|
|
Nagios
1#########################通过rz或sftp命令将CentOS-Base.repo.oldboy上传到linux上
/bin/cp CentOS-Base.repo.oldboy /etc/yum.repos.d
mv CentOS-Base.repo CentOS-Base.repo.save
/bin/cp CentOS-Base.repo.oldboy CentOS-Base.repo
这样yum安装源就配好了
解决perl编译问题:
echo 'export LC_ALL=C'>> /etc/profile
source /etc/profile #←使修改生效
关闭nagios server iptables防火墙
/etc/init.d/iptables stop
禁止自启动
chkconfig iptables off
解决时间同步
/usr/sbin/ntpdate pool.ntp.org
安装nagios需要的基础软件包
yum install gcc glibc glibc-common -y
yum install gd gd-devel -y
yum install httpd php -y
vi /etc/yum.conf
more /etc/yum.repos.d/CentOS-Base.repo
创建nagios需要的用户及组
/usr/sbin/useradd -m nagios
/usr/sbin/useradd apache -M -s /sbin/nologin
/usr/sbin/groupadd nagcmd
/usr/sbin/usermod -a -G nagcmd nagios
/usr/sbin/usermod -a -G nagcmd apache
上传软件包到指定目录或通过URL下载
mkdir -p /home/rhy/tools/nagios
cd /home/rhy/tools/nagios
rz -y #从本地上传oldboytraining_nagiossoft.zip
安装nagios软件包
cd /home/rhy/tools/nagios
unzip oldboytraining_nagiossoft.zip #←使用unzip解压
tar xzf nagios-3.2.0.tar.gz
cd nagios-3.2.0
./configure --with-command-group=nagcmd
make all
make install
make install-init
make install-config
make install-commandmode
安装nagios web配置文件及创建登陆用户
#安装nagios web配置文件
make install-webconf
cd ../
注:如果为单独的apache源代码编译，则操作如下
mkdir -p /etc/httpd/conf.d/
make install-webconf
cp /etc/httpd/conf.d/nagios.conf /usr/local/apache2/conf/extra/
假定apache安装路径/usr/local/apache2，以下同，不在提及。
编辑vi /usr/local/apache2/conf/httpd.conf 增加
Include conf/extra/nagios.conf
；如果为yum安装的httpd 上面几行绿色的不需要操作。
#创建nagios监控界面登入需要的用户名及密码
htpasswd -c /usr/local/nagios/etc/htpasswd.users oldboy
添加监控报警的接收email
vi /usr/local/nagios/etc/objects/contacts.cfg +35
修改如下行：
email nagios@localhost
改为：
email hyran@126.com
保存，退出。
注意：此功能依赖本机的sendmail服务，可执行service sendmail start 开启。（
可稍后再启动）
配置apache服务
vi /etc/httpd/conf/httpd.conf +231
启动apache并加入系统自启动:
service httpd start
chkconfig httpd on
检查apache port：
netstat -lntup|grep 80
tcp 0 0 :::80 :::* LISTEN
安装nagios插件软件包
tar zxzf nagios-plugins-1.4.13.tar.gz
cd nagios-plugins-1.4.13
./configure --with-nagios-user=nagios --with-nagios-group=nagios --enable-perl-modules
make
make install
cd ..
#此编译如遇到make: *** [all] Error 2 则configure加--with-mysql=/usr/local/mysql解决
检查插件个数：
ls /usr/local/nagios/libexec/|wc -l
63
#
添加到系统开机自启动
chkconfig --add nagios
chkconfig nagios on
验证nagios配置文件（检查语法）
/etc/init.d/nagios checkconfig #←用此方法检查需要需要做下特殊处理详见附录九
[iyunv@linux training_soft]# /etc/init.d/nagios checkconfig
Running configuration check... OK.
不显示错误 用
vim /etc/init.d/nagios +178
把>后面的删掉即可
Total Warnings: 0
Total Errors: 0
Things look okay - No serious problems were detected during the pre-flight check
启动nagios
service nagios start或/etc/init.d/nagios start
出现问题
[iyunv@linux ~]# /etc/init.d/nagios start
Starting nagios:su: warning: cannot change directory to /home/nagios: No such file or directory
需要建立目录
#mkdir –p /home/nagios
检查进程：
[iyunv@nagiosserver nagios-plugins-1.4.13]#ps -ef|grep nagios
nagios 17686 1 0 21:29 ? 00:00:00 /usr/local/nagios/bin/nagios -d /usr/local/nagios/etc/nagios.cfg
关闭服务器开启的SElinux
setenforce 0#使之直接生效，
然后编辑文件
vi /etc/selinux/config #修改SELINUX项为disabled
SELINUX=disabled #重起生效
或者
chcon -R -t httpd_sys_content_t /usr/local/nagios/sbin/
chcon -R -t httpd_sys_content_t /usr/local/nagios/share/
打开网页输入 虚拟机ip/nagios
安装nrpe
tar zxvf nrpe-2.12.tar.gz
cd nrpe-2.12
./configure
make all
make install-plugin
make install-daemon
make install-daemon-config
cd ..
2#######################################################
Nagios客户端安装部分
nagios client端基础准备:
echo 'export LC_ALL=C'>> /etc/profile
source /etc/profile #←使修改生效
关闭nagios server iptables防火墙
/etc/init.d/iptables stop
禁止自启动
chkconfig iptables off
解决时间同步
/usr/sbin/ntpdate pool.ntp.org
安装nagios 客户端插件
mkdir -p /home/rhy/tools/nagios
cd /home/rhy/tools/nagios
rz -y #←从本地上传oldboytraining_nagiossoft.zip 或自行下载nagios软件：
unzip oldboytraining_nagiossoft.zip
/usr/sbin/adduser nagios -M
tar zxvf nagios-plugins-1.4.13.tar.gz
cd nagios-plugins-1.4.13
./configure --prefix=/usr/local/nagios --enable-perl-modules --enable-redhat-pthread-workaround
make
make install
cd ..
检查插件个数：
ls /usr/local/nagios/libexec/|wc -l
63
#此编译如遇到make: *** [all] Error 2 则configure加--with-mysql=/usr/local/mysql解决
#如果为red hat linux，可能会卡到如下位置：
configure: See http://nagiosplugins.org/faq/compile/configure_appears_to_hang if this next part takes a long time
checking for redhat spopen problem...
解决：
多等会就OK了。或增加编译参数 --enable-redhat-pthread-workaround重新编译
即：./configure --prefix=/usr/local/nagios --enable-perl-modules --enable-redhat-pthread-workaround
#安装nrpe
tar zxvf nrpe-2.12.tar.gz
cd nrpe-2.12
./configure
make all
make install-plugin
make install-daemon
##生成nrpe.cfg
make install-daemon-config
cd ..
#安装其它相关的插件
tar zxvf Params-Validate-0.91.tar.gz
cd Params-Validate-0.91
perl Makefile.PL
make
make install
cd ..
tar zxvf Class-Accessor-0.31.tar.gz
cd Class-Accessor-0.31
perl Makefile.PL
make
make install
cd ..
tar zxvf Config-Tiny-2.12.tar.gz
cd Config-Tiny-2.12
perl Makefile.PL
make
make install
cd ..
tar zxvf Math-Calc-Units-1.07.tar.gz
cd Math-Calc-Units-1.07
perl Makefile.PL
make
make install
cd ..
tar zxvf Regexp-Common-2010010201.tar.gz
cd Regexp-Common-2010010201
perl Makefile.PL
make
make install
cd ..
tar zxvf Nagios-Plugin-0.34.tar.gz
cd Nagios-Plugin-0.34
perl Makefile.PL
make
make install
cd ..
yum install sysstat -y
注*:上文提到的各种插件本文附带了一个大的软件包，用户也可自行去下载
配置开发的几个基础脚本插件
/bin/cp /home/rhy/tools/nagios/training_soft/check_memory.pl /usr/local/nagios/libexec
/bin/cp /home/rhy/tools/nagios/training_soft/check_iostat /usr/local/nagios/libexec #注意路径
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
配置nrpe
#config nrpe.cfg cd /usr/local/nagios/etc
vi nrpe.cfg +79
加入可以监控该服务器的nagios server端的IP。
allowed_hosts=127.0.0.1, 172.16.1.196,172.16.1.190 ←主机的IP
shift+g到结尾
注释掉或者干脆删除199-203行即下面几行
#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_hda1]=/usr/local/nagios//libexec/check_disk -w 20% -c 10% -p /dev/hda1
#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 150 -c 200
同时在下面新添加要监控的内容：
启动：nagios client
/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
ps -ef|grep nagios
nagios 28466 1 0 21:50 ? 00:00:00 /usr/local/nagios/bin/nrpe -c /usr/local/nagios/etc/nrpe.cfg -d
注意：
1、#执行完启动命令，进行检查是个良好的习惯
2、tips:重起nagios nrpe组合命令
pkill nrpe && /usr/local/nagios/bin/nrpe -c /usr/local/nagios/etc/nrpe.cfg -d
另外注意防火墙要允许5666端口加到/etc/sysconfig/iptables里，重起iptables.
vi /etc/sysconfig/iptables
-A INPUT -p udp --dport 5666 -j ACCEPT
-A INPUT -s 10.0.0.0/255.255.255.0 -p tcp -m tcp -j ACCEPT
-A INPUT -s 10.0.0.0/255.255.255.0 -p udp -m udp -j ACCEPT
测试环境，建议最好先把iptables关掉，等nagios都测试通了在来调试iptables，否则给学习测试增加了复杂度。关闭命令/etc/init.d/iptables stop
配置 nagios 监控服务
以下为server 端的操作
nagios.cfg 基本配置
在 nagios.cfg 文件中找到cfg_file 的部分，进行如下设置：
vi /usr/local/nagios/etc/nagios.cfg +34
#包含配置目录，目录下所有cfg 文件将被包含,通过这种方式便于写脚本批量处理。
需要增加的仅为以下三行
cfg_dir=/usr/local/nagios/etc/ objects/commands
cfg_dir=/usr/local/nagios/etc/ objects/services
cfg_dir=/usr/local/nagios/etc/ objects/hosts
#注*：相关配置文件用途上面已列表格说明，在此不重复了
下面绿色的配置当前不需要添加但以后会经常编辑，因此说明下
# You can specify individual object config files as shown below:
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/timeperiods.cfg
cfg_file=/usr/local/nagios/etc/objects/templates.cfg
# Definitions for monitoring etiantian.org server and service
cfg_file=/usr/local/nagios/etc/objects/host.cfg
cfg_file=/usr/local/nagios/etc/objects/service.cfg
#cfg_file=/usr/local/nagios/etc/objects/servicegroups.cfg
注意：需要注释掉如下localhost.cfg 行，否则和我们要配的会冲突原 36 行
# Definitions for monitoring the local (Linux) host
#cfg_file=/usr/local/nagios/etc/objects/localhost.cfg
生产库各配置文件实战配置例子写法
nagios 实战实例配置过程细节：
a.配置监控客户端服务器的磁盘分区、Load、Mem、Swap、磁盘io
首先需要在host.cfg 里添加客户端主机和主机组（HOST GROUP）
cd /usr/local/nagios/etc/objects/ #←进入到辅助配置文件的目录
vi host.cfg #←默认情况下host.cfg 是不存在的，需要手工创建
define host {
use linux-server
host_name 197-etiantian-1-1
alias 197-etiantian-1-1
address 172.16.1.197 #←注意是改成客户端的IP
check_command check-host-alive
max_check_attempts 3
normal_check_interval 2
retry_check_interval 2
check_period 24x7
notification_interval 300
notification_period 24x7
notification_options d,u,r
contact_groups admins
process_perf_data 1
}
#######################################################
# HOST GROUP DEFINITION
#create by ryan (qq:49000448)
#######################################################
# 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 197-etiantian-1-1
}
3#################################################################
同理添加要监控的服务配置到service.cfg
vi service.cfg
define service {
use generic-service
host_name 197-etiantian-1-1
service_description Current Load
check_command check_nrpe!check_load
max_check_attempts 2
normal_check_interval 4
retry_check_interval 4
check_period 24x7
notification_interval 1440
notification_period 24x7
notification_options w,u,c,r
contact_groups admins
process_perf_data 1
}
define service {
use generic-service
host_name 197-etiantian-1-1
service_description MEM Useage
check_command check_nrpe!check_mem
max_check_attempts 2
normal_check_interval 4
retry_check_interval 4
check_period 24x7
notification_interval 1440
notification_period 24x7
notification_options w,u,c,r
contact_groups admins
process_perf_data 1
}
define service {
use generic-service
host_name 197-etiantian-1-1
service_description Swap Useage
check_command check_nrpe!check_swap
max_check_attempts 10
normal_check_interval 3
retry_check_interval 4
check_period 24x7
notification_interval 480
notification_period workhours
notification_options w,u,c,r
contact_groups admins
process_perf_data 1
}
define service {
use generic-service
host_name 197-etiantian-1-1
service_description Disk Partition
check_command check_nrpe!check_disk
max_check_attempts 8
normal_check_interval 3
retry_check_interval 2
check_period 24x7
notification_interval 360
notification_period 24x7
notification_options w,u,c,r
contact_groups admins
process_perf_data 1
}
define service {
use generic-service
host_name 197-etiantian-1-1
service_description Disk Iostat
check_command check_nrpe!check_iostat!5!11
max_check_attempts 2
normal_check_interval 4
retry_check_interval 4
check_period 24x7
notification_interval 1440
notification_period 24x7
notification_options w,u,c,r
contact_groups admins
process_perf_data 1
}
#注*:
1.以上service.cfg 中添加了对磁盘分区、Load、Mem、Swap、磁盘io 的监控
2.以上hots.cfg 及service 的内容的详细解释见附录八
若此时执行如下检查nagios 语法命令：
检查语法：
/etc/init.d/nagios checkconfig
会发现报错：
Checking services...
Error: Service check command 'check_nrpe' specified in service 'Swap Useage' for host '197-etiantian-1-1'not
defined anywhere!
省略若干。。
Total Warnings: 0
Total Errors: 5
根据错误提示，我们可以知道，是check_nrpe 插件没有定义导致。
#注意没有出现
Total Warnings: 0
Total Errors: 5
而是出现的
[iyunv@linux objects]# /etc/init.d/nagios checkconfig
Running configuration check...
Nagios Core 3.2.0
……………………….
Processing object config file '/usr/local/nagios/etc/objects/commands.cfg'...
Processing object config file '/usr/local/nagios/etc/objects/contacts.cfg'...
Processing object config file '/usr/local/nagios/etc/objects/timeperiods.cfg'...
Processing object config file '/usr/local/nagios/etc/objects/templates.cfg'...
Processing object config directory '/usr/local/nagios/etc/commands'...
Error: Could not open config directory '/usr/local/nagios/etc/commands' for reading.
………………………….
CONFIG ERROR! Check your Nagios configuration.
#配置文件没有改IP
需要在commands.cfg 中加入check_nrpe 的插件配置
#vi commands.cfg 进入后按shift+g 切到结尾加入下面内容。
# 'check_nrpe' command definition
define command{
command_name check_nrpe
command_line $USER1$/check_nrpe -H $HOSTADDRESS$ -c $ARG1$
}
此时重新执行检查语法命令：
检查语法：
/etc/init.d/nagios checkconfig
Total Warnings: 0
Total Errors: 0
注*:修改配置不需要restart
打开网页会出现
It appears as though you do not have permission to view information for any of theservices you requested...
解决方法
[iyunv@nagiosserver objects]#cd /usr/local/nagios/etc
[iyunv@nagiosserver objects]#vi cgi.cfg +119
#把在1.6 节建立的用户oldboy 加到后面，注意用逗号隔开。
#default_user_name=oldboy
authorized_for_system_information=nagiosadmin,oldboy
authorized_for_configuration_information=nagiosadmin,oldboy
authorized_for_system_commands=nagiosadmin,oldboy
authorized_for_all_services=nagiosadmin,oldboy
authorized_for_all_hosts=nagiosadmin,oldboy
authorized_for_all_service_commands=nagiosadmin,oldboy
authorized_for_all_host_commands=nagiosadmin,oldboy
记得reload nagios 命令为：/etc/init.d/nagios reload
增加从nagios 服务器端发起的监控：如url 地址，端口监控
1.添加要监控的服务配置到service.cfg
########check url
#check_weburl (http://blog.etiantian.org) 197-etiantian-1-1
define service{
use generic-service
host_name 197-etiantian-1-1
service_description blog_url
check_command check_weburl!-H blog.etiantian.org
max_check_attempts 3
normal_check_interval 2
retry_check_interval 1
check_period 24x7
notification_interval 30
notification_period 24x7
notification_options w,u,c,r
contact_groups admins
}
#check_weburl(http://blog.etiantian.org/oldboy/) 197-etiantian-1-1
define service{
use generic-service
host_name 197-etiantian-1-1
service_description blog_oldboy_url
check_command check_weburl!-H blog.etiantian.org -u /oldboy/
max_check_attempts 3
normal_check_interval 2
retry_check_interval 1
check_period 24x7
notification_interval 30
notification_period 24x7
notification_options w,u,c,r
contact_groups admins
}
|
|
窥视卡
雷达卡
发表于 2015-11-22 17:18:07