Nagios安装部署

Nagios工作原理

Nagios主要配置文件

Nagios软件包

链接：http://pan.baidu.com/s/1skGSBIP 密码：6fwr

Nagios服务端环境及依赖

cat /etc/redhat-release
CentOS release 6.6 (Final)
uname -rm
2.6.32-504.el6.x86_64 x86_64
echo "export LC_ALL=C" >> /etc/profile  # 恢复默认语言环境
tail -1 /etc/profile
source /etc/profile
echo $LC_ALL
yum install gcc glibc glibc-common gd-devel mysql-server httpd php php-gd -y
rpm -qa mysql httpd php
useradd nagios
groupadd nagcmd
usermod -a -G nagcmd nagios
usermod -a -G nagcmd apache
groups nagios
groups apache

 Nagios服务端主程序安装

mkdir -p /server/tools/nagios
cd /server/tools/nagios
rz -y   #上传软件包
tree /server/tools/nagios
/etc/init.d/httpd start
lsof -i :80
tar xf nagios-3.5.1.tar.gz
cd nagios
./configure --with-command-group=nagcmd
make all
make install
make install-init
make install-config
make install-commandmode
make install-webconf
cd ..
htpasswd -bc /usr/local/nagios/etc/htpasswd.users peter 123456
cat /usr/local/nagios/etc/htpasswd.users
/etc/init.d/httpd reload
sed -i 's#nagios@localhost#asdftttt@163.com#g' /usr/local/nagios/etc/objects/contacts.cfg
sed -n '35p' /usr/local/nagios/etc/objects/contacts.cfg
echo -e "set from=asdftttt@163.com\nset smtp=smtp.163.com smtp-auth-user=asdftttt smtp-auth-password=xxxxx smtp-auto=login" >> /etc/mail.rc
echo "#time sync by peter at 2017-9-14" >> /var/spool/cron/root      #时间同步
echo "*/5 * * * * /usr/sbin/ntpdate time.nist.gov > /dev/null 2>&1" >> /var/spool/cron/root
crontab -l
/etc/init.d/httpd restart
chkconfig httpd on
netstat -nutlp | grep httpd
#网页
172.16.1.53/nagios

 Nagios插件包安装

yum install perl-devel perl-CPAN openssl-devel -y
cd /server/tools/nagios
tar xf nagios-plugins-1.4.16.tar.gz
cd nagios-plugins-1.4.16
./configure --with-nagios-user=nagios --with-nagios-group=nagios --enable-perl-modules --with-mysql
make
make install
cd ..
ls /usr/local/nagios/libexec/ | wc -l
59 #也可能61

Nrpe软件安装

tar xf nrpe-2.12.tar.gz
cd nrpe-2.12
./configure
make all
make install-plugin
make install-daemon
make install-daemon-config
cd ..
ls /usr/local/nagios/libexec/check_nrpe  #服务端安装nrpe是为了获得check_nrpe插件

Nagios服务端配置和启动

chkconfig nagios on
chkconfig --list nagios
/etc/init.d/nagios checkconfig
Running configuration check... OK.
/usr/local/nagios/bin/nagios -v /usr/local/nagios/etc/nagios.cfg
vim /etc/init.d/nagios +183
$NagiosBin -v $NagiosCfgFile
/etc/init.d/nagios checkconfig
/etc/init.d/nagios start
Starting nagios: done.
ps -ef | grep nagios
nagios    47748      1  0 15:22 ?        00:00:00 /usr/local/nagios/bin/nagios -d /usr/local/nagios/etc/nagios.cfg

 Nagios客户端环境准备（web01 web02）

yum install gcc glibc glibc-common mysql-server perl-devel perl-CPAN openssl-devel -y
mkdir -p /server/tools/nagios
cd /server/tools/nagios
rz -y
useradd nagios -M -s /sbin/nologin

 Nagios插件包安装

tar xf nagios-plugins-1.4.16.tar.gz
cd nagios-plugins-1.4.16
./configure --with-nagios-user=nagios --with-nagios-group=nagios --enable-perl-modules --with-mysql
make
make install
cd ..
ls /usr/local/nagios/libexec/ | wc -l

Nrpe服务安装

tar xf nrpe-2.12.tar.gz
cd nrpe-2.12
./configure
make all
make install-plugin
make install-daemon
make install-daemon-config
cd ..

 安装check_iostat插件依赖包

for n in Params-Validate-0.91 Class-Accessor-0.31 Config-Tiny-2.12 Math-Calc-Units-1.07 Regexp-Common-2010010201 Nagios-Plugin-0.34
do 
tar xf ${n}.tar.gz
cd $n
perl Makefile.PL
make 
make install 
cd ..
done

 配置监控内存、磁盘I/O脚本插件

yum install -y sysstat dos2unix 
cp /server/tools/nagios/check_memory.pl /usr/local/nagios/libexec
cp /server/tools/nagios/check_iostat /usr/local/nagios/libexec
chmod 755 /usr/local/nagios/libexec/check_memory.pl
chmod 755 /usr/local/nagios/libexec/check_iostat 
dos2unix /usr/local/nagios/libexec/check_memory.pl
dos2unix /usr/local/nagios/libexec/check_iostat

客户端Nrpe服务配置

cd /usr/local/nagios/etc
sed -i 's#allowed_hosts=127.0.0.1#allowed_hosts=127.0.0.1,172.16.1.53#g' nrpe.cfg
vim nrpe.cfg +199
#删掉原来的
command[check_load]=/usr/local/nagios/libexec/check_load -w 15,10,5 -c 30,25,20
command[check_mem]=/usr/local/nagios/libexec/check_memory.pl -w 10% -c 3%
command[check_disk]=/usr/local/nagios/libexec/check_disk -w 15% -c 7% -p /
command[check_swap]=/usr/local/nagios/libexec/check_swap -w 20% -c 10%
command[check_iostat]=/usr/local/nagios/libexec/check_iostat -w 6 -c 10

/usr/local/nagios/bin/nrpe -c /usr/local/nagios/etc/nrpe.cfg -d
netstat -nutlp | grep nrpe
tcp        0      0 0.0.0.0:5666                0.0.0.0:*                   LISTEN      39042/nrpe         

#重启nrpe
pkill nrpe
/usr/local/nagios/bin/nrpe -c /usr/local/nagios/etc/nrpe.cfg -d

#加入开机启动
echo "#nagios nrpe process cmd by peter 2017-08-31" >> /etc/rc.local
echo "/usr/local/nagios/bin/nrpe -c /usr/local/nagios/etc/nrpe.cfg -d" >> /etc/rc.local
tail -2 /etc/rc.local

Nagios服务端配置文件设置

vim /usr/local/nagios/etc/nagios.cfg +34

cfg_file=/usr/local/nagios/etc/objects/hosts.cfg
cfg_file=/usr/local/nagios/etc/objects/services.cfg
cfg_dir=/usr/local/nagios/etc/objects/services             #该目录下只要以.cfg结尾都会被加载
# Definitions for monitoring the local (Linux) host
#cfg_file=/usr/local/nagios/etc/objects/localhost.cfg

cd /usr/local/nagios/etc/objects/
head -51 localhost.cfg > hosts.cfg
chown nagios.nagios /usr/local/nagios/etc/objects/hosts.cfg
touch services.cfg
chown nagios.nagios services.cfg
mkdir services
chown -R nagios.nagios services

vim hosts.cfg

# Define a host for the local machine

define host{
        use                     linux-server            ; Name of host template to use
                                                        ; This host definition will inherit all variables that are defined
                                                        ; in (or inherited by) the linux-server host template definition.
        host_name               13-web01
        alias                   13-web01
        address                 172.16.1.13
        }

define host{
        use                     linux-server            ; Name of host template to use
                                                        ; This host definition will inherit all variables that are defined
                                                        ; in (or inherited by) the linux-server host template definition.
        host_name               14-web02
        alias                   14-web02
        address                 172.16.1.14
        }



# Define an optional hostgroup for Linux machines

define hostgroup{
        hostgroup_name  linux-servers ; The name of the hostgroup
        alias           Linux Servers ; Long name of the group
        members         13-web01,14-web02     ; Comma separated list of hosts that belong to this group
        }

vim services.cfg

define service {
        use                     generic-service
        host_name               13-web01,14-web02
        service_description     Disk Partition
        check_command           check_nrpe!check_disk
}
define service {
        use                     generic-service
        host_name               13-web01,14-web02
        service_description     Swap Usage
        check_command           check_nrpe!check_swap
}
define service {
        use                     generic-service
        host_name               13-web01,14-web02
        service_description     Mem Usage
        check_command           check_nrpe!check_mem
}
define service {
        use                     generic-service
        host_name               13-web01,14-web02
        service_description     Current Load
        check_command           check_nrpe!check_load
}
define service {
        use                     generic-service
        host_name               13-web01,14-web02
        service_description     Disk IOstat
        check_command           check_nrpe!check_iostat
}
define service {
        use                     generic-service
        host_name               13-web01,14-web02
        service_description     PING
        check_command           check_ping!100.0,20%!500.0,60%
}


vim commands.cfg

define command{
        command_name    check_nrpe
        command_line    $USER1$/check_nrpe -H $HOSTADDRESS$ -c $ARG1$
        }

/etc/init.d/nagios checkconfig
/etc/init.d/nagios start
/etc/init.d/nagios reload

cd /usr/local/nagios/etc
sed -i 's#nagiosadmin#peter#g' cgi.cfg
grep "^authorized_for" cgi.cfg 
/etc/init.d/nagios reload

#监控URL
vim objects/services.cfg

define service {
        use                     generic-service
        host_name               13-web01
        service_description     blog_url
        check_command           check_http!-H 172.16.1.13
}
define service {
        use                     generic-service
        host_name               14-web02
        service_description     blog_url
        check_command           check_http!-H 172.16.1.14
}

/etc/init.d/nagios checkconfig
/etc/init.d/nagios reload

#监控TCP端口
vim objects/services.cfg

define service {
        use                     generic-service
        host_name               13-web01,14-web02
        service_description     http_80
        check_command           check_tcp!80
}
define service {
        use                     generic-service
        host_name               13-web01,14-web02
        service_description     ssh_22
        check_command           check_tcp!22
}

/etc/init.d/nagios checkconfig
/etc/init.d/nagios reload

Nagios配置出图

yum install cairo pango zlib-devel freetype-devel  gd-devel libart_lgpl-devel rrdtool-devel perl-Time-HiRes -y
rpm -qa cairo pango zlib zlib-devel freetype freetype-devel gd gd-devel libart_lgpl libart_lgpl-devel rrdtool rrdtool-devel  perl-Time-HiRes
cd /server/tools/nagios/
tar xf pnp-0.4.14.tar.gz
cd pnp-0.4.14
./configure --with-rrdtool --with-perfdata-dir=/usr/local/nagios/share/perfdata/
make all
make install
make install-config
make install-init
ll /usr/local/nagios/libexec/ | grep process

vim /usr/local/nagios/etc/nagios.cfg +835

process_performance_data=1
...
host_perfdata_command=process-host-perfdata
service_perfdata_command=process-service-perfdata

vim /usr/local/nagios/etc/objects/commands.cfg +227

# 'process-host-perfdata' command definition
define command{
        command_name    process-host-perfdata
        command_line    /usr/local/nagios/libexec/process_perfdata.pl
        }

# 'process-service-perfdata' command definition
define command{
        command_name    process-service-perfdata
        command_line    /usr/local/nagios/libexec/process_perfdata.pl
        }

/etc/init.d/nagios checkconfig
/etc/init.d/nagios reload

#网页
172.16.1.53/nagios/pnp

vim /usr/local/nagios/etc/objects/hosts.cfg

# Define a host for the local machine

define host{
        use                     linux-server            ; Name of host template to use
                                                        ; This host definition will inherit all variables that are defined
                                                        ; in (or inherited by) the linux-server host template definition.
        host_name               13-web01
        alias                   13-web01
        address                 172.16.1.13
        process_perf_data       1
        }

define host{
        use                     linux-server            ; Name of host template to use
                                                        ; This host definition will inherit all variables that are defined
                                                        ; in (or inherited by) the linux-server host template definition.
        host_name               14-web02
        alias                   14-web02
        address                 172.16.1.14
        process_perf_data       1
        }

#service.cfg中每个服务下也要添加，但generic-service模板中已经定义好了

/etc/init.d/nagios checkconfig
/etc/init.d/nagios reload

#网页
172.16.1.53/nagios/pnp

 

整合PNP URL到Nagios Web界面

vim objects/hosts.cfg

# Define a host for the local machine

define host{
        use                     linux-server            ; Name of host template to use
                                                        ; This host definition will inherit all variables that are defined
                                                        ; in (or inherited by) the linux-server host template definition.
        host_name               13-web01
        alias                   13-web01
        address                 172.16.1.13
        process_perf_data       1
        action_url              /nagios/pnp/index.php?host=$HOSTNAME$
        }

define host{
        use                     linux-server            ; Name of host template to use
                                                        ; This host definition will inherit all variables that are defined
                                                        ; in (or inherited by) the linux-server host template definition.
        host_name               14-web02
        alias                   14-web02
        address                 172.16.1.14
        process_perf_data       1
        action_url              /nagios/pnp/index.php?host=$HOSTNAME$
        }

vim objects/templates.cfg
#直接配置services.cfg中使用的模板文件
define service{
        name                            generic-service         ; The 'name' of this service template
        active_checks_enabled           1                       ; Active service checks are enabled
        passive_checks_enabled          1                       ; Passive service checks are enabled/accepted
        parallelize_check               1                       ; Active service checks should be parallelized (disabling this can lead to major performance problems)
        obsess_over_service             1                       ; We should obsess over this service (if necessary)
        check_freshness                 0                       ; Default is to NOT check service 'freshness'
        notifications_enabled           1                       ; Service notifications are enabled
        event_handler_enabled           1                       ; Service event handler is enabled
        flap_detection_enabled          1                       ; Flap detection is enabled
        failure_prediction_enabled      1                       ; Failure prediction is enabled
        process_perf_data               1                       ; Process performance data
        retain_status_information       1                       ; Retain status information across program restarts
        retain_nonstatus_information    1                       ; Retain non-status information across program restarts
        is_volatile                     0                       ; The service is not volatile
        check_period                    24x7                    ; The service can be checked at any time of the day
        max_check_attempts              3                       ; Re-check the service up to 3 times in order to determine its final (hard) state
        normal_check_interval           10                      ; Check the service every 10 minutes under normal conditions
        retry_check_interval            2                       ; Re-check the service every two minutes until a hard state can be determined
        contact_groups                  admins                  ; Notifications get sent out to everyone in the 'admins' group
        notification_options            w,u,c,r                 ; Send notifications about warning, unknown, critical, and recovery events
        notification_interval           60                      ; Re-notify about service problems every hour
        notification_period             24x7                    ; Notifications can be sent out at any time
         register                        0                      ; DONT REGISTER THIS DEFINITION - ITS NOT A REAL SERVICE, JUST A TEMPLATE!
        action_url                      /nagios/pnp/index.php?host=$HOSTNAME$&srv=$SERVICEDESC$
        }

/etc/init.d/nagios checkconfig
/etc/init.d/nagios reload

#网页
172.16.1.53/nagios

#服务状态数据存放目录，注意备份
tree /usr/local/nagios/share/perfdata
/usr/local/nagios/share/perfdata
|-- 13-web01
|   |-- Current_Load.rrd
|   |-- Current_Load.xml
|   |-- Disk_IOstat.rrd
|   |-- Disk_IOstat.xml
|   |-- Disk_Partition.rrd
|   |-- Disk_Partition.xml
|   |-- Mem_Usage.rrd
|   |-- Mem_Usage.xml
|   |-- PING.rrd
|   |-- PING.xml
|   |-- Swap_Usage.rrd
|   |-- Swap_Usage.xml
|   |-- blog_url.rrd
|   |-- blog_url.xml
|   |-- http_80.rrd
|   |-- http_80.xml
|   |-- ssh_22.rrd
|   `-- ssh_22.xml
`-- 14-web02
    |-- Current_Load.rrd
    |-- Current_Load.xml
    |-- Disk_IOstat.rrd
    |-- Disk_IOstat.xml
    |-- Disk_Partition.rrd
    |-- Disk_Partition.xml
    |-- Mem_Usage.rrd
    |-- Mem_Usage.xml
    |-- PING.rrd
    |-- PING.xml
    |-- Swap_Usage.rrd
    |-- Swap_Usage.xml
    |-- blog_url.rrd
    |-- blog_url.xml
    |-- http_80.rrd
    |-- http_80.xml
    |-- ssh_22.rrd
    `-- ssh_22.xml

 

Nagios故障报警（邮件）

vim objects/contacts.cfg
        email                           asdftttt@163.com    
 
vim objects/commands.cfg
#优化一下报警信息
# 'notify-host-by-email' command definition
define command{
        command_name    notify-host-by-email
        command_line    /usr/bin/printf "%b" "***** Nagios *****\n\nNotification Type: $NOTIFICATIONTYPE$\nHost: $HOSTNAME$\nState: $HOSTSTATE$\nAddress: $HOSTADDRESS$\nInfo: $HOSTOUTPUT$\n\nDate/Time: $LONGDATETIME$\n" | /bin/mail -s "Host $HOSTSTATE$ alert for $HOSTNAME$!" $CONTACTEMAIL$
        }

# 'notify-service-by-email' command definition
define command{
        command_name    notify-service-by-email
        command_line    /usr/bin/printf "%b" "***** Nagios *****\n\nNotification Type: $NOTIFICATIONTYPE$\n\nService: $SERVICEDESC$\nHost: $HOSTALIAS$\nAddress: $HOSTADDRESS$\nState: $SERVICESTATE$\n\nDate/Time: $LONGDATETIME$\n\nAdditional Info:\n\n$SERVICEOUTPUT$\n" | /bin/mail -s " $HOSTALIAS$/$SERVICEDESC$ is $SERVICESTATE$ " $CONTACTEMAIL$
        }

  

 Shell开发Nagios插件

#Nagios为插件提供两个接口：退出状态码和控制台打印的第一行信息
#主动模式：编写一个探测url的插件
cd /usr/local/nagios/libexec
vim check_url.sh
#!/bin/bash
PROGNAME=`basename $0`
PROGPATH=`dirname $0`
usage() {
     echo "Usage: /bin/sh $PROGNAME url"
     exit 1
}
[ $# -ne 1 ]&&usage
. $PROGPATH/utils.sh
if wget -T 20 --spider $1 > /dev/null 2>&1;then
     echo 'url $1 OK'
     exit $STATE_OK
else
     echo 'url $1 NO'
     exit $STATE_CRITICAL
fi

#[root@mage-monitor-01 libexec]# cat ./utils.sh
#! /bin/sh
#
#STATE_OK=0
#STATE_WARNING=1
#STATE_CRITICAL=2
#STATE_UNKNOWN=3
#STATE_DEPENDENT=4

sh /usr/local/nagios/libexec/check_url 172.16.1.14
chmod +x check_url.sh
cd  /usr/local/nagios/etc/objects/

vim commands.cfg

#'check_url' command defined by peter
define command{
        command_name    check_url
        command_line    $USER1$/check_url.sh 172.16.1.14
}

vim services.cfg

define service {
        use                     generic-service
        host_name               14-web02
        service_description     check_url
        check_command           check_url
} E

/etc/init.d/nagios checkconfig
/etc/init.d/nagios reload

#被动模式：监控/etc/passwd文件是否变化
#web02
md5sum /etc/passwd > /opt/ps.md5
cat /opt/ps.md5
70fe6e84988c7298fe6c5f108e02df39  /etc/passwd
cd /usr/local/nagios/libexec/
vim check_passwd.sh

#!/bin/bash
OriMd5="70fe6e84988c7298fe6c5f108e02df39"
CurrMd5=`md5sum /etc/passwd|cut -c 1-32`
if [ "$OriMd5" == "$CurrMd5" ];then
     echo "/etc/passwd:ok"
     exit 0
else
     echo "/etc/passwd:failed"
     exit 2
fi
sh check_passwd.sh
chmod +x check_passwd.sh

cd /usr/local/nagios/etc/
vim nrpe.cfg

command[check_passwd]=/usr/local/nagios/libexec/check_passwd.sh

netstat -nutlp | grep nrpe
pkill nrpe
/usr/local/nagios/bin/nrpe -c /usr/local/nagios/etc/nrpe.cfg -d
netstat -nutlp | grep nrpe

#nagios服务端

vim services.cfg

define service {
        use                     generic-service
        host_name               14-web02
        service_description     check_passwd
        check_command           check_nrpe!check_passwd
}

/etc/init.d/nagios checkconfig
/etc/init.d/nagios reload