kafka install for ansible

$ tree roles/kafka
roles/kafka
├── tasks
│   ├── download.yml
│   ├── kafka.yml
│   ├── main.yml
│   └── zookeeper.yml
├── templates
│   ├── kafka.service.j2
│   ├── server.properties.j2
│   ├── zoo.cfg.j2
│   └── zookeeper.service.j2
└── vars
    └── main.yml

$ cat download.yml 
---
- name: Check if kafka tar file 
  stat:
    path: "/tmp/{{ kafka_tar_file }}"
  register: kafka_tar

- name: Check if zookeeper tar file
  stat:
    path: "/tmp/{{ zookeeper_tar_file }}"
  register: zookeeper_tar

- name: Download zookeeper
  get_url:
    url: "{{ zookeeper_download_url }}"
    dest: /tmp
    mode: 0755
  when: zookeeper_tar.stat.exists == False
  become: true  

- name: Download kafka
  get_url:
    url: "{{ kafka_download_url }}"
    dest: /tmp
    mode: 0755
  when: kafka_tar.stat.exists == False
  become: true
  
- name: Check kafka untar file
  stat: 
    path: "{{ kafka_base_dir }}"
  register: kafka_untar

- name: Unarchive kafka file
  unarchive:
    src: "/tmp/{{ kafka_tar_file }}"
    dest: /tmp
    remote_src: yes
    owner: root
    group: root
  when: kafka_untar.stat.exists == False
  become: true

- name: Check zookeeper untar file
  stat:
    path: "{{ zookeeper_base_dir }}"
  register: zookeeper_untar

- name: Unarchive zookeeper file
  unarchive:
    src: "/tmp/{{ zookeeper_tar_file }}"
    dest: /tmp
    remote_src: yes
    owner: root
    group: root
  when: zookeeper_untar.stat.exists == False
  become: true

- name: Mv kafka to /usr/local
  command: "mv {{ kafka_untar_dir }} {{ kafka_base_dir }}"
  args:
    chdir: /tmp
  when: kafka_untar.stat.exists == False
  become: true

- name: Mv zookeeper to /usr/local
  command: "mv {{ zookeeper_untar_dir }} {{ zookeeper_base_dir }}"
  args:
    chdir: /tmp
  when: zookeeper_untar.stat.exists == False
  become: true

$ cat zookeeper.yml 
---
- name: Create zookeeper dir
  file:
    path: "{{ item.path }}"
    state: directory
    mode: 0755
  with_items:
    - path: "{{ zookeeper_data_dir }}"
    - path: "{{ zookeeper_log_dir }}"
  become: true

- name: Create myid file
  file:
    path: "{{ zookeeper_data_dir }}/myid"
    state: touch
    mode: 0644
  become: true

- name: Set myid
  lineinfile:
    path: "{{ zookeeper_data_dir }}/myid"
    line: "{{ zookeeper_myid }}"
  become: true

- name: Copy zoo file
  template:
    src: zoo.cfg.j2
    dest: "{{ zookeeper_base_dir }}/conf/zoo.cfg"
  become: true

- name: Delete zoo_sample file
  file:
    path: "{{ zookeeper_base_dir }}/conf/zoo_sample.cfg"
    state: absent
  become: true

- name: Set hosts
  lineinfile:
    path: /etc/hosts
    line: "{{ item.host }} {{ item.domain }}"
  with_items: "{{ zookeeper_hosts }}"
  become: true

- name: Copy service file
  template:
    src: zookeeper.service.j2
    dest: /lib/systemd/system/zookeeper.service
  become: true

- name: Start zookeeper
  systemd:
    name: zookeeper
    state: restarted
    enabled: yes
    daemon_reload: yes
    masked: no
  become: true

$ cat kafka.yml 
---
- name: Create log dir
  file:
    path: "{{ kafka_log_dir }}"
    state: directory
    mode: 0755
  become: true

- name: Copy server.properties file
  template:
    src: server.properties.j2
    dest: "{{ kafka_base_dir }}/config/server.properties"
  become: true

- name: Copy service file
  template:
    src: kafka.service.j2
    dest: /lib/systemd/system/kafka.service
  become: true

- name: Start kafka
  systemd:
    name: kafka
    state: restarted
    enabled: yes
    daemon_reload: yes
    masked: no
  become: true

$ cat kafka.service.j2 
[Unit]
Description=Kafka
After=zookeeper.service

[Service]
Type=simple
Environment=LOG_DIR={{ kafka_log_dir }}
ExecStart={{ kafka_base_dir }}/bin/kafka-server-start.sh {{ kafka_base_dir }}/config/server.properties
ExecStop={{ kafka_base_dir }}/bin/kafka-server-stop.sh
Restart=always

[Install]
WantedBy=multi-user.target

$ cat zookeeper.service.j2 
[Unit]
Description=zookeeper.service
After=network.target

[Service]
Type=forking
Environment=ZOO_LOG_DIR={{ zookeeper_log_dir }}
ExecStart={{ zookeeper_base_dir }}/bin/zkServer.sh start
ExecStop={{ zookeeper_base_dir }}/bin/zkServer.sh stop
ExecReload={{ zookeeper_base_dir }}/bin/zkServer.sh restart

[Install]
WantedBy=multi-user.target

$ cat server.properties.j2 
# 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={{ broker_id }}     #设置broker id，默认从0开始

############################# 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 receive buffer (SO_RCVBUF) used by the socket server
socket.receive.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 separated list of directories under which to store log files
log.dirs={{ kafka_log_dir }}

# 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:
#    1. Durability: Unflushed data may be lost if you are not using replication.
#    2. Latency: Very large flush intervals may lead to latency spikes when the flush does occur as there will be a lot of data to flush.
#    3. Throughput: The flush is generally the most expensive operation, and a small flush interval may lead to excessive seeks.
# The settings below allow one to configure the flush policy to flush data after a period of time or
# every N messages (or both). This can be done globally and overridden on a per-topic basis.

# 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={{ zookeeper_connect }}    #设置连接zookeeper的地址

# 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

$ cat zoo.cfg.j2 
# The number of milliseconds of each tick
tickTime=2000
# The number of ticks that the initial 
# synchronization phase can take
initLimit=10
# The number of ticks that can pass between 
# sending a request and getting an acknowledgement
syncLimit=5
# the directory where the snapshot is stored.
# do not use /tmp for storage, /tmp here is just 
# example sakes.
dataDir={{ zookeeper_data_dir }}
# the zookeepr log dir
dataLogDir={{ zookeeper_log_dir }}
# the port at which the clients will connect
clientPort=2181
# the maximum number of client connections.
# increase this if you need to handle more clients
#maxClientCnxns=60
#
# Be sure to read the maintenance section of the 
# administrator guide before turning on autopurge.
#
# http://zookeeper.apache.org/doc/current/zookeeperAdmin.html#sc_maintenance
#
# The number of snapshots to retain in dataDir
autopurge.snapRetainCount=3
# Purge task interval in hours
# Set to "0" to disable auto purge feature
autopurge.purgeInterval=1
#
#add server cluster addr
{% for zookeeper_cluster in zookeeper_cluster_server %}
server.{{ zookeeper_cluster.id }}={{ zookeeper_cluster.host }}:2888:3888
{% endfor %}

$ cat main.yml 
kafka_untar_dir: kafka_2.11-2.1.0
zookeeper_untar_dir: zookeeper-3.4.12

kafka_tar_file: "{{ kafka_untar_dir }}.tgz"
zookeeper_tar_file: "{{ zookeeper_untar_dir }}.tar.gz"

kafka_download_url: "http://mirrors.hust.edu.cn/apache/kafka/2.1.0/{{ kafka_tar_file }}"
zookeeper_download_url: "http://mirrors.hust.edu.cn/apache/zookeeper/stable/{{ zookeeper_tar_file }}"

zookeeper_base_dir: /usr/local/zookeeper
kafka_base_dir: /usr/local/kafka

zookeeper_data_dir: "{{ zookeeper_base_dir }}/data"
kafka_data_dir: "{{ kafka_base_dir }}/data"

zookeeper_log_dir: "{{ zookeeper_base_dir }}/logs"
kafka_log_dir: "{{ kafka_base_dir }}/logs"


zookeeper_cluster_server:
  - id: 1
    host: zoo1.tianchiapi.com
  - id: 2
    host: zoo2.tianchiapi.com
  - id: 3
    host: zoo3.tianchiapi.com

zookeeper_hosts:
  - host: 10.0.3.150
    domain: zoo1.tianchiapi.com
  - host: 10.0.3.115
    domain: zoo2.tianchiapi.com
  - host: 10.0.3.116
    domain: zoo3.tianchiapi.com

zookeeper_connect: "zoo1.tianchiapi.com:2181,zoo2.tianchiapi.com:2181,zoo3.tianchiapi.com:2181"

$ cat setup.yml
- hosts: kafka
  roles: 
    - role: kafka

$ cat hosts
[kafka]
10.0.3.150 zookeeper_myid=1 broker_id=0
10.0.3.115 zookeeper_myid=2 broker_id=1
10.0.3.116 zookeeper_myid=3 broker_id=2