monit守护进程使用

nix-env -iA nixpkgs.monit
# 帮助文档
export MANPATH=~/.nix-profile/share/man/:$MANPATH
  • 默认配置文件 ~/.monitrc

###############################################################################
## Monit control file
###############################################################################
##
## Comments begin with a '#' and extend through the end of the line. Keywords
## are case insensitive. All path's MUST BE FULLY QUALIFIED, starting with '/'.
##
## Below you will find examples of some frequently used statements. For
## information about the control file and a complete list of statements and
## options, please have a look in the Monit manual.
##
##
###############################################################################
## Global section
###############################################################################
##
## Start Monit in the background (run as a daemon):
#
set daemon  30              # check services at 30 seconds intervals
#   with start delay 240    # optional: delay the first check by 4-minutes (by
#                           # default Monit check immediately after Monit start)
#
#
## Set syslog logging. If you want to log to a standalone log file instead,
## specify the full path to the log file
#
# set log syslog
set log /home/jcleng/desktop/work/moint/monit.log
#
#
## Set the location of the Monit lock file which stores the process id of the
## running Monit instance. By default this file is stored in $HOME/.monit.pid
#
set pidfile /tmp/monit.pid
#
## Set the location of the Monit id file which stores the unique id for the
## Monit instance. The id is generated and stored on first Monit start. By
## default the file is placed in $HOME/.monit.id.
#
set idfile /tmp/.monit.id
#
## Set the location of the Monit state file which saves monitoring states
## on each cycle. By default the file is placed in $HOME/.monit.state. If
## the state file is stored on a persistent filesystem, Monit will recover
## the monitoring state across reboots. If it is on temporary filesystem, the
## state will be lost on reboot which may be convenient in some situations.
#
# set statefile /var/.monit.state
#
#

## Set limits for various tests. The following example shows the default values:
##
# set limits {
#     programOutput:     512 B,      # check program's output truncate limit
#     sendExpectBuffer:  256 B,      # limit for send/expect protocol test
#     fileContentBuffer: 512 B,      # limit for file content test
#     httpContentBuffer: 1 MB,       # limit for HTTP content test
#     networkTimeout:    5 seconds   # timeout for network I/O
#     programTimeout:    300 seconds # timeout for check program
#     stopTimeout:       30 seconds  # timeout for service stop
#     startTimeout:      30 seconds  # timeout for service start
#     restartTimeout:    30 seconds  # timeout for service restart
# }

## Set global SSL options (just most common options showed, see manual for
## full list).
#
# set ssl {
#     verify     : enable, # verify SSL certificates (disabled by default but STRONGLY RECOMMENDED)
#     selfsigned : allow   # allow self signed SSL certificates (reject by default)
# }
#
#
## Set the list of mail servers for alert delivery. Multiple servers may be
## specified using a comma separator. If the first mail server fails, Monit
# will use the second mail server in the list and so on. By default Monit uses
# port 25 - it is possible to override this with the PORT option.
#
# set mailserver mail.bar.baz,               # primary mailserver
#                backup.bar.baz port 10025,  # backup mailserver on port 10025
#                localhost                   # fallback relay
#
#
## By default Monit will drop alert events if no mail servers are available.
## If you want to keep the alerts for later delivery retry, you can use the
## EVENTQUEUE statement. The base directory where undelivered alerts will be
## stored is specified by the BASEDIR option. You can limit the queue size
## by using the SLOTS option (if omitted, the queue is limited by space
## available in the back end filesystem).
#
# set eventqueue
#     basedir /var/monit  # set the base directory where events will be stored
#     slots 100           # optionally limit the queue size
#
#
## Send status and events to M/Monit (for more information about M/Monit
## see https://mmonit.com/). By default Monit registers credentials with
## M/Monit so M/Monit can smoothly communicate back to Monit and you don't
## have to register Monit credentials manually in M/Monit. It is possible to
## disable credential registration using the commented out option below.
## Though, if safety is a concern we recommend instead using https when
## communicating with M/Monit and send credentials encrypted. The password
## should be URL encoded if it contains URL-significant characters like
## ":", "?", "@". Default timeout is 5 seconds, you can customize it by
## adding the timeout option.
#
# set mmonit http://monit:[email protected]:8080/collector
#     # with timeout 30 seconds              # Default timeout is 5 seconds
#     # and register without credentials     # Don't register credentials
#
#
## Monit by default uses the following format for alerts if the mail-format
## statement is missing::
## --8<--
## set mail-format {
##   from:    Monit <monit@$HOST>
##   subject: monit alert --  $EVENT $SERVICE
##   message: $EVENT Service $SERVICE
##                 Date:        $DATE
##                 Action:      $ACTION
##                 Host:        $HOST
##                 Description: $DESCRIPTION
##
##            Your faithful employee,
##            Monit
## }
## --8<--
##
## You can override this message format or parts of it, such as subject
## or sender using the MAIL-FORMAT statement. Macros such as $DATE, etc.
## are expanded at runtime. For example, to override the sender, use:
#
# set mail-format { from: [email protected] }
#
#
## You can set alert recipients whom will receive alerts if/when a
## service defined in this file has errors. Alerts may be restricted on
## events by using a filter as in the second example below.
#
# set alert [email protected]                       # receive all alerts
#
## Do not alert when Monit starts, stops or performs a user initiated action.
## This filter is recommended to avoid getting alerts for trivial cases.
#
# set alert [email protected] not on { instance, action }
#
#
## Monit has an embedded HTTP interface which can be used to view status of
## services monitored and manage services from a web interface. The HTTP
## interface is also required if you want to issue Monit commands from the
## command line, such as 'monit status' or 'monit restart service' The reason
## for this is that the Monit client uses the HTTP interface to send these
## commands to a running Monit daemon. See the Monit Wiki if you want to
## enable SSL for the HTTP interface.
#
set httpd port 2812 and
    use address localhost  # only accept connection from localhost (drop if you use M/Monit)
    allow localhost        # allow localhost to connect to the server and
    allow admin:jcleng789      # require user 'admin' with password 'monit'
    #with ssl {            # enable SSL/TLS and set path to server certificate
    #    pemfile: /etc/ssl/certs/monit.pem
    #}
#
## Monit can perform act differently regarding services previous state when
## going back in duty. By default, Monit will 'start' all services. Monit can
## also takes no action to start services in 'nostart' mode. Monit can try to
## restore the 'laststate' of the service when Monit was shutdown.
# set onreboot start # start, nostart, laststart

###############################################################################
## Services
###############################################################################
##
## Check general system resources such as load average, cpu and memory
## usage. Each test specifies a resource, conditions and the action to be
## performed should a test fail.
#
#  check system $HOST
#    if loadavg (1min) per core > 2 for 5 cycles then alert
#    if loadavg (5min) per core > 1.5 for 10 cycles then alert
#    if cpu usage > 95% for 10 cycles then alert
#    if memory usage > 75% then alert
#    if swap usage > 25% then alert
#
#
## Check if a file exists, checksum, permissions, uid and gid. In addition
## to alert recipients in the global section, customized alert can be sent to
## additional recipients by specifying a local alert handler. The service may
## be grouped using the GROUP option. More than one group can be specified by
## repeating the 'group name' statement.
#
#  check file apache_bin with path /usr/local/apache/bin/httpd
#    if failed checksum and
#       expect the sum 8f7f419955cefa0b33a2ba316cba3659 then unmonitor
#    if failed permission 755 then unmonitor
#    if failed uid "root" then unmonitor
#    if failed gid "root" then unmonitor
#    alert [email protected] on {
#           checksum, permission, uid, gid, unmonitor
#        } with the mail-format { subject: Alarm! }
#    group server
#
#
## Check that a process is running, in this case Apache, and that it respond
## to HTTP and HTTPS requests. Check its resource usage such as cpu and memory,
## and number of children. If the process is not running, Monit will restart
## it by default. In case the service is restarted very often and the
## problem remains, it is possible to disable monitoring using the TIMEOUT
## statement. This service depends on another service (apache_bin) which
## is defined above.
#
#  check process apache with pidfile /usr/local/apache/logs/httpd.pid
#    start program = "/etc/init.d/httpd start" with timeout 60 seconds
#    stop program  = "/etc/init.d/httpd stop"
#    if cpu > 60% for 2 cycles then alert
#    if cpu > 80% for 5 cycles then restart
#    if totalmem > 200.0 MB for 5 cycles then restart
#    if children > 250 then restart
#    if disk read > 500 kb/s for 10 cycles then alert
#    if disk write > 500 kb/s for 10 cycles then alert
#    if failed host www.tildeslash.com port 80 protocol http and request "/somefile.html" then restart
#    if failed port 443 protocol https with timeout 15 seconds then restart
#    if 3 restarts within 5 cycles then unmonitor
#    depends on apache_bin
#    group server
#
#
## Check filesystem permissions, uid, gid, space usage, inode usage and disk I/O.
## Other services, such as databases, may depend on this resource and an automatically
## graceful stop may be cascaded to them before the filesystem will become full and data
## lost.
#
#  check filesystem datafs with path /dev/sdb1
#    start program  = "/bin/mount /data"
#    stop program  = "/bin/umount /data"
#    if failed permission 660 then unmonitor
#    if failed uid "root" then unmonitor
#    if failed gid "disk" then unmonitor
#    if space usage > 80% for 5 times within 15 cycles then alert
#    if space usage > 99% then stop
#    if inode usage > 30000 then alert
#    if inode usage > 99% then stop
#    if read rate > 1 MB/s for 5 cycles then alert
#    if read rate > 500 operations/s for 5 cycles then alert
#    if write rate > 1 MB/s for 5 cycles then alert
#    if write rate > 500 operations/s for 5 cycles then alert
#    if service time > 10 milliseconds for 3 times within 5 cycles then alert
#    group server
#
#
## Check a file's timestamp. In this example, we test if a file is older
## than 15 minutes and assume something is wrong if its not updated. Also,
## if the file size exceed a given limit, execute a script
#
#  check file database with path /data/mydatabase.db
#    if failed permission 700 then alert
#    if failed uid "data" then alert
#    if failed gid "data" then alert
#    if timestamp > 15 minutes then alert
#    if size > 100 MB then exec "/my/cleanup/script" as uid dba and gid dba
#
#
## Check directory permission, uid and gid.  An event is triggered if the
## directory does not belong to the user with uid 0 and gid 0.  In addition,
## the permissions have to match the octal description of 755 (see chmod(1)).
#
#  check directory bin with path /bin
#    if failed permission 755 then unmonitor
#    if failed uid 0 then unmonitor
#    if failed gid 0 then unmonitor
#
#
## Check a remote host availability by issuing a ping test and check the
## content of a response from a web server. Up to three pings are sent and
## connection to a port and an application level network check is performed.
#
#  check host myserver with address 192.168.1.1
#    if failed ping then alert
#    if failed port 3306 protocol mysql with timeout 15 seconds then alert
#    if failed port 80 protocol http
#       and request /some/path with content = "a string"
#    then alert
#
#
## Check a network link status (up/down), link capacity changes, saturation
## and bandwidth usage.
#
#  check network public with interface eth0
#    if link down then alert
#    if changed link then alert
#    if saturation > 90% then alert
#    if download > 10 MB/s then alert
#    if total uploaded > 1 GB in last hour then alert
#
#
## Check custom program status output.
#
#  check program myscript with path /usr/local/bin/myscript.sh
#    if status != 0 then alert
#
#
###############################################################################
## Includes
###############################################################################
##
## It is possible to include additional configuration parts from other files or
## directories.
#
include /home/jcleng/desktop/work/moint/monit.d/*
#

  • 可访问端口2812进入管理界面

# 启动
monit
# 退出
monit quit
# 检查配置语法
monit -t
# 重载配置文件
monit reload

# 版本
monit --version
# This is Monit version 5.33.0
  • 检查周期时间间隔

set daemon  30 # check services at 30 seconds intervals
  • 管理端口

# 允许账户密码访问,不限制地址
set httpd port 2812 and
    allow admin:monit # require user 'admin' with password 'monit'
  • 使用include包含配置目录文件夹,创建.conf结尾的配置文件

# nginx.conf
check process nginx with pidfile /tmp/nginx.pid
   start program = "/home/jcleng/.nix-profile/bin/nginx -e /tmp/nginx.err -c /home/jcleng/desk/work/nginx/nginx.conf"
   stop  program = "/run/current-system/sw/bin/pkill nginx"
# mariadb1058.conf
check process mariadb1058 with pidfile /tmp/mariadb1058.pid
   start program = "/home/jcleng/.nix-profile/bin/mysqld_safe"
   stop  program = "/run/current-system/sw/bin/pkill mariadbd"
# phpfpm.conf
check process php-fpm with pidfile /tmp/php-fpm71.pid
   start program = "/home/jcleng/.nix-profile/bin/php-fpm -y /home/jcleng/desk/work/php-fpm/php-fpm.conf -c /home/jcleng/desk/work/php-fpm/php.ini"
   stop  program = "/run/current-system/sw/bin/pkill php-fpm"
# 监控端口访问状态并通知alert
check host myserver with address "127.0.0.1"
   if failed port 9999 protocol http then alert

# 流量下载速度监控
check network ens5 with interface ens5
   if DOWNLOAD > 1 MB/s then alert

# 检查总流量
check program check_total_net_down with path "/home/jcleng/desktop/work/moint/check_total_net_down.sh"
    if status != 0 for 5 cycles then alert
#!/usr/bin/env php
<?php
# nix-env -iA nixpkgs.php
date_default_timezone_set("Asia/Shanghai");

function alt($msg = '通知')
{
    throw new \Exception($msg . PHP_EOL . PHP_EOL);
}
function msg($msg = '')
{
    echo $msg;
}

function isH($Hi)
{
    $dateH = date('H:i');
    if ($Hi == $dateH) {
        return true;
    }
    return false;
}

function formatBytes($bytes, $precision = 2)
{
    $kb = 1024; // 1 KB = 1024 Bytes
    $mb = $kb * 1024; // 1 MB = 1024 KB
    $gb = $mb * 1024; // 1 GB = 1024 MB

    if ($bytes < $kb) {
        return $bytes . ' bytes';
    } elseif ($bytes < $mb) {
        return round($bytes / $kb, $precision) . ' KB';
    } elseif ($bytes < $gb) {
        return round($bytes / $mb, $precision) . ' MB';
    } else {
        return round($bytes / $gb, $precision) . ' GB';
    }
}

// 通过ifconfig获取网卡的信息
$result = [];
$eth = 'ens5'; // eth0
$max = 107374182400;

exec("ifconfig $eth", $result);
$line = $result[6];
$row = explode(' ', $line);
$bit = $row[13];
if (isH('08:30') || $bit > $max) {
    alt('下行流量: ' . formatBytes($bit));
} else {
    msg('下行流量: ' . formatBytes($bit));
}
  • 配置邮件通知,新增配置文件到include的目录 notice.conf

# 配置接收邮箱和事件, 文档说明[Setting an event filter], 默认是on全部, 每10个周期通知一次
set alert [email protected] only on { timeout, nonexist, status, timeout, connection } with reminder on 10 cycle

# 配置邮件服务器
set mailserver smtp.qq.com
port 465
username "[email protected]" password "qq邮箱授权码"
using tls
with timeout 30 seconds

# 配置邮件格式,from要和username的邮箱一致
set mail-format { from: [email protected] }
# 或者这样
set mail-format {
  from:    [email protected]
  subject: 监控通知 --  $EVENT $SERVICE
  message: $EVENT Service $SERVICE
                Date:        $DATE
                Action:      $ACTION
                Host:        $HOST
                Description: $DESCRIPTION

           Monit
}

# 检查端口
nix-shell -p inetutils
telnet smtp.qq.com 465
ping smtp.qq.com

# 其他异常: https://mmonit.com/wiki/Monit/Gmail
For monit <= 5.16:
using tlsv12
For monit 5.17 or later:
using tls
  • 创建一个带pid的sleep脚本,通过该程序实现定时通知

#!/usr/bin/env bash
case "$1" in
    start)
        echo "Starting hold runing..."
        sleep 86400 >> /tmp/health_check.log 2>&1 &
        echo $! > /tmp/health_check.pid
        ;;
    stop)
        echo "Stopping hold runing..."
        kill `cat /tmp/health_check.pid`
        rm -rf /tmp/health_check.pid
        ;;
    restart)
        $0 stop
        sleep 1
        $0 start
        ;;
    *)
        echo "Usage: $0 {start|stop|restart}"
        exit 1
        ;;
esac
exit 0
  • 定时重启服务并发送通知

#!/usr/bin/env bash
export TZ=Asia/Shanghai
date="08:50"
if [ "$(TZ=UTC+16 date +%H:%M)" = $date ]; then
    echo "当前时间是$date, 需要重启通知服务"
    exit 1
else
    echo "当前时间不是$date, 继续检测"
fi

check program everyday_notice with path "/home/jcleng/desktop/work/moint/everyday_notice.sh"
    if status != 0 then alert
  • php实现整点通知

touch time_check.sh
chmod +x time_check.sh
nano time_check.sh

#!/usr/bin/env php
<?php
# nix-env -iA nixpkgs.php
date_default_timezone_set("Asia/Shanghai");
function alt($msg = '通知')
{
    throw new \Exception($msg);
}
function msg($msg = '')
{
    echo $msg;
}


$date = date('Y-m-d H:i:s');
$dateI = date('i');
$dateH = date('H');
if ($dateI == '00' && $dateH > 8 && $dateH < 22) {
    alt('整点通知, 当前时间: ' . $date);
} else {
    msg('非整点: ' . $date);
}

time_check.conf

check program time_check with path "/home/jcleng/desktop/work/moint/time_check.sh"
    if status != 0 then alert
  • nixos使用

{ config, lib, pkgs, modulesPath, ... }:

{
  services.monit.enable = true;
  services.monit.config = "include /home/jcleng/desktop/work/moint/monit.d/*";
}

# 实际生成的 /etc/monitrc 文件内容:
include /home/jcleng/desktop/work/moint/monit.d/*

# 文件夹里面放一个主配置文件, 默认的配置文件,主要配置管理端口,日志,刷新间隔时间等
/home/jcleng/desktop/work/moint/monit.d/main.conf
# 放自己的文件
/home/jcleng/desktop/work/moint/monit.d/frpc.conf

# 还是通过 创建一个带pid的脚本 实现
check process frpc with pidfile /tmp/frp.pid
   start program = "/home/jcleng/desktop/work/moint/frp.sh start"
   stop program = "/home/jcleng/desktop/work/moint/frp.sh stop"


#!/run/current-system/sw/bin/bash
case "$1" in
    start)
        echo "Starting hold runing..."
        /home/jcleng/desk/work/frp/frp_0.47.0_linux_amd64/frpc -c /home/jcleng/desk/work/frp/frp_0.47.0_linux_amd64/frpc.ini >> /tmp/frp.log 2>&1 &
        echo $! > /tmp/frp.pid
        ;;
    stop)
        echo "Stopping hold runing..."
        kill `cat /tmp/frp.pid`
        rm -rf /tmp/frp.pid
        ;;
    restart)
        $0 stop
        sleep 1
        $0 start
        ;;
    *)
        echo "Usage: $0 {start|stop|restart}"
        exit 1
        ;;
esac
exit 0
  • 可以通过验证正则来验证所有的配置文件是否正确

monit procmatch "test"
monit procmatch "^.*frpc*"
# 配置文件的格式需要是lf