前一阶段看下CarbonData，说是基于HDFS列式存储，据说性能很好，支持复杂的查询，对我们的业务来说目前很需要，所以想尝试下。
1.源码下载
去官网下载源码，没有编译好的，只能自己编译，好搓哦。
1）安装maven
这个简单，下载设置好mavenhome：
export MAVEN_HOME=/ssd/bigdata/software/apache-maven-3.3.9
和bin路径就可以了。
2）安装JAVA
这个安装过了，忽略。
3）安装Thrift 0.9.3
./configure JAVAC=/ssd/bigdata/software/jdk/bin/javac
报错：
configure: error: Bison version 2.5 or higher must be installed on the system!
改命令：
./configure JAVAC=/ssd/bigdata/software/jdk/bin/javac --prefix=/ssd/bigdata/software/bison-3.0/install
安装完成后，在环境变量的path前面加上安装路径。
再次安装thrift
make
然后检查 make check
然后用root用户进行make install
4)安装CarbonData
mvn clean -DskipTests -Pbuild-with-format -Pspark-2.1 install
无法连外网，安装不起来- -
转环境到自己虚拟机上编译试试。
[ERROR] Failed to execute goal on project carbondata-core: Could not resolve dependencies for project org.apache.carbondata:carbondata-core:jar:1.0.0-incubating: The following artifacts could not be resolved: pentaho-kettle:kettle-engine:jar:4.4.0-stable, pentaho-kettle:kettle-core:jar:4.4.0-stable, pentaho-kettle:kettle-db:jar:4.4.0-stable, org.apache.spark:spark-core_2.11:jar:2.1.0, org.apache.spark:spark-catalyst_2.11:jar:2.1.0: Failure to find pentaho-kettle:kettle-engine:jar:4.4.0-stable in
