理论与实践太难了，这玩意错误太多，遍地是坑，还有就是不知道怎么用，一脸懵逼
https://github.com/linkedin/datahub
安装docker
yum -y install docker
# 未启动docker，出现如下问题
[root@localhost ~]# docker pull java:8
Cannot connect to the Docker daemon at unix:///var/run/docker.sock. Is the docker daemon running?
[root@localhost ~]# systemctl daemon-reload
[root@localhost ~]# systemctl restart docker.service
# 启动
# 成功解决
安装python3.8
下载wget https://www.python.org/ftp/python/3.8.2/Python-3.8.0.tgz
#第一步
#非常重要要不然要报错
ModuleNotFoundError: No module named '_ctypes'
yum install libffi-devel -y
cd /app
wget https://www.python.org/ftp/python/3.8.2/Python-3.8.0.tgz
tar -zxvf Python-3.8.0.tgz
cd /app/Python-3.8.0
#编译安装
./configure --prefix=/usr/local/python3
make && make install
#创建软连接
ln -s /usr/local/python3/bin/python3 /usr/local/bin/python3
ln -s /usr/local/python3/bin/pip3 /usr/local/bin/pip3
#验证是否成功
[root@xxx Python-3.8.2]# python3 -V
Python 3.8.2
[root@xxx Python-3.8.2]# pip3 -V
pip 19.2.3 from /usr/local/python3/lib/python3.8/site-packages/pip (python 3.8)
安装pip3
#更新pip3
[root@artemis python3]# pip3 install --upgrade pip -i http://pypi.douban.com/simple --trusted-host pypi.douban.com
Looking in indexes: http://pypi.douban.com/simple
Collecting pip
Downloading http://pypi.doubanio.com/packages/54/eb/4a3642e971f404d69d4f6fa3885559d67562801b99d7592487f1ecc4e017/pip-20.3.3-py2.py3-none-any.whl (1.5MB)
|████████████████████████████████| 1.5MB 6.3MB/s
Installing collected packages: pip
Found existing installation: pip 19.2.3
Uninstalling pip-19.2.3:
Successfully uninstalled pip-19.2.3
Successfully installed pip-20.3.3
设置自由切换python2和python3 实际不需要这步
本文方法使用的是update-alternatives工具
第一步
查看是否已经存在python的可选项
update-alternatives --display python
#!若无则不显示任何信息
第二步
将python2和python3分别添加为可选项
sudo update-alternatives --install /usr/bin/python python /usr/bin/python2.7 1
sudo update-alternatives --install /usr/bin/python python /usr/local/bin/python3 2
#! /usr/bin/python链接文件相同，/usr/local/bin/python3.4 1则根据自己具体安装目录来设定，1、2分别代表优先级
第三步
查看版本，此时的版本是Python2
python --version
Python 2.7.5
第四步
切换版本
sudo update-alternatives --config python
There are 2 programs which provide 'python'.
Selection Command
-----------------------------------------------
+ 1 /usr/bin/python2.7
* 2 /usr/local/bin/python3.6
Enter to keep the current selection[+], or type selection number: 2(1为python2.7，2为python3.6)
第五步
如上，我们选择的选项是2，因此此时版本应该为Python3
python --version
Python 3.6.5
附加，删除可选项
sudo update-alternatives --remove python /usr/bin/python2.7 (删除2.7)
sudo update-alternatives --remove python /usr/local/bin/python3.6 (删除3.6)
安装 sklearn
pip3 install sklearn -i http://pypi.douban.com/simple --trusted-host pypi.douban.com
安装docker-compose 方法1 会报错2 不建议
pip3 install docker-compose -i http://pypi.douban.com/simple --trusted-host pypi.douban.com
安装docker-compose 方法2 可以解决报错2
curl -L "https://github.com/docker/compose/releases/download/1.27.4/docker-compose-$(uname -s)-$(uname -m)" -o /usr/local/bin/docker-compose
chmod +x /usr/local/bin/docker-compose
安装完毕后重启下docker服务
systemctl 方式
守护进程重启
sudo systemctl daemon-reload
重启docker服务
sudo systemctl restart docker
关闭docker
sudo systemctl stop docker
报错1可能是网络引起的
[root@ares datahub]# ./docker/quickstart.sh
Pulling mysql ... done
Pulling zookeeper ... done
Pulling elasticsearch ... done
Pulling elasticsearch-setup ... done
Pulling kibana ... done
Pulling broker ... done
Pulling neo4j ... done
Pulling schema-registry ... done
Pulling schema-registry-ui ... done
Pulling kafka-setup ... done
Pulling datahub-mae-consumer ... done
Pulling datahub-gms ... done
Pulling datahub-mce-consumer ... done
Pulling datahub-frontend ... done
Pulling kafka-rest-proxy ... done
Pulling kafka-topics-ui ... done
Building elasticsearch-setup
Step 1/6 : FROM jwilder/dockerize:0.6.1
---> 849596ab86ff
Step 2/6 : RUN apk add --no-cache curl jq
---> Running in 8ca0149674f7
fetch http://dl-cdn.alpinelinux.org/alpine/v3.6/main/x86_64/APKINDEX.tar.gz
WARNING: Ignoring http://dl-cdn.alpinelinux.org/alpine/v3.6/main/x86_64/APKINDEX.tar.gz: network error (check Internet connection and firewall)
fetch http://dl-cdn.alpinelinux.org/alpine/v3.6/community/x86_64/APKINDEX.tar.gz
WARNING: Ignoring http://dl-cdn.alpinelinux.org/alpine/v3.6/community/x86_64/APKINDEX.tar.gz: network error (check Internet connection and firewall)
ERROR: unsatisfiable constraints:
curl (missing):
required by: world[curl]
jq (missing):
required by: world[jq]
ERROR: Service 'elasticsearch-setup' failed to build : The command '/bin/sh -c apk add --no-cache curl jq' returned a non-zero code: 2
报错2 docker-compose
[root@artemis datahub]# ./docker/quickstart.sh
/usr/lib/python2.7/site-packages/paramiko/transport.py:33: CryptographyDeprecationWarning: Python 2 is no longer supported by the Python core team. Support for it is now deprecated in cryptography, and will be removed in the next release.
from cryptography.hazmat.backends import default_backend
Traceback (most recent call last):
File "/usr/bin/docker-compose", line 5, in <module>
from compose.cli.main import main
File "/usr/lib/python2.7/site-packages/compose/cli/main.py", line 24, in <module>
from ..config import ConfigurationError
File "/usr/lib/python2.7/site-packages/compose/config/__init__.py", line 6, in <module>
from .config import ConfigurationError
File "/usr/lib/python2.7/site-packages/compose/config/config.py", line 51, in <module>
from .validation import match_named_volumes
File "/usr/lib/python2.7/site-packages/compose/config/validation.py", line 12, in <module>
from jsonschema import Draft4Validator
File "/usr/lib/python2.7/site-packages/jsonschema/__init__.py", line 21, in <module>
from jsonschema._types import TypeChecker
File "/usr/lib/python2.7/site-packages/jsonschema/_types.py", line 3, in <module>
from pyrsistent import pmap
File "/usr/lib64/python2.7/site-packages/pyrsistent/__init__.py", line 3, in <module>
from pyrsistent._pmap import pmap, m, PMap
File "/usr/lib64/python2.7/site-packages/pyrsistent/_pmap.py", line 98
) from e
^
SyntaxError: invalid syntax
报错3 替换国内源在报错5还有一种解决方案，视情况替换
WARNING: Ignoring http://dl-cdn.alpinelinux.org/alpine/v3.6/main/x86_64/APKINDEX.tar.gz: network error (check Internet connection and firewall)
正确的做法是使用国内源完全覆盖 /etc/apk/repositories在Dockerfile中增加下面的第二行
FROM alpine:3.7
RUN echo -e http://mirrors.ustc.edu.cn/alpine/v3.7/main/ > /etc/apk/repositories
可能修改的文件
/app/datahub/docker/datahub-mae-consumer/Dockerfile
/app/datahub/docker/datahub-gms/Dockerfile
/app/datahub/docker/datahub-frontend/Dockerfile
/app/datahub/docker/datahub-mae-consumer/Dockerfile
/app/datahub/docker/datahub-mce-consumer/Dockerfile
具体是哪个或者哪几个不清楚，宁可错杀不可放过，在所有的FROM 后面都加上，一个文件里面可能有多个，好像有问题等会放一放
https://www.jianshu.com/p/eb34e7088c77
官方使用指南
检查启动
docker container ls
[root@ares ~]# docker container ls
CONTAINER ID IMAGE COMMAND CREATED STATUS PORTS NAMES
14ef8eedaf60 linkedin/datahub-frontend:latest "datahub-frontend/bi…" 15 hours ago Up 15 hours 0.0.0.0:9001->9001/tcp datahub-frontend
8377aad77608 landoop/kafka-topics-ui:0.9.4 "/run.sh" 15 hours ago Up 15 hours 0.0.0.0:18000->8000/tcp kafka-topics-ui
a5ef70bde9f1 linkedin/datahub-mae-consumer:latest "/bin/sh -c /datahub…" 15 hours ago Up 15 hours 9090/tcp, 0.0.0.0:9091->9091/tcp datahub-mae-consumer
f5ab5ae53011 linkedin/datahub-gms:latest "/bin/sh -c /datahub…" 15 hours ago Up 15 hours 0.0.0.0:8080->8080/tcp datahub-gms
f5cda035d5e5 confluentinc/cp-kafka-rest:5.4.0 "/etc/confluent/dock…" 15 hours ago Up 15 hours 0.0.0.0:8082->8082/tcp kafka-rest-proxy
2328387122a3 landoop/schema-registry-ui:latest "/run.sh" 15 hours ago Up 15 hours 0.0.0.0:8000->8000/tcp schema-registry-ui
95acca24d698 confluentinc/cp-schema-registry:5.4.0 "/etc/confluent/dock…" 15 hours ago Up 15 hours 0.0.0.0:8081->8081/tcp schema-registry
58e7a0d307d2 confluentinc/cp-kafka:5.4.0 "/etc/confluent/dock…" 15 hours ago Up 15 hours 0.0.0.0:9092->9092/tcp, 0.0.0.0:29092->29092/tcp broker
1b4b6dec57e9 kibana:5.6.8 "/docker-entrypoint.…" 15 hours ago Up 15 hours 0.0.0.0:5601->5601/tcp kibana
61a90895e756 neo4j:4.0.6 "/sbin/tini -g -- /d…" 15 hours ago Up 15 hours 0.0.0.0:7474->7474/tcp, 7473/tcp, 0.0.0.0:7687->7687/tcp neo4j
5b7ab8c768c1 confluentinc/cp-zookeeper:5.4.0 "/etc/confluent/dock…" 15 hours ago Up 15 hours 2888/tcp, 0.0.0.0:2181->2181/tcp, 3888/tcp zookeeper
da9188c1035f elasticsearch:5.6.8 "/docker-entrypoint.…" 15 hours ago Up 15 hours 0.0.0.0:9200->9200/tcp, 9300/tcp elasticsearch
49252b1240b8 mysql:5.7 "docker-entrypoint.s…" 15 hours ago Up 15 hours 0.0.0.0:3306->3306/tcp, 33060/tcp mysql
docker内切换阿里源及安装vim方法，在下面报错5还有个在加载docker时修改的方案
#切换阿里源
echo -e "deb http://mirrors.ustc.edu.cn/debian buster main contrib non-free \n\
deb http://mirrors.ustc.edu.cn/debian buster-backports main contrib non-free \n\
deb http://mirrors.ustc.edu.cn/debian buster-proposed-updates main contrib non-free \n\
deb http://mirrors.ustc.edu.cn/debian-security buster/updates main contrib non-free \n" \
> /etc/apt/sources.list
root@mysql:/# apt-get clean
root@mysql:/# apt-get update
Get:1 http://mirrors.ustc.edu.cn/debian buster InRelease [121 kB]
Get:2 http://mirrors.ustc.edu.cn/debian buster-backports InRelease [46.7 kB]
Get:3 http://mirrors.ustc.edu.cn/debian buster-proposed-updates InRelease [54.5 kB]
Get:4 http://mirrors.ustc.edu.cn/debian-security buster/updates InRelease [65.4 kB]
Get:5 http://mirrors.ustc.edu.cn/debian buster/non-free amd64 Packages [87.7 kB]
Get:6 http://mirrors.ustc.edu.cn/debian buster/contrib amd64 Packages [50.2 kB]
Hit:7 http://repo.mysql.com/apt/debian buster InRelease
Get:8 http://mirrors.ustc.edu.cn/debian buster/main amd64 Packages [7907 kB]
Get:9 http://mirrors.ustc.edu.cn/debian buster-backports/non-free amd64 Packages [29.0 kB]
Get:10 http://mirrors.ustc.edu.cn/debian buster-backports/contrib amd64 Packages [7816 B]
Get:11 http://mirrors.ustc.edu.cn/debian buster-backports/main amd64 Packages [410 kB]
Get:12 http://mirrors.ustc.edu.cn/debian buster-proposed-updates/main amd64 Packages [50.1 kB]
Get:13 http://mirrors.ustc.edu.cn/debian-security buster/updates/main amd64 Packages [260 kB]
Get:14 http://mirrors.ustc.edu.cn/debian-security buster/updates/non-free amd64 Packages [556 B]
Fetched 9090 kB in 4s (2509 kB/s)
Reading package lists... Done
#安装vim
apt-get update，
这个命令的作用是：同步 /etc/apt/sources.list 和 /etc/apt/sources.list.d 中列出的源的索引，这样才能获取到最新的软件包。
等更新完毕 apt-get install vim命令即可。
登录mysql方法
docker exec -it mysql /usr/bin/mysql datahub --user=datahub --password=datahub
查看所有镜像
docker images
1、启动所有容器
docker start $(docker ps -a | awk '{ print $1}' | tail -n +2)
2、关闭所有容器
docker stop $(docker ps -a | awk '{ print $1}' | tail -n +2)
3、删除所有容器
docker rm $(docker ps -a | awk '{ print $1}' | tail -n +2)
4、删除所有镜像（慎用）
docker rmi $(docker images | awk '{print $3}' |tail -n +2)
systemctl status docker
docker container ls
检查各个Docker容器日志docker logs <<container_name>>。
对于datahub-gms，您应该在初始化结束时看到类似以下的日志：
docker logs datahub-gms
2020-02-06 09:20:54.870:INFO:oejs.Server:main: Started @18807ms
对于datahub-frontend，您应该在初始化结束时看到类似以下的日志：
docker logs datahub-frontend
09:20:22 [main] INFO play.core.server.AkkaHttpServer - Listening for HTTP on /0.0.0.0:9001
运行.docker/ingestion/ingestion.sh 报错4
[root@ares datahub]# ./docker/ingestion/ingestion.sh
WARNING: Native build is an experimental feature and could change at any time
WARNING: Found orphan containers (datahub-mae-consumer, schema-registry-ui, broker, kafka-setup, kafka-topics-ui, datahub-frontend, mysql, datahub-mce-consumer, kafka-rest-proxy, neo4j, kibana, elasticsearch-setup, datahub-gms, elasticsearch, schema-registry, zookeeper) for this project. If you removed or renamed this service in your compose file, you can run this command with the --remove-orphans flag to clean it up.
Building ingestion
[+] Building 86.4s (9/11)
=> [internal] load build definition from Dockerfile 0.0s
=> => transferring dockerfile: 32B 0.0s
=> [internal] load .dockerignore 0.0s
=> => transferring context: 35B 0.0s
=> [internal] load metadata for docker.io/library/openjdk:8 3.7s
=> [internal] load metadata for docker.io/library/openjdk:8-jre-alpine 4.7s
=> [prod-build 1/3] FROM docker.io/library/openjdk:8@sha256:c1dcc499d35d74a93c6cbfb1819a88bd588e06741d23f9a1962f636799d77822 0.0s
=> [internal] load build context 0.5s
=> => transferring context: 385.15kB 0.4s
=> CACHED [base 1/1] FROM docker.io/library/openjdk:8-jre-alpine@sha256:f362b165b870ef129cbe730f29065ff37399c0aa8bcab3e44b51c302938c9193 0.0s
=> CACHED [prod-build 2/3] COPY . datahub-src 0.0s
=> ERROR [prod-build 3/3] RUN cd datahub-src && ./gradlew :metadata-ingestion-examples:mce-cli:build 81.2s
------
> [prod-build 3/3] RUN cd datahub-src && ./gradlew :metadata-ingestion-examples:mce-cli:build:
#9 0.579 Downloading https://services.gradle.org/distributions/gradle-5.6.4-bin.zip
#9 4.484 .........................................................................................
#9 32.15
#9 32.15 Welcome to Gradle 5.6.4!
#9 32.15
#9 32.15 Here are the highlights of this release:
#9 32.15 - Incremental Groovy compilation
#9 32.15 - Groovy compile avoidance
#9 32.15 - Test fixtures for Java projects
#9 32.15 - Manage plugin versions via settings script
#9 32.15
#9 32.15 For more details see https://docs.gradle.org/5.6.4/release-notes.html
#9 32.15
#9 32.34 To honour the JVM settings for this build a new JVM will be forked. Please consider using the daemon: https://docs.gradle.org/5.6.4/userguide/gradle_daemon.html.
#9 33.84 Daemon will be stopped at the end of the build stopping after processing
#9 36.74 Configuration on demand is an incubating feature.
#9 80.64
#9 80.64 FAILURE: Build failed with an exception.
#9 80.64
#9 80.64 * What went wrong:
#9 80.64 A problem occurred configuring root project 'datahub-src'.
#9 80.64 > Could not resolve all artifacts for configuration ':classpath'.
#9 80.64 > Could not resolve com.linkedin.pegasus:gradle-plugins:28.3.7.
#9 80.64 Required by:
#9 80.64 project :
#9 80.64 > Could not resolve com.linkedin.pegasus:gradle-plugins:28.3.7.
#9 80.64 > Could not get resource 'https://linkedin.bintray.com/maven/com/linkedin/pegasus/gradle-plugins/28.3.7/gradle-plugins-28.3.7.pom'.
#9 80.64 > Could not GET 'https://linkedin.bintray.com/maven/com/linkedin/pegasus/gradle-plugins/28.3.7/gradle-plugins-28.3.7.pom'.
#9 80.64 > linkedin.bintray.com: Temporary failure in name resolution
#9 80.64
#9 80.64 * Try:
#9 80.64 Run with --stacktrace option to get the stack trace. Run with --info or --debug option to get more log output. Run with --scan to get full insights.
#9 80.64
#9 80.64 * Get more help at https://help.gradle.org
#9 80.64
#9 80.64 BUILD FAILED in 1m 20s
------
executor failed running [/bin/sh -c cd datahub-src && ./gradlew :metadata-ingestion-examples:mce-cli:build]: exit code: 1
ERROR: Service 'ingestion' failed to build
解决方案1:
1确认运行目录是在datahub的根目录下
在目录下新建一个文件
vim sources.list
deb http://mirrors.ustc.edu.cn/debian buster main contrib non-free
deb http://mirrors.ustc.edu.cn/debian buster-backports main contrib non-free
deb http://mirrors.ustc.edu.cn/debian buster-proposed-updates main contrib non-free
deb http://mirrors.ustc.edu.cn/debian-security buster/updates main contrib non-free
2.修改./docker/ingestion/Dockerfile
cat ./docker/ingestion/Dockerfile
# Defining environment
ARG APP_ENV=prod
FROM openjdk:8-jre-alpine as base
FROM openjdk:8 as prod-build
COPY . datahub-src
COPY sources.list /etc/apt/sources.list
#为阿里云的地址
RUN apt-get update
#更新
RUN ls /etc/apt/sources.list
RUN cd datahub-src && ./gradlew :metadata-ingestion-examples:mce-cli:build
FROM base as prod-install
COPY --from=prod-build datahub-src/metadata-ingestion-examples/mce-cli/build/libs/mce-cli.jar /datahub/ingestion/bin/mce-cli.jar
COPY --from=prod-build datahub-src/metadata-ingestion-examples/mce-cli/example-bootstrap.json /datahub/ingestion/example-bootstrap.json
FROM base as dev-install
# Dummy stage for development. Assumes code is built on your machine and mounted to this image.
# See this excellent thread https://github.com/docker/cli/issues/1134
FROM ${APP_ENV}-install as final
CMD java -jar /datahub/ingestion/bin/mce-cli.jar -m produce /datahub/ingestion/example-bootstrap.json
3.多次运行./docker/ingestion/ingestion.sh
报错5
Step 1/7 : FROM jwilder/dockerize:0.6.1
---> 849596ab86ff
Step 2/7 : RUN apk add --no-cache curl jq
---> [Warning] IPv4 forwarding is disabled. Networking will not work.
解决方案
第一步：在宿主机上执行echo "net.ipv4.ip_forward=1" >>/usr/lib/sysctl.d/00-system.conf
第二步：重启network和docker服务
[root@localhost /]# systemctl restart network && systemctl restart docker
截图留念
图片.png
图片.png
