils.scala index 9da3408a336..929897d4814 100644 --- a/kyuubi-server/src/main/scala/org/apache/kyuubi/util/KubernetesUtils.scala +++ b/kyuubi-server/src/main/scala/org/apache/kyuubi/util/KubernetesUtils.scala @@ -130,21 +130,27 @@ object KubernetesUtils extends Logging { .replaceAll("^[0-9]", "x") } - def generateDriverPodName(appName: String, engineRefId: String): String = { - val resolvedResourceName = s"kyuubi-${getResourceNamePrefix(appName, engineRefId)}-driver" - if (resolvedResourceName.length <= DRIVER_POD_NAME_MAX_LENGTH) { - resolvedResourceName - } else { + def generateDriverPodName( + appName: String, + engineRefId: String, + forciblyRewrite: Boolean): String = { + lazy val resolvedResourceName = s"kyuubi-${getResourceNamePrefix(appName, engineRefId)}-driver" + if (forciblyRewrite || resolvedResourceName.length > DRIVER_POD_NAME_MAX_LENGTH) { s"kyuubi-$engineRefId-driver" + } else { + resolvedResourceName } } - def generateExecutorPodNamePrefix(appName: String, engineRefId: String): String = { + def generateExecutorPodNamePrefix( + appName: String, + engineRefId: String, + forciblyRewrite: Boolean): String = { val resolvedResourceName = s"kyuubi-${getResourceNamePrefix(appName, engineRefId)}" - if (resolvedResourceName.length <= EXECUTOR_POD_NAME_PREFIX_MAX_LENGTH) { - resolvedResourceName - } else { + if (forciblyRewrite || resolvedResourceName.length > EXECUTOR_POD_NAME_PREFIX_MAX_LENGTH) { s"kyuubi-$engineRefId" + } else { + resolvedResourceName } } } diff --git a/kyuubi-server/src/test/scala/org/apache/kyuubi/engine/spark/SparkProcessBuilderSuite.scala b/kyuubi-server/src/test/scala/org/apache/kyuubi/engine/spark/SparkProcessBuilderSuite.scala index 408f42f6404..7bbe4ad0670 100644 --- a/kyuubi-server/src/test/scala/org/apache/kyuubi/engine/spark/SparkProcessBuilderSuite.scala +++ b/kyuubi-server/src/test/scala/org/apache/kyuubi/engine/spark/SparkProcessBuilderSuite.scala @@ -28,7 +28,7 @@ import org.scalatestplus.mockito.MockitoSugar import org.apache.kyuubi._ import org.apache.kyuubi.config.KyuubiConf -import org.apache.kyuubi.config.KyuubiConf.{ENGINE_LOG_TIMEOUT, ENGINE_SPARK_MAIN_RESOURCE} +import org.apache.kyuubi.config.KyuubiConf.{ENGINE_LOG_TIMEOUT, ENGINE_SPARK_MAIN_RESOURCE, KUBERNETES_FORCIBLY_REWRITE_DRIVER_POD_NAME, KUBERNETES_FORCIBLY_REWRITE_EXEC_POD_NAME_PREFIX} import org.apache.kyuubi.engine.ProcBuilder.KYUUBI_ENGINE_LOG_PATH_KEY import org.apache.kyuubi.engine.spark.SparkProcessBuilder._ import org.apache.kyuubi.ha.HighAvailabilityConf @@ -336,6 +336,15 @@ class SparkProcessBuilderSuite extends KerberizedTestHelper with MockitoSugar { val conf4 = Map(APP_KEY -> chineseAppName) val driverPodName4 = processBuilder.appendPodNameConf(conf4).get(KUBERNETES_DRIVER_POD_NAME) assert(driverPodName4 === Some(s"kyuubi-test-$engineRefId-driver")) + val newProcessBuilder = new SparkProcessBuilder( + "kyuubi", + conf.set(MASTER_KEY, "k8s://internal").set(DEPLOY_MODE_KEY, "cluster").set( + KUBERNETES_FORCIBLY_REWRITE_DRIVER_POD_NAME, + true), + engineRefId) + val conf5 = Map(APP_KEY -> "test-forcibly-rewrite-app") + val driverPodName5 = newProcessBuilder.appendPodNameConf(conf5).get(KUBERNETES_DRIVER_POD_NAME) + assert(driverPodName5 === Some(s"kyuubi-$engineRefId-driver")) } test("[KYUUBI #5165] Test SparkProcessBuilder#appendExecutorPodPrefix") { @@ -363,6 +372,16 @@ class SparkProcessBuilderSuite extends KerberizedTestHelper with MockitoSugar { val execPodNamePrefix3 = processBuilder .appendPodNameConf(conf3).get(KUBERNETES_EXECUTOR_POD_NAME_PREFIX) assert(execPodNamePrefix3 === Some(s"kyuubi-$engineRefId")) + val newProcessBuilder = new SparkProcessBuilder( + "kyuubi", + conf.set(MASTER_KEY, "k8s://internal").set(DEPLOY_MODE_KEY, "cluster").set( + KUBERNETES_FORCIBLY_REWRITE_EXEC_POD_NAME_PREFIX, + true), + engineRefId) + val conf5 = Map(APP_KEY -> "test-forcibly-rewrite-app") + val execPodNamePrefix4 = newProcessBuilder + .appendPodNameConf(conf5).get(KUBERNETES_EXECUTOR_POD_NAME_PREFIX) + assert(execPodNamePrefix4 === Some(s"kyuubi-$engineRefId")) } test("extract spark core scala version") {