Flink高可用集群搭建

安装节点要求：

• jdk1.8
• hadoop2.7.6
• scala2.11.8
• zookeeper3.4.10

节点分配

	JobManager	TaskManager	ZooKeeper
hadoop01	√	√	√
hadoop02	√	√	√
hadoop03		√	√

1.高可用集群搭建

1.1上传安装包

rz -E C:/flink-1.7.2-bin-hadoop27-scala_2.11.tgz

1.2解压

tar -zxvf flink-1.7.2-bin-hadoop27-scala_2.11.tgz -C ~/apps/

1.3重命名

mv flink-1.7.2 flink

1.4配置环境变量

vim ~/.bash_profile

export FLINK_HOME=/home/hadoop/apps/flink
export PATH=$PATH:$FLINK_HOME/bin

重新加载配置文件

source ~/.bash_profile

1.5修改配置文件

1.5.1masters

vi $FLINK_HOME/conf/masters

hadoop01:8081
hadoop02:8081

1.5.2slaves

vi $FLINK_HOME/conf/slaves

hadoop01
hadoop02
hadoop03

1.5.3flink-conf.yaml

vi $FLINK_HOME/conf/flink-conf.yaml

################################################################################
#  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
# JobManager runs.

#指定主节点，可以为localhost，这样在哪里启动谁就是JobManager
jobmanager.rpc.address: hadoop01

# The RPC port where the JobManager is reachable.
jobmanager.rpc.port: 6123


# The heap size for the JobManager JVM

jobmanager.heap.size: 1024m


# The heap size for the TaskManager JVM

taskmanager.heap.size: 1024m


# 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'.
# 指定使用 zookeeper 进行 HA 协调
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://bd1906/flink172/hastorage/

# 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: hadoop01:2181,hadoop02:2181,hadoop03:2181


# 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>.
#
# 指定 checkpoint 的类型和对应的数据存储目录
state.backend: filesystem
state.backend.fs.checkpointdir: hdfs://bd1906/flink-checkpoints

# 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://namenode-host:port/flink-checkpoints

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

#==============================================================================
# Web Frontend
#==============================================================================

# The address under which the web-based runtime monitor listens.
#
#web.address: 0.0.0.0

# The port under which the web-based runtime monitor listens.
# A value of -1 deactivates the web server.

rest.port: 8081

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

#web.submit.enable: false

#==============================================================================
# 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

# Specify whether TaskManager's managed memory should be allocated when starting
# up (true) or when memory is requested.
#
# We recommend to set this value to 'true' only in setups for pure batch
# processing (DataSet API). Streaming setups currently do not use the TaskManager's
# managed memory: The 'rocksdb' state backend uses RocksDB's own memory management,
# while the 'memory' and 'filesystem' backends explicitly keep data as objects
# to save on serialization cost.
#
# taskmanager.memory.preallocate: false

# 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, teh default max is 1GB.
# 
# taskmanager.network.memory.fraction: 0.1
# taskmanager.network.memory.min: 64mb
# taskmanager.network.memory.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

1.6拷贝配置文件

拷贝zoo.cfg、hdfs-site.xml、core-site.xml到flink配置文件目录

cp $ZOOKEEPER_HOME/conf/zoo.cfg $FLINK_HOME/conf/
cp $HADOOP_HOME/etc/hadoop/hdfs-site.xml $FLINK_HOME/conf/
cp $HADOOP_HOME/etc/hadoop/core-site.xml $FLINK_HOME/conf/

1.7远程发送文件

scp -r flink hadoop02:$PWD
scp -r flink hadoop03:$PWD
scp ~/.bash_profile hadoop02:/home/hadoop/
scp ~/.bash_profile hadoop03:/home/hadoop/

三台机器都要重新加载配置文件

source ~/.bash_profile

如果前面修改了jobmanager.rpc.address的值，请修改hadoop02上的flink-conf.yaml中jobmanager.rpc.address的值为hadoop02，hadoop03可改可不改，这样才能看出高可用集群的效果！！

依次启动zk、hdfs、flink

zkServer.sh start
start-dfs.sh
start-cluster.sh

查看进程

jps

查看Web UI http://hadoop01:8081/

可以跑一个官方案例测试一下（输入文件为flink文件夹中的README.txt文件）

flink run -m hadoop02:8081 \
$FLINK_HOME/examples/batch/WordCount.jar

至此集群搭建成功！！

停止集群命令

stop-cluster.sh

2.WordCount程序

Maven依赖

    <properties>
        <flink.version>1.7.2</flink.version>
        <hadoop.version>2.7.6</hadoop.version>
        <scala.version>2.11.8</scala.version>
    </properties>
    <dependencies>
        <!-- flink核心API -->
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-java</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-scala_2.11</artifactId>
            <version>${flink.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-java_2.11</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-scala_2.11</artifactId>
            <version>${flink.version}</version>
        </dependency>
    </dependencies>

2.1java版本

WordCountJava.java

package wc;

import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.common.functions.MapFunction;
import org.apache.flink.api.common.typeinfo.Types;
import org.apache.flink.api.java.ExecutionEnvironment;
import org.apache.flink.api.java.operators.AggregateOperator;
import org.apache.flink.api.java.operators.DataSource;
import org.apache.flink.api.java.operators.FlatMapOperator;
import org.apache.flink.api.java.operators.MapOperator;
import org.apache.flink.api.java.tuple.Tuple2;

/**
 * @Author Daniel
 * @Description java版本Flink wordcount 程序
 **/
public class WordCountJava {

    public static void main(String[] args) {
        //编程入口
        ExecutionEnvironment batchEnv = ExecutionEnvironment.getExecutionEnvironment();
        //数据源
        DataSource<String> dataSource = batchEnv.fromElements("hadoop hadoop", "spark saprk saprk", "flink flink flink");
        //flatMap算子，一行转多行
        FlatMapOperator<String, String> wordDataSet = dataSource.flatMap((FlatMapFunction<String, String>) (value, out) -> {
            String[] words = value.split(" ");
            for (String word : words) {
                out.collect(word);
            }
        }).returns(Types.STRING);
        //map算子，计数
        MapOperator<String, Tuple2<String, Integer>> wordAndOneDataSet = wordDataSet.map((MapFunction<String, Tuple2<String, Integer>>) value -> new Tuple2(value, 1))
                .returns(Types.TUPLE(Types.STRING, Types.INT));
        //分组并计数
        AggregateOperator<Tuple2<String, Integer>> lastResult = wordAndOneDataSet.groupBy(0)
                .sum(1);
        try {
            //Sink打印结果
            lastResult.print();
//             batchEnv.execute("WordCountJava");//批处理不用此方法，流处理得使用
        } catch (Exception e) {
            e.printStackTrace();
        }
    }
}

2.2scala版本

WordCountScala.scala

package wc

import org.apache.flink.streaming.api.scala.{DataStream, StreamExecutionEnvironment, _}

/**
  * @Author Daniel
  * @Description scala版本Flink wordcount 程序
  **/
object WordCountScala {

  def main(args: Array[String]): Unit = {
    //获取flink编程入口
    val streamEnv = StreamExecutionEnvironment.getExecutionEnvironment
    //从网络端口读取流数据
    val dS = streamEnv.socketTextStream("hadoop01", 9999)
    // 主要业务逻辑
    val resultDS = dS.flatMap(line => line.toString.split(" "))
      .map(word => Word(word, 1))
      .keyBy("word")
      .sum("count")
    //输出
    resultDS.print()
    //进行流数据处理，不间断的运行
    streamEnv.execute("StreamWordCountScala")
  }
}

//良好的数据结构
case class Word(word: String, count: Int)

nc -lk hadoop01 9999
> hadoop hadoop spark spark spark flink flink flink flink