nagios监控服务器的搭建(借鉴总结)
下载软件wgethttp://prdownloads.sourceforge.net/sourceforge/nagios/nagios-3.2.1.tar.gz
http://prdownloads.sourceforge.net/sourceforge/nagiosplug/nagios-plugins-1.4.14.tar.gz
http://prdownloads.sourceforge.net/sourceforge/nagios/nrpe-2.12.tar.gz
安装环境搭建
yum -y install gcc glibc glibc-common gd gd-devel
安装apache+php rpm或者tar包都可以
创建用户
groupadd nagios
usermod -a -G nagcmd nagios
usermod -a -G nagcmd apache (tar包apache用户是daemon)
安装nagios主程序
tar nagios
cd nagios
./configure --with-command-group=nagcmd \
> --with-nagios-user=nagios \
> --with-nagios-group=nagios
make all
make install
make install-init #生成init 启动脚本
make install-commandmode #设置相应的目录权限
make install-config #生成模板配置文件
make install-webconf #生成apache 配置文件(如果是tar包需要手动创建# pwd
/etc/httpd/conf.d 里面建nagios.conf,然后把里面产生的数据写到tar包apache的主配置文档httpd.conf最后边)
htpasswd -c /usr/local/nagios/etc/htpasswd.users
nagiosadmin #为apache 创建一个登陆用户，注意用户名是nagiosadmin
注意：第一次添加用户用-c 选项，以后再添加千万别在用这个选项了，会覆盖以前的所有用户。
添加开机启动
chkconfig --add nagios
chkconfig nagios on
chkconfig httpd on
安装nagios插件nagios-plugins
# cd /usr/local/src
# tar zxvf nagios-plugins-1.4.14.tar.gz
# cd nagios-plugins-1.4.14
# ./configure --prefix=/usr/local/nagios
--with-nagios-user=nagios --with-nagios-group=nagios
# make && make install
启动nagios
service httpd start
service nagios start
web查看
ip/nagios/ 如果无显示后面加index.php
添加需要的配置文件
vi /usr/local/nagios/etc/nagios.cfg
cfg_file=/usr/local/nagios/etc/objects/commands.cfg #命令配置文件
cfg_file=/usr/local/nagios/etc/objects/contacts.cfg #联系人配置文件
cfg_file=/usr/local/nagios/etc/objects/timeperiods.cfg
cfg_file=/usr/local/nagios/etc/objects/templates.cfg
cfg_file=/usr/local/nagios/etc/objects/contactgroups.cfg #联系组定义文件
cfg_file=/usr/local/nagios/etc/objects/hosts.cfg #增加主机配置文件
cfg_file=/usr/local/nagios/etc/objects/hostgroups.cfg #增加主机组配置文件
cfg_file=/usr/local/nagios/etc/objects/services.cfg #增加服务配置文件
cfg_file=/usr/local/nagios/etc/objects/servicegroups.cfg #增加服务组配置文件
# Definitions for monitoring the local (Linux) host
#cfg_file=/usr/local/nagios/etc/objects/localhost.cfg #注释掉
主机定义文件
# vi /usr/local/nagios/etc/objects/hosts.cfg
define host{
host_name Nagios-Server #设置主机的名字，该名字会出现在
hostgroups.cfg 和services.cfg 中。
alias Nagios Server #别名
address 192.168.140.128 #主机的IP 地址
check_command check-host-alive #检查的命令
check_interval 5 #检测的时间间隔
retry_interval 1 #检测失败后重试的时间间隔
max_check_attempts 5 #最大重试次数
check_period 24x7 #检测的时段
process_perf_data 0
retain_nonstatus_information 0
contact_groups sagroup #联系组
notification_interval 30 #通知的时间间隔
notification_period 24x7 #通知的时间段
notification_options d,u,r #通知的选项
#w—报警(warning)，u—未知(unkown)
#c—严重(critical)，r—从异常情况恢复正常
}
define host{
host_name Nagios-Client
alias Nagios Client
address 192.168.140.129
check_command check-host-alive
check_interval 5
retry_interval 1
max_check_attempts 5
check_period 24x7
process_perf_data 0
retain_nonstatus_information 0
contact_groups sagroup
notification_interval 30
notification_period 24x7
notification_options d,u,r
}
主机组文件
# vi /usr/local/nagios/etc/objects/hostgroups.cfg
define hostgroup {
hostgroup_name Nagios-Example #主机组名字
alias Nagios Example #主机组别名
members Nagios-Server,Nagios-Client #主机组成员，用逗号隔开
}
服务定义文件
vi /usr/local/nagios/etc/objects/services.cfg
define service {
host_name Nagios-Server #主机名
service_description check-host-alive #服务描述
check_period 24x7 #检测的时间段
max_check_attempts 4
normal_check_interval 3
retry_check_interval 2
contact_groups sagroup
notification_interval 10
notification_period 24x7
notification_options w,u,c,r
check_command check-host-alive#调用的命令
}
define service {
host_name Nagios-Client
service_description check-host-alive
check_period 24x7
max_check_attempts 4
normal_check_interval 3
retry_check_interval 2
contact_groups sagroup
notification_interval 10
notification_period 24x7
notification_options w,u,c,r
check_command check-host-alive
}
服务组定义文件
vi /usr/local/nagios/etc/objects/servicegroup.cfg
define servicegroup{
servicegroup_name Host-Alive
alias Host Alive
members Nagios-Server,check-host-alive,Nagios-Client,check-host-alive
}
联系人定义文件
vi /usr/local/nagios/etc/objects/contacts.cfg
define contact{
contact_name nagiosadmin
use generic-contact
alias System Administrator
email nagios@localhost
}
定义联系组
# vi /usr/local/nagios/etc/objects/contactgroups.cfg
define contactgroup{
contactgroup_name sagroup
alias Nagios Administrators
members nagiosadmin
}
检查错误
/usr/local/nagios/bin/nagios -v /usr/local/nagios/etc/nagios.cfg
监控远程服务器
服务器端
安装NRPE
# cd /usr/local/src/
# tar zxvf nrpe-2.12.tar.gz
# cd nrpe-2.12
# ./configure && make all
# make install-plugin
# make install-daemon
# make install-daemon-config
# make install-xinetd
配置NRPE
# vi /etc/xinetd.d/nrpe
# default: on
# description: NRPE (Nagios Remote Plugin Executor)
service nrpe
{
flags = REUSE
socket_type = stream
port = 5666
wait = no
user = nagios
group = nagios
server = /usr/local/nagios/bin/nrpe
server_args = -c /usr/local/nagios/etc/nrpe.cfg --inetd
log_on_failure += USERID
disable = no
only_from = 127.0.0.1 192.168.140.129 添加要监控主机的ip
vim /etc/services
nrpe 5666/tcp #nrpe
/etc/init.d/xinetd restart 重启
netstat -na | grep 5666 检测是否启动
修改命令定义文件
vim /usr/local/nagios/etc/objects/commands.cfg
define command{
command_name check_nrpe #用于远程监控的命令
command_line /usr/local/nagios/libexec/check_nrpe -H $HOSTADDRESS$ -c $ARG1$
}
受监控服务器配置
useradd -s /sbin/nologin nagios
安装nagios-plugin 与nrpe
安装步骤同上
配置nrpe
vi /etc/xinetd.d/nrpe
only_from = 127.0.0.1 192.168.140.128 #加上nagios服务器ip
添加服务端口
vim /etc/services
nrpe 5666/tcp #nrpe
重启
/etc/init.d/xinetd restart
查看
netstat -na | grep 5666
chown -R nagios:nagios /usr/local/nagios/
修改受控端nrpe配置文档
# vi /usr/local/nagios/etc/nrpe.cfg
command=/usr/local/nagios/libexec/check_load -w 15,10,5 -c 30,25,20
command=/usr/local/nagios/libexec/check_disk -w 20% -c 10%
-p /dev/mapper/VolGroup00-LogVol00 #我的Client 端根分区时LVM 逻辑卷 如果是普通的就是-p /dev/sda1
command=/usr/local/nagios/libexec/check_procs -w 5 -c 10 -s Z
command=/usr/local/nagios/libexec/check_procs -w 150 -c 200
command=/usr/local/nagios/libexec/check_swap -w 20% -c 10%
4.4 修改Nagios 服务器服务定义文件
# vi /usr/local/nagios/etc/objects/services.cfg
添加服务
define service {
host_name Nagios-Client
service_description check-users
check_period 24x7
max_check_attempts 4
normal_check_interval 3
retry_check_interval 2
contact_groups sagroup
notification_interval 10
notification_period 24x7
notification_options w,u,c,r
check_command check_nrpe!check_users
}
define service {
host_name Nagios-Client
service_description check-load
check_period 24x7
max_check_attempts 4
normal_check_interval 3
retry_check_interval 2
contact_groups sagroup
notification_interval 10
notification_period 24x7
notification_options w,u,c,r
check_command check_nrpe!check_load
}
define service {
host_name Nagios-Client
service_description check-/
check_period 24x7
max_check_attempts 4
normal_check_interval 3
retry_check_interval 2
contact_groups sagroup
notification_interval 10
notification_period 24x7
notification_options w,u,c,r
check_command check_nrpe!check_/
}
然后/etc/init.d/nagios> 监控内存
/usr/local/nagios/libexec 添加插件
check_mem.sh 插件
#script to check real memory usage
# L.Gill 02/05/06 - V.1.0
# ------------------------------------------
# ########Script Modifications##########
# ------------------------------------------
# Who When What
# --- ---- ----
# LGill 17/05/06"$percent" lt 1% fix - sed edits dc result beggining with "."
#
#
#!/bin/bash
USAGE="`basename $0` [-w|--warning] [-c|--critical]"
THRESHOLD_USAGE="WARNING threshold must be greater than CRITICAL: `basename $0` $*"
calc=/tmp/memcalc
percent_free=/tmp/mempercent
critical=""
warning=""
STATE_OK=0
STATE_WARNING=1
STATE_CRITICAL=2
STATE_UNKNOWN=3
# print usage
if [[ $# -lt 4 ]]
then
echo ""
echo "Wrong Syntax: `basename $0` $*"
echo ""
echo "Usage: $USAGE"
echo ""
exit 0
fi
# read input
while [[ $# -gt 0 ]]
do
case "$1" in
-w|--warning)
shift
warning=$1
;;
-c|--critical)
shift
critical=$1
;;
esac
shift
done
# verify input
if [[ $warning -eq $critical || $warning -lt $critical ]]
then
echo ""
echo "$THRESHOLD_USAGE"
echo ""
echo "Usage: $USAGE"
echo ""
exit 0
fi
# Total memory available
total=`free -m | head -2 |tail -1 |gawk '{print $2}'`
# Total memory used
used=`free -m | head -2 |tail -1 |gawk '{print $3}'`
# Calc total minus used
free=`free -m | head -2 |tail -1 |gawk '{print $2-$3}'`
# normal values
#echo "$total"MB total
#echo "$used"MB used
#echo "$free"MB free
# make it into % percent free = ((free mem / total mem) * 100)
echo "5" > $calc # decimal accuracy
echo "k" >> $calc # commit
echo "100" >> $calc # multiply
echo "$free" >> $calc # division integer
echo "$total" >> $calc # division integer
echo "/" >> $calc # division sign
echo "*" >> $calc # multiplication sign
echo "p" >> $calc # print
percent=`/usr/bin/dc $calc|/bin/sed 's/^\./0./'|/usr/bin/tr "." " "|/usr/bin/gawk {'print $1'}`
#percent1=`/usr/bin/dc $calc`
#echo "$percent1"
if [[ "$percent" -le$critical ]]
then
echo "CRITICAL - $free MB ($percent%) Free Memory"
exit 2
fi
if [[ "$percent" -le$warning ]]
then
echo "WARNING - $free MB ($percent%) Free Memory"
exit 1
fi
if [[ "$percent" -gt$warning ]]
then
echo "OK - $free MB ($percent%) Free Memory"
exit 0
fi
给予执行权限
nrpe里添加命令
command=/usr/local/nagios/libexec/check_mem.sh-w 10 -c 5
做短信与邮件报警
修改contacts.cfg添加联系人邮箱
define contact{
contact_name nagiosadmin
use generic-contact
alias System Administrator
email 15910613577@139.com 575926838@qq.com
}
用第三方邮件sendEmail报警
修改 command.cfg在原有报警机制上更改
# 'notify-host-by-email' command definition
define command{
command_name notify-host-by-email
command_line /usr/bin/printf "%b" "***** Nagios-BJ *****\n\nNotification Type: $NOTIFICATIONTYPE$\nHost: $HOSTNAME$\nState: $HOSTSTATE$\nAddress:
$HOSTADDRESS$\nInfo: $HOSTOUTPUT$\n\nDate/Time: $LONGDATETIME$\n" | /usr/local/bin/sendEmail -f fanhb***@sina.com -t $CONTACTEMAIL$ -s smtp.sina.com -u "** $
NOTIFICATIONTYPE$ Host Alert: $HOSTNAME$ is $HOSTSTATE$ **" -xu fanhb***@sina.com -xp ******* -l /var/log/sendEmail.log
}
# 'notify-service-by-email' command definition
define command{
command_name notify-service-by-email
command_line /usr/bin/printf "%b" "***** Nagios-BJ *****\n\nNotification Type: $NOTIFICATIONTYPE$\n\nService: $SERVICEDESC$\nHost: $HOSTNAME$\nAdd
ress: $HOSTADDRESS$\nState: $SERVICESTATE$\n\nDate/Time: $LONGDATETIME$\n\nAdditional Info:\n\n$SERVICEOUTPUT$\n" | /usr/local/bin/sendEmail -f fanhb517@sina
.com -t $CONTACTEMAIL$ -s smtp.sina.com -u"** $NOTIFICATIONTYPE$ Service Alert: $HOSTNAME$/$SERVICEDESC$ is $SERVICESTATE$ **" -xu fanhb***@sina.com -xp ******* -l /var/log/sendEmail.log
}
安装sendEmail
[*]wget http://caspian.dotconf.net/menu/ ... dEmail-v1.55.tar.gz
[*]tar ?zxvf sendEmail-v1.55.tar.gz
[*]cd sendEmail-v1.55
[*]cp sendEmail /usr/local/bin
[*]chmod 0755 /usr/local/bin/sendEmail
解释:
-f 表示发送者的邮箱
-t 表示接收者的邮箱
-s 表示SMTP服务器的域名或者ip
-u 表示邮件的主题
-xu 表示SMTP验证的用户名
-xp 表示SMTP验证的密码(注意,这个密码貌似有限制,例如我用d!5neyland就不能被正确识别)
-m 表示邮件的内容
剩下的就是139邮箱手机短信通知的设置了略
先这么多,想起再写
页:
[1]