docker - Spark 提交在 Kubernetes (EKS) 上失败，出现 "invalid null input: name"

Question

我正在尝试在 EKS 上运行 spark 示例 SparkPi docker 镜像。我的 Spark 版本是 3.0。
我创建了 spark serviceaccount 和角色绑定(bind)。当我提交作业时，出现以下错误:

2020-07-05T12:19:40.862635502Z Exception in thread "main" java.io.IOException: failure to login
2020-07-05T12:19:40.862756537Z  at org.apache.hadoop.security.UserGroupInformation.loginUserFromSubject(UserGroupInformation.java:841)
2020-07-05T12:19:40.862772672Z  at org.apache.hadoop.security.UserGroupInformation.getLoginUser(UserGroupInformation.java:777)
2020-07-05T12:19:40.862777401Z  at org.apache.hadoop.security.UserGroupInformation.getCurrentUser(UserGroupInformation.java:650)
2020-07-05T12:19:40.862788327Z  at org.apache.spark.util.Utils$.$anonfun$getCurrentUserName$1(Utils.scala:2412)
2020-07-05T12:19:40.862792294Z  at scala.Option.getOrElse(Option.scala:189)
2020-07-05T12:19:40.8628321Z    at org.apache.spark.util.Utils$.getCurrentUserName(Utils.scala:2412)
2020-07-05T12:19:40.862836906Z  at org.apache.spark.deploy.k8s.features.BasicDriverFeatureStep.configurePod(BasicDriverFeatureStep.scala:119)
2020-07-05T12:19:40.862907673Z  at org.apache.spark.deploy.k8s.submit.KubernetesDriverBuilder.$anonfun$buildFromFeatures$3(KubernetesDriverBuilder.scala:59)
2020-07-05T12:19:40.862917119Z  at scala.collection.LinearSeqOptimized.foldLeft(LinearSeqOptimized.scala:126)
2020-07-05T12:19:40.86294845Z   at scala.collection.LinearSeqOptimized.foldLeft$(LinearSeqOptimized.scala:122)
2020-07-05T12:19:40.862964245Z  at scala.collection.immutable.List.foldLeft(List.scala:89)
2020-07-05T12:19:40.862979665Z  at org.apache.spark.deploy.k8s.submit.KubernetesDriverBuilder.buildFromFeatures(KubernetesDriverBuilder.scala:58)
2020-07-05T12:19:40.863055425Z  at org.apache.spark.deploy.k8s.submit.Client.run(KubernetesClientApplication.scala:98)
2020-07-05T12:19:40.863060434Z  at org.apache.spark.deploy.k8s.submit.KubernetesClientApplication.$anonfun$run$4(KubernetesClientApplication.scala:221)
2020-07-05T12:19:40.863096062Z  at org.apache.spark.deploy.k8s.submit.KubernetesClientApplication.$anonfun$run$4$adapted(KubernetesClientApplication.scala:215)
2020-07-05T12:19:40.863103831Z  at org.apache.spark.util.Utils$.tryWithResource(Utils.scala:2539)
2020-07-05T12:19:40.863163804Z  at org.apache.spark.deploy.k8s.submit.KubernetesClientApplication.run(KubernetesClientApplication.scala:215)
2020-07-05T12:19:40.863168546Z  at org.apache.spark.deploy.k8s.submit.KubernetesClientApplication.start(KubernetesClientApplication.scala:188)
2020-07-05T12:19:40.863194449Z  at org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:928)
2020-07-05T12:19:40.863218817Z  at org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:180)
2020-07-05T12:19:40.863246594Z  at org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:203)
2020-07-05T12:19:40.863252341Z  at org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:90)
2020-07-05T12:19:40.863277236Z  at org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1007)
2020-07-05T12:19:40.863314173Z  at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1016)
2020-07-05T12:19:40.863319847Z  at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
2020-07-05T12:19:40.863653699Z Caused by: javax.security.auth.login.LoginException: java.lang.NullPointerException: invalid null input: name
2020-07-05T12:19:40.863660447Z  at com.sun.security.auth.UnixPrincipal.<init>(UnixPrincipal.java:71)
2020-07-05T12:19:40.863663683Z  at com.sun.security.auth.module.UnixLoginModule.login(UnixLoginModule.java:133)
2020-07-05T12:19:40.863667173Z  at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
2020-07-05T12:19:40.863670199Z  at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
2020-07-05T12:19:40.863673467Z  at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
2020-07-05T12:19:40.86367674Z   at java.lang.reflect.Method.invoke(Method.java:498)
2020-07-05T12:19:40.863680205Z  at javax.security.auth.login.LoginContext.invoke(LoginContext.java:755)
2020-07-05T12:19:40.863683401Z  at javax.security.auth.login.LoginContext.access$000(LoginContext.java:195)
2020-07-05T12:19:40.86368671Z   at javax.security.auth.login.LoginContext$4.run(LoginContext.java:682)
2020-07-05T12:19:40.863689794Z  at javax.security.auth.login.LoginContext$4.run(LoginContext.java:680)
2020-07-05T12:19:40.863693081Z  at java.security.AccessController.doPrivileged(Native Method)
2020-07-05T12:19:40.863696183Z  at javax.security.auth.login.LoginContext.invokePriv(LoginContext.java:680)
2020-07-05T12:19:40.863698579Z  at javax.security.auth.login.LoginContext.login(LoginContext.java:587)
2020-07-05T12:19:40.863700844Z  at org.apache.hadoop.security.UserGroupInformation.loginUserFromSubject(UserGroupInformation.java:815)
2020-07-05T12:19:40.863703393Z  at org.apache.hadoop.security.UserGroupInformation.getLoginUser(UserGroupInformation.java:777)
2020-07-05T12:19:40.86370659Z   at org.apache.hadoop.security.UserGroupInformation.getCurrentUser(UserGroupInformation.java:650)
2020-07-05T12:19:40.863709809Z  at org.apache.spark.util.Utils$.$anonfun$getCurrentUserName$1(Utils.scala:2412)
2020-07-05T12:19:40.863712847Z  at scala.Option.getOrElse(Option.scala:189)
2020-07-05T12:19:40.863716102Z  at org.apache.spark.util.Utils$.getCurrentUserName(Utils.scala:2412)
2020-07-05T12:19:40.863719273Z  at org.apache.spark.deploy.k8s.features.BasicDriverFeatureStep.configurePod(BasicDriverFeatureStep.scala:119)
2020-07-05T12:19:40.86372651Z   at org.apache.spark.deploy.k8s.submit.KubernetesDriverBuilder.$anonfun$buildFromFeatures$3(KubernetesDriverBuilder.scala:59)
2020-07-05T12:19:40.863728947Z  at scala.collection.LinearSeqOptimized.foldLeft(LinearSeqOptimized.scala:126)
2020-07-05T12:19:40.863731207Z  at scala.collection.LinearSeqOptimized.foldLeft$(LinearSeqOptimized.scala:122)
2020-07-05T12:19:40.863733458Z  at scala.collection.immutable.List.foldLeft(List.scala:89)
2020-07-05T12:19:40.863736237Z  at org.apache.spark.deploy.k8s.submit.KubernetesDriverBuilder.buildFromFeatures(KubernetesDriverBuilder.scala:58)
2020-07-05T12:19:40.863738769Z  at org.apache.spark.deploy.k8s.submit.Client.run(KubernetesClientApplication.scala:98)
2020-07-05T12:19:40.863742105Z  at org.apache.spark.deploy.k8s.submit.KubernetesClientApplication.$anonfun$run$4(KubernetesClientApplication.scala:221)
2020-07-05T12:19:40.863745486Z  at org.apache.spark.deploy.k8s.submit.KubernetesClientApplication.$anonfun$run$4$adapted(KubernetesClientApplication.scala:215)
2020-07-05T12:19:40.863749154Z  at org.apache.spark.util.Utils$.tryWithResource(Utils.scala:2539)
2020-07-05T12:19:40.863752601Z  at org.apache.spark.deploy.k8s.submit.KubernetesClientApplication.run(KubernetesClientApplication.scala:215)
2020-07-05T12:19:40.863756118Z  at org.apache.spark.deploy.k8s.submit.KubernetesClientApplication.start(KubernetesClientApplication.scala:188)
2020-07-05T12:19:40.863759673Z  at org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:928)
2020-07-05T12:19:40.863762774Z  at org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:180)
2020-07-05T12:19:40.863765929Z  at org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:203)
2020-07-05T12:19:40.86376906Z   at org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:90)
2020-07-05T12:19:40.863792673Z  at org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1007)
2020-07-05T12:19:40.863797161Z  at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1016)
2020-07-05T12:19:40.863799703Z  at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
2020-07-05T12:19:40.863802085Z 
2020-07-05T12:19:40.863804184Z  at javax.security.auth.login.LoginContext.invoke(LoginContext.java:856)
2020-07-05T12:19:40.863806454Z  at javax.security.auth.login.LoginContext.access$000(LoginContext.java:195)
2020-07-05T12:19:40.863808705Z  at javax.security.auth.login.LoginContext$4.run(LoginContext.java:682)
2020-07-05T12:19:40.863811134Z  at javax.security.auth.login.LoginContext$4.run(LoginContext.java:680)
2020-07-05T12:19:40.863815328Z  at java.security.AccessController.doPrivileged(Native Method)
2020-07-05T12:19:40.863817575Z  at javax.security.auth.login.LoginContext.invokePriv(LoginContext.java:680)
2020-07-05T12:19:40.863819856Z  at javax.security.auth.login.LoginContext.login(LoginContext.java:587)
2020-07-05T12:19:40.863829171Z  at org.apache.hadoop.security.UserGroupInformation.loginUserFromSubject(UserGroupInformation.java:815)
2020-07-05T12:19:40.86385963Z   ... 24 more

我的部署是:

apiVersion: v1
kind: Namespace
metadata:
  name: helios
---
apiVersion: v1
kind: ServiceAccount
metadata:
  name: spark
  namespace: helios
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  name: spark-role-binding
  namespace: helios
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: edit
subjects:
  - kind: ServiceAccount
    name: spark
    namespace: helios
---
apiVersion: batch/v1
kind: Job
metadata:
  name: spark-pi
  namespace: helios
spec:
  template:
    spec:
      containers:
        - name: spark-pi
          image: <registry>/spark-pi-3.0
          command: [
            "/bin/sh",
            "-c",
            "/opt/spark/bin/spark-submit \
            --master k8s://https://<EKS_API_SERVER> \
            --deploy-mode cluster \
            --name spark-pi \
            --class org.apache.spark.examples.SparkPi \
            --conf spark.kubernetes.namespace=helios
            --conf spark.executor.instances=2 \
            --conf spark.executor.memory=2G \
            --conf spark.executor.cores=2 \
            --conf spark.kubernetes.container.image=<registry>/spark-pi-3.0 \
            --conf spark.kubernetes.container.image.pullPolicy=Always \
            --conf spark.kubernetes.authenticate.driver.serviceAccountName=spark \
            --conf spark.jars.ivy=/tmp/.ivy
            local:///opt/spark/examples/jars/spark-examples_2.11-2.4.0.jar"
          ]
      serviceAccountName: spark
      restartPolicy: Never

docker 镜像是使用 Spark 安装中提供的 OOTB dockerfile 创建的。

docker build -t spark:latest -f kubernetes/dockerfiles/spark/Dockerfile .

我在这里做错了什么？请帮忙。
解决方案
在我从 docker 文件中评论以下行之后，它终于解决了。

USER ${spark_uid}

虽然，现在容器以 root 身份运行，但至少它正在工作。

Answer 1

我有同样的问题。我通过更改 k8s 工作解决了这个问题。
Hadoop 未能找到用户的用户名。您可以通过运行 whoami 来查看问题。在容器中，产生 whoami: cannot find name for user ID 185 . Spark 图片 entrypoint.sh包含 code将用户添加到 /etc/passwd ，它设置一个用户名。然而command绕过entrypoint.sh , 所以你应该使用 args像这样:

      containers:
        - name: spark-pi
          image: <registry>/spark-pi-3.0
      args: [
            "/bin/sh",
            "-c",
            "/opt/spark/bin/spark-submit \
            --master k8s://https://10.100.0.1:443 \
            --deploy-mode cluster ..."
      ]