Nagios监控Oralce

一、本文说明：

   本文是监控本地的Oracle，其实监控远端的Oracle也是跟下面的步骤差不多的。

二、安装Nagios、Nagios插件、NRPE软件：

    安装步骤可以参考《Linux下Nagios的安装与配置》

    注意点：
    1、由于nagios脚本需要读取oracle相关文件。所在运行nagios的用户需要定义为Oracle服务用户。并且修改/etc/xinted.d/nrpe中配置。

[oracle@rhel5 libexec]$ cat /etc/xinetd.d/nrpe 
# default: on
# description: NRPE (Nagios Remote Plugin Executor)
service nrpe
{
           flags           = REUSE
        socket_type     = stream    
    port        = 5666    
           wait            = no
        user            = oracle
    group        = oinstall
           server          = /usr/local/nagios/bin/nrpe
        server_args     = -c /usr/local/nagios/etc/nrpe.cfg --inetd
           log_on_failure  += USERID
        disable         = no
    only_from       = 127.0.0.1 192.168.11.149
}

    2、修改check_oracle脚本，将$ORACLE_HOME以及$PATH手动加入。

[oracle@rhel5 libexec]$ cat /usr/local/nagios/libexec/check_oracle 
#! /bin/sh
#
# latigid010@yahoo.com
# 01/06/2000
#
#  This Nagios plugin was created to check Oracle status
#


ORACLE_HOME=/u01/app/oracle/product/11.2.0/db_1
PATH=$PATH:/u01/app/oracle/product/11.2.0/db_1/bin

三、配置nrpe服务：

    修改/usr/local/nagios/etc/nrpe.cfg文件。加入以下内容：

[oracle@rhel5 libexec]$ cat /usr/local/nagios/etc/nrpe.cfg

#Check Oracle  
 
command[check_oracle_tns]=/usr/local/nagios/libexec/check_oracle --tns orcl jack jack  
 
command[check_oracle_db]=/usr/local/nagios/libexec/check_oracle --db orcl  
 
command[check_oracle_login]=/usr/local/nagios/libexec/check_oracle --login orcl jack jack
 
command[check_oracle_cache]=/usr/local/nagios/libexec/check_oracle --cache orcl system oracle 80 90  
 
command[check_oracle_tablespace]=/usr/local/nagios/libexec/check_oracle --tablespace orcl jack jack jack  90 80  

    具体参数写法参考 check_oracle -help

[oracle@rhel5 libexec]$ ./check_oracle -help
Usage:
  check_oracle --tns <Oracle Sid or Hostname/IP address>
  check_oracle --db <ORACLE_SID>
  check_oracle --login <ORACLE_SID>
  check_oracle --cache <ORACLE_SID> <USER> <PASS> <CRITICAL> <WARNING>
  check_oracle --tablespace <ORACLE_SID> <USER> <PASS> <TABLESPACE> <CRITICAL> <WARNING>
  check_oracle --oranames <Hostname>
  check_oracle --help
  check_oracle --version

    添加nrpe端口号

[oracle@rhel5 libexec]$ tail -4 /etc/services 
iqobject    48619/tcp            # iqobject
iqobject    48619/udp            # iqobject
# Local services
nrpe            5666/tcp                        #nrpe

    配置完成后，重启xinetd服务

[oracle@rhel5 libexec]$ service xinetd restart

四、配置Nagios：
    1、在nagios服务器端添加nrpe命令配置。修改/usr/local/nagios/etc/objects/command.cfg文件：

[oracle@rhel5 etc]$ tail -10 objects/commands.cfg
define command{
    command_name    process-service-perfdata
    command_line    /usr/bin/printf "%b" "$LASTSERVICECHECK$	$HOSTNAME$	$SERVICEDESC$	$SERVICESTATE$	$SERVICEATTEMPT$	$SERVICESTATETYPE$	$SERVICEEXECUTIONTIME$	$SERVICELATENCY$	$SERVICEOUTPUT$	$SERVICEPERFDATA$
" >> /usr/local/nagios/var/service-perfdata.out
    }

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

    2、添加hosts.cfg和services.cfg

[oracle@rhel5 etc]$ cat hosts.cfg 
define host{
        use                     linux-server2
        host_name               oracle
        alias                   Nagios-node2
        address                 192.168.11.149
        }

define hostgroup{      
        hostgroup_name          bsmart-servers      
        alias                   bsmart servers        
        members                 oracle
        }

[oracle@rhel5 etc]$ cat services.cfg 
 
define service {  
 
use generic-service  
 
host_name oracle  
 
service_description TNS Check  
 
check_command check_nrpe!check_oracle_tns  
 
}  
 
define service {  
 
use generic-service  
 
host_name oracle  
 
service_description DB Check  
 
check_command check_nrpe!check_oracle_db  
 
}  
 
define service {  
 
use generic-service  
 
host_name oracle  
 
service_description Login Check  
 
check_command check_nrpe!check_oracle_login  
 
}  
 
define service {  
 
use generic-service  
 
host_name oracle  
 
service_description Cache Check  
 
check_command check_nrpe!check_oracle_cache  

notifications_enabled 0
 
}  
 
define service {  
 
use generic-service  
 
host_name oracle  
 
service_description Tablespace Check  
 
check_command check_nrpe!check_oracle_tablespace  
 
}  

    3、在templates.cfg中添加如下内容：

define host{
        name                            linux-server2    ; The name of this host template
        use                             generic-host    ; This template inherits other values from the generic-host template
        check_period                    24x7            ; By default, Linux hosts are checked round the clock
        check_interval                  5               ; Actively check the host every 5 minutes
        retry_interval                  1               ; Schedule host check retries at 1 minute intervals
        max_check_attempts              10              ; Check each Linux host 10 times (max)
        check_command                   check-host-alive ; Default command to check Linux hosts
        notification_period             workhours       ; Linux admins hate to be woken up, so we only notify during the day
                                                        ; Note that the notification_period variable is being overridden from
                                                        ; the value that is inherited from the generic-host template!
        notification_interval           120             ; Resend notifications every 2 hours
        notification_options            d,u,r           ; Only send notifications for specific host states
        contact_groups                  admins          ; Notifications get sent to the admins by default
        register                        0               ; DONT REGISTER THIS DEFINITION - ITS NOT A REAL HOST, JUST A TEMPLATE!
        }

五、重点说明：

    由于nagios的用户是oracle，所以在nagios启动的命令应该使用：

    [oracle@rhel5 etc]$ /usr/local/nagios/bin/nagios -d /usr/local/nagios/etc/nagios.cfg

    关闭命令使用：

    [oracle@rhel5 etc]$ killall nagios

[oracle@rhel5 etc]$ ll
总计 148
-rw-rw-r-- 1 oracle oinstall 11437 09-27 19:26 cgi.cfg
-rw-r--r-- 1 oracle oinstall 11408 09-27 19:20 cgi.cfg.bak
-rw-r--r-- 1 oracle oinstall   382 09-27 19:59 hosts.cfg
-rw-r--r-- 1 oracle oinstall    44 09-27 17:17 htpasswd
-rw-r--r-- 1 oracle oinstall    44 09-27 19:20 htpasswd.bak
-rw-rw-r-- 1 oracle oinstall 43863 09-27 20:18 nagios.cfg
-rw-r--r-- 1 oracle oinstall 43774 09-27 19:20 nagios.cfg.bak
-rw-r--r-- 1 oracle oinstall  7834 09-27 21:12 nrpe.cfg
drwxrwxr-x 2 oracle oinstall  4096 09-27 21:35 objects
-rw-rw---- 1 oracle oinstall  1340 09-27 16:42 resource.cfg
-rw-r----- 1 oracle oinstall  1340 09-27 19:20 resource.cfg.bak
-rw-r--r-- 1 oracle oinstall   805 09-27 21:16 services.cfg
[oracle@rhel5 etc]$ ll objects/
总计 100
-rw-rw-r-- 1 oracle oinstall  7891 09-27 19:44 commands.cfg
-rw-r--r-- 1 oracle oinstall  7716 09-27 19:19 commands.cfg.bak
-rw-rw-r-- 1 oracle oinstall  2153 09-27 19:24 contacts.cfg
-rw-r--r-- 1 oracle oinstall  2166 09-27 19:19 contacts.cfg.bak
-rw-rw-r-- 1 oracle oinstall  5386 09-27 19:22 localhost.cfg
-rw-r--r-- 1 oracle oinstall  5403 09-27 19:19 localhost.cfg.bak
-rw-rw-r-- 1 oracle oinstall  3124 09-27 16:42 printer.cfg
-rw-r--r-- 1 oracle oinstall  3124 09-27 19:19 printer.cfg.bak
-rw-rw-r-- 1 oracle oinstall  3293 09-27 16:42 switch.cfg
-rw-r--r-- 1 oracle oinstall  3293 09-27 19:19 switch.cfg.bak
-rw-rw-r-- 1 oracle oinstall 12360 09-27 20:00 templates.cfg
-rw-r--r-- 1 oracle oinstall 10812 09-27 19:19 templates.cfg.bak
-rw-rw-r-- 1 oracle oinstall  3208 09-27 16:42 timeperiods.cfg
-rw-r--r-- 1 oracle oinstall  3208 09-27 19:20 timeperiods.cfg.bak
-rw-rw-r-- 1 oracle oinstall  4019 09-27 16:42 windows.cfg
-rw-r--r-- 1 oracle oinstall  4019 09-27 19:20 windows.cfg.bak

七、nagios网页截图：