目录

1、组件版本

环境变量配置

2、hadoop配置

hadoop-env.sh

core-site.xml

hdfs-site.xml

mapred-site.xml

yarn-site.xml

3、hive配置

hive-env.sh

hive-site.xml

HIVE LIB 原始JAR

4、flink配置集成HDFS和YARN

修改iceberg源码

编译iceberg-flink-runtime-1.20-1.8.1.jar

为了兼容HIVE 4.0.1

config.yaml

Flink Lib目录

TEZ

/cluster/tez/conf/tez-site.xml

TEZ LIB

启动程序 

docker启动postgresql数据库

 Hive命令行执行

FlinkSQL执行命令

---

1、组件版本

名称	版本
hadoop	3.4.1
flink	1.20.1
hive	4.0.1
kafka	3.9.0
zookeeper	3.9.3
tez	0.10.4
spark（hadoop3）	3.5.4
jdk	11.0.13
maven	3.9.9

环境变量配置

vim编辑保存后，要执行source /etc/profile

LD_LIBRARY_PATH=/usr/local/lib

export LD_LIBRARY_PATH

# Java环境

export JAVA_HOME=/cluster/jdk

export CLASSPATH=.:$JAVA_HOME/lib:$JAVA_HOME/lib/tools.jar:$JAVA_HOME/lib/dt.jar

export TEZ_HOME=/cluster/tez/

export TEZ_CONF_DIR=$TEZ_HOME/conf

export TEZ_JARS=$TEZ_HOME/*.jar:$TEZ_HOME/lib/*.jar

# Hadoop生态

export HADOOP_HOME=/cluster/hadoop3

export HADOOP_CONF_DIR=$HADOOP_HOME/etc/hadoop

HADOOP_CLASSPATH=`hadoop classpath`

export HADOOP_CLASSPATH=$TEZ_CONF_DIR:$TEZ_JARS:$HADOOP_CLASSPATH

export HDFS_NAMENODE_USER=root

export HDFS_DATANODE_USER=root

export HDFS_SECONDARYNAMENODE_USER=root

export YARN_RESOURCEMANAGER_USER=root

export YARN_NODEMANAGER_USER=root

# Hive配置

export HIVE_HOME=/cluster/hive

export HIVE_CONF_DIR=$HIVE_HOME/conf

# Spark配置

export SPARK_HOME=/cluster/spark

export SPARK_LOCAL_IP=10.10.10.99

export SPARK_CONF_DIR=$SPARK_HOME/conf

# Flink配置

export FLINK_HOME=/cluster/flink

# ZooKeeper/Kafka

export ZOOKEEPER_HOME=/cluster/zookeeper

export KAFKA_HOME=/cluster/kafka

# 其他工具

export FLUME_HOME=/cluster/flume

export M2_HOME=/cluster/maven

# 动态链接库

export LD_LIBRARY_PATH=$HADOOP_HOME/lib/native/:$LD_LIBRARY_PATH

# 环境变量合并

export PATH=$PATH:$HIVE_HOME/bin:$JAVA_HOME/bin:$SPARK_HOME/bin:$SPARK_HOME/sbin:$HADOOP_HOME/bin:$HADOOP_HOME/sbin:$M2_HOME/bin:$FLINK_HOME/bin:$ZOOKEEPER_HOME/bin

export LC_ALL=zh_CN.UTF-8

export LANG=zh_CN.UTF-8

2、hadoop配置

hadoop-env.sh

#

# 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.

# Set Hadoop-specific environment variables here.

##

## THIS FILE ACTS AS THE MASTER FILE FOR ALL HADOOP PROJECTS.

## SETTINGS HERE WILL BE READ BY ALL HADOOP COMMANDS.  THEREFORE,

## ONE CAN USE THIS FILE TO SET YARN, HDFS, AND MAPREDUCE

## CONFIGURATION OPTIONS INSTEAD OF xxx-env.sh.

##

## Precedence rules:

##

## {yarn-env.sh|hdfs-env.sh} > hadoop-env.sh > hard-coded defaults

##

## {YARN_xyz|HDFS_xyz} > HADOOP_xyz > hard-coded defaults

##

# Many of the options here are built from the perspective that users

# may want to provide OVERWRITING values on the command line.

# For example:

#

#  JAVA_HOME=/usr/java/testing hdfs dfs -ls

#

# Therefore, the vast majority (BUT NOT ALL!) of these defaults

# are configured for substitution and not append.  If append

# is preferable, modify this file accordingly.

###

# Generic settings for HADOOP

###

# Technically, the only required environment variable is JAVA_HOME.

# All others are optional.  However, the defaults are probably not

# preferred.  Many sites configure these options outside of Hadoop,

# such as in /etc/profile.d

# The java implementation to use. By default, this environment

# variable is REQUIRED on ALL platforms except OS X!

# export JAVA_HOME=

# Location of Hadoop.  By default, Hadoop will attempt to determine

# this location based upon its execution path.

# export HADOOP_HOME=

# Location of Hadoop's configuration information.  i.e., where this

# file is living. If this is not defined, Hadoop will attempt to

# locate it based upon its execution path.

#

# NOTE: It is recommend that this variable not be set here but in

# /etc/profile.d or equivalent.  Some options (such as

# --config) may react strangely otherwise.

#

# export HADOOP_CONF_DIR=${HADOOP_HOME}/etc/hadoop

# The maximum amount of heap to use (Java -Xmx).  If no unit

# is provided, it will be converted to MB.  Daemons will

# prefer any Xmx setting in their respective _OPT variable.

# There is no default; the JVM will autoscale based upon machine

# memory size.

# export HADOOP_HEAPSIZE_MAX=

# The minimum amount of heap to use (Java -Xms).  If no unit

# is provided, it will be converted to MB.  Daemons will

# prefer any Xms setting in their respective _OPT variable.

# There is no default; the JVM will autoscale based upon machine

# memory size.

# export HADOOP_HEAPSIZE_MIN=

# Enable extra debugging of Hadoop's JAAS binding, used to set up

# Kerberos security.

# export HADOOP_JAAS_DEBUG=true

# Extra Java runtime options for all Hadoop commands. We don't support

# IPv6 yet/still, so by default the preference is set to IPv4.

# export HADOOP_OPTS="-Djava.net.preferIPv4Stack=true"

# For Kerberos debugging, an extended option set logs more information

# export HADOOP_OPTS="-Djava.net.preferIPv4Stack=true -Dsun.security.krb5.debug=true -Dsun.security.spnego.debug"

# Some parts of the shell code may do special things dependent upon

# the operating system.  We have to set this here. See the next

# section as to why....

export HADOOP_OS_TYPE=${HADOOP_OS_TYPE:-$(uname -s)}

# Extra Java runtime options for some Hadoop commands

# and clients (i.e., hdfs dfs -blah).  These get appended to HADOOP_OPTS for

# such commands.  In most cases, # this should be left empty and

# let users supply it on the command line.

# export HADOOP_CLIENT_OPTS=""

#

# A note about classpaths.

#

# By default, Apache Hadoop overrides Java's CLASSPATH

# environment variable.  It is configured such

# that it starts out blank with new entries added after passing

# a series of checks (file/dir exists, not already listed aka

# de-deduplication).  During de-deduplication, wildcards and/or

# directories are *NOT* expanded to keep it simple. Therefore,

# if the computed classpath has two specific mentions of

# awesome-methods-1.0.jar, only the first one added will be seen.

# If two directories are in the classpath that both contain

# awesome-methods-1.0.jar, then Java will pick up both versions.

# An additional, custom CLASSPATH. Site-wide configs should be

# handled via the shellprofile functionality, utilizing the

# hadoop_add_classpath function for greater control and much

# harder for apps/end-users to accidentally override.

# Similarly, end users should utilize ${HOME}/.hadooprc .

# This variable should ideally only be used as a short-cut,

# interactive way for temporary additions on the command line.

# export HADOOP_CLASSPATH="/some/cool/path/on/your/machine"

# Should HADOOP_CLASSPATH be first in the official CLASSPATH?

# export HADOOP_USER_CLASSPATH_FIRST="yes"

# If HADOOP_USE_CLIENT_CLASSLOADER is set, the classpath along

# with the main jar are handled by a separate isolated

# client classloader when 'hadoop jar', 'yarn jar', or 'mapred job'

# is utilized. If it is set, HADOOP_CLASSPATH and

# HADOOP_USER_CLASSPATH_FIRST are ignored.

# export HADOOP_USE_CLIENT_CLASSLOADER=true

# HADOOP_CLIENT_CLASSLOADER_SYSTEM_CLASSES overrides the default definition of

# system classes for the client classloader when HADOOP_USE_CLIENT_CLASSLOADER

<