Nagios 是一个开源的监控工具,能够监控 windows、Linux等系统的主机状态信息,以及交换机、路由器等网络设备。Nagios有一个主程序(Nagios)、一个插件程序(Nagios-plugins)和一些可选的附加程序 (NPRE、NSClient++、NSCA 和NDAOUtils)等组成。
服务器端:安装nagios和nagios-plugins插件(必选),NDOUtils(可选),存储配置信息和产生的数据。
客服端:linux/unix 安装NRPE组件( 被动方式),windows安装NSClient++组件。
服务器 nagios 192.168.122.34
客户端 nfssvr 192.168.122.41
一、 服务器安装
在nagios上执行操作
1. 配置对时,192.168.122.1为服务器
echo '#time sync by oliver on 2016-09-30 ' >> /var/spool/cron/root
echo '*/5 * * * * /usr/sbin/ntpdate 192.168.122.1 > /dev/null 2>&1' >> /var/spool/cron/root
crontab -l
2. 安装软件
yum install -y gcc glibc glibc-common
yum install -y gd gd-devel
yum install -y mysql-server mysql-devel
yum install -y httpd php php-gd
3. 创建用户组和用户
/usr/sbin/useradd nagios -g nagios
/usr/sbin/useradd apache -g nagios -M -s /sbin/nologin
/usr/sbin/groupadd nagcmd
/usr/sbin/usermod -a -G nagcmd nagios
/usr/sbin/usermod -a -G nagcmd apache
4. 启动httpd
vi /etc/httpd/conf/httpd.conf
设置
ServerName 192.168.122.34:80
service httpd start 或者 /etc/init.d/httpd start
5. 下载nagios的软件包
check_iostat
check_memory.pl
Class-Accessor-0.31.tar.gz
Config-Tiny-2.12.tar.gz
libart_lgpl-2.3.17.tar.gz
Math-Calc-Units-1.07.tar.gz
nagios-3.5.1.tar.gz
Nagios-Plugin-0.34.tar.gz
nagios-plugins-1.4.16.tar.gz
nrpe-2.12.tar.gz
Params-Validate-0.91.tar.gz
pnp-0.4.14.tar.gz
Regexp-Common-2010010201.tar.gz
rrdtool-1.2.14.tar.gz
在网上可以搜到。可以进入http://www.filewatcher.com/ 这个网站搜。
6. 编译nagios-3.5.1.tar.gz
tar -xvf 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
htpasswd -bc /usr/local/nagios/etc/htpasswd.users nagios 123456
service httpd restart
配置邮件(这一步没有实际测试)
sed -i 's#nagios@localhost#em21@qq.com#g' /usr/local/nagios/etc/objects/contacts.cfg
7. 编译nagios-plugins-1.4.16.tar.gz
tar xvf 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 ..
确认configure的输出,然后在执行make 和 make install
config.status: creating po/Makefile
--with-apt-get-command:
--with-ping6-command: /bin/ping6 -n -U -w %d -c %d %s
--with-ping-command: /bin/ping -n -U -w %d -c %d %s
--with-ipv6: yes
--with-mysql: /usr/bin/mysql_config
--with-openssl: yes
--with-gnutls: no
--enable-extra-opts: no
--with-perl: /usr/bin/perl
--enable-perl-modules: yes
--with-cgiurl: /nagios/cgi-bin
--with-trusted-path: /bin:/sbin:/usr/bin:/usr/sbin
--enable-libtap: no
8. 编译nrpe-2.12.tar.gz
tar xvf nrpe-2.12.tar.gz
cd nrpe-2.12
./configure
make all
make install-plugin
make install-daemon
make install-daemon-config
ls /usr/local/nagios/libexec/check_nrpe
9.启动httpd和nagios
chkconfig httpd on
chkconfig nagios on
二、 客服端安装配置
在nfssvr上操作
1.安装基本软件、增加用户
yum install -y gcc glibc glibc-common
yum install -y mysql-server mysql-devel
yum install -y perl-devel perl-CPAN openssl-devel
useradd nagios -M -s /sbin/nologin
2.编译nagios-plugins-1.4.16.tar.gz
tar -xvf nagios-plugins-1.4.16.tar.gz
cd nagios-plugins-1.4.16
./configure --with-nagios=nagios --with-nagios-group=nagios --enable-perl-modules --with-mysql
make
make install
cd ..
检查插件个数
[root@nfssvr _soft]# ls /usr/local/nagios/libexec/ |wc -l
58
[root@nfssvr _soft]#
3.安装插件
#---------------
tar xvf nrpe-2.12.tar.gz
cd nrpe-2.12
./configure
make all
make install-plugin
make install-daemon
make install-daemon-config
cd ..
#-------------------------
tar xvf Params-Validate-0.91.tar.gz
cd Params-Validate-0.91
perl Makefile.PL
make
make install
cd ..
#----------------------------------
tar xvf Class-Accessor-0.31.tar.gz
cd Class-Accessor-0.31
perl Makefile.PL
make
make install
cd ..
#---------------------------------
tar xvf Config-Tiny-2.12.tar.gz
cd Config-Tiny-2.12
perl Makefile.PL
make
make install
cd ..
#-------------------------------
tar xvf Math-Calc-Units-1.07.tar.gz
cd Math-Calc-Units-1.07
perl Makefile.PL
make
make install
cd ..
#-------------------------------
tar xvf Regexp-Common-2010010201.tar.gz
cd Regexp-Common-2010010201
perl Makefile.PL
make
make install
cd ..
#-------------------------------
tar xvf Nagios-Plugin-0.34.tar.gz
cd Nagios-Plugin-0.34
perl Makefile.PL
make
make install
cd ..
yum install -y sysstat
yum install -y dos2unix
cp /_soft/check_memory.pl /usr/local/nagios/libexec
cp /_soft/check_iostat /usr/local/nagios/libexec
chmod 755 check_memory.pl
chmod 755 check_iostat
dos2unix /usr/local/nagios/libexec/check_memory.pl
dos2unix /usr/local/nagios/libexec/check_iostat
4.配置nrpe服务
[root@nfssvr etc]# cd /usr/local/nagios/etc
[root@nfssvr etc]# sed -n '79'p nrpe.cfg
allowed_hosts=127.0.0.1
[root@nfssvr etc]# sed -i 's#allowed_hosts=127.0.0.1#allowed_hosts=127.0.0.1,192.168.122.34#g' nrpe.cfg
[root@nfssvr etc]# sed -n '79'p nrpe.cfg
allowed_hosts=127.0.0.1,192.168.122.34
vi nrpe.cfg
199~233行替换为
command[check_load]=/usr/local/nagios/libexec/check_load -w 15,10,5 -c 30,25,20
command[check_hda1]=/usr/local/nagios/libexec/check_memory.pl -w 10% -c 3%
command[check_hda1]=/usr/local/nagios/libexec/check_disk -w 15% -c 7% -p /
command[check_hda1]=/usr/local/nagios/libexec/check_swap -w 20% -c 10%
command[check_hda1]=/usr/local/nagios/libexec/check_iostat -w 6 -c 10
启动nrep服务并检查
/usr/local/nagios/bin/nrpe -c /usr/local/nagios/etc/nrpe.cfg -d
netstat -lntup|grep nrpe
ps -ef|grep nrpe |grep -v grep
三、服务器端配置
1.编辑 /usr/local/nagios/etc/nagios.cfg
在34行下增加
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
注释
#cfg_file=/usr/local/nagios/etc/objects/localhost.cfg
2. 在ojbects 下将services目录
3. 配置/usr/local/nagios/etc/objects/hosts.cfg
cd /usr/local/nagios/etc/objects
head -51 localhost.cfg > hosts.cfg
chown nagios.nagios /usr/local/nagios/etc/objects/hosts.cfg
增加host
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 nfssvr
alias nfssvr
address 192.168.122.41
}
在组内增加一个成员
define hostgroup{
hostgroup_name linux-servers ; The name of the hostgroup
alias Linux Servers ; Long name of the group
members nfssvr ; Comma separated list of hosts that belong to this group
}
4. 配置/usr/local/nagios/etc/objects/services.cfg
touch services.cfg
chown nagios.nagios services.cfg
增加以下内容
define service {
use generic-service
host_name nfssvr
service_description Disk Partition
check_command check_nrpe!check_disk
}
define service {
use generic-service
host_name nfssvr
service_description Swap Useage
check_command check_nrpe!check_swap
}
define service {
use generic-service
host_name nfssvr
service_description MEM Useage
check_command check_nrpe!check_mem
}
define service {
use generic-service
host_name nfssvr
service_description Current Load
check_command check_nrpe!check_load
}
define service {
use generic-service
host_name nfssvr
service_description Disk Iostat
check_command check_nrpe!check_iostat!5!11
}
define service {
use generic-service
host_name nfssvr
service_description PING
check_command check_ping!100.0,20%!500.0,60%
}
5. 配置/usr/local/nagios/etc/objects/commands.cfg
增加以下内容
define command{
command_name check_nrpe
command_line $USER1$/check_nrpe -h $HOSTADDRESS$ -c $ARG1$
}
6.建目录
mkdir -p /usr/local/nagios/etc/objects/services
chown -R nagios.nagios services
7. 修改 /usr/local/nagios/etc/cgi.cfg
将授权用户改为nagios,否则用nagios登录,不能查看相应的信息。
grep ^"authorized_for" cgi.cfg
sed -i 's#nagiosadmin#nagios#g' cgi.cfg
8. 验证
/usr/local/nagios/bin/nagios -v /usr/local/nagios/etc/nagios.cfg
验证无误后重新启动nagios服务
servie nagios restart
9. 浏览器登录
四、问题诊断
如出现问题,可用以下方法诊断。
1. 检查客服端的nrpe是否能连接上,连接上会打印出版本号
在服务器端操作
[root@nagios libexec]# pwd
/usr/local/nagios/libexec
[root@nagios libexec]# ./check_nrpe -H 192.168.122.41
Connection refused by host
[root@nagios libexec]# ./check_nrpe -H 192.168.122.41
NRPE v2.12
[root@nagios libexec]#
2. 检查某个service是否正常
在服务器端操作
[root@nagios libexec]# ./check_nrpe -H 192.168.122.41 -c check_mem
OK - 77.9% (391240 kB) free.|TOTAL=502096KB;;;; USED=110856KB;;;; FREE=391240KB;;;; CACHES=54296KB;;;;
[root@nagios libexec]# ./check_nrpe -H 192.168.122.41 -c check_disk
DISK OK - free space: / 8937 MB (90% inode=95%);| /=990MB;8895;9732;0;10465
[root@nagios libexec]#
如无返回可以倒客服端上执行相应的命令,及在客户端上执行如下命令(在/usr/local/nagios/etc/nrpe.cfg)
[root@nfssvr etc]# /usr/local/nagios/libexec/check_disk -w 15% -c 7% -p /
DISK OK - free space: / 8937 MB (90% inode=95%);| /=990MB;8895;9732;0;10465
[root@nfssvr etc]#