supervisior安装配置

supervisior基础介绍

      supervisord    是后台管理服务器,用来依据配置文件的策略管理后台守护进程,它会随着系统自动启动

      supervisorctl  用于管理员向后台管理程序发送 启动 重启  停止  等指令

supervisorctl介绍

     执行supervisorctl指令的时候指定配置文件

     sudo   supervisorctl   -c    /home/admin/supervisor/etc/supervisord.conf status

     sudo supervisorctl -c /home/admin/supervisor/etc/supervisord.conf restart jlogstash

 启动用户权限问题

     如果是supervisior是以root用户启动的,那么普通用户就不能直接使用supervisorctl命令来操作supervisiord进程

 启动说明

supervisor注册成系统服务

      1.安装supervisor

      2.把supervisor注册成系统服务

      3.把所有的业务进程注册到supervisor中来统一管理

# taishi enterprise supervisord service for systemd (CentOS 7.0+)
[Unit]
Description=taishi Enterprise Supervisor daemon
After=taishi.service

[Service]
Type=forking
LimitNOFILE=655350
LimitNPROC=655350
ExecStart=/bin/bash __install_dir__/etc/start_taishi.sh
ExecStop=/usr/bin/supervisorctl $OPTIONS shutdown
ExecReload=/usr/bin/supervisorctl $OPTIONS reload
KillMode=process
Restart=no
RestartSec=42s

[Install]
WantedBy=multi-user.target

taishi.service

#!/bin/bash

# add hostname into /etc/hosts if necessary
os_version=`cat /etc/redhat-release | grep -oE '[0-9]+\.[0-9\.]+'`
os_major_version=${os_version:0:1}
if [ $os_major_version -eq "7" ];then
    hostname=`/usr/bin/hostname`
else
    hostname=`/bin/hostname`
fi
ping -c 1 -q $hostname > /dev/null 2>&1
if [ $? -ne 0 ]; then
    echo "127.0.0.1 $hostname" >> /etc/hosts
fi


if [ -e __install_dir__/jdk ]; then
    setcap cap_net_bind_service=+epi __install_dir__/jdk/bin/java
fi

# chmod in order to support license check
chmod u+s `which dmidecode`

#elasticsearch memory locking
ulimit -l unlimited
/usr/bin/supervisord -c __install_dir__/etc/supervisord.conf

start-taishi.sh

#Hansight Enterprise supervisor config file.

[unix_http_server]
file=__install_dir__/tmp/supervisor.sock   ; (the path to the socket file)
chown=__user__                              ;

[inet_http_server]          ; inet (TCP) server disabled by default
port=*:9001                 ; (ip_address:port specifier, *:port for all iface)
;username=user              ; (default is no username (open server))
;password=123               ; (default is no password (open server)

[supervisord]
logfile=__install_dir__/logs/supervisord.log ; (main log file;default $CWD/supervisord.log)
logfile_maxbytes=50MB        ; (max main logfile bytes b4 rotation;default 50MB)
logfile_backups=10           ; (num of main logfile rotation backups;default 10)
loglevel=info                ; (log level;default info; others: debug,warn,trace)
pidfile=__install_dir__/tmp/supervisord.pid ; (supervisord pidfile;default supervisord.pid)
nodaemon=false               ; (start in foreground if true;default false)
user=__user__               ; (default is current user, required if root)
minfds=655350                ; (min. avail startup file descriptors;default 1024)
minprocs=655350              ; (min. avail process descriptors;default 200)
;umask=022                   ; (process file creation umask;default 022)
;user=hansight               ; (default is current user, required if root)
;identifier=supervisor       ; (supervisord identifier, default is 'supervisor')
;directory=/tmp              ; (default is not to cd during start)
;nocleanup=true              ; (don't clean up tempfiles at start;default false)
;childlogdir=/tmp            ; ('AUTO' child log dir, default $TEMP)
;environment=KEY="value"     ; (key value pairs to add to environment)
;strip_ansi=false            ; (strip ansi escape codes in logs; def. false)

[rpcinterface:supervisor]
supervisor.rpcinterface_factory = supervisor.rpcinterface:make_main_rpcinterface

[supervisorctl]
serverurl=unix://__install_dir__/tmp/supervisor.sock ; use a unix:// URL  for a unix socket

[include]
files=__install_dir__/etc/supervisord/*.ini

supervisord.conf

function Install_Supervisor()
{
    #Install supervisord
    cd ../src/supervisor/
    tar -zxvf setuptools-24.0.2.tar.gz 2>&1 >/dev/null
    cd setuptools-24.0.2/
    python setup.py install >/dev/null 2>&1
    cd ..
    easy_install elementtree-1.2.7-20070827-preview.zip >/dev/null 2>&1
    easy_install meld3-0.6.5.tar.gz 2>/dev/null 2>&1
    easy_install supervisor-3.3.0.tar.gz >/dev/null 2>&1
    cd ../../script/
    mkdir -p ${INSTALL_DIR}/etc/
    cp ../etc/supervisord.conf ${INSTALL_DIR}/etc/
    sed -i "s#__install_dir__#${INSTALL_DIR}#g" ${INSTALL_DIR}/etc/supervisord.conf
    sed -i "s#__user__#${USER}#g" ${INSTALL_DIR}/etc/supervisord.conf
    ln -s /usr/bin/supervisorctl ${INSTALL_DIR}/hanctl
}

function Registration_System_Services()
{
    cp ../etc/start_taishi.sh ${INSTALL_DIR}/etc/
    sed -i "s#__install_dir__#${INSTALL_DIR}#g" ${INSTALL_DIR}/etc/start_taishi.sh
    sed -i "s#__user__#${USER}#g" ${INSTALL_DIR}/etc/start_taishi.sh
    chown ${USER}:${USER} ${INSTALL_DIR}/etc/start_taishi.sh
    if [ ${os_major_version} -eq "7" ];then
        \cp ../etc/taishi.service ../tmp/taishi.service
        #注册成service
        sed -i "s#__install_dir__#${INSTALL_DIR}#g" ../tmp/taishi.service
        cp ../tmp/taishi.service /etc/systemd/system/
        chown ${USER}:${USER} /etc/systemd/system/taishi.service
        chmod 644 /etc/systemd/system/taishi.service
        systemctl daemon-reload
    else
        #centos6上的注册服务形式
        \cp ../etc/hanent ../tmp/hanent
        #注册成service
        sed -i "s#__install_dir__#${INSTALL_DIR}#g" ../tmp/hanent
        cp ../tmp/hanent /etc/init.d/
        chown ${USER}:${USER} /etc/init.d/hanent
        chmod 755 /etc/init.d/hanent
        chkconfig --add hanent
    fi
}

安装脚本

 systemctl start taishi

supervisor使用场景

       supervisor比较适合监控业务应用,且只能监控前台程序,实现的daemon【后台启动】的程序不能用它监控,否则supervisor> status 会提示：BACKOFF  Exited too quickly (process log may have details)

       /app/chuangfa/taishi/zookeeper/bin/zkServer.sh   start        后台方式运行 supervisor无法监控

       /app/chuangfa/taishi/zookeeper/bin/zkServer.sh     start-foreground   前台方式运行才能使用supervisor监控

       /usr/sbin/nginx -c /app/chuangfa/taishi/etc/nginx.conf -g "daemon off;"    以前台方式运行nginx进程

       /usr/sbin/nginx -c /app/chuangfa/taishi/etc/nginx.conf                                后台方式启动nginx 无法被监控到

      注册新的管理进程
               supervisorctl update

       重启所有进程
                supervisorctl reload

Supervisor管理java应用

    在supervisor的ini配置目录中添加配置启动文件

[program:admin]
directory=/home/admin/app
command=java -jar -Xmx2048m -Xms2048m -XX:MetaspaceSize=128m -XX:MaxMetaspaceSize=256m admin-dev.jar
priority=120
process_name=%(program_name)s
autostart=true
startsecs=60
user=admin
redirect_stderr=true
stdout_logfile_maxbytes=10MB
stdout_logfile_backups=10
stdout_logfile=/home/admin/supervisor/logs/admin_supervisord.log

admin.ini

   添加好配置文件后就表示此程序已经可以被supervisor管理起来

script {
              
                res = sh(script: "ansible webservers --user=admin -m shell -a 'supervisorctl restart register'", returnStatus: true)
                if(res != 0){
                   error("register服务启动失败,本次发布流程终止")
                }
               

                
                //sh "ansible webservers --user=admin -m shell -a '/home/admin/app/start-gateway.sh'"
               // res = sh(script: "ansible webservers --user=admin -m shell -a '/home/admin/app/start-gateway.sh'", returnStdout: true)
                 //if (res.contains("Start Fail")){
                   //   error("gateway服务启动失败,本次发布流程终止")
                //}
                
                 res = sh(script: "ansible webservers --user=admin -m shell -a 'supervisorctl restart gateway'", returnStatus: true)
                 if(res != 0){
                     error("gateway服务启动失败,本次发布流程终止")
                 }
                
                
                 
                 res = sh(script: "ansible webservers --user=admin -m shell -a 'supervisorctl restart admin'", returnStatus: true)
                 if(res != 0){
                     error("admin服务启动失败,本次发布流程终止")
                 }
                

                 res = sh(script: "ansible webservers --user=admin -m shell -a 'supervisorctl restart sdccollectconfig'", returnStatus: true)
                 if(res != 0){
                     error("sdccollectconfig服务启动失败,本次发布流程终止")
                 }
                 
                 
                 res = sh(script: "ansible webservers --user=admin -m shell -a 'supervisorctl restart sdcruleconfig'", returnStatus: true)
                 if(res != 0){
                     error("sdc-rule-config服务启动失败,本次发布流程终止")
                 }
                 
                 
                 res = sh(script: "ansible webservers --user=admin -m shell -a 'supervisorctl restart sdces'", returnStatus: true)
                 if(res != 0){
                     error("sdces服务启动失败,本次发布流程终止")
                 }
              }

流水线  

    通过流水线脚本自动重启相关服务

supervisor启动时候找不到命令

    directory=/app/taishi/app/register-center
    command=/bin/bash -c 'source "$0" && exec "$@"' /etc/profile java -jar -Xmx2048m -Xms2048m -Dspring.profiles.active=prod -XX:MetaspaceSize=128m -        XX:MaxMetaspaceSize=256m register-center-prod.jar

     成功启动java -jar

supervisor通信方式

       supervisor通常有以下两种方式通信：
        1、本地socket
        2、http连接   默认通过rpc连接9001端口进行通信
             在supervisor.conf配置文件中，启用socket连接，注释http方式，supervisorctl配置项也使用unix socket

supervisor管理进程重启策略

supervisor更新服务进程

     supervisor修改管理服务的ini文件后 不能直接重启 直接重启服务不会生效
     必须先执行supervisorctl update