apache impala3.4编译安装

安装

升级cmake

1 版本要求高于

下载地址

	https://cmake.org/files/v3.19/cmake-3.19.0-Linux-x86_64.tar.gz
	yum remove cmake
	
	export CMAKE_HOME=/app/cmake
	export PATH=$PATH:$CMAKE_HOME/bin

2 安装boost

	scl enable devtoolset-9 bash
	yum -y install boost

配置编译环境

1 部署配置maven

	tar -xvf apache-maven-3.5.4-bin.tar.gz
	mv apache-maven-3.5.4 maven
	
	vi maven/conf/settings.xml
	<localRepository>/app/compileenv/maven/repo</localRepository>

2 修改环境变量

	cd ~
	vi .bash_profile
	export M2_HOME=/app/compileenv/maven
	export M2=$M2_HOME/bin
	export PATH=$M2:$PATH
	export IMPALA_HOME=/app/impala

3 编译

	cd /usr/MyWorkSpace/CDH/apache-impala-3.4.0
	./buildall.sh -notests

4 拷贝编译后文件

#!/bin/bash
IMPALA_HOME=/app/impala
IMPALA_BUILD=/app/impala-build

# if exist the dest directory then clear it.
if [ -d "${IMPALA_BUILD}" ]; then
        rm -rf ${IMPALA_BUILD}/*
else
        mkdir -p ${IMPALA_BUILD}
fi

mkdir -p ${IMPALA_BUILD}/etc/default/
mkdir -p ${IMPALA_BUILD}/etc/hadoop/
mkdir -p ${IMPALA_BUILD}/be
mkdir -p ${IMPALA_BUILD}/lib64/
mkdir ${IMPALA_BUILD}/hadoop/
mkdir ${IMPALA_BUILD}/dependency/
mkdir ${IMPALA_BUILD}/shell

cp -rf ${IMPALA_HOME}/be/build/debug/* ${IMPALA_BUILD}/be/
cp -rf ${IMPALA_HOME}/toolchain/gcc-4.9.2/lib64/*   ${IMPALA_BUILD}/lib64/
cp -rf ${IMPALA_HOME}/fe/target/impala-frontend-0.1-SNAPSHOT.jar   ${IMPALA_BUILD}/dependency/
cp -rf ${IMPALA_HOME}/fe/target/dependency/*      ${IMPALA_BUILD}/dependency/
cp -rf ${IMPALA_HOME}/shell/build/impala-shell-3.4.0-RELEASE/*   ${IMPALA_BUILD}/shell
cp -r ${IMPALA_HOME}/www ${IMPALA_BUILD}/

echo "Finished"

bug处理

1 修改bootstrap_toolchain.py报错，由于这个文件里的包都比较大，下载容易失败建议将方法改为如下，自己手动下载相关包

	def needs_download(self):
		return False
	
	vi /usr/MyWorkSpace/CDH/apache-impala-3.4.0/bin/bootstrap_toolchain.py 
	加入
	import sys
	reload(sys)
	sys.setdefaultencoding('utf-8')

2 解决DistributionNotFound: No matching distribution found for thrift>=0.9.3 (from impyla==0.16.2->-r /usr/MyWorkSpace/CDH/apache-impala-3.4.0/bin/…/infra/python/deps/compiled-requirements.txt (line 2))

	wget https://bootstrap.pypa.io/2.7/get-pip.py
	python get-pip.py
	/usr/MyWorkSpace/CDH/apache-impala-3.4.0/infra/python/env/bin/pip install thrift==0.9.3

3 解决boost报错问题

下载boost版本boost-1.61.0

	cp boost_1_61_0.tar.gz /usr/MyWorkSpace/CDH/apache-impala-3.4.0/toolchain
	cd /usr/MyWorkSpace/CDH/apache-impala-3.4.0/toolchain
	tar -xvf boost_1_61_0.tar.gz
	mv boost_1_61_0.tar.gz boost-1.61.0-p2
	cd boost-1.61.0-p2
	./bootstrap.sh
	./b2

4 解决logredactor-2.0.7报错

github上下载https://github.com/cloudera/logredactor/tree/2.0.7
	mvn clean install

修改cloudera仓库地址

	Plugin net.sourceforge.czt.dev:cup-maven-plugin:1.6-cdh or one of its dependencies could not be resolved: Could not find artifact net.sourceforge.czt.dev:cup-maven-plugin:jar:1.6-cdh in cloudera.thirdparty.repo (https://repository.cloudera.com/content/repositories/third-party)

修改/usr/MyWorkSpace/CDH/apache-impala-3.4.0/impala-parent/pom.xml
	
	<repository>
  		<id>cloudera.thirdparty.repo</id>
  		<url>https://repository.cloudera.com/artifactory/public</url>
  		<name>Cloudera Third Party Repository</name>
  		<snapshots>
    		<enabled>false</enabled>
  		</snapshots>
	</repository>

	<pluginRepositories>
		<pluginRepository>
  			<id>cloudera.thirdparty.repo</id>
  			<url>https://repository.cloudera.com/artifactory/public</url>
  			<name>Cloudera Third Party Repository</name>
  			<snapshots>
    			<enabled>false</enabled>
  			</snapshots>
		</pluginRepository>
	</pluginRepositories>

5 解决ranger-plugins-common-2.0.0.7.0.2.0-212.pom

修改/usr/MyWorkSpace/CDH/apache-impala-3.4.0/fe/pom.xml

    <dependency>
      <groupId>org.apache.ranger</groupId>
      <artifactId>ranger-plugins-common</artifactId>
      <version>2.0.0</version>
      <exclusions>
        <exclusion>
          <groupId>com.sun.jersey</groupId>
          <artifactId>jersey-bundle</artifactId>
        </exclusion>
      </exclusions>
    </dependency>

    <dependency>
      <groupId>org.apache.ranger</groupId>
      <artifactId>ranger-plugins-audit</artifactId>
      <version>2.0.0</version>
      <exclusions>
        <exclusion>
          <groupId>org.apache.kafka</groupId>
          <artifactId>kafka_2.11</artifactId>
        </exclusion>
      </exclusions>
	</dependency>

6 修改https://native-toolchain.s3.amazonaws.com/build/cdh_components/1814051/maven/org/apache/kudu/kudu-client/1.12.0-SNAPSHOT/kudu-client-1.12.0-SNAPSHOT.pom

修改/usr/MyWorkSpace/CDH/apache-impala-3.4.0/fe/pom.xml

    <dependency>
      <groupId>org.apache.kudu</groupId>
      <artifactId>kudu-client</artifactId>
      <version>1.12.0</version>
    </dependency>