我是如何优雅设计 OpenIM 多进程管理策略的

healthcheck:
  test: ["CMD-SHELL", "./scripts/check-all.sh"]
  interval: 30s
  timeout: 10s
  retries: 5

apt install supervisor || yum install supervisor

files = /etc/supervisor/conf.d/*.conf

files = /opt/supervisord.d/*.ini   

;进程名称 即项目名
[program:test]

;脚本目录 运行的进程文件目录
directory=/opt/ytgMateriel/materialBackend

;启动命令 此处为java的jar 启动命令
command=/opt/jdk1.8.0_171/bin/java -Xms512m -Xmx1024m -jar -Dspring.profiles.active=prd -Djava.io.tmpdir=./tmp -Dloader.path=lib ytg-material-backend.jar

;停止进程的命令 默认 quit
stopsignal=KILL

;supervisor启动的时候是否随着同时启动，默认True   
;当程序exit的时候，这个program不会自动重启,默认unexpected，设置子进程挂掉后自动重启的情况，有三个选项，false,unexpected和true。如果为false的时候，无论什么情况下，都不会被重新启动，如果为unexpected，只有当进程的退出码不在下面的exitcodes里面定义的 
autorestart=true

;这个选项是子进程启动多少秒之后，此时状态如果是running，则我们认为启动成功了。默认值为1
startsecs=3

;日志
stdout_logfile=/opt/ytgMateriel/materialBackend/logs/ytg-material-backend.log

;stdout日志文件大小，默认 50MB
stdout_logfile_maxbytes=100MB

;stdout日志文件备份数
stdout_logfile_backups=50
user = root

;把stderr重定向到stdout，默认 false
redirect_stderr=true

supervisord -c /etc/supervisord.conf

supervisorctl status        //查看所有进程的状态
supervisorctl stop 进程名       //停止es
supervisorctl start 进程名      //启动es
supervisorctl restart 进程名      //重启es
supervisorctl update        //配置文件修改后使用该命令加载新的配置
supervisorctl reload        //重新启动配置中的所有程序

; group.target
[Unit]
Description=Application
Wants=prog1.service prog2.service

; prog1.service
[Unit]
Description=prog1
PartOf=group.target

[Service]
ExecStart=/usr/bin/prog1
Restart=on-failure

; prog2.service
[Unit]
Description=prog2
PartOf=group.target

[Service]
ExecStart=/usr/bin/prog2
Restart=on-failure

[program:prog1]
command=python /home/user/myapp/prog1.py

[program:prog2]
command=python /home/user/myapp/prog2.py

[group:prog]
programs=prog1,prog2

[Unit]
Description=Ping service %i

[Service]
Type=simple
ExecStart=/usr/bin/ping %i

[Install]
WantedBy=multi-user.target

[Unit]
Description=Ping service %i

[Service]
Type=simple
ExecStart=/usr/bin/ping 127.0.0.%i

[Install]
WantedBy=multi-user.target

# cat /etc/systemd/system/C.service
[Unit]
Description=C Process
Requires=B.service
After=B.service

[Service]
Type=simple
ExecStart=/export/CProgram

[Install]
WantedBy=multi-user.target

# cat /etc/systemd/system/B.service
[Unit]
Description=B Process
Requires=A.service
After=A.service

[Service]
Type=simple
ExecStart=/export/BProgram

[Install]
WantedBy=multi-user.target

# cat /etc/systemd/system/A.service
[Unit]
Description=A Process

[Service]
Type=simple
ExecStart=/export/AProgram

[Install]
WantedBy=multi-user.target

# 查看所有日志（默认情况下 ，只保存本次启动的日志）
$ sudo journalctl

# 查看内核日志（不显示应用日志）
$ sudo journalctl -k

# 查看系统本次启动的日志
$ sudo journalctl -b
$ sudo journalctl -b -0

# 查看上一次启动的日志（需更改设置）
$ sudo journalctl -b -1

# 查看指定时间的日志
$ sudo journalctl --since="2012-10-30 18:17:16"
$ sudo journalctl --since "20 min ago"
$ sudo journalctl --since yesterday
$ sudo journalctl --since "2015-01-10" --until "2015-01-11 03:00"
$ sudo journalctl --since 09:00 --until "1 hour ago"

# 显示尾部的最新10行日志
$ sudo journalctl -n

# 显示尾部指定行数的日志
$ sudo journalctl -n 20

# 实时滚动显示最新日志
$ sudo journalctl -f

# 查看指定服务的日志
$ sudo journalctl /usr/lib/systemd/systemd

# 查看指定进程的日志
$ sudo journalctl _PID=1

# 查看某个路径的脚本的日志
$ sudo journalctl /usr/bin/bash

# 查看指定用户的日志
$ sudo journalctl _UID=33 --since today

# 查看某个 Unit 的日志
$ sudo journalctl -u nginx.service
$ sudo journalctl -u nginx.service --since today

# 实时滚动显示某个 Unit 的最新日志
$ sudo journalctl -u nginx.service -f

# 合并显示多个 Unit 的日志
$ journalctl -u nginx.service -u php-fpm.service --since today

# 查看指定优先级（及其以上级别）的日志，共有8级
# 0: emerg
# 1: alert
# 2: crit
# 3: err
# 4: warning
# 5: notice
# 6: info
# 7: debug
$ sudo journalctl -p err -b

# 日志默认分页输出，--no-pager 改为正常的标准输出
$ sudo journalctl --no-pager

# 以 JSON 格式（单行）输出
$ sudo journalctl -b -u nginx.service -o json

# 以 JSON 格式（多行）输出，可读性更好
$ sudo journalctl -b -u nginx.serviceqq
 -o json-pretty

# 显示日志占据的硬盘空间
$ sudo journalctl --disk-usage

# 指定日志文件占据的最大空间
$ sudo journalctl --vacuum-size=1G

# 指定日志文件保存多久
$ sudo journalctl --vacuum-time=1years

example@instance1.service

$ sudo systemctl daemon-reload

#!/usr/bin/env bash

# Copyright © 2023 OpenIM. All rights reserved.
#
# Licensed 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.
# 
# OpenIM CronTask Control Script
# 
# Description:
# This script provides a control interface for the OpenIM CronTask service within a Linux environment. It supports two installation methods: installation via function calls to systemctl, and direct installation through background processes.
# 
# Features:
# 1. Robust error handling leveraging Bash built-ins such as 'errexit', 'nounset', and 'pipefail'.
# 2. Capability to source common utility functions and configurations, ensuring environmental consistency.
# 3. Comprehensive logging tools, offering clear operational insights.
# 4. Support for creating, managing, and interacting with Linux systemd services.
# 5. Mechanisms to verify the successful running of the service.
#
# Usage:
# 1. Direct Script Execution:
#    This will start the OpenIM CronTask directly through a background process.
#    Example: ./openim-crontask.sh openim::crontask::start
# 
# 2. Controlling through Functions for systemctl operations:
#    Specific operations like installation, uninstallation, and status check can be executed by passing the respective function name as an argument to the script.
#    Example: ./openim-crontask.sh openim::crontask::install
# 
# Note: Ensure that the appropriate permissions and environmental variables are set prior to script execution.
# 

OPENIM_ROOT=$(cd "$(dirname "${BASH_SOURCE[0]}")"/../.. && pwd -P)
[[ -z ${COMMON_SOURCED} ]] && source "${OPENIM_ROOT}"/scripts/install/common.sh

SERVER_NAME="openim-crontask"

function openim::crontask::start()
{
    openim::log::info "Start OpenIM Cron, binary root: ${SERVER_NAME}"
    openim::log::status "Start OpenIM Cron, path: ${OPENIM_CRONTASK_BINARY}"

    openim::util::stop_services_with_name ${SERVER_NAME}

    openim::log::status "start cron_task process, path: ${OPENIM_CRONTASK_BINARY}"
    nohup ${OPENIM_CRONTASK_BINARY} >> ${LOG_FILE} 2>&1 &
    openim::util::check_process_names ${SERVER_NAME}
}

###################################### Linux Systemd ######################################
SYSTEM_FILE_PATH="/etc/systemd/system/${SERVER_NAME}.service"

# Print the necessary information after installation
function openim::crontask::info() {
cat << EOF
openim-crontask listen on: ${OPENIM_CRONTASK_HOST}
EOF
}

# install openim-crontask
function openim::crontask::install()
{
  pushd "${OPENIM_ROOT}"

  # 1. Build openim-crontask
  make build BINS=${SERVER_NAME}
  openim::common::sudo "cp ${OPENIM_OUTPUT_HOSTBIN}/${SERVER_NAME} ${OPENIM_INSTALL_DIR}/bin"

  openim::log::status "${SERVER_NAME} binary: ${OPENIM_INSTALL_DIR}/bin/${SERVER_NAME}"

  # 2. Generate and install the openim-crontask configuration file (openim-crontask.yaml)
  echo ${LINUX_PASSWORD} | sudo -S bash -c \
    "./scripts/genconfig.sh ${ENV_FILE} deployments/templates/${SERVER_NAME}.yaml > ${OPENIM_CONFIG_DIR}/${SERVER_NAME}.yaml"
  openim::log::status "${SERVER_NAME} config file: ${OPENIM_CONFIG_DIR}/${SERVER_NAME}.yaml"

  # 3. Create and install the ${SERVER_NAME} systemd unit file
  echo ${LINUX_PASSWORD} | sudo -S bash -c \
    "./scripts/genconfig.sh ${ENV_FILE} deployments/templates/init/${SERVER_NAME}.service > ${SYSTEM_FILE_PATH}"
  openim::log::status "${SERVER_NAME} systemd file: ${SYSTEM_FILE_PATH}"

  # 4. Start the openim-crontask service
  openim::common::sudo "systemctl daemon-reload"
  openim::common::sudo "systemctl restart ${SERVER_NAME}"
  openim::common::sudo "systemctl enable ${SERVER_NAME}"
  openim::crontask::status || return 1
  openim::crontask::info

  openim::log::info "install ${SERVER_NAME} successfully"
  popd
}


# Unload
function openim::crontask::uninstall()
{
  set +o errexit
  openim::common::sudo "systemctl stop ${SERVER_NAME}"
  openim::common::sudo "systemctl disable ${SERVER_NAME}"
  openim::common::sudo "rm -f ${OPENIM_INSTALL_DIR}/bin/${SERVER_NAME}"
  openim::common::sudo "rm -f ${OPENIM_CONFIG_DIR}/${SERVER_NAME}.yaml"
  openim::common::sudo "rm -f /etc/systemd/system/${SERVER_NAME}.service"
  set -o errexit
  openim::log::info "uninstall ${SERVER_NAME} successfully"
}

# Status Check
function openim::crontask::status()
{
  # Check the running status of the ${SERVER_NAME}. If active (running) is displayed, the ${SERVER_NAME} is started successfully.
  systemctl status ${SERVER_NAME}|grep -q 'active' || {
    openim::log::error "${SERVER_NAME} failed to start, maybe not installed properly"
    return 1
  }

  # The listening port is hardcode in the configuration file
  if echo | telnet 127.0.0.1 7070 2>&1|grep refused &>/dev/null;then
    openim::log::error "cannot access health check port, ${SERVER_NAME} maybe not startup"
    return 1
  fi
}

if [[ "$*" =~ openim::crontask:: ]];then
  eval $*
fi

[Unit]
Description=OPENIM OPENIM CRONTASK
Documentation=Manages the OpenIM CronTask service, with both direct and systemctl installation methods.
Documentation=https://github.com/OpenIMSDK/Open-IM-Server/blob/main/deployment/init/README.md

[Service]
WorkingDirectory=${OPENIM_DATA_DIR}/openim-crontask
ExecStartPre=/usr/bin/mkdir -p ${OPENIM_DATA_DIR}/openim-crontask
ExecStartPre=/usr/bin/mkdir -p ${OPENIM_LOG_DIR}
ExecStart=${OPENIM_INSTALL_DIR}/bin/openim-crontask -c=${OPENIM_CONFIG_DIR}
Restart=always
RestartSec=5
StartLimitInterval=0

[Install]
WantedBy=multi-user.target