天天看點

Nagios 監控執行個體部署

Nagios是一款企業級開源軟體,專注于監控伺服器上服務是否正常,不生成圖形,提供報警機制,郵件或者短信發送監控狀态,它通過各種插件實作不同的功能。

Nagios        監控平台主程式

Nagios-plugins     必選插件

NRPE         監控遠端伺服器的主機資源

NSClient++      用于監控Windows主機

NDOUtils       将資料寫入資料庫

執行個體應用:

1 監控快速部署

監控需要安裝http php nagios nagios-plugins NRPE軟體包

yum install -y gd gd-devel openssl openssl-devel httpd php gcc glibc glib-common make wget

net-snmp

setenforce 0

iptables -F

安裝nagios 源碼包下載下傳安裝

wget http://sourceforge.net/projects/nagios/files/nagios-3.x/nagios-3.5.0/nagios-3.5.0.tar.gz/download

groupadd nagios

useradd -g nagios nagios

tar -zxf nagios-3.5.0.tar.gz -C /usr/src/

cd /usr/src/nagios

./configure --with-nagios-user=nagios --with-nagios-group=nagios

make all

make install

make install-init             #安裝啟動腳本

make install-commandmode          #安裝與配置目錄權限

make install-config            #安裝配置檔案模闆

make install-webconf            #web監控界面配置

安裝nagios-plugins和nrpe

wget   http://nchc.dl.sourceforge.net/project/nagiosplug/nagiosplug/1.4.16/nagios-plugins-1.4.16.tar.gz

tar -zxf nagios-plugins-1.4.16.tar.gz -C /usr/src/

cd /usr/src/nagios-plugins-1.4.16

./configure  --prefix=/usr/local/nagios/

make && make install

wget wget http://nchc.dl.sourceforge.net/project/nagios/nrpe-2.x/nrpe-2.14/nrpe-2.14.tar.gz

tar -zxf nrpe-2.14.tar.gz -C /usr/src/

cd /usr/src/nrpe-2.14

./configure

make install-plugin

make install-daemon

make install-daemon-config

chown -R nagions.nagions /usr/local/nagios

建立賬戶資訊

htpasswd -c /usr/local/nagions/etc/htpasswd.users tomcat

iptables -I INPUT -p tcp --dport 80 -j ACCEPT

service iptables save

啟動服務

service httpd start

/etc/init.d/nagios start

chkconfig httpd on

chkconfig --add nagios

chkconfig nagios on

2 修改配置檔案

nagios的配置檔案較多,主要位于/usr/local/nagios/etc 下

nagios.conf             主配置檔案

nrpe.cfg                    遠端監控配置檔案

cgi.conf                    CGI配置檔案

commands.cfg            指令定義檔案

contacts.cfg                定義聯系人檔案

timepreriods.cfg              時間周期定義檔案

tempaltes.cfg                    對象定義參考模闆

localhost.cfg                    監控本機配置模闆

printer.cfg                        監控列印機模闆

switch.cfg                            監控交換模闆

windows.cfg                        監控Windows配置模闆

很多配置檔案無需修改可以直接使用

修改主配置檔案nagios.cfg,主要是用cfg_file配置加載其他配置檔案。

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

cfg_file=/usr/local/nagios/etc/objects/commands.cfg

cfg_file=/usr/local/nagios/etc/objects/contacts.cfg

cfg_file=/usr/local/nagios/etc/objects/templates.cfg

cfg_file=/usr/local/nagios/etc/objects/timeperiods.cfg

cfg_file=/usr/local/nagios/etc/objects/localhost.cfg

cfg_file=/usr/local/nagios/etc/web1.cfg

cfg_file=/usr/local/nagios/etc/web2.cfg

修改CGI配置檔案cgi.cfg,添加tomcat賬戶進來

vim /usr/local/nagios/etc/cgi.cfg

default_user_name=tomcat

authorized_for_system_information=nagiosadmin,tomcat

authorized_for_configuration_information=nagiosadmin,tomcat

authorized_for_system_commands=nagiosadmin,tomcat

authorized_for_all_services=nagiosadmin,tomcat

authorized_for_all_hosts=nagiosadmin,tomcat

authorized_for_all_service_commands=nagiosadmin,tomcat

authorized_for_all_host_commands=nagiosadmin,tomcat

修改指令配置檔案command.cfg,定義指令實作的方式,如郵件報警,使用工具,内容格式等。

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

define command{

       command_name    check_nrpe

       command_line    $USER1$/check_nrpe -H $HOSTADDRESS$ -t 30 -c $ARG1$

       }

       command_name    check_nrpe_args

       command_line    $USER1$/check_nrpe -H $HOSTADDRESS$ -t 30 -c $ARG1$ -a $ARG2$

修改聯系人配置檔案contacts.cfg 報警的聯系人及聯系方式

define contact{

       contact_name                    nagiosadmin             

       use                             generic-contact         

       alias                           Nagios Admin            

       email                           [email protected] 

修改報警時間周期timeperiods.cfg

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

define timeperiods{

       timeperiod_name 24x7   #監控所有時間段(7*24小時)

       alias           24 Hours A Day, 7 Days A Week

       sunday          00:00-24:00

       monday          00:00-24:00

       tuesday         00:00-24:00

       wednesday       00:00-24:00

       thursday        00:00-24:00

       friday          00:00-24:00

       saturday        00:00-24:00

修改本機的配置localhost.cfg

define host{

       use                          linux-server

       host_name                    duangr-1

       alias                        duangr-1

       address                      192.168.56.10

define service{

       use                             local-service

       host_name                       duangr-1

       service_description             Host Alive

       check_command                   check-host-alive

       service_description             Users

       check_command                   check_local_users!20!50

       service_description             CPU

       check_command                   check_local_load!5.0,4.0,3.0!10.0,6.0,4.0

       service_description             Disk Root

       check_command                   check_local_disk!20%!10%!/

       service_description             Disk Home

       check_command                   check_local_disk!20%!10%!/export/home

       service_description             Zombie Procs

       check_command                   check_local_procs!5!10!Z

       service_description             Total Procs

       check_command                   check_local_procs!250!400!RSZDT

       service_description             Swap Usage

       check_command                   check_local_swap!20!10

修改模闆檔案templates.cfg

vi /usr/local/nagios/etc/objects/templates.cfg

#聯系人模闆generic-contact

        name                            generic-contact        

        service_notification_period     24x7                    

        host_notification_period        24x7                    

        service_notification_options    w,u,c,r,f,s            

        host_notification_options       d,u,r,f,s               

        service_notification_commands   notify-service-by-email 

        host_notification_commands      notify-host-by-email    

        register                        0                       

        }

#定義generic-host主機模闆

        name                            generic-host    

        notifications_enabled           1               

        event_handler_enabled           1               

        flap_detection_enabled          1              

        failure_prediction_enabled      1              

        process_perf_data               1              

        retain_status_information       1              

        retain_nonstatus_information    1              

        notification_period             24x7           

        register                        0              

#定義Linux主機模闆

        name                            linux-server    

        use                             generic-host    

        check_period                    24x7            

        check_interval                  5               

        retry_interval                  1              

        max_check_attempts              10              

        check_command                   check-host-alive 

        notification_period             workhours       

        notification_interval           120             

        notification_options            d,u,r           

        contact_groups                  admins          

        register                        0               

建立遠端監控web1.cfg

vim /usr/local/nagios/etc/web1.cfg

define host{

       use                     linux-server

       host_name               duangr-2

       alias                   duangr-2

       address                 192.168.56.11

       }

define service{

       use                             local-service

       host_name                       duangr-2

       service_description             Host Alive

       check_command                   check-host-alive

       service_description             Users

       check_command                   check_nrpe_args!check_users!5 10

       service_description             CPU

       check_command                   check_nrpe_args!check_load!15,10,5 30,25,20

       service_description             Disk Root

       check_command                   check_nrpe_args!check_disk!20% 10% /

       service_description             Disk /export/home

       check_command                   check_nrpe_args!check_disk!20% 10% /export/home

      use                             local-service

      host_name                       duangr-2

      service_description             Procs Zombie

      check_command                   check_nrpe_args!check_procs!5 10 Z

      }

      service_description             Procs Total

      check_command                   check_nrpe_args!check_procs_args!"-w400 -c600"      }

       service_description             Swap Usage

       check_command                   check_nrpe_args!check_swap!20% 10%

;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;

;;  下面是一些常用程序的監控,主要是雲平台相關程序

;; 監控crond程序

       service_description             PS: crond

       check_command                   check_nrpe_args!check_procs_args!"-c1:1 -Ccrond"       }

;; 監控zookeeper程序

       service_description             PS: QuorumPeerMain

       check_command                   check_nrpe_args!check_procs_args!"-c1:1 -Cjava -aserver.quorum.QuorumPeerMain"       }

;;監控storm的從節點程序

       service_description             PS: supervisor

       check_command                   check_nrpe_args!check_procs_args!"-c1:1 -Cjava -adaemon.supervisor"       }

;; 監控storm的主節點程序

       service_description             PS: nimbus

       check_command                   check_nrpe_args!check_procs_args!"-c1:1 -Cjava -adaemon.nimbus"       }

;; 監控MetaQ程序

       service_description             PS: MetaQ

       check_command                   check_nrpe_args!check_procs_args!"-c1:1 -Cjava -ametamorphosis-server-w"       }

;; 監控Redis程序

       service_description             PS: redis-server

       check_command                   check_nrpe_args!check_procs_args!"-c1:1 -Credis-server"       }

;; 監控hadoop主節點NameNode程序

       service_description             PS: NameNode 

       check_command                   check_nrpe_args!check_procs_args!"-c1:1 -Cjava -aserver.namenode.NameNode"       }

;; 監控hadoop主節點SecondaryNameNode程序

       service_description             PS: SecondaryNameNode

       check_command                   check_nrpe_args!check_procs_args!"-c1:1 -Cjava -aserver.namenode.SecondaryNameNode"       }

;; 監控hadoop主節點ResourceManager程序

       service_description             PS: ResourceManager

       check_command                   check_nrpe_args!check_procs_args!"-c1:1 -Cjava -aserver.resourcemanager.ResourceManager"       }

;; 監控hadoop從節點DataNode程序

       service_description             PS: DataNode

       check_command                   check_nrpe_args!check_procs_args!"-c1:1 -Cjava -aserver.datanode.DataNode"       }

;;監控hadoop從節點NodeManager程序

       service_description             PS: NodeManager

       check_command                   check_nrpe_args!check_procs_args!"-c1:1 -Cjava -aserver.nodemanager.NodeManager"       }

由于duangr-2是遠端主機,是以使用check_nrpe_args指令來監控.

/etc/init.d/nagios restart

快速定位配置檔案問題所在指令

/usr/local/nagios/bin/nagios -V /usr/local/nagios/etc/nagios.cfg

3 被監控機安裝軟體  nagios-plugin  nrpe

yum install -y openssl openssl-devel

useradd -g nagios -s /sbin/nologin nagios

tar -zxf nagios-plugins-2.1.6.tar.gz -C /usr/src/

cd /usr/src/nagios-plugins-2.1.6

./configure  --prefix=/usr/local/nagios/ --with-nagios-user=nagios --with-nagios-group=nagios

修改用戶端的NRPE配置檔案

command[check_users]=/usr/local/nagios/libexec/check_users -w 5 -c 10

command[check_load]=/usr/local/nagios/libexec/check_load -w 15,10,5 -c 30,25,20

command[check_sda2]=/usr/local/nagios/libexec/check_disk -w 20% -c 10% -p /dev/sda2

command[check_swap]=/usr/local/nagios/libexec/check_disk -w 20% -c 10% -p /dev/shm

command[check_home]=/usr/local/nagios/libexec/check_disk -w 20% -c 10% -p /dev/mapper/VolGroup00-LogVol00

command[check_zombie_procs]=/usr/local/nagios/libexec/check_procs -w 5 -c 10 -s Z

command[check_total_procs]=/usr/local/nagios/libexec/check_procs -w 200 -c 300

command[check_ping81]=/usr/local/nagios/libexec/check_ping -H 10.155.0.1 -w 100.0,20% -c 500.0,60%#

command[check_hda1]=/usr/local/nagios/libexec/check_disk -w 20 -c 10 -p /dev/hda1

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

echo "/usr/local/nagios/bin/nrpe -c /usr/local/nagios/etc/nrpe.cfg -d" >> /etc/rc.local

netstat -lnupt |grep 5666

iptables -I INPUT -p tcp --dport 5666 -j ACCEPT

檢查監控指令配置是否ok

/usr/local/nagios/libexec/check_nrpe -H localhost -c check_users  -a 5 10

/usr/local/nagios/libexec/check_nrpe -H localhost -c check_load   -a 15,10,5 30,25,20

/usr/local/nagios/libexec/check_nrpe -H localhost -c check_disk   -a 20% 10% /

/usr/local/nagios/libexec/check_nrpe -H localhost -c check_procs  -a 200 400 RSZDT

/usr/local/nagios/libexec/check_nrpe -H localhost -c check_swap   -a 20% 10%

沒有問題就可以用浏覽器通路nagios了

本文轉自super李導51CTO部落格,原文連結:http://blog.51cto.com/superleedo/1891718 ,如需轉載請自行聯系原作者