[root@tuge1 flink-1.10.1]# ./bin/flink run -m yarn-cluster -ynm ryj -c vip.shuai7boy.flink.checkpoint.TestSavepoints /data/flinkdata/MyFlinkObj-1.0-SNAPSHOT-jar-with-dependencies.jar

------------------------------------------------------------
 The program finished with the following exception:

org.apache.flink.client.program.ProgramInvocationException: The main method caused an error: org.apache.flink.client.program.ProgramInvocationException: Job failed (JobID: 12b759f143190ee08d831f2fabb4c3f2)
    at org.apache.flink.client.program.PackagedProgram.callMainMethod(PackagedProgram.java:335)
    at org.apache.flink.client.program.PackagedProgram.invokeInteractiveModeForExecution(PackagedProgram.java:205)
    at org.apache.flink.client.ClientUtils.executeProgram(ClientUtils.java:138)
    at org.apache.flink.client.cli.CliFrontend.executeProgram(CliFrontend.java:662)
    at org.apache.flink.client.cli.CliFrontend.run(CliFrontend.java:210)
    at org.apache.flink.client.cli.CliFrontend.parseParameters(CliFrontend.java:893)
    at org.apache.flink.client.cli.CliFrontend.lambda$main$10(CliFrontend.java:966)
    at java.security.AccessController.doPrivileged(Native Method)
    at javax.security.auth.Subject.doAs(Subject.java:422)
    at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1692)
    at org.apache.flink.runtime.security.HadoopSecurityContext.runSecured(HadoopSecurityContext.java:41)
    at org.apache.flink.client.cli.CliFrontend.main(CliFrontend.java:966)
Caused by: java.util.concurrent.ExecutionException: org.apache.flink.client.program.ProgramInvocationException: Job failed (JobID: 12b759f143190ee08d831f2fabb4c3f2)
    at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:357)
    at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:1895)
    at org.apache.flink.streaming.api.environment.StreamContextEnvironment.execute(StreamContextEnvironment.java:83)
    at org.apache.flink.streaming.api.environment.StreamExecutionEnvironment.execute(StreamExecutionEnvironment.java:1620)
    at org.apache.flink.streaming.api.environment.StreamExecutionEnvironment.execute(StreamExecutionEnvironment.java:1602)
    at org.apache.flink.streaming.api.scala.StreamExecutionEnvironment.execute(StreamExecutionEnvironment.scala:667)
    at vip.shuai7boy.flink.checkpoint.TestSavepoints$.main(TestSavepoints.scala:30)
    at vip.shuai7boy.flink.checkpoint.TestSavepoints.main(TestSavepoints.scala)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:498)
    at org.apache.flink.client.program.PackagedProgram.callMainMethod(PackagedProgram.java:321)
    ... 11 more
Caused by: org.apache.flink.client.program.ProgramInvocationException: Job failed (JobID: 12b759f143190ee08d831f2fabb4c3f2)
    at org.apache.flink.client.deployment.ClusterClientJobClientAdapter.lambda$null$6(ClusterClientJobClientAdapter.java:112)
    at java.util.concurrent.CompletableFuture.uniApply(CompletableFuture.java:602)
    at java.util.concurrent.CompletableFuture$UniApply.tryFire(CompletableFuture.java:577)
    at java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:474)
    at java.util.concurrent.CompletableFuture.complete(CompletableFuture.java:1962)
    at org.apache.flink.client.program.rest.RestClusterClient.lambda$pollResourceAsync$21(RestClusterClient.java:565)
    at java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:760)
    at java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:736)
    at java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:474)
    at java.util.concurrent.CompletableFuture.complete(CompletableFuture.java:1962)
    at org.apache.flink.runtime.concurrent.FutureUtils.lambda$retryOperationWithDelay$8(FutureUtils.java:291)
    at java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:760)
    at java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:736)
    at java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:474)
    at java.util.concurrent.CompletableFuture.postFire(CompletableFuture.java:561)
    at java.util.concurrent.CompletableFuture$UniCompose.tryFire(CompletableFuture.java:929)
    at java.util.concurrent.CompletableFuture$Completion.run(CompletableFuture.java:442)
    at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
    at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
    at java.lang.Thread.run(Thread.java:748)
Caused by: org.apache.flink.runtime.client.JobExecutionException: Job execution failed.
    at org.apache.flink.runtime.jobmaster.JobResult.toJobExecutionResult(JobResult.java:147)
    at org.apache.flink.client.deployment.ClusterClientJobClientAdapter.lambda$null$6(ClusterClientJobClientAdapter.java:110)
    ... 19 more
Caused by: org.apache.flink.runtime.JobException: Recovery is suppressed by NoRestartBackoffTimeStrategy
    at org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.handleFailure(ExecutionFailureHandler.java:110)
    at org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.getFailureHandlingResult(ExecutionFailureHandler.java:76)
    at org.apache.flink.runtime.scheduler.DefaultScheduler.handleTaskFailure(DefaultScheduler.java:192)
    at org.apache.flink.runtime.scheduler.DefaultScheduler.maybeHandleTaskFailure(DefaultScheduler.java:186)
    at org.apache.flink.runtime.scheduler.DefaultScheduler.updateTaskExecutionStateInternal(DefaultScheduler.java:180)
    at org.apache.flink.runtime.scheduler.SchedulerBase.updateTaskExecutionState(SchedulerBase.java:496)
    at org.apache.flink.runtime.scheduler.UpdateSchedulerNgOnInternalFailuresListener.notifyTaskFailure(UpdateSchedulerNgOnInternalFailuresListener.java:49)
    at org.apache.flink.runtime.executiongraph.ExecutionGraph.notifySchedulerNgAboutInternalTaskFailure(ExecutionGraph.java:1703)
    at org.apache.flink.runtime.executiongraph.Execution.processFail(Execution.java:1252)
    at org.apache.flink.runtime.executiongraph.Execution.processFail(Execution.java:1220)
    at org.apache.flink.runtime.executiongraph.Execution.markFailed(Execution.java:1051)
    at org.apache.flink.runtime.executiongraph.ExecutionVertex.markFailed(ExecutionVertex.java:748)
    at org.apache.flink.runtime.scheduler.DefaultExecutionVertexOperations.markFailed(DefaultExecutionVertexOperations.java:41)
    at org.apache.flink.runtime.scheduler.DefaultScheduler.handleTaskDeploymentFailure(DefaultScheduler.java:446)
    at org.apache.flink.runtime.scheduler.DefaultScheduler.lambda$assignResourceOrHandleError$5(DefaultScheduler.java:433)
    at java.util.concurrent.CompletableFuture.uniHandle(CompletableFuture.java:822)
    at java.util.concurrent.CompletableFuture$UniHandle.tryFire(CompletableFuture.java:797)
    at java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:474)
    at java.util.concurrent.CompletableFuture.completeExceptionally(CompletableFuture.java:1977)
    at org.apache.flink.runtime.jobmaster.slotpool.SchedulerImpl.lambda$internalAllocateSlot$0(SchedulerImpl.java:168)
    at java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:760)
    at java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:736)
    at java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:474)
    at java.util.concurrent.CompletableFuture.completeExceptionally(CompletableFuture.java:1977)
    at org.apache.flink.runtime.jobmaster.slotpool.SlotSharingManager$SingleTaskSlot.release(SlotSharingManager.java:726)
    at org.apache.flink.runtime.jobmaster.slotpool.SlotSharingManager$MultiTaskSlot.release(SlotSharingManager.java:537)
    at org.apache.flink.runtime.jobmaster.slotpool.SlotSharingManager$MultiTaskSlot.lambda$new$0(SlotSharingManager.java:432)
    at java.util.concurrent.CompletableFuture.uniHandle(CompletableFuture.java:822)
    at java.util.concurrent.CompletableFuture$UniHandle.tryFire(CompletableFuture.java:797)
    at java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:474)
    at java.util.concurrent.CompletableFuture.completeExceptionally(CompletableFuture.java:1977)
    at org.apache.flink.runtime.concurrent.FutureUtils.lambda$forward$21(FutureUtils.java:1065)
    at java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:760)
    at java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:736)
    at java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:474)
    at java.util.concurrent.CompletableFuture.completeExceptionally(CompletableFuture.java:1977)
    at org.apache.flink.runtime.concurrent.FutureUtils$Timeout.run(FutureUtils.java:999)
    at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRunAsync(AkkaRpcActor.java:402)
    at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:195)
    at org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:74)
    at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:152)
    at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:26)
    at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:21)
    at scala.PartialFunction.applyOrElse(PartialFunction.scala:123)
    at scala.PartialFunction.applyOrElse$(PartialFunction.scala:122)
    at akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:21)
    at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171)
    at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:172)
    at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:172)
    at akka.actor.Actor.aroundReceive(Actor.scala:517)
    at akka.actor.Actor.aroundReceive$(Actor.scala:515)
    at akka.actor.AbstractActor.aroundReceive(AbstractActor.scala:225)
    at akka.actor.ActorCell.receiveMessage(ActorCell.scala:592)
    at akka.actor.ActorCell.invoke(ActorCell.scala:561)
    at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:258)
    at akka.dispatch.Mailbox.run(Mailbox.scala:225)
    at akka.dispatch.Mailbox.exec(Mailbox.scala:235)
    at akka.dispatch.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
    at akka.dispatch.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
    at akka.dispatch.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
    at akka.dispatch.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)
Caused by: org.apache.flink.runtime.jobmanager.scheduler.NoResourceAvailableException: Could not allocate the required slot within slot request timeout. Please make sure that the cluster has enough resources.
    at org.apache.flink.runtime.scheduler.DefaultScheduler.maybeWrapWithNoResourceAvailableException(DefaultScheduler.java:452)
    ... 47 more
Caused by: java.util.concurrent.CompletionException: java.util.concurrent.TimeoutException
    at java.util.concurrent.CompletableFuture.encodeThrowable(CompletableFuture.java:292)
    at java.util.concurrent.CompletableFuture.completeThrowable(CompletableFuture.java:308)
    at java.util.concurrent.CompletableFuture.uniApply(CompletableFuture.java:593)
    at java.util.concurrent.CompletableFuture$UniApply.tryFire(CompletableFuture.java:577)
    ... 27 more
Caused by: java.util.concurrent.TimeoutException
    ... 25 more

################################################################################
#  Licensed to the Apache Software Foundation (ASF) under one
#  or more contributor license agreements.  See the NOTICE file
#  distributed with this work for additional information
#  regarding copyright ownership.  The ASF licenses this file
#  to you under the Apache License, Version 2.0 (the
#  "License"); you may not use this file except in compliance
#  with the License.  You may obtain a copy of the License at
#
#      http://www.apache.org/licenses/LICENSE-2.0
#
#  Unless required by applicable law or agreed to in writing, software
#  distributed under the License is distributed on an "AS IS" BASIS,
#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
#  See the License for the specific language governing permissions and
# limitations under the License.
################################################################################


#==============================================================================
# Common
#==============================================================================

# The external address of the host on which the JobManager runs and can be
# reached by the TaskManagers and any clients which want to connect. This setting
# is only used in Standalone mode and may be overwritten on the JobManager side
# by specifying the --host <hostname> parameter of the bin/jobmanager.sh executable.
# In high availability mode, if you use the bin/start-cluster.sh script and setup
# the conf/masters file, this will be taken care of automatically. Yarn/Mesos
# automatically configure the host name based on the hostname of the node where the

#设置task内存
taskmanager.network.memory.fraction: 0.1
taskmanager.network.memory.min: 64mb
taskmanager.network.memory.max: 1gb
# JobManager runs.

jobmanager.rpc.address: tuge1 

# The RPC port where the JobManager is reachable.

jobmanager.rpc.port: 6123


# The heap size for the JobManager JVM

jobmanager.heap.size: 1024m


# The total process memory size for the TaskManager.
#
# Note this accounts for all memory usage within the TaskManager process, including JVM metaspace and other overhead.

taskmanager.memory.process.size: 1024m

# To exclude JVM metaspace and overhead, please, use total Flink memory size instead of 'taskmanager.memory.process.size'.
# It is not recommended to set both 'taskmanager.memory.process.size' and Flink memory.
#
# taskmanager.memory.flink.size: 1280m

# The number of task slots that each TaskManager offers. Each slot runs one parallel pipeline.

taskmanager.numberOfTaskSlots: 2 

# The parallelism used for programs that did not specify and other parallelism.

parallelism.default: 1

# The default file system scheme and authority.
# 
# By default file paths without scheme are interpreted relative to the local
# root file system 'file:///'. Use this to override the default and interpret
# relative paths relative to a different file system,
# for example 'hdfs://mynamenode:12345'
#
# fs.default-scheme

#==============================================================================
# High Availability
#==============================================================================

# The high-availability mode. Possible options are 'NONE' or 'zookeeper'.
#
 high-availability: zookeeper

# The path where metadata for master recovery is persisted. While ZooKeeper stores
# the small ground truth for checkpoint and leader election, this location stores
# the larger objects, like persisted dataflow graphs.
# 
# Must be a durable file system that is accessible from all nodes
# (like HDFS, S3, Ceph, nfs, ...) 
#
high-availability.storageDir: hdfs://tuge1:9000/ha/

# The list of ZooKeeper quorum peers that coordinate the high-availability
# setup. This must be a list of the form:
# "host1:clientPort,host2:clientPort,..." (default clientPort: 2181)
#
high-availability.zookeeper.quorum: tuge1:2181,tuge2:2181,tuge3:2181


# ACL options are based on https://zookeeper.apache.org/doc/r3.1.2/zookeeperProgrammers.html#sc_BuiltinACLSchemes
# It can be either "creator" (ZOO_CREATE_ALL_ACL) or "open" (ZOO_OPEN_ACL_UNSAFE)
# The default value is "open" and it can be changed to "creator" if ZK security is enabled
#
# high-availability.zookeeper.client.acl: open

#==============================================================================
# Fault tolerance and checkpointing
#==============================================================================

# The backend that will be used to store operator state checkpoints if
# checkpointing is enabled.
#
# Supported backends are 'jobmanager', 'filesystem', 'rocksdb', or the
# <class-name-of-factory>.
#
# state.backend: filesystem

# Directory for checkpoints filesystem, when using any of the default bundled
# state backends.
#
# state.checkpoints.dir: hdfs://namenode-host:port/flink-checkpoints

# Default target directory for savepoints, optional.
#
state.savepoints.dir: hdfs://tuge1:9000/flink-checkpoints

# Flag to enable/disable incremental checkpoints for backends that
# support incremental checkpoints (like the RocksDB state backend). 
#
# state.backend.incremental: false

# The failover strategy, i.e., how the job computation recovers from task failures.
# Only restart tasks that may have been affected by the task failure, which typically includes
# downstream tasks and potentially upstream tasks if their produced data is no longer available for consumption.

jobmanager.execution.failover-strategy: region

#==============================================================================
# Rest & web frontend
#==============================================================================

# The port to which the REST client connects to. If rest.bind-port has
# not been specified, then the server will bind to this port as well.
#
#rest.port: 8081

# The address to which the REST client will connect to
#
#rest.address: 0.0.0.0

# Port range for the REST and web server to bind to.
#
#rest.bind-port: 8080-8090

# The address that the REST & web server binds to
#
#rest.bind-address: 0.0.0.0

# Flag to specify whether job submission is enabled from the web-based
# runtime monitor. Uncomment to disable.

# web.submit.enable: true
#==============================================================================
# Advanced
#==============================================================================

# Override the directories for temporary files. If not specified, the
# system-specific Java temporary directory (java.io.tmpdir property) is taken.
#
# For framework setups on Yarn or Mesos, Flink will automatically pick up the
# containers' temp directories without any need for configuration.
#
# Add a delimited list for multiple directories, using the system directory
# delimiter (colon ':' on unix) or a comma, e.g.:
#     /data1/tmp:/data2/tmp:/data3/tmp
#
# Note: Each directory entry is read from and written to by a different I/O
# thread. You can include the same directory multiple times in order to create
# multiple I/O threads against that directory. This is for example relevant for
# high-throughput RAIDs.
#
io.tmp.dirs: /tmp

# The classloading resolve order. Possible values are 'child-first' (Flink's default)
# and 'parent-first' (Java's default).
#
# Child first classloading allows users to use different dependency/library
# versions in their application than those in the classpath. Switching back
# to 'parent-first' may help with debugging dependency issues.
#
# classloader.resolve-order: child-first

# The amount of memory going to the network stack. These numbers usually need 
# no tuning. Adjusting them may be necessary in case of an "Insufficient number
# of network buffers" error. The default min is 64MB, the default max is 1GB.
# 
# taskmanager.memory.network.fraction: 0.1
# taskmanager.memory.network.min: 64mb
# taskmanager.memory.network.max: 1gb

#==============================================================================
# Flink Cluster Security Configuration
#==============================================================================

# Kerberos authentication for various components - Hadoop, ZooKeeper, and connectors -
# may be enabled in four steps:
# 1. configure the local krb5.conf file
# 2. provide Kerberos credentials (either a keytab or a ticket cache w/ kinit)
# 3. make the credentials available to various JAAS login contexts
# 4. configure the connector to use JAAS/SASL

# The below configure how Kerberos credentials are provided. A keytab will be used instead of
# a ticket cache if the keytab path and principal are set.

# security.kerberos.login.use-ticket-cache: true
# security.kerberos.login.keytab: /path/to/kerberos/keytab
# security.kerberos.login.principal: flink-user

# The configuration below defines which JAAS login contexts

# security.kerberos.login.contexts: Client,KafkaClient

#==============================================================================
# ZK Security Configuration
#==============================================================================

# Below configurations are applicable if ZK ensemble is configured for security

# Override below configuration to provide custom ZK service name if configured
# zookeeper.sasl.service-name: zookeeper

# The configuration below must match one of the values set in "security.kerberos.login.contexts"
# zookeeper.sasl.login-context-name: Client

#==============================================================================
# HistoryServer
#==============================================================================

# The HistoryServer is started and stopped via bin/historyserver.sh (start|stop)

# Directory to upload completed jobs to. Add this directory to the list of
# monitored directories of the HistoryServer as well (see below).
#jobmanager.archive.fs.dir: hdfs:///completed-jobs/

# The address under which the web-based HistoryServer listens.
#historyserver.web.address: 0.0.0.0

# The port under which the web-based HistoryServer listens.
#historyserver.web.port: 8082

# Comma separated list of directories to monitor for completed jobs.
#historyserver.archive.fs.dir: hdfs:///completed-jobs/

# Interval in milliseconds for refreshing the monitored directories.
#historyserver.archive.fs.refresh-interval: 10000
yarn.application-attempts: 10