[ 
https://issues.apache.org/jira/browse/FLINK-31974?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17719525#comment-17719525
 ] 

Sergio Sainz commented on FLINK-31974:
--------------------------------------

Hi [~mapohl] - let me setup a new cluster later on to get the full logs. Below 
please find the thread dump from the Flink 1.17.0 crash:

 
{code:java}
2023-04-28 20:50:50,305 INFO  
org.apache.flink.runtime.resourcemanager.slotmanager.DeclarativeSlotManager [] 
- Received resource requirements from job 0a97c80a173b7ebb619c5b030b607520: 
[ResourceRequirement{resourceProfile=ResourceProfile{UNKNOWN}, 
numberOfRequiredSlots=1}]
...
2023-04-28 20:50:50,534 ERROR org.apache.flink.util.FatalExitExceptionHandler   
           [] - FATAL: Thread 'flink-akka.actor.default-dispatcher-15' produced 
an uncaught exception. Stopping the process...
java.util.concurrent.CompletionException: 
org.apache.flink.kubernetes.shaded.io.fabric8.kubernetes.client.KubernetesClientException:
 Failure executing: POST at: 
https://10.96.0.1/api/v1/namespaces/env-my-namespace/pods. Message: 
Forbidden!Configured service account doesn't have access. Service account may 
have been revoked. pods "my-namespace-flink-cluster-taskmanager-1-2" is 
forbidden: exceeded quota: my-namespace-realtime-server-resource-quota, 
requested: limits.cpu=3, used: limits.cpu=12100m, limited: limits.cpu=13.
        at java.util.concurrent.CompletableFuture.encodeThrowable(Unknown 
Source) ~[?:?]
        at java.util.concurrent.CompletableFuture.completeThrowable(Unknown 
Source) ~[?:?]
        at java.util.concurrent.CompletableFuture$AsyncRun.run(Unknown Source) 
~[?:?]
        at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source) 
~[?:?]
        at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source) 
~[?:?]
        at java.lang.Thread.run(Unknown Source) ~[?:?]
Caused by: 
org.apache.flink.kubernetes.shaded.io.fabric8.kubernetes.client.KubernetesClientException:
 Failure executing: POST at: 
https://10.96.0.1/api/v1/namespaces/env-my-namespace/pods. Message: 
Forbidden!Configured service account doesn't have access. Service account may 
have been revoked. pods "my-namespace-flink-cluster-taskmanager-1-2" is 
forbidden: exceeded quota: my-namespace-realtime-server-resource-quota, 
requested: limits.cpu=3, used: limits.cpu=12100m, limited: limits.cpu=13.
        at 
org.apache.flink.kubernetes.shaded.io.fabric8.kubernetes.client.dsl.base.OperationSupport.requestFailure(OperationSupport.java:684)
 ~[flink-dist-1.17.0.jar:1.17.0]
        at 
org.apache.flink.kubernetes.shaded.io.fabric8.kubernetes.client.dsl.base.OperationSupport.requestFailure(OperationSupport.java:664)
 ~[flink-dist-1.17.0.jar:1.17.0]
        at 
org.apache.flink.kubernetes.shaded.io.fabric8.kubernetes.client.dsl.base.OperationSupport.assertResponseCode(OperationSupport.java:613)
 ~[flink-dist-1.17.0.jar:1.17.0]
        at 
org.apache.flink.kubernetes.shaded.io.fabric8.kubernetes.client.dsl.base.OperationSupport.handleResponse(OperationSupport.java:558)
 ~[flink-dist-1.17.0.jar:1.17.0]
        at 
org.apache.flink.kubernetes.shaded.io.fabric8.kubernetes.client.dsl.base.OperationSupport.handleResponse(OperationSupport.java:521)
 ~[flink-dist-1.17.0.jar:1.17.0]
        at 
org.apache.flink.kubernetes.shaded.io.fabric8.kubernetes.client.dsl.base.OperationSupport.handleCreate(OperationSupport.java:308)
 ~[flink-dist-1.17.0.jar:1.17.0]
        at 
org.apache.flink.kubernetes.shaded.io.fabric8.kubernetes.client.dsl.base.BaseOperation.handleCreate(BaseOperation.java:644)
 ~[flink-dist-1.17.0.jar:1.17.0]
        at 
org.apache.flink.kubernetes.shaded.io.fabric8.kubernetes.client.dsl.base.BaseOperation.handleCreate(BaseOperation.java:83)
 ~[flink-dist-1.17.0.jar:1.17.0]
        at 
org.apache.flink.kubernetes.shaded.io.fabric8.kubernetes.client.dsl.base.CreateOnlyResourceOperation.create(CreateOnlyResourceOperation.java:61)
 ~[flink-dist-1.17.0.jar:1.17.0]
        at 
org.apache.flink.kubernetes.kubeclient.Fabric8FlinkKubeClient.lambda$createTaskManagerPod$1(Fabric8FlinkKubeClient.java:163)
 ~[flink-dist-1.17.0.jar:1.17.0]
        ... 4 more
2023-04-28 20:50:50,602 ERROR org.apache.flink.util.FatalExitExceptionHandler   
           [] - Thread dump: 
"main" prio=5 Id=1 WAITING on 
java.util.concurrent.CompletableFuture$Signaller@2897b146
        at java.base@11.0.19/jdk.internal.misc.Unsafe.park(Native Method)
        -  waiting on java.util.concurrent.CompletableFuture$Signaller@2897b146
        at 
java.base@11.0.19/java.util.concurrent.locks.LockSupport.park(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.CompletableFuture$Signaller.block(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ForkJoinPool.managedBlock(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.CompletableFuture.waitingGet(Unknown 
Source)
        at java.base@11.0.19/java.util.concurrent.CompletableFuture.get(Unknown 
Source)
        at 
app//org.apache.flink.runtime.entrypoint.ClusterEntrypoint.runClusterEntrypoint(ClusterEntrypoint.java:741)
        at 
app//org.apache.flink.kubernetes.entrypoint.KubernetesSessionClusterEntrypoint.main(KubernetesSessionClusterEntrypoint.java:61)"Reference
 Handler" daemon prio=10 Id=2 RUNNABLE
        at 
java.base@11.0.19/java.lang.ref.Reference.waitForReferencePendingList(Native 
Method)
        at 
java.base@11.0.19/java.lang.ref.Reference.processPendingReferences(Unknown 
Source)
        at 
java.base@11.0.19/java.lang.ref.Reference$ReferenceHandler.run(Unknown 
Source)"Finalizer" daemon prio=8 Id=3 WAITING on 
java.lang.ref.ReferenceQueue$Lock@2b21a3e4
        at java.base@11.0.19/java.lang.Object.wait(Native Method)
        -  waiting on java.lang.ref.ReferenceQueue$Lock@2b21a3e4
        at java.base@11.0.19/java.lang.ref.ReferenceQueue.remove(Unknown Source)
        at java.base@11.0.19/java.lang.ref.ReferenceQueue.remove(Unknown Source)
        at 
java.base@11.0.19/java.lang.ref.Finalizer$FinalizerThread.run(Unknown 
Source)"Signal Dispatcher" daemon prio=9 Id=4 RUNNABLE"Common-Cleaner" daemon 
prio=8 Id=9 TIMED_WAITING on java.lang.ref.ReferenceQueue$Lock@16aab001
        at java.base@11.0.19/java.lang.Object.wait(Native Method)
        -  waiting on java.lang.ref.ReferenceQueue$Lock@16aab001
        at java.base@11.0.19/java.lang.ref.ReferenceQueue.remove(Unknown Source)
        at java.base@11.0.19/jdk.internal.ref.CleanerImpl.run(Unknown Source)
        at java.base@11.0.19/java.lang.Thread.run(Unknown Source)
        at java.base@11.0.19/jdk.internal.misc.InnocuousThread.run(Unknown 
Source)"Log4j2-TF-3-Scheduled-1" daemon prio=5 Id=12 TIMED_WAITING on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@2ee9ffbd
        at java.base@11.0.19/jdk.internal.misc.Unsafe.park(Native Method)
        -  waiting on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@2ee9ffbd
        at 
java.base@11.0.19/java.util.concurrent.locks.LockSupport.parkNanos(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.getTask(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown 
Source)
        ..."Log4j2-TF-6-Scheduled-2" daemon prio=5 Id=18 TIMED_WAITING on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@3b6166a7
        at java.base@11.0.19/jdk.internal.misc.Unsafe.park(Native Method)
        -  waiting on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@3b6166a7
        at 
java.base@11.0.19/java.util.concurrent.locks.LockSupport.parkNanos(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.getTask(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown 
Source)
        ..."flink-scheduler-1" prio=5 Id=19 TIMED_WAITING
        at java.base@11.0.19/java.lang.Thread.sleep(Native Method)
        at 
akka.actor.LightArrayRevolverScheduler.waitNanos(LightArrayRevolverScheduler.scala:90)
        at 
akka.actor.LightArrayRevolverScheduler$$anon$3.nextTick(LightArrayRevolverScheduler.scala:300)
        at 
akka.actor.LightArrayRevolverScheduler$$anon$3.run(LightArrayRevolverScheduler.scala:270)
        at java.base@11.0.19/java.lang.Thread.run(Unknown 
Source)"flink-akka.actor.internal-dispatcher-2" prio=5 Id=20 WAITING on 
akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinPool@1d79ccac
        at java.base@11.0.19/jdk.internal.misc.Unsafe.park(Native Method)
        -  waiting on 
akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinPool@1d79ccac
        at 
java.base@11.0.19/java.util.concurrent.locks.LockSupport.park(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.ForkJoinPool.runWorker(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.ForkJoinWorkerThread.run(Unknown 
Source)"flink-akka.actor.default-dispatcher-4" prio=5 Id=22 WAITING on 
akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinPool@5e904dba
        at java.base@11.0.19/jdk.internal.misc.Unsafe.park(Native Method)
        -  waiting on 
akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinPool@5e904dba
        at 
java.base@11.0.19/java.util.concurrent.locks.LockSupport.park(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.ForkJoinPool.runWorker(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.ForkJoinWorkerThread.run(Unknown 
Source)"flink-akka.remote.default-remote-dispatcher-5" prio=5 Id=23 WAITING on 
akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinPool@3fe545c2
        at java.base@11.0.19/jdk.internal.misc.Unsafe.park(Native Method)
        -  waiting on 
akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinPool@3fe545c2
        at 
java.base@11.0.19/java.util.concurrent.locks.LockSupport.park(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.ForkJoinPool.runWorker(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.ForkJoinWorkerThread.run(Unknown 
Source)"flink-akka.remote.default-remote-dispatcher-6" prio=5 Id=24 
TIMED_WAITING on 
akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinPool@3fe545c2
        at java.base@11.0.19/jdk.internal.misc.Unsafe.park(Native Method)
        -  waiting on 
akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinPool@3fe545c2
        at 
java.base@11.0.19/java.util.concurrent.locks.LockSupport.parkUntil(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ForkJoinPool.runWorker(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.ForkJoinWorkerThread.run(Unknown 
Source)"New I/O worker #1" prio=5 Id=25 RUNNABLE (in native)
        at java.base@11.0.19/sun.nio.ch.EPoll.wait(Native Method)
        at java.base@11.0.19/sun.nio.ch.EPollSelectorImpl.doSelect(Unknown 
Source)
        at java.base@11.0.19/sun.nio.ch.SelectorImpl.lockAndDoSelect(Unknown 
Source)
        -  locked sun.nio.ch.Util$2@f0148c7
        -  locked sun.nio.ch.EPollSelectorImpl@5c4ee927
        at java.base@11.0.19/sun.nio.ch.SelectorImpl.select(Unknown Source)
        at 
org.jboss.netty.channel.socket.nio.SelectorUtil.select(SelectorUtil.java:68)
        at 
org.jboss.netty.channel.socket.nio.AbstractNioSelector.select(AbstractNioSelector.java:434)
        at 
org.jboss.netty.channel.socket.nio.AbstractNioSelector.run(AbstractNioSelector.java:212)
        at 
org.jboss.netty.channel.socket.nio.AbstractNioWorker.run(AbstractNioWorker.java:89)
        ...        Number of locked synchronizers = 1
        - java.util.concurrent.ThreadPoolExecutor$Worker@708d421"New I/O boss 
#2" prio=5 Id=27 RUNNABLE
        at java.base@11.0.19/sun.nio.ch.EPoll.wait(Native Method)
        at java.base@11.0.19/sun.nio.ch.EPollSelectorImpl.doSelect(Unknown 
Source)
        at java.base@11.0.19/sun.nio.ch.SelectorImpl.lockAndDoSelect(Unknown 
Source)
        -  locked sun.nio.ch.Util$2@6f9289
        -  locked sun.nio.ch.EPollSelectorImpl@15b10c13
        at java.base@11.0.19/sun.nio.ch.SelectorImpl.select(Unknown Source)
        at 
org.jboss.netty.channel.socket.nio.SelectorUtil.select(SelectorUtil.java:68)
        at 
org.jboss.netty.channel.socket.nio.AbstractNioSelector.select(AbstractNioSelector.java:434)
        at 
org.jboss.netty.channel.socket.nio.AbstractNioSelector.run(AbstractNioSelector.java:212)
        at 
org.jboss.netty.channel.socket.nio.NioClientBoss.run(NioClientBoss.java:42)
        ...        Number of locked synchronizers = 1
        - java.util.concurrent.ThreadPoolExecutor$Worker@409550d1"New I/O 
worker #3" prio=5 Id=28 RUNNABLE (in native)
        at java.base@11.0.19/sun.nio.ch.EPoll.wait(Native Method)
        at java.base@11.0.19/sun.nio.ch.EPollSelectorImpl.doSelect(Unknown 
Source)
        at java.base@11.0.19/sun.nio.ch.SelectorImpl.lockAndDoSelect(Unknown 
Source)
        -  locked sun.nio.ch.Util$2@10733912
        -  locked sun.nio.ch.EPollSelectorImpl@3bdffdea
        at java.base@11.0.19/sun.nio.ch.SelectorImpl.select(Unknown Source)
        at 
org.jboss.netty.channel.socket.nio.SelectorUtil.select(SelectorUtil.java:68)
        at 
org.jboss.netty.channel.socket.nio.AbstractNioSelector.select(AbstractNioSelector.java:434)
        at 
org.jboss.netty.channel.socket.nio.AbstractNioSelector.run(AbstractNioSelector.java:212)
        at 
org.jboss.netty.channel.socket.nio.AbstractNioWorker.run(AbstractNioWorker.java:89)
        ...        Number of locked synchronizers = 1
        - java.util.concurrent.ThreadPoolExecutor$Worker@dbc95df"New I/O server 
boss #4" prio=5 Id=29 RUNNABLE (in native)
        at java.base@11.0.19/sun.nio.ch.EPoll.wait(Native Method)
        at java.base@11.0.19/sun.nio.ch.EPollSelectorImpl.doSelect(Unknown 
Source)
        at java.base@11.0.19/sun.nio.ch.SelectorImpl.lockAndDoSelect(Unknown 
Source)
        -  locked sun.nio.ch.Util$2@4758dbc2
        -  locked sun.nio.ch.EPollSelectorImpl@5a1496ae
        at java.base@11.0.19/sun.nio.ch.SelectorImpl.select(Unknown Source)
        at 
org.jboss.netty.channel.socket.nio.NioServerBoss.select(NioServerBoss.java:163)
        at 
org.jboss.netty.channel.socket.nio.AbstractNioSelector.run(AbstractNioSelector.java:212)
        at 
org.jboss.netty.channel.socket.nio.NioServerBoss.run(NioServerBoss.java:42)
        at 
org.jboss.netty.util.ThreadRenamingRunnable.run(ThreadRenamingRunnable.java:108)
        ...        Number of locked synchronizers = 1
        - java.util.concurrent.ThreadPoolExecutor$Worker@85887aa"Timer-0" 
daemon prio=5 Id=32 TIMED_WAITING on java.util.TaskQueue@53a69f57
        at java.base@11.0.19/java.lang.Object.wait(Native Method)
        -  waiting on java.util.TaskQueue@53a69f57
        at java.base@11.0.19/java.util.TimerThread.mainLoop(Unknown Source)
        at java.base@11.0.19/java.util.TimerThread.run(Unknown Source)"BLOB 
Server listener at 6124" daemon prio=5 Id=31 RUNNABLE (in native)
        at java.base@11.0.19/java.net.PlainSocketImpl.socketAccept(Native 
Method)
        at java.base@11.0.19/java.net.AbstractPlainSocketImpl.accept(Unknown 
Source)
        at java.base@11.0.19/java.net.ServerSocket.implAccept(Unknown Source)
        at java.base@11.0.19/java.net.ServerSocket.accept(Unknown Source)
        at 
app//org.apache.flink.util.NetUtils.acceptWithoutTimeout(NetUtils.java:143)
        at 
app//org.apache.flink.runtime.blob.BlobServer.run(BlobServer.java:316)"flink-metrics-scheduler-1"
 prio=5 Id=34 TIMED_WAITING
        at java.base@11.0.19/java.lang.Thread.sleep(Native Method)
        at 
akka.actor.LightArrayRevolverScheduler.waitNanos(LightArrayRevolverScheduler.scala:90)
        at 
akka.actor.LightArrayRevolverScheduler$$anon$3.nextTick(LightArrayRevolverScheduler.scala:300)
        at 
akka.actor.LightArrayRevolverScheduler$$anon$3.run(LightArrayRevolverScheduler.scala:270)
        at java.base@11.0.19/java.lang.Thread.run(Unknown 
Source)"flink-metrics-akka.actor.internal-dispatcher-3" prio=5 Id=36 WAITING on 
akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinPool@17521864
        at java.base@11.0.19/jdk.internal.misc.Unsafe.park(Native Method)
        -  waiting on 
akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinPool@17521864
        at 
java.base@11.0.19/java.util.concurrent.locks.LockSupport.park(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.ForkJoinPool.runWorker(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.ForkJoinWorkerThread.run(Unknown 
Source)"flink-metrics-akka.remote.default-remote-dispatcher-5" prio=5 Id=38 
TIMED_WAITING on 
akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinPool@16555787
        at java.base@11.0.19/jdk.internal.misc.Unsafe.park(Native Method)
        -  waiting on 
akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinPool@16555787
        at 
java.base@11.0.19/java.util.concurrent.locks.LockSupport.parkUntil(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ForkJoinPool.runWorker(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.ForkJoinWorkerThread.run(Unknown 
Source)"flink-metrics-akka.remote.default-remote-dispatcher-6" prio=5 Id=39 
WAITING on akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinPool@16555787
        at java.base@11.0.19/jdk.internal.misc.Unsafe.park(Native Method)
        -  waiting on 
akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinPool@16555787
        at 
java.base@11.0.19/java.util.concurrent.locks.LockSupport.park(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.ForkJoinPool.runWorker(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.ForkJoinWorkerThread.run(Unknown 
Source)"New I/O worker #5" prio=5 Id=40 RUNNABLE (in native)
        at java.base@11.0.19/sun.nio.ch.EPoll.wait(Native Method)
        at java.base@11.0.19/sun.nio.ch.EPollSelectorImpl.doSelect(Unknown 
Source)
        at java.base@11.0.19/sun.nio.ch.SelectorImpl.lockAndDoSelect(Unknown 
Source)
        -  locked sun.nio.ch.Util$2@688a0205
        -  locked sun.nio.ch.EPollSelectorImpl@f316464
        at java.base@11.0.19/sun.nio.ch.SelectorImpl.select(Unknown Source)
        at 
org.jboss.netty.channel.socket.nio.SelectorUtil.select(SelectorUtil.java:68)
        at 
org.jboss.netty.channel.socket.nio.AbstractNioSelector.select(AbstractNioSelector.java:434)
        at 
org.jboss.netty.channel.socket.nio.AbstractNioSelector.run(AbstractNioSelector.java:212)
        at 
org.jboss.netty.channel.socket.nio.AbstractNioWorker.run(AbstractNioWorker.java:89)
        ...        Number of locked synchronizers = 1
        - java.util.concurrent.ThreadPoolExecutor$Worker@7d652799"New I/O boss 
#6" prio=5 Id=42 RUNNABLE (in native)
        at java.base@11.0.19/sun.nio.ch.EPoll.wait(Native Method)
        at java.base@11.0.19/sun.nio.ch.EPollSelectorImpl.doSelect(Unknown 
Source)
        at java.base@11.0.19/sun.nio.ch.SelectorImpl.lockAndDoSelect(Unknown 
Source)
        -  locked sun.nio.ch.Util$2@827ccde
        -  locked sun.nio.ch.EPollSelectorImpl@34f25b32
        at java.base@11.0.19/sun.nio.ch.SelectorImpl.select(Unknown Source)
        at 
org.jboss.netty.channel.socket.nio.SelectorUtil.select(SelectorUtil.java:68)
        at 
org.jboss.netty.channel.socket.nio.AbstractNioSelector.select(AbstractNioSelector.java:434)
        at 
org.jboss.netty.channel.socket.nio.AbstractNioSelector.run(AbstractNioSelector.java:212)
        at 
org.jboss.netty.channel.socket.nio.NioClientBoss.run(NioClientBoss.java:42)
        ...        Number of locked synchronizers = 1
        - java.util.concurrent.ThreadPoolExecutor$Worker@73a2c645"New I/O 
worker #7" prio=5 Id=43 RUNNABLE (in native)
        at java.base@11.0.19/sun.nio.ch.EPoll.wait(Native Method)
        at java.base@11.0.19/sun.nio.ch.EPollSelectorImpl.doSelect(Unknown 
Source)
        at java.base@11.0.19/sun.nio.ch.SelectorImpl.lockAndDoSelect(Unknown 
Source)
        -  locked sun.nio.ch.Util$2@cd0fd83
        -  locked sun.nio.ch.EPollSelectorImpl@846aa39
        at java.base@11.0.19/sun.nio.ch.SelectorImpl.select(Unknown Source)
        at 
org.jboss.netty.channel.socket.nio.SelectorUtil.select(SelectorUtil.java:68)
        at 
org.jboss.netty.channel.socket.nio.AbstractNioSelector.select(AbstractNioSelector.java:434)
        at 
org.jboss.netty.channel.socket.nio.AbstractNioSelector.run(AbstractNioSelector.java:212)
        at 
org.jboss.netty.channel.socket.nio.AbstractNioWorker.run(AbstractNioWorker.java:89)
        ...        Number of locked synchronizers = 1
        - java.util.concurrent.ThreadPoolExecutor$Worker@779d4ce9"New I/O 
server boss #8" prio=5 Id=44 RUNNABLE (in native)
        at java.base@11.0.19/sun.nio.ch.EPoll.wait(Native Method)
        at java.base@11.0.19/sun.nio.ch.EPollSelectorImpl.doSelect(Unknown 
Source)
        at java.base@11.0.19/sun.nio.ch.SelectorImpl.lockAndDoSelect(Unknown 
Source)
        -  locked sun.nio.ch.Util$2@3eb1c6d3
        -  locked sun.nio.ch.EPollSelectorImpl@18bc21fc
        at java.base@11.0.19/sun.nio.ch.SelectorImpl.select(Unknown Source)
        at 
org.jboss.netty.channel.socket.nio.NioServerBoss.select(NioServerBoss.java:163)
        at 
org.jboss.netty.channel.socket.nio.AbstractNioSelector.run(AbstractNioSelector.java:212)
        at 
org.jboss.netty.channel.socket.nio.NioServerBoss.run(NioServerBoss.java:42)
        at 
org.jboss.netty.util.ThreadRenamingRunnable.run(ThreadRenamingRunnable.java:108)
        ...        Number of locked synchronizers = 1
        - 
java.util.concurrent.ThreadPoolExecutor$Worker@329fcc7e"flink-rest-server-netty-boss-thread-1"
 daemon prio=5 Id=48 RUNNABLE (in native)
        at java.base@11.0.19/sun.nio.ch.EPoll.wait(Native Method)
        at java.base@11.0.19/sun.nio.ch.EPollSelectorImpl.doSelect(Unknown 
Source)
        at java.base@11.0.19/sun.nio.ch.SelectorImpl.lockAndDoSelect(Unknown 
Source)
        -  locked 
org.apache.flink.shaded.netty4.io.netty.channel.nio.SelectedSelectionKeySet@130bfb8d
        -  locked sun.nio.ch.EPollSelectorImpl@2ea19cb7
        at java.base@11.0.19/sun.nio.ch.SelectorImpl.select(Unknown Source)
        at 
app//org.apache.flink.shaded.netty4.io.netty.channel.nio.SelectedSelectionKeySetSelector.select(SelectedSelectionKeySetSelector.java:68)
        at 
app//org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.select(NioEventLoop.java:879)
        at 
app//org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:526)
        at 
app//org.apache.flink.shaded.netty4.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:997)
        ..."Flink-DispatcherRestEndpoint-thread-1" daemon prio=5 Id=49 
TIMED_WAITING on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@1e9640ee
        at java.base@11.0.19/jdk.internal.misc.Unsafe.park(Native Method)
        -  waiting on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@1e9640ee
        at 
java.base@11.0.19/java.util.concurrent.locks.LockSupport.parkNanos(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.getTask(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown 
Source)
        ..."cluster-io-thread-1" daemon prio=5 Id=50 WAITING on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@67dc2101
        at java.base@11.0.19/jdk.internal.misc.Unsafe.park(Native Method)
        -  waiting on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@67dc2101
        at 
java.base@11.0.19/java.util.concurrent.locks.LockSupport.park(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.LinkedBlockingQueue.take(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.getTask(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown 
Source)
        at java.base@11.0.19/java.lang.Thread.run(Unknown 
Source)"pool-2-thread-1" prio=5 Id=51 WAITING on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@2bc769e4
        at java.base@11.0.19/jdk.internal.misc.Unsafe.park(Native Method)
        -  waiting on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@2bc769e4
        at 
java.base@11.0.19/java.util.concurrent.locks.LockSupport.park(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.LinkedBlockingQueue.take(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.getTask(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown 
Source)
        at java.base@11.0.19/java.lang.Thread.run(Unknown 
Source)"cluster-io-thread-2" daemon prio=5 Id=52 WAITING on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@67dc2101
        at java.base@11.0.19/jdk.internal.misc.Unsafe.park(Native Method)
        -  waiting on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@67dc2101
        at 
java.base@11.0.19/java.util.concurrent.locks.LockSupport.park(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.LinkedBlockingQueue.take(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.getTask(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown 
Source)
        at java.base@11.0.19/java.lang.Thread.run(Unknown 
Source)"flink-akka.actor.default-dispatcher-13" prio=5 Id=55 WAITING on 
akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinPool@5e904dba
        at java.base@11.0.19/jdk.internal.misc.Unsafe.park(Native Method)
        -  waiting on 
akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinPool@5e904dba
        at 
java.base@11.0.19/java.util.concurrent.locks.LockSupport.park(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.ForkJoinPool.runWorker(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.ForkJoinWorkerThread.run(Unknown 
Source)"flink-akka.actor.default-dispatcher-14" prio=5 Id=56 WAITING on 
akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinPool@5e904dba
        at java.base@11.0.19/jdk.internal.misc.Unsafe.park(Native Method)
        -  waiting on 
akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinPool@5e904dba
        at 
java.base@11.0.19/java.util.concurrent.locks.LockSupport.park(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.ForkJoinPool.runWorker(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.ForkJoinWorkerThread.run(Unknown 
Source)"resourcemanager_1-main-scheduler-thread-1" daemon prio=5 Id=73 
TIMED_WAITING on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@9a11c0f
        at java.base@11.0.19/jdk.internal.misc.Unsafe.park(Native Method)
        -  waiting on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@9a11c0f
        at 
java.base@11.0.19/java.util.concurrent.locks.LockSupport.parkNanos(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.getTask(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown 
Source)
        ..."flink-kubeclient-io-for-resourcemanager-thread-1" daemon prio=5 
Id=74 WAITING on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@251cace5
        at java.base@11.0.19/jdk.internal.misc.Unsafe.park(Native Method)
        -  waiting on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@251cace5
        at 
java.base@11.0.19/java.util.concurrent.locks.LockSupport.park(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.LinkedBlockingQueue.take(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.getTask(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown 
Source)
        at java.base@11.0.19/java.lang.Thread.run(Unknown 
Source)"flink-akka.actor.default-dispatcher-15" prio=5 Id=75 RUNNABLE
        at 
java.management@11.0.19/sun.management.ThreadImpl.dumpThreads0(Native Method)
        at 
java.management@11.0.19/sun.management.ThreadImpl.dumpAllThreads(Unknown Source)
        at 
java.management@11.0.19/sun.management.ThreadImpl.dumpAllThreads(Unknown Source)
        at 
app//org.apache.flink.util.concurrent.ThreadUtils.errorLogThreadDump(ThreadUtils.java:33)
        at 
app//org.apache.flink.util.FatalExitExceptionHandler.uncaughtException(FatalExitExceptionHandler.java:47)
        at 
app//org.apache.flink.util.concurrent.FutureUtils.lambda$handleUncaughtException$20(FutureUtils.java:1216)
        at 
app//org.apache.flink.util.concurrent.FutureUtils$$Lambda$623/0x00000001006a9840.accept(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.CompletableFuture.uniWhenComplete(Unknown
 Source)
        ..."OkHttp https://10.96.0.1/..."; prio=5 Id=76 RUNNABLE (in native)
        at java.base@11.0.19/java.net.SocketInputStream.socketRead0(Native 
Method)
        at java.base@11.0.19/java.net.SocketInputStream.socketRead(Unknown 
Source)
        at java.base@11.0.19/java.net.SocketInputStream.read(Unknown Source)
        at java.base@11.0.19/java.net.SocketInputStream.read(Unknown Source)
        at java.base@11.0.19/sun.security.ssl.SSLSocketInputRecord.read(Unknown 
Source)
        at 
java.base@11.0.19/sun.security.ssl.SSLSocketInputRecord.readHeader(Unknown 
Source)
        at 
java.base@11.0.19/sun.security.ssl.SSLSocketInputRecord.bytesInCompletePacket(Unknown
 Source)
        at 
java.base@11.0.19/sun.security.ssl.SSLSocketImpl.readApplicationRecord(Unknown 
Source)
        ...        Number of locked synchronizers = 2
        - java.util.concurrent.locks.ReentrantLock$NonfairSync@234e456e
        - java.util.concurrent.ThreadPoolExecutor$Worker@330607e6"OkHttp 
ConnectionPool" daemon prio=5 Id=77 TIMED_WAITING on 
org.apache.flink.kubernetes.shaded.okhttp3.internal.connection.RealConnectionPool@335680aa
        at java.base@11.0.19/java.lang.Object.wait(Native Method)
        -  waiting on 
org.apache.flink.kubernetes.shaded.okhttp3.internal.connection.RealConnectionPool@335680aa
        at java.base@11.0.19/java.lang.Object.wait(Unknown Source)
        at 
app//org.apache.flink.kubernetes.shaded.okhttp3.internal.connection.RealConnectionPool.lambda$new$0(RealConnectionPool.java:62)
        at 
app//org.apache.flink.kubernetes.shaded.okhttp3.internal.connection.RealConnectionPool$$Lambda$709/0x000000010071d040.run(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown 
Source)
        at java.base@11.0.19/java.lang.Thread.run(Unknown Source)        Number 
of locked synchronizers = 1
        - java.util.concurrent.ThreadPoolExecutor$Worker@457b7a36"Okio 
Watchdog" daemon prio=5 Id=78 TIMED_WAITING on java.lang.Class@711498ff
        at java.base@11.0.19/java.lang.Object.wait(Native Method)
        -  waiting on java.lang.Class@711498ff
        at 
app//org.apache.flink.kubernetes.shaded.okio.AsyncTimeout.awaitTimeout(AsyncTimeout.java:348)
        at 
app//org.apache.flink.kubernetes.shaded.okio.AsyncTimeout$Watchdog.run(AsyncTimeout.java:313)"flink-kubeclient-io-for-resourcemanager-thread-2"
 daemon prio=5 Id=80 RUNNABLE
        at 
java.base@11.0.19/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native 
Method)
        at 
java.base@11.0.19/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown 
Source)
        at 
java.base@11.0.19/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown
 Source)
        at java.base@11.0.19/java.lang.reflect.Method.invoke(Unknown Source)
        at 
app//org.apache.flink.shaded.jackson2.com.fasterxml.jackson.databind.ser.BeanPropertyWriter.serializeAsField(BeanPropertyWriter.java:689)
        at 
app//org.apache.flink.shaded.jackson2.com.fasterxml.jackson.databind.ser.std.BeanSerializerBase.serializeFields(BeanSerializerBase.java:774)
        at 
app//org.apache.flink.shaded.jackson2.com.fasterxml.jackson.databind.ser.BeanSerializer.serialize(BeanSerializer.java:178)
        at 
app//org.apache.flink.shaded.jackson2.com.fasterxml.jackson.databind.ser.impl.IndexedListSerializer.serializeContents(IndexedListSerializer.java:119)
        ...        Number of locked synchronizers = 1
        - 
java.util.concurrent.ThreadPoolExecutor$Worker@5fdf1d80"cluster-io-thread-3" 
daemon prio=5 Id=84 WAITING on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@67dc2101
        at java.base@11.0.19/jdk.internal.misc.Unsafe.park(Native Method)
        -  waiting on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@67dc2101
        at 
java.base@11.0.19/java.util.concurrent.locks.LockSupport.park(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.LinkedBlockingQueue.take(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.getTask(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown 
Source)
        at java.base@11.0.19/java.lang.Thread.run(Unknown 
Source)"Flink-DispatcherRestEndpoint-thread-2" daemon prio=5 Id=85 WAITING on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@1e9640ee
        at java.base@11.0.19/jdk.internal.misc.Unsafe.park(Native Method)
        -  waiting on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@1e9640ee
        at 
java.base@11.0.19/java.util.concurrent.locks.LockSupport.park(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.getTask(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown 
Source)
        ..."flink-rest-server-netty-worker-thread-1" daemon prio=5 Id=86 
RUNNABLE (in native)
        at java.base@11.0.19/sun.nio.ch.EPoll.wait(Native Method)
        at java.base@11.0.19/sun.nio.ch.EPollSelectorImpl.doSelect(Unknown 
Source)
        at java.base@11.0.19/sun.nio.ch.SelectorImpl.lockAndDoSelect(Unknown 
Source)
        -  locked 
org.apache.flink.shaded.netty4.io.netty.channel.nio.SelectedSelectionKeySet@3296b3ab
        -  locked sun.nio.ch.EPollSelectorImpl@72ad4a98
        at java.base@11.0.19/sun.nio.ch.SelectorImpl.select(Unknown Source)
        at 
app//org.apache.flink.shaded.netty4.io.netty.channel.nio.SelectedSelectionKeySetSelector.select(SelectedSelectionKeySetSelector.java:68)
        at 
app//org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.select(NioEventLoop.java:879)
        at 
app//org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:526)
        at 
app//org.apache.flink.shaded.netty4.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:997)
        ..."Flink-DispatcherRestEndpoint-thread-3" daemon prio=5 Id=88 WAITING 
on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@1e9640ee
        at java.base@11.0.19/jdk.internal.misc.Unsafe.park(Native Method)
        -  waiting on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@1e9640ee
        at 
java.base@11.0.19/java.util.concurrent.locks.LockSupport.park(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.getTask(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown 
Source)
        ..."Flink-DispatcherRestEndpoint-thread-4" daemon prio=5 Id=89 
TIMED_WAITING on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@1e9640ee
        at java.base@11.0.19/jdk.internal.misc.Unsafe.park(Native Method)
        -  waiting on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@1e9640ee
        at 
java.base@11.0.19/java.util.concurrent.locks.LockSupport.parkNanos(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.getTask(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown 
Source)
        ..."OkHttp WebSocket https://10.96.0.1/..."; prio=5 Id=98 TIMED_WAITING 
on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@23991496
        at java.base@11.0.19/jdk.internal.misc.Unsafe.park(Native Method)
        -  waiting on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@23991496
        at 
java.base@11.0.19/java.util.concurrent.locks.LockSupport.parkNanos(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.getTask(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown 
Source)
        ..."jobmanager-io-thread-1" daemon prio=5 Id=99 WAITING on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@24cd939f
        at java.base@11.0.19/jdk.internal.misc.Unsafe.park(Native Method)
        -  waiting on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@24cd939f
        at 
java.base@11.0.19/java.util.concurrent.locks.LockSupport.park(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.LinkedBlockingQueue.take(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.getTask(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown 
Source)
        at java.base@11.0.19/java.lang.Thread.run(Unknown 
Source)"flink-akka.actor.supervisor-dispatcher-16" prio=5 Id=100 TIMED_WAITING 
on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@23417746
        at java.base@11.0.19/jdk.internal.misc.Unsafe.park(Native Method)
        -  waiting on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@23417746
        at 
java.base@11.0.19/java.util.concurrent.locks.LockSupport.parkNanos(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.LinkedBlockingQueue.poll(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.getTask(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown 
Source)
        at java.base@11.0.19/java.lang.Thread.run(Unknown 
Source)"flink-metrics-13" prio=1 Id=102 TIMED_WAITING on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@3ba0103c
        at java.base@11.0.19/jdk.internal.misc.Unsafe.park(Native Method)
        -  waiting on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@3ba0103c
        at 
java.base@11.0.19/java.util.concurrent.locks.LockSupport.parkNanos(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.LinkedBlockingQueue.poll(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.getTask(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown 
Source)
        at java.base@11.0.19/java.lang.Thread.run(Unknown 
Source)"cluster-io-thread-4" daemon prio=5 Id=108 WAITING on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@67dc2101
        at java.base@11.0.19/jdk.internal.misc.Unsafe.park(Native Method)
        -  waiting on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@67dc2101
        at 
java.base@11.0.19/java.util.concurrent.locks.LockSupport.park(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.LinkedBlockingQueue.take(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.getTask(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown 
Source)
        at java.base@11.0.19/java.lang.Thread.run(Unknown 
Source)"jobmanager-future-thread-1" daemon prio=5 Id=109 WAITING on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@50769e7a
        at java.base@11.0.19/jdk.internal.misc.Unsafe.park(Native Method)
        -  waiting on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@50769e7a
        at 
java.base@11.0.19/java.util.concurrent.locks.LockSupport.park(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.getTask(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown 
Source)
        ..."flink-kubeclient-io-for-resourcemanager-thread-3" daemon prio=5 
Id=112 WAITING on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@251cace5
        at java.base@11.0.19/jdk.internal.misc.Unsafe.park(Native Method)
        -  waiting on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@251cace5
        at 
java.base@11.0.19/java.util.concurrent.locks.LockSupport.park(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.LinkedBlockingQueue.take(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.getTask(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown 
Source)
        at java.base@11.0.19/java.lang.Thread.run(Unknown Source)"OkHttp 
10.96.0.1 Writer" prio=5 Id=113 TIMED_WAITING on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@186fae80
        at java.base@11.0.19/jdk.internal.misc.Unsafe.park(Native Method)
        -  waiting on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@186fae80
        at 
java.base@11.0.19/java.util.concurrent.locks.LockSupport.parkNanos(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.getTask(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown 
Source)
        ..."OkHttp 10.96.0.1" daemon prio=5 Id=114 RUNNABLE (in native)
        at java.base@11.0.19/java.net.SocketInputStream.socketRead0(Native 
Method)
        at java.base@11.0.19/java.net.SocketInputStream.socketRead(Unknown 
Source)
        at java.base@11.0.19/java.net.SocketInputStream.read(Unknown Source)
        at java.base@11.0.19/java.net.SocketInputStream.read(Unknown Source)
        at java.base@11.0.19/sun.security.ssl.SSLSocketInputRecord.read(Unknown 
Source)
        at 
java.base@11.0.19/sun.security.ssl.SSLSocketInputRecord.readHeader(Unknown 
Source)
        at 
java.base@11.0.19/sun.security.ssl.SSLSocketInputRecord.bytesInCompletePacket(Unknown
 Source)
        at 
java.base@11.0.19/sun.security.ssl.SSLSocketImpl.readApplicationRecord(Unknown 
Source)
        ...        Number of locked synchronizers = 1
        - java.util.concurrent.locks.ReentrantLock$NonfairSync@303c118c"OkHttp 
Http2Connection" daemon prio=5 Id=115 TIMED_WAITING on 
java.util.concurrent.SynchronousQueue$TransferStack@ba6d647
        at java.base@11.0.19/jdk.internal.misc.Unsafe.park(Native Method)
        -  waiting on 
java.util.concurrent.SynchronousQueue$TransferStack@ba6d647
        at 
java.base@11.0.19/java.util.concurrent.locks.LockSupport.parkNanos(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.SynchronousQueue$TransferStack.awaitFulfill(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.SynchronousQueue$TransferStack.transfer(Unknown
 Source)
        at java.base@11.0.19/java.util.concurrent.SynchronousQueue.poll(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.getTask(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown 
Source)
        ..."FlinkCompletableFutureDelayScheduler-thread-1" daemon prio=5 Id=117 
TIMED_WAITING on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@6fc71c07
        at java.base@11.0.19/jdk.internal.misc.Unsafe.park(Native Method)
        -  waiting on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@6fc71c07
        at 
java.base@11.0.19/java.util.concurrent.locks.LockSupport.parkNanos(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.getTask(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown 
Source)
        ..."flink-kubeclient-io-for-resourcemanager-thread-4" daemon prio=5 
Id=118 WAITING on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@251cace5
        at java.base@11.0.19/jdk.internal.misc.Unsafe.park(Native Method)
        -  waiting on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@251cace5
        at 
java.base@11.0.19/java.util.concurrent.locks.LockSupport.park(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.LinkedBlockingQueue.take(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.getTask(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown 
Source)
        at java.base@11.0.19/java.lang.Thread.run(Unknown 
Source)"AkkaRpcService-Supervisor-Termination-Future-Executor-thread-1" daemon 
prio=5 Id=119 WAITING on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@ab9b4d1
        at java.base@11.0.19/jdk.internal.misc.Unsafe.park(Native Method)
        -  waiting on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@ab9b4d1
        at 
java.base@11.0.19/java.util.concurrent.locks.LockSupport.park(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.LinkedBlockingQueue.take(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.getTask(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown 
Source)
        at java.base@11.0.19/java.lang.Thread.run(Unknown 
Source)"jobmanager_3-main-scheduler-thread-1" daemon prio=5 Id=121 
TIMED_WAITING on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@5a59647b
        at java.base@11.0.19/jdk.internal.misc.Unsafe.park(Native Method)
        -  waiting on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@5a59647b
        at 
java.base@11.0.19/java.util.concurrent.locks.LockSupport.parkNanos(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.getTask(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown 
Source)
        ..."SourceCoordinator-Source: *anonymous_kafka$15*[66]" prio=5 Id=122 
WAITING on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@67708599
        at java.base@11.0.19/jdk.internal.misc.Unsafe.park(Native Method)
        -  waiting on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@67708599
        at 
java.base@11.0.19/java.util.concurrent.locks.LockSupport.park(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.getTask(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown 
Source)
        ..."Checkpoint Timer" daemon prio=5 Id=123 TIMED_WAITING on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@30809a54
        at java.base@11.0.19/jdk.internal.misc.Unsafe.park(Native Method)
        -  waiting on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@30809a54
        at 
java.base@11.0.19/java.util.concurrent.locks.LockSupport.parkNanos(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.getTask(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown 
Source)
        ..."kafka-admin-client-thread | 
KafkaSource--5297459524620964018-enumerator-admin-client" daemon prio=5 Id=125 
RUNNABLE (in native)
        at java.base@11.0.19/sun.nio.ch.EPoll.wait(Native Method)
        at java.base@11.0.19/sun.nio.ch.EPollSelectorImpl.doSelect(Unknown 
Source)
        at java.base@11.0.19/sun.nio.ch.SelectorImpl.lockAndDoSelect(Unknown 
Source)
        -  locked sun.nio.ch.Util$2@77d8bfa9
        -  locked sun.nio.ch.EPollSelectorImpl@66b37795
        at java.base@11.0.19/sun.nio.ch.SelectorImpl.select(Unknown Source)
        at 
app//org.apache.kafka.common.network.Selector.select(Selector.java:873)
        at app//org.apache.kafka.common.network.Selector.poll(Selector.java:465)
        at 
app//org.apache.kafka.clients.NetworkClient.poll(NetworkClient.java:560)
        at 
app//org.apache.kafka.clients.admin.KafkaAdminClient$AdminClientRunnable.processRequests(KafkaAdminClient.java:1408)
        ..."SourceCoordinator-Source: *anonymous_kafka$15*[66]-worker-thread-1" 
daemon prio=5 Id=127 WAITING on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@58c6a97
        at java.base@11.0.19/jdk.internal.misc.Unsafe.park(Native Method)
        -  waiting on 
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject@58c6a97
        at 
java.base@11.0.19/java.util.concurrent.locks.LockSupport.park(Unknown Source)
        at 
java.base@11.0.19/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(Unknown
 Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.getTask(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown 
Source)
        at 
java.base@11.0.19/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown 
Source)
        ...
2023-04-28 20:50:50,607 INFO  
org.apache.flink.runtime.entrypoint.ClusterEntrypoint        [] - Shutting 
KubernetesSessionClusterEntrypoint down with application status UNKNOWN. 
Diagnostics Cluster entrypoint has been closed externally..
2023-04-28 20:50:50,609 INFO  org.apache.flink.runtime.blob.BlobServer          
           [] - Stopped BLOB server at 0.0.0.0:6124
[pod@my-namespace-flink-cluster-59cd575d6b-bll6b log]$ {code}
 

 

> JobManager crashes after KubernetesClientException exception with 
> FatalExitExceptionHandler
> -------------------------------------------------------------------------------------------
>
>                 Key: FLINK-31974
>                 URL: https://issues.apache.org/jira/browse/FLINK-31974
>             Project: Flink
>          Issue Type: Bug
>          Components: Deployment / Kubernetes
>    Affects Versions: 1.17.0
>            Reporter: Sergio Sainz
>            Assignee: Weijie Guo
>            Priority: Major
>
> When resource quota limit is reached JobManager will throw
>  
> org.apache.flink.kubernetes.shaded.io.fabric8.kubernetes.client.KubernetesClientException:
>  Failure executing: POST at: 
> https://10.96.0.1/api/v1/namespaces/my-namespace/pods. Message: 
> Forbidden!Configured service account doesn't have access. Service account may 
> have been revoked. pods "my-namespace-flink-cluster-taskmanager-1-2" is 
> forbidden: exceeded quota: my-namespace-resource-quota, requested: 
> limits.cpu=3, used: limits.cpu=12100m, limited: limits.cpu=13.
>  
> In {*}1.16.1 , this is handled gracefully{*}:
> {code}
> 2023-04-28 22:07:24,631 WARN  
> org.apache.flink.runtime.resourcemanager.active.ActiveResourceManager [] - 
> Failed requesting worker with resource spec WorkerResourceSpec 
> \{cpuCores=1.0, taskHeapSize=25.600mb (26843542 bytes), taskOffHeapSize=0 
> bytes, networkMemSize=64.000mb (67108864 bytes), managedMemSize=230.400mb 
> (241591914 bytes), numSlots=4}, current pending count: 0
> java.util.concurrent.CompletionException: 
> io.fabric8.kubernetes.client.KubernetesClientException: Failure executing: 
> POST at: https://10.96.0.1/api/v1/namespaces/my-namespace/pods. Message: 
> Forbidden!Configured service account doesn't have access. Service account may 
> have been revoked. pods "my-namespace-flink-cluster-taskmanager-1-138" is 
> forbidden: exceeded quota: my-namespace-resource-quota, requested: 
> limits.cpu=3, used: limits.cpu=12100m, limited: limits.cpu=13.
>         at java.util.concurrent.CompletableFuture.encodeThrowable(Unknown 
> Source) ~[?:?]
>         at java.util.concurrent.CompletableFuture.completeThrowable(Unknown 
> Source) ~[?:?]
>         at java.util.concurrent.CompletableFuture$AsyncRun.run(Unknown 
> Source) ~[?:?]
>         at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source) 
> ~[?:?]
>         at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source) 
> ~[?:?]
>         at java.lang.Thread.run(Unknown Source) ~[?:?]
> Caused by: io.fabric8.kubernetes.client.KubernetesClientException: Failure 
> executing: POST at: https://10.96.0.1/api/v1/namespaces/my-namespace/pods. 
> Message: Forbidden!Configured service account doesn't have access. Service 
> account may have been revoked. pods 
> "my-namespace-flink-cluster-taskmanager-1-138" is forbidden: exceeded quota: 
> my-namespace-resource-quota, requested: limits.cpu=3, used: 
> limits.cpu=12100m, limited: limits.cpu=13.
>         at 
> io.fabric8.kubernetes.client.dsl.base.OperationSupport.requestFailure(OperationSupport.java:684)
>  ~[flink-dist-1.16.1.jar:1.16.1]
>         at 
> io.fabric8.kubernetes.client.dsl.base.OperationSupport.requestFailure(OperationSupport.java:664)
>  ~[flink-dist-1.16.1.jar:1.16.1]
>         at 
> io.fabric8.kubernetes.client.dsl.base.OperationSupport.assertResponseCode(OperationSupport.java:613)
>  ~[flink-dist-1.16.1.jar:1.16.1]
>         at 
> io.fabric8.kubernetes.client.dsl.base.OperationSupport.handleResponse(OperationSupport.java:558)
>  ~[flink-dist-1.16.1.jar:1.16.1]
>         at 
> io.fabric8.kubernetes.client.dsl.base.OperationSupport.handleResponse(OperationSupport.java:521)
>  ~[flink-dist-1.16.1.jar:1.16.1]
>         at 
> io.fabric8.kubernetes.client.dsl.base.OperationSupport.handleCreate(OperationSupport.java:308)
>  ~[flink-dist-1.16.1.jar:1.16.1]
>         at 
> io.fabric8.kubernetes.client.dsl.base.BaseOperation.handleCreate(BaseOperation.java:644)
>  ~[flink-dist-1.16.1.jar:1.16.1]
>         at 
> io.fabric8.kubernetes.client.dsl.base.BaseOperation.handleCreate(BaseOperation.java:83)
>  ~[flink-dist-1.16.1.jar:1.16.1]
>         at 
> io.fabric8.kubernetes.client.dsl.base.CreateOnlyResourceOperation.create(CreateOnlyResourceOperation.java:61)
>  ~[flink-dist-1.16.1.jar:1.16.1]
>         at 
> org.apache.flink.kubernetes.kubeclient.Fabric8FlinkKubeClient.lambda$createTaskManagerPod$1(Fabric8FlinkKubeClient.java:163)
>  ~[flink-dist-1.16.1.jar:1.16.1]
>         ... 4 more
> {code}
> But , {*}in Flink 1.17.0 , Job Manager crashes{*}:
> {code}
> 2023-04-28 20:50:50,534 ERROR org.apache.flink.util.FatalExitExceptionHandler 
>              [] - FATAL: Thread 'flink-akka.actor.default-dispatcher-15' 
> produced an uncaught exception. Stopping the process...
> java.util.concurrent.CompletionException: 
> org.apache.flink.kubernetes.shaded.io.fabric8.kubernetes.client.KubernetesClientException:
>  Failure executing: POST at: 
> https://10.96.0.1/api/v1/namespaces/my-namespace/pods. Message: 
> Forbidden!Configured service account doesn't have access. Service account may 
> have been revoked. pods "my-namespace-flink-cluster-taskmanager-1-2" is 
> forbidden: exceeded quota: my-namespace-resource-quota, requested: 
> limits.cpu=3, used: limits.cpu=12100m, limited: limits.cpu=13.
>         at java.util.concurrent.CompletableFuture.encodeThrowable(Unknown 
> Source) ~[?:?]
>         at java.util.concurrent.CompletableFuture.completeThrowable(Unknown 
> Source) ~[?:?]
>         at java.util.concurrent.CompletableFuture$AsyncRun.run(Unknown 
> Source) ~[?:?]
>         at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source) 
> ~[?:?]
>         at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source) 
> ~[?:?]
>         at java.lang.Thread.run(Unknown Source) ~[?:?]
> Caused by: 
> org.apache.flink.kubernetes.shaded.io.fabric8.kubernetes.client.KubernetesClientException:
>  Failure executing: POST at: 
> https://10.96.0.1/api/v1/namespaces/my-namespace/pods. Message: 
> Forbidden!Configured service account doesn't have access. Service account may 
> have been revoked. pods "my-namespace-flink-cluster-taskmanager-1-2" is 
> forbidden: exceeded quota: my-namespace-resource-quota, requested: 
> limits.cpu=3, used: limits.cpu=12100m, limited: limits.cpu=13.
>         at 
> org.apache.flink.kubernetes.shaded.io.fabric8.kubernetes.client.dsl.base.OperationSupport.requestFailure(OperationSupport.java:684)
>  ~[flink-dist-1.17.0.jar:1.17.0]
>         at 
> org.apache.flink.kubernetes.shaded.io.fabric8.kubernetes.client.dsl.base.OperationSupport.requestFailure(OperationSupport.java:664)
>  ~[flink-dist-1.17.0.jar:1.17.0]
>         at 
> org.apache.flink.kubernetes.shaded.io.fabric8.kubernetes.client.dsl.base.OperationSupport.assertResponseCode(OperationSupport.java:613)
>  ~[flink-dist-1.17.0.jar:1.17.0]
>         at 
> org.apache.flink.kubernetes.shaded.io.fabric8.kubernetes.client.dsl.base.OperationSupport.handleResponse(OperationSupport.java:558)
>  ~[flink-dist-1.17.0.jar:1.17.0]
>         at 
> org.apache.flink.kubernetes.shaded.io.fabric8.kubernetes.client.dsl.base.OperationSupport.handleResponse(OperationSupport.java:521)
>  ~[flink-dist-1.17.0.jar:1.17.0]
>         at 
> org.apache.flink.kubernetes.shaded.io.fabric8.kubernetes.client.dsl.base.OperationSupport.handleCreate(OperationSupport.java:308)
>  ~[flink-dist-1.17.0.jar:1.17.0]
>         at 
> org.apache.flink.kubernetes.shaded.io.fabric8.kubernetes.client.dsl.base.BaseOperation.handleCreate(BaseOperation.java:644)
>  ~[flink-dist-1.17.0.jar:1.17.0]
>         at 
> org.apache.flink.kubernetes.shaded.io.fabric8.kubernetes.client.dsl.base.BaseOperation.handleCreate(BaseOperation.java:83)
>  ~[flink-dist-1.17.0.jar:1.17.0]
>         at 
> org.apache.flink.kubernetes.shaded.io.fabric8.kubernetes.client.dsl.base.CreateOnlyResourceOperation.create(CreateOnlyResourceOperation.java:61)
>  ~[flink-dist-1.17.0.jar:1.17.0]
>         at 
> org.apache.flink.kubernetes.kubeclient.Fabric8FlinkKubeClient.lambda$createTaskManagerPod$1(Fabric8FlinkKubeClient.java:163)
>  ~[flink-dist-1.17.0.jar:1.17.0]
>         ... 4 more
> {code}



--
This message was sent by Atlassian Jira
(v8.20.10#820010)

Reply via email to