Update kafka ansible role

- use kraft instead of zookeeper
- add handlers in case of cfg changes
- create a separate user for the kafka service
- bump kafka version
- make the role more configurable

data/ansible/roles/cgrates/tasks/main.yaml

@@ -5,7 +5,6 @@
     name: "{{ cgrates_dependencies }}"
     state: present
     update_cache: yes
-    cache_valid_time: 86400
 
 - name: Create cgrates directory
   ansible.builtin.file:

data/ansible/roles/kafka/defaults/main.yaml

@@ -1,5 +1,23 @@
 ---
-kafka_version: 3.5.0
-scala_version: 2.13
-kafka_service_state: started
-kafka_service_enabled: true
+kafka_download_base_url: https://downloads.apache.org/kafka
+kafka_download_validate_certs: yes
+kafka_version: 3.6.0
+kafka_scala_version: 2.13
+
+# The kafka user and group to create files/dirs with and for running the kafka service
+kafka_create_user_group: true
+kafka_user: kafka
+kafka_group: kafka
+
+kafka_root_dir: /opt
+kafka_dir: "{{ kafka_root_dir }}/kafka"
+kafka_unit_path: /lib/systemd/system/kafka.service
+
+# Start kafka after installation
+kafka_start: yes
+
+# Restart kafka on configuration change
+kafka_restart: yes
+
+# A comma separated list of directories under which to store data log files
+kafka_data_log_dirs: /var/lib/kafka/kraft-combined-logs

data/ansible/roles/kafka/handlers/main.yaml

@@ -0,0 +1,7 @@
+---
+- name: Restart Kafka
+  systemd:
+    name: kafka
+    state: restarted
+    daemon_reload: yes
+  when: kafka_restart | bool

data/ansible/roles/kafka/tasks/main.yaml

@@ -6,39 +6,112 @@
     state: present
     update_cache: yes
 
+- name: Create kafka group
+  become: yes
+  group:
+    name: "{{ kafka_group }}"
+    state: present
+    system: yes
+  when: kafka_create_user_group | bool
+
+- name: Create kafka user
+  become: yes
+  user:
+    name: "{{ kafka_user }}"
+    group: "{{ kafka_group }}"
+    state: present
+    createhome: no
+    system: yes
+  when: kafka_create_user_group | bool
+
+- name: Check if Kafka has already been downloaded and unpacked
+  stat:
+    path: "{{ kafka_dir }}_{{ kafka_scala_version }}-{{ kafka_version }}"
+  register: dir
+
 - name: Download Apache Kafka
   get_url:
-    url: "https://downloads.apache.org/kafka/{{ kafka_version }}/kafka_{{ scala_version }}-{{ kafka_version }}.tgz"
-    dest: "/tmp/kafka_{{ scala_version }}-{{ kafka_version }}.tgz"
-    mode: '0755'
+    url: "{{ kafka_download_base_url }}/{{ kafka_version }}/kafka_{{ kafka_scala_version }}-{{ kafka_version }}.tgz"
+    dest: /tmp
+    validate_certs: "{{ kafka_download_validate_certs }}"
+  when: not dir.stat.exists
 
-- name: Extract Apache Kafka
+- name: Unpack Apache Kafka
   become: yes
   unarchive:
-    src: "/tmp/kafka_{{ scala_version }}-{{ kafka_version }}.tgz"
-    dest: "/usr/local"
+    src: /tmp/kafka_{{ kafka_scala_version }}-{{ kafka_version }}.tgz
+    dest: "{{ kafka_root_dir }}"
     remote_src: yes
-    creates: "/usr/local/kafka_{{ scala_version }}-{{ kafka_version }}"
+    group: "{{ kafka_group }}"
+    owner: "{{ kafka_user }}"
+  when: not dir.stat.exists
 
-- name: Ensure Kafka and Zookeeper services are created
+- name: Create symlink to kafka installation directory
+  become: yes
+  file:
+    src: "{{ kafka_root_dir }}/kafka_{{ kafka_scala_version }}-{{ kafka_version }}"
+    dest: "{{ kafka_dir }}"
+    state: link
+    group: "{{ kafka_group }}"
+    owner: "{{ kafka_user }}"
+
+- name: Create directory for kafka data log files
+  become: yes
+  file:
+    path: "{{ item }}"
+    state: directory
+    group: "{{ kafka_group }}"
+    owner: "{{ kafka_user }}"
+    mode: 0755
+  with_items: "{{ kafka_data_log_dirs.split(',') }}"
+
+- name: Template configuration file to kraft server.properties
   become: yes
   template:
-    src: "{{ item.service_file }}"
-    dest: "/etc/systemd/system/{{ item.service_name }}"
-    owner: root
-    group: root
-    mode: '0644'
-  loop:
-    - { service_file: 'zookeeper.service.j2', service_name: 'zookeeper.service' }
-    - { service_file: 'kafka.service.j2', service_name: 'kafka.service' }
+    src: server.properties.j2
+    dest: "{{ kafka_dir }}/config/kraft/server.properties"
+    group: "{{ kafka_group }}"
+    owner: "{{ kafka_user }}"
+    mode: 0644
+  notify:
+    - Restart Kafka
 
-- name: Enable Kafka and Zookeeper services
+- name: Check if kraft logs dir has been initialized
+  shell: "{{ kafka_dir }}/bin/kafka-storage.sh info -c {{ kafka_dir }}/config/kraft/server.properties"
+  register: storage_info
+  ignore_errors: yes
+
+- name: Generate a random UUID for KAFKA_CLUSTER_ID if necessary
+  command: "{{ kafka_dir }}/bin/kafka-storage.sh random-uuid"
+  register: kafka_cluster_id
+  changed_when: false
+  when: '"is not formatted" in storage_info.stdout'
+
+- name: Init kraft logs dir
   become: yes
-  systemd:
-    name: "{{ item }}"
-    state: "{{ kafka_service_state }}"
-    enabled: "{{ kafka_service_enabled }}"
-    daemon_reload: yes
-  loop:
-    - zookeeper
-    - kafka
+  shell: "{{ kafka_dir }}/bin/kafka-storage.sh format -t {{ kafka_cluster_id.stdout }} -c {{ kafka_dir }}/config/kraft/server.properties"
+  when: '"is not formatted" in storage_info.stdout'
+
+- name: Template kafka systemd service
+  become: yes
+  template:
+    src: kafka.service.j2
+    dest: "{{ kafka_unit_path }}"
+    group: "{{ kafka_group }}"
+    owner: "{{ kafka_user }}"
+    mode: 0644
+  notify:
+    - Restart Kafka
+
+- name: Install and start the kafka service
+  become: yes
+  service:
+    name: kafka
+    state: started
+    enabled: yes
+  when: kafka_start
+
+- name: Delete the kafka archive file
+  file:
+    path: /tmp/kafka_{{ kafka_scala_version }}-{{ kafka_version }}.tgz
+    state: absent

data/ansible/roles/kafka/templates/kafka.service.j2

@@ -1,13 +1,17 @@
 [Unit]
-Description=Apache Kafka Server
+Description=Apache Kafka
 Documentation=http://kafka.apache.org/documentation.html
-Requires=zookeeper.service
+Requires=network.target
+After=network.target
 
 [Service]
 Type=simple
-Environment="JAVA_HOME=/usr/lib/jvm/java-11-openjdk-amd64"
-ExecStart=/usr/local/kafka_{{ scala_version }}-{{ kafka_version }}/bin/kafka-server-start.sh /usr/local/kafka_{{ scala_version }}-{{ kafka_version }}/config/server.properties
-ExecStop=/usr/local/kafka_{{ scala_version }}-{{ kafka_version }}/bin/kafka-server-stop.sh
+ExecStart={{ kafka_dir }}/bin/kafka-server-start.sh {{ kafka_dir }}/config/kraft/server.properties
+ExecStop={{ kafka_dir }}/bin/kafka-server-stop.sh
+User={{ kafka_user }}
+Group={{ kafka_group }}
+Restart=on-abnormal
 
 [Install]
 WantedBy=multi-user.target
+Alias=kafka.service

data/ansible/roles/kafka/templates/server.properties.j2

@@ -0,0 +1,132 @@
+# 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.
+
+#
+# This configuration file is intended for use in KRaft mode, where
+# Apache ZooKeeper is not present.
+#
+
+############################# Server Basics #############################
+
+# The role of this server. Setting this puts us in KRaft mode
+process.roles=broker,controller
+
+# The node id associated with this instance's roles
+node.id=1
+
+# The connect string for the controller quorum
+controller.quorum.voters=1@localhost:9093
+
+############################# Socket Server Settings #############################
+
+# The address the socket server listens on.
+# Combined nodes (i.e. those with `process.roles=broker,controller`) must list the controller listener here at a minimum.
+# If the broker listener is not defined, the default listener will use a host name that is equal to the value of java.net.InetAddress.getCanonicalHostName(),
+# with PLAINTEXT listener name, and port 9092.
+#   FORMAT:
+#     listeners = listener_name://host_name:port
+#   EXAMPLE:
+#     listeners = PLAINTEXT://your.host.name:9092
+listeners=PLAINTEXT://:9092,CONTROLLER://:9093
+
+# Name of listener used for communication between brokers.
+inter.broker.listener.name=PLAINTEXT
+
+# Listener name, hostname and port the broker will advertise to clients.
+# If not set, it uses the value for "listeners".
+advertised.listeners=PLAINTEXT://localhost:9092
+
+# A comma-separated list of the names of the listeners used by the controller.
+# If no explicit mapping set in `listener.security.protocol.map`, default will be using PLAINTEXT protocol
+# This is required if running in KRaft mode.
+controller.listener.names=CONTROLLER
+
+# 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=CONTROLLER:PLAINTEXT,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_data_log_dirs }}
+
+# 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 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

data/ansible/roles/kafka/templates/zookeeper.service.j2

@@ -1,14 +0,0 @@
-[Unit]
-Description=Apache Zookeeper server
-Documentation=http://zookeeper.apache.org
-Requires=network.target remote-fs.target
-After=network.target remote-fs.target
-
-[Service]
-Type=simple
-ExecStart=/usr/local/kafka_{{ scala_version }}-{{ kafka_version }}/bin/zookeeper-server-start.sh /usr/local/kafka_{{ scala_version }}-{{ kafka_version }}/config/zookeeper.properties
-ExecStop=/usr/local/kafka_{{ scala_version }}-{{ kafka_version }}/bin/zookeeper-server-stop.sh
-Restart=on-abnormal
-
-[Install]
-WantedBy=multi-user.target