Nagios 是一種開放原始碼監視軟件，它可以掃瞄主機、服務、網絡方面存在的問題。Nagios 與其他類似的包之間的主要區別在於，Nagios 將所有的信息簡化為“工作（working）”、“可疑的（questionable）”和“故障（failure）”狀態，並且 Nagios 支持由插件組成的非常豐富的“生態系統”。這些特性使得用戶能夠進行有效安裝，在此過程中無需過多地關心細節內容，只提供他們所需的信息即可。

install

$ sudo apt-get install nagios3 nagios-nrpe-plugin
		

add user nagiosadmin for nagios

$ sudo htpasswd -c /etc/nagios2/htpasswd.users nagiosadmin
New password:
Re-type new password:
Adding password for user nagiosadmin
		

Create a new nagcmd group for allowing external commands to be submitted through the web interface. Add both the nagios user and the apache user to the group.

$ groupadd nagcmd
$ sudo usermod -a -G nagcmd nagios
$ sudo usermod -a -G nagcmd www-data
$ cat /etc/group
nagcmd:x:1003:nagios,www-data
		

reload apache

$ sudo /etc/init.d/apache2 reload
 * Reloading web server config apache2                    [ OK ]
		

		
nagios-nrpe-server --------> nagios core (nagios-nrpe-plugin)
		
		

nagios-nrpe-server 的功能是向伺服器發送監控數據, 而伺服器端通過nagios-nrpe-plugin接收監控數據。

sudo apt-get install nagios-nrpe-server nagios-plugins
		

/etc/nagios/nrpe.cfg

/etc/nagios/nrpe_local.cfg

$ sudo vim /etc/nagios/nrpe_local.cfg
allowed_hosts=172.16.1.2

command[check_users]=/usr/lib/nagios/plugins/check_users -w 5 -c 10
command[check_load]=/usr/lib/nagios/plugins/check_load -w 15,10,5 -c 30,25,20
command[check_zombie_procs]=/usr/lib/nagios/plugins/check_procs -w 5 -c 10 -s Z
command[check_total_procs]=/usr/lib/nagios/plugins/check_procs -w 150 -c 200
command[check_procs]=/usr/lib/nagios/plugins/check_procs -w 150 -c 200
command[check_swap]=/usr/lib/nagios/plugins/check_swap -w 20% -c 10%
command[check_all_disks]=/usr/lib/nagios/plugins/check_disk -w 20% -c 10% -e
command[check_disk_root]=/usr/lib/nagios/plugins/check_disk -w 20% -c 10% -p /
command[check_disk_home]=/usr/lib/nagios/plugins/check_disk -w 20% -c 10% -p /home
command[check_sda_iostat]=/usr/lib/nagios/plugins/check_iostat -d sda -w 100 -c 200
command[check_sdb_iostat]=/usr/lib/nagios/plugins/check_iostat -d sdb -w 100 -c 200
# command[check_uri_user]=/usr/lib/nagios/plugins/check_http -I 127.0.0.1 -p 80 -u http://example.com/test/ok.php
# command[check_mysql]=/usr/lib/nagios/plugins/check_mysql -H localhost -u root -ppassword test -P 3306
		

重啟後生效

/etc/init.d/nagios-nrpe-server restart
		

Nagios 可以監控windows伺服器，需要安裝下面軟件。

NSClient++

http://sourceforge.net/projects/nscplus

http://www.pnp4nagios.org/

add user neo for nagios

$ sudo htpasswd /etc/nagios3/htpasswd.users neo
New password:
Re-type new password:
Adding password for user neo
			

# grep default_user_name cgi.cfg
#default_user_name=guest

# grep authorized cgi.cfg
authorized_for_system_information=nagiosadmin
authorized_for_configuration_information=nagiosadmin
authorized_for_system_commands=nagiosadmin
authorized_for_all_services=nagiosadmin
authorized_for_all_hosts=nagiosadmin
authorized_for_all_service_commands=nagiosadmin
authorized_for_all_host_commands=nagiosadmin
#authorized_for_read_only=user1,user2
			

$ sudo vim /etc/nagios3/cgi.cfg

authorized_for_all_services=nagiosadmin,neo
authorized_for_all_hosts=nagiosadmin,neo

			

$ sudo vim /etc/nagios3/conf.d/contacts_nagios2.cfg

###############################################################################
# contacts.cfg
###############################################################################

define contact{
        contact_name                    neo
        alias                           Neo
        service_notification_period     24x7
        host_notification_period        24x7
        service_notification_options    w,u,c,r
        host_notification_options       d,r
        service_notification_commands   notify-service-by-email
        host_notification_commands      notify-host-by-email
        email                           neo.chen@example.com
        }

###############################################################################
###############################################################################
#
# CONTACT GROUPS
#
###############################################################################
###############################################################################

# We only have one contact in this simple configuration file, so there is
# no need to create more than one contact group.

define contactgroup{
        contactgroup_name       admins
        alias                   Nagios Administrators
        members                 root, neo
        }

			

當服務出現w—報警(warning),u—未知(unkown),c—嚴重(critical),r—從異常恢復到正常，在這四種情況下通知聯繫人

當主機出現d－當機(down),u—返回不可達(unreachable),r—從異常情況恢復正常,在這3種情況下通知聯繫人

確認 contact_groups 已經設置

neo@monitor:/etc/nagios3$ grep admins conf.d/generic-host_nagios2.cfg
                contact_groups                  admins
neo@monitor:/etc/nagios3$ grep admins conf.d/generic-service_nagios2.cfg
                contact_groups                  admins
			

$ sudo vim /etc/nagios3/conf.d/hostgroups_nagios2.cfg

define hostgroup {
        hostgroup_name  mysql-servers
                alias           MySQL Servers
                members         *
        }

			

$ cat /etc/nagios3/conf.d/generic-service_nagios2.cfg
# generic service template definition
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
                notification_interval           0               ; Only send notifications on status change by default.
                is_volatile                     0
                check_period                    24x7
                normal_check_interval           5
                retry_check_interval            1
                max_check_attempts              4
                notification_period             24x7
                notification_options            w,u,c,r
                contact_groups                  admins
        register                        0       ; DONT REGISTER THIS DEFINITION - ITS NOT A REAL SERVICE, JUST A TEMPLATE!
        }
			

發出警報聲

			
$ sudo vim /etc/nagios3/cgi.cfg

# SOUND OPTIONS
# These options allow you to specify an optional audio file
# that should be played in your browser window when there are
# problems on the network.  The audio files are used only in
# the status CGI.  Only the sound for the most critical problem
# will be played.  Order of importance (higher to lower) is as
# follows: unreachable hosts, down hosts, critical services,
# warning services, and unknown services. If there are no
# visible problems, the sound file optionally specified by
# 'normal_sound' variable will be played.
#
#
# <varname>=<sound_file>
#
# Note: All audio files must be placed in the /media subdirectory
# under the HTML path (i.e. /usr/local/nagios/share/media/).

host_unreachable_sound=hostdown.wav
host_down_sound=hostdown.wav
service_critical_sound=critical.wav
service_warning_sound=warning.wav
service_unknown_sound=warning.wav
normal_sound=noproblem.wav
			
			

vim /etc/nagios3/commands.cfg

# 'notify-host-by-sms' command definition
define command{
        command_name    notify-host-by-sms
        command_line    /srv/sms/sms $CONTACTPAGER$ "Host: $HOSTNAME$\nState: $HOSTSTATE$\nAddress: $HOSTADDRESS$\nInfo: $HOSTOUTPUT$\n\nDate/Time: $LONGDATETIME$\n"
        }

# 'notify-service-by-sms' command definition
define command{
        command_name    notify-service-by-sms
        command_line    /srv/sms/sms $CONTACTPAGER$ "Service: $SERVICEDESC$\nHost: $HOSTALIAS$\nAddress: $HOSTADDRESS$\nState: $SERVICESTATE$\n\nDate/Time: $LONGDATETIME$\n\nAdditional Info:\n\n$SERVICEOUTPUT$"
        }
			

sudo vim /etc/nagios3/conf.d/contacts_nagios2.cfg
define contact{
        contact_name                    neo
        alias                           Neo
        service_notification_period     24x7
        host_notification_period        24x7
        service_notification_options    w,u,c,r
        host_notification_options       d,r
        service_notification_commands   notify-service-by-email, notify-service-by-sms
        host_notification_commands      notify-host-by-email, notify-host-by-sms
        email                           neo.chen@example.com
        pager 							13113668899
        }

			

neo@monitor:/etc/nagios3/hosts$ sudo cat www.example.com.cfg

define host{
        use             generic-host            ; Inherit default values from a template
        host_name       www.example.com             ; The name we're giving to this host
        alias           Some Remote Host        ; A longer name associated with the host
        address         172.16.1.10              ; IP address of the host
        hostgroups      http-servers                    ; Host groups this host is associated with
        }

# NRPE disk check.
define service {
        use                             generic-service
        host_name                       www.example.com
        service_description             nrpe-disk
        check_command                   check_nrpe_1arg!check_all_disks!172.16.1.10
}
define service {
        use                             generic-service
        host_name                       www.example.com
        service_description             nrpe-users
        check_command                   check_nrpe_1arg!check_users!172.16.1.10
}
define service {
        use                             generic-service
        host_name                       www.example.com
        service_description             nrpe-swap
        check_command                   check_nrpe_1arg!check_swap!172.16.1.10
}
define service {
        use                             generic-service
        host_name                       www.example.com
        service_description             nrpe-procs
        check_command                   check_nrpe_1arg!check_total_procs!172.16.1.10
}
define service {
        use                             generic-service
        host_name                       www.example.com
        service_description             nrpe-load
        check_command                   check_nrpe_1arg!check_load!172.16.1.10
}
define service {
        use                             generic-service
        host_name                       www.example.com
        service_description             nrpe-zombie_procs
        check_command                   check_nrpe_1arg!check_zombie_procs!172.16.1.10
}

			

vim /etc/nagios3/routers/firewall.cfg

define host{

        use             generic-host; Inherit default values from a template

        host_name       firewall         ; The name we're giving to this switch

        alias           Cisco PIX 515E Firewall ; A longer name associated with the switch

        address         172.16.1.254            ; IP address of the switch

        hostgroups      all,networks            ; Host groups this switch is associated with

        }

define service{

        use                     generic-service ; Inherit values from a template

        host_name                       firewall ; The name of the host the service is associated with

        service_description     PING            ; The service description

        check_command           check_ping!200.0,20%!600.0,60%  ; The command used to monitor the service

        normal_check_interval   5       ; Check the service every 5 minutes under normal conditions

        retry_check_interval    1       ; Re-check the service every minute until its final/hard state is determined

        }

define service{

        use                     generic-service ; Inherit values from a template

        host_name                       firewall

        service_description     Uptime

        check_command           check_snmp!-C public -o sysUpTime.0

        }

			

define service{
    use                             local-service
    host_name                       www.example.com
    service_description             Host Alive
    check_command                   check-host-alive
    }
			

nagios check_ping命令使用方法

具體如下：
-H    主機地址
-w     WARNING 狀態：   響應時間(毫秒)，丟包率 (%)   閥值
-c     CRITICAL狀態：    響應時間(毫秒)，丟包率 (%)   閥值
-p     發送的包數           預設5個包
-t     超時時間             預設10秒
-4|-6                        使用ipv4|ipv6 地址     預設ipv4
		

實例：

/usr/lib64/nagios/plugins/check_ping -H 74.125.71.106 -w 100.0,20% -c 200.0,50%
		

# /usr/lib64/nagios/plugins/check_procs
PROCS OK: 75 processes

# /usr/lib64/nagios/plugins/check_procs -a mingetty
PROCS OK: 6 processes with args 'mingetty'

# /usr/lib64/nagios/plugins/check_procs -C crond
PROCS OK: 1 process with command name 'crond'
		

監控如果有用戶登陸就發出警告

# /usr/lib64/nagios/plugins/check_users -w 0 -c 5
USERS WARNING - 1 users currently logged in |users=1;0;5;0
		

監控用戶上線5

# /usr/lib64/nagios/plugins/check_users -w 5 -c 50
USERS OK - 1 users currently logged in |users=1;5;50;0
		

命令定義

define command{
        command_name    check_http_404
        command_line    /usr/lib/nagios/plugins/check_http -H '$HOSTADDRESS$' -I '$HOSTADDRESS$' -e '404'
        }

define command{
        command_name    check_http_status
        command_line    /usr/lib/nagios/plugins/check_http -H '$HOSTADDRESS$' -I '$HOSTADDRESS$' -e '$ARG1$'
        }

define command{
        command_name    check_http_url
        command_line    /usr/lib/nagios/plugins/check_http -H '$HOSTADDRESS$' -I '$HOSTADDRESS$'  -u '$ARG1$'
        }
		

預設HTTP健康檢查超時時間是10秒，如果你的網站需要更長的時間才能打開可以使用-t參數修改預設Timeout時間

# 'check_http' command definition
define command{
        command_name    check_http
        command_line    /usr/lib/nagios/plugins/check_http -t 30 -H '$HOSTADDRESS$' -I '$HOSTADDRESS$'
        }
		

# /srv/nagios/libexec/check_http -H www.163.com
HTTP OK: HTTP/1.0 200 OK - 657627 bytes in 1.772 second response time |time=1.771681s;;;0.000000 size=657627B;;;0

$ /usr/lib/nagios/plugins/check_http -H www.example.com -I 172.16.0.8 -s "HTTs"
HTTP CRITICAL: HTTP/1.1 404 Not Found - string not found - 336 bytes in 0.001 second response time |time=0.000733s;;;0.000000 size=336B;;;0

$ /usr/lib/nagios/plugins/check_http -H www.example.com -I 172.16.0.8 -e '404'
HTTP OK: Status line output matched "404" - 336 bytes in 0.001 second response time |time=0.000715s;;;0.000000 size=336B;;;0
		

命令參數

check_mysql [-d database] [-H host] [-P port] [-s socket]
       [-u user] [-p password] [-S]


/usr/lib64/nagios/plugins/check_mysql -d dbname -H 202.176.120.10 -P 3306 -u test -p password
Uptime: 254264  Threads: 16  Questions: 535110791  Slow queries: 21  Opens: 110  Flush tables: 1  Open tables: 81  Queries per second avg: 2104.547
		

$ /usr/lib64/nagios/plugins/check_mysql --hostname=172.16.1.5 --port=3306 --username=monitor --password=monitor
Uptime: 27001  Threads: 8  Questions: 25280156  Slow queries: 14941  Opens: 1389932  Flush tables: 3  Open tables: 128  Queries per second avg: 936.267
				

				
cat >> /usr/lib64/nagios/plugins/check_mysql_replication <<EOF
#!/bin/bash

declare -a slave_is

slave_is=($(mysql -h$1 -umonitor -pxmNhj -e "show slave status\G"|grep Running |awk '{print $2}'))

if [ "${slave_is[0]}" = "Yes" -a "${slave_is[1]}" = "Yes" ]
     then
     echo "OK - Slave is running"
     exit 0
else
     echo "Critical - Slave is error"
     exit 2
fi
EOF
				
				

sudo chmod +x /usr/lib64/nagios/plugins/check_mysql_replication
/usr/lib64/nagios/plugins/check_mysql_replication 172.16.1.4
Critical - slave is error
				

vim /etc/nagios-plugins/config/mysql.cfg

# 'check_mysql_replication' command definition
define command{
        command_name    check_mysql_replication
        command_line    /usr/lib/nagios/plugins/check_mysql_replication $HOSTADDRESS$
}
define command{
        command_name    check_mysql_replication_host
        command_line    /usr/lib/nagios/plugins/check_mysql_replication '$ARG1$'
}
				

				
cat >> /usr/lib64/nagios/plugins/check_mysql_replication <<EOF
#!/bin/bash

declare -a slave_is

slave_is=($(mysql -umonitor -pxmNhj -e "show slave status\G"|grep Running |awk '{print $2}'))

if [ "${slave_is[0]}" = "Yes" -a "${slave_is[1]}" = "Yes" ]
     then
     echo "OK - slave is running"
     exit 0
else
     echo "Critical - slave is error"
     exit 2
fi
EOF

command[check_mysql_slave]=/usr/lib64/nagios/plugins/check_mysql_replication

/usr/local/nagios/libexec/check_nrpe -H 192.168.1.1
/usr/local/nagios/libexec/check_nrpe -H 192.168.1.1 -c check_mysql_replication


define service {
	host_name 192.168.10.232
	service_description check_mysql_replication
	check_period 24x7
	max_check_attempts 5
	normal_check_interval 3
	retry_check_interval 2
	contact_groups mygroup
	notification_interval 5
	notification_period 24x7
	notification_options w,u,c,r
	check_command check_nrpe!check_mysql_replication
}
				
				

官方的 check_log 有很多缺陷，不能監控大檔案。它的監控原理是cat log to oldlog 然後通過diff比較

http://exchange.nagios.org/directory/Plugins/Network-Connections,-Stats-and-Bandwidth/check_traffic-2Esh/details

https://github.com/cloved/check_traffic

網卡流量監測

nrpe 插件接收來自nagios-nrpe-server數據報告

cat /etc/nagios3/hosts/host.example.org.cfg

define host{

        use             generic-host            ; Inherit default values from a template

        host_name       host.example.org        ; The name we're giving to this host

        alias           Some Remote Host        ; A longer name associated with the host

        address         172.16.1.3              ; IP address of the host

        hostgroups      all                     ; Host groups this host is associated with

        }

# NRPE disk check.
define service {
        use                             generic-service
        host_name                       backup
        service_description             nrpe-disk
        check_command                   check_nrpe_1arg!check_all_disks!172.16.1.3
}
define service {
        use                             generic-service
        host_name                       backup
        service_description             nrpe-users
        check_command                   check_nrpe_1arg!check_users!172.16.1.3
}
define service {
        use                             generic-service
        host_name                       backup
        service_description             nrpe-swap
        check_command                   check_nrpe_1arg!check_swap!172.16.1.3
}
define service {
        use                             generic-service
        host_name                       backup
        service_description             nrpe-procs
        check_command                   check_nrpe_1arg!check_procs!172.16.1.3
}

			

Define windows services that should be monitored.

# Define a host for the Windows machine we'll be monitoring
# Change the host_name, alias, and address to fit your situation

define host{
use             windows-server              ; Inherit default values from a template
host_name   remote-windows-host      ; The name we're giving to this host
alias            Remote Windows Host     ; A longer name associated with the host
address       192.168.1.4                   ; IP address of the remote windows host
}

define service{
use                     generic-service
host_name               remote-windows-host
service_description     NSClient++ Version
check_command           check_nt!CLIENTVERSION
}
define service{
use                     generic-service
host_name               remote-windows-host
service_description     Uptime
check_command           check_nt!UPTIME
}
define service{
use                     generic-service
host_name               remote-windows-host
service_description     CPU Load
check_command           check_nt!CPULOAD!-l 5,80,90
}
define service{
use                     generic-service
host_name               remote-windows-host
service_description     Memory Usage
check_command           check_nt!MEMUSE!-w 80 -c 90
}
define service{
use                     generic-service
host_name               remote-windows-host
service_description     C:\ Drive Space
check_command           check_nt!USEDDISKSPACE!-l c -w 80 -c 90
}
define service{
use                     generic-service
host_name               remote-windows-host
service_description     W3SVC
check_command           check_nt!SERVICESTATE!-d SHOWALL -l W3SVC
}
define service{
use                     generic-service
host_name               remote-windows-host
service_description     Explorer
check_command           check_nt!PROCSTATE!-d SHOWALL -l Explorer.exe
}
		

Enable Password Protection

define command{
command_name	check_nt
command_line	$USER1$/check_nt -H $HOSTADDRESS$ -p 12489 -s My2Secure$Password -v $ARG1$ $ARG2$
}
		

# yum install nsca
		

https://code.google.com/p/jmxquery/

wget https://jmxquery.googlecode.com/files/jmxquery-1.3-bin.zip
unzip jmxquery-1.3-bin.zip
chmod +x check_jmx		
		

		<![CDATA[
# ./check_jmx -help
Usage: check_jmx [-option...] -U url -O object -A attribute
       (to query an attribute)
   or  check_jmx [-option...] -U url -O object -M method
       (to invoke a zero-argument method)
   or  check_jmx -help
       (to display this help page)

Mandatory parameters are:
 -U     JMX URL, for example: "service:jmx:rmi:///jndi/rmi://localhost:1616/jmxrmi"
 -O     Object name to be checked, for example, "java.lang:type=Memory"
 -A   	Attribute of the object to be checked, for example, "NonHeapMemoryUsage" (not compatible with -M switch)
 -M     Zero-argument method to be invoked (not compatible with -A switch)

Options are:
 -K <key>
        Key for compound data, for example, "used"
 -I <info attribute>
        Attribute of the object containing information for text output
 -J <info attribute key>
        Attribute key for -I attribute compound data, for example, "used"
 -v[v[v[v]]]
	    Verbatim level controlled as a number of v
 -w <limit>
	    Warning long value
 -c <limit>
	    Critical long value
 -default <value>
        Use default value if requested object/attribute/method does not exist
 -username <user name> -password <password>
	    Credentials for JMX

Note that if warning level > critical, system checks object attribute value to be LESS THAN OR EQUAL warning, critical
If warning level < critical, system checks object attribute value to be MORE THAN OR EQUAL warning, critical 		
		
		

# ./check_jmx -U service:jmx:rmi:///jndi/rmi://localhost:9012/jmxrmi -O java.lang:type=Memory -A HeapMemoryUsage -K used -I HeapMemoryUsage -J used -vvvv -w 731847066 -c 1045495808
JMX OK - HeapMemoryUsage.used=98617544 | HeapMemoryUsage.used=98617544,committed=514850816;init=536870912;max=7635730432;used=98617544			
			

# ./check_jmx -U service:jmx:rmi:///jndi/rmi://localhost:9012/jmxrmi -O org:type=Spring,name=BackgroundService -A QueueSize -w 10 -c 20
JMX CRITICAL - org:type=Spring,name=BackgroundService
			

http://nagios.sourceforge.net/docs/3_0/macrolist.html

https://nagios-plugins.org/doc/guidelines.html#THRESHOLDFORMAT