FROM ubuntu
MAINTAINER shaonaiyi shaonaiyi@163.com
ENV BUILD_ON 2019-01-28
RUN apt-get update -qqy
RUN apt-get -qqy install vim wget net-tools  iputils-ping  openssh-server
#添加JDK
MAINTAINER shaonaiyi shaonaiyi@163.com
ENV BUILD_ON 2019-03-12
RUN apt-get update -qqy
RUN apt-get -qqy install vim wget net-tools  iputils-ping  openssh-server
#添加JDK
ADD ./jdk-8u161-linux-x64.tar.gz /usr/local/
#添加hadoop
ADD ./hadoop-2.7.5.tar.gz  /usr/local/
#添加scala
ADD ./scala-2.11.8.tgz /usr/local/
#添加spark
ADD ./zookeeper-3.4.10.tar.gz /usr/local/
#添加HBase
ADD ./hbase-1.2.6-bin.tar.gz /usr/local/
#添加Hive
ADD ./apache-hive-2.3.3-bin.tar.gz /usr/local/
#添加Flume
ADD ./apache-flume-1.8.0-bin.tar.gz /usr/local/
#添加Kafka
ADD ./kafka_2.11-1.0.0.tgz /usr/local/
ENV CHECKPOINT 2019-03-12
#增加JAVA_HOME环境变量
ENV JAVA_HOME /usr/local/jdk1.8.0_161
#hadoop环境变量
ENV HADOOP_HOME /usr/local/hadoop-2.7.5
#scala环境变量
ENV SCALA_HOME /usr/local/scala-2.11.8
#spark环境变量
ENV SPARK_HOME /usr/local/spark-2.2.0-bin-hadoop2.7
#zk环境变量
ENV ZK_HOME /usr/local/zookeeper-3.4.10
#HBase环境变量
ENV HBASE_HOME /usr/local/hbase-1.2.6
#Hive环境变量
ENV HIVE_HOME /usr/local/apache-hive-2.3.3-bin
#Flume环境变量
ENV FLUME_HOME /usr/local/apache-flume-1.8.0-bin
#Kafka环境变量
ENV KAFKA_HOME /usr/local/kafka_2.11-1.0.0
#将环境变量添加到系统变量中
RUN ssh-keygen -t rsa -f ~/.ssh/id_rsa -P '' && \
    cat ~/.ssh/id_rsa.pub >> ~/.ssh/authorized_keys && \
    chmod 600 ~/.ssh/authorized_keys
#复制配置到/tmp目录
COPY config /tmp
#将配置移动到正确的位置
RUN mv /tmp/ssh_config    ~/.ssh/config && \
    mv /tmp/profile /etc/profile && \
    mv /tmp/masters $SPARK_HOME/conf/masters && \
    cp /tmp/slaves $SPARK_HOME/conf/ && \
    mv /tmp/spark-defaults.conf $SPARK_HOME/conf/spark-defaults.conf && \
    mv /tmp/spark-env.sh $SPARK_HOME/conf/spark-env.sh && \
    mv /tmp/hadoop-env.sh $HADOOP_HOME/etc/hadoop/hadoop-env.sh && \
    mv /tmp/hdfs-site.xml $HADOOP_HOME/etc/hadoop/hdfs-site.xml && \
    mv /tmp/core-site.xml $HADOOP_HOME/etc/hadoop/core-site.xml && \
    mv /tmp/yarn-site.xml $HADOOP_HOME/etc/hadoop/yarn-site.xml && \
    mv /tmp/mapred-site.xml $HADOOP_HOME/etc/hadoop/mapred-site.xml && \
    mv /tmp/master $HADOOP_HOME/etc/hadoop/master && \
    mv /tmp/slaves $HADOOP_HOME/etc/hadoop/slaves && \
    mv /tmp/start-hadoop.sh ~/start-hadoop.sh && \
    mv /tmp/init_zk.sh ~/init_zk.sh && \
    mkdir -p /usr/local/hadoop2.7/dfs/data && \
    mkdir -p /usr/local/hadoop2.7/dfs/name && \
    mkdir -p /usr/local/zookeeper-3.4.10/datadir && \
    mkdir -p /usr/local/zookeeper-3.4.10/log && \
    mv /tmp/zoo.cfg $ZK_HOME/conf/zoo.cfg && \
    mv /tmp/hbase-env.sh $HBASE_HOME/conf/hbase-env.sh && \
    mv /tmp/hbase-site.xml $HBASE_HOME/conf/hbase-site.xml  && \
    mv /tmp/regionservers $HBASE_HOME/conf/regionservers && \
    mv /tmp/hive-env.sh $HIVE_HOME/conf/hive-env.sh && \
    mv /tmp/flume-env.sh $FLUME_HOME/conf/flume-env.sh && \
    mv /tmp/server.properties $KAFKA_HOME/config/server.properties && \
    mv /tmp/init_kafka.sh ~/init_kafka.sh
RUN echo $JAVA_HOME
#设置工作目录
WORKDIR /root
#启动sshd服务
RUN /etc/init.d/ssh start
#修改start-hadoop.sh权限为700
RUN chmod 700 start-hadoop.sh
#修改init_zk.sh权限为700
RUN chmod 700 init_zk.sh
#修改init_kafka.sh权限为700
RUN chmod 700 init_kafka.sh
#修改root密码
RUN echo "root:shaonaiyi" | chpasswd
CMD ["/bin/bash"]

# 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.
# see kafka.server.KafkaConfig for additional details and defaults
############################# Server Basics #############################
# The id of the broker. This must be set to a unique integer for each broker.
broker.id=0
############################# Socket Server Settings #############################
# The address the socket server listens on. It will get the value returned from
# java.net.InetAddress.getCanonicalHostName() if not configured.
#   FORMAT:
#     listeners = listener_name://host_name:port
#   EXAMPLE:
#     listeners = PLAINTEXT://your.host.name:9092
#listeners=PLAINTEXT://:9092
# Hostname and port the broker will advertise to producers and consumers. If not set,
# it uses the value for "listeners" if configured.  Otherwise, it will use the value
# returned from java.net.InetAddress.getCanonicalHostName().
#advertised.listeners=PLAINTEXT://your.host.name:9092
# Maps listener names to security protocols, the default is for them to be the same. See the config documentation for more details
#listener.security.protocol.map=PLAINTEXT:PLAINTEXT,SSL:SSL,SASL_PLAINTEXT:SASL_PLAINTEXT,SASL_SSL:SASL_SSL
# The number of threads that the server uses for receiving requests from the network and sending responses to the network
num.network.threads=3
# The number of threads that the server uses for processing requests, which may include disk I/O
num.io.threads=8
# The send buffer (SO_SNDBUF) used by the socket server
socket.send.buffer.bytes=102400
# The maximum size of a request that the socket server will accept (protection against OOM)
socket.request.max.bytes=104857600
############################# Log Basics #############################
# A comma seperated list of directories under which to store log files
log.dirs=/root/logs/kafka-logs
# The default number of log partitions per topic. More partitions allow greater
# parallelism for consumption, but this will also result in more files across
# the brokers.
num.partitions=1
# The number of threads per data directory to be used for log recovery at startup and flushing at shutdown.
# This value is recommended to be increased for installations with data dirs located in RAID array.
num.recovery.threads.per.data.dir=1
############################# Internal Topic Settings  #############################
# The replication factor for the group metadata internal topics "__consumer_offsets" and "__transaction_state"
# For anything other than development testing, a value greater than 1 is recommended for to ensure availability such as 3.
offsets.topic.replication.factor=1
transaction.state.log.replication.factor=1
transaction.state.log.min.isr=1
############################# Log Flush Policy #############################
# Messages are immediately written to the filesystem but by default we only fsync() to sync
# the OS cache lazily. The following configurations control the flush of data to disk.
# There are a few important trade-offs here:
#    3. Throughput: The flush is generally the most expensive operation, and a small flush interval may lead to exceessive seeks.
# The number of messages to accept before forcing a flush of data to disk
#log.flush.interval.messages=10000
# The maximum amount of time a message can sit in a log before we force a flush
#log.flush.interval.ms=1000
############################# Log Retention Policy #############################
# The following configurations control the disposal of log segments. The policy can
# be set to delete segments after a period of time, or after a given size has accumulated.
# A segment will be deleted whenever *either* of these criteria are met. Deletion always happens
# from the end of the log.
# The minimum age of a log file to be eligible for deletion due to age
log.retention.hours=168
# A size-based retention policy for logs. Segments are pruned from the log unless the remaining
# segments drop below log.retention.bytes. Functions independently of log.retention.hours.
#log.retention.bytes=1073741824
# The maximum size of a log segment file. When this size is reached a new log segment will be created.
log.segment.bytes=1073741824
# The interval at which log segments are checked to see if they can be deleted according
# to the retention policies
log.retention.check.interval.ms=300000
############################# Zookeeper #############################
# Zookeeper connection string (see zookeeper docs for details).
# This is a comma separated host:port pairs, each corresponding to a zk
# server. e.g. "127.0.0.1:3000,127.0.0.1:3001,127.0.0.1:3002".
# You can also append an optional chroot string to the urls to specify the
# root directory for all kafka znodes.
zookeeper.connect=hadoop-master:2181,hadoop-slave1:2181,hadoop-slave2:2181
# Timeout in ms for connecting to zookeeper
zookeeper.connection.timeout.ms=6000
############################# Group Coordinator Settings #############################
# The following configuration specifies the time, in milliseconds, that the GroupCoordinator will delay the initial consumer rebalance.
# The rebalance will be further delayed by the value of group.initial.rebalance.delay.ms as new members join the group, up to a maximum of max.poll.interval.ms.
# The default value for this is 3 seconds.
# We override this to 0 here as it makes for a better out-of-the-box experience for development and testing.
# However, in production environments the default value of 3 seconds is more suitable as this will help to avoid unnecessary, and potentially expensive, rebalances during application startup.
group.initial.rebalance.delay.ms=0

export KAFKA_HOME=/usr/local/kafka_2.11-1.0.0
export PATH=$PATH:$KAFKA_HOME/bin

#!/bin/bash
# 将某个文件中的"broker.id=0"字符串替换为"broker.id=x",master这句可删除
ssh root@hadoop-master "sed -i 's/broker.id=0/broker.id=0/g' $KAFKA_HOME/config/server.properties"
ssh root@hadoop-slave1 "sed -i 's/broker.id=0/broker.id=1/g' $KAFKA_HOME/config/server.properties"
ssh root@hadoop-slave2 "sed -i 's/broker.id=0/broker.id=2/g' $KAFKA_HOME/config/server.properties"