目标
配置分布式的icinga2监控系统。分布式监控适用于服务器遍布在多个区域，且需要一个master做统一管理。
搭建环境
服务器
系统: ubuntu 15.04/ubuntu 14.04
icinga2主节点: 192.168.19.77 负责分发配置，统一展示监控结果。
icinga2子节点1: 192.168.19.45 负责监控openstack RegionOne区域的所有服务器
icinga2子节点2: 192.168.19.30 负责将空openstack RegionTwo区域的所有服务器
为了充分利用现有的nagios插件，使用nrpe监控服务器。
安装配置icinga2
注意: 如果特别说明，所有操作均在192.168.19.77,45,30执行。
设置包源
# add-apt-repository ppa:formorer/icinga
# apt-get update
安装icinga2
# apt-get install icinga2
安装classicui界面
在192.168.77上执行
apt-get install icinga2-classicui -y
配置分布式监控
设置ssl
在192.168.77上执行
生成ca证书
#icinga2 pki new-ca
生成各个节点需要用的key,crt
设置节点名
key与crt的名字需要与节点名吻合，默认使用hostname。如果要自定义节点名需要编辑/etc/icinga2/constants.conf,修改如下配置
const NodeName = “node-master”
node-master是新的节点名
生成key,crt
# cd /tmp
##192.168.19.77
# icinga2 pki new-cert --cn node-master --key node-master.key --csr node-master.csr
# icinga2 pki sign-csr --csr node-master.csr --cert node-master.crt
##192.168.19.45
# icinga2 pki new-cert --cn node-45 --key node-45.key --csr node-45.csr
# icinga2 pki sign-csr --csr node-45.csr --cert node-45.crt
##192.168.19.30
# icinga2 pki new-cert --cn node-30 --key node-30.key --csr node-30.csr
# icinga2 pki sign-csr --csr node-30.csr --cert node-30.crt
分布复制ca.crt, .crt, .key到3台服务器的 /etc/icinga2/pki/目录。下面显示的是192.168.19.77的pki目录
# ll /etc/icinga2/pki/
total 20
drwxr-xr-x 2 root root 4096 May 11 17:19 ./
drwxr-x— 9 nagios nagios 4096 May 13 12:09 ../
-rw-rw-rw- 1 root root 1688 May 11 15:25 ca.crt
-rw-rw-rw- 1 root root 1663 May 11 15:28 node-master.crt
-rw-rw-rw- 1 root root 3243 May 11 15:26 node-master.key
启用api功能
# icinga2 feature enable api
添加accept_config = true, accept_commands = true参数
# vim /etc/icinga2/features-enabled/api.conf
/**
* The API listener is used for distributed monitoring setups.
*/
object ApiListener “api” {
cert_path = SysconfDir + “/icinga2/pki/” + NodeName + “.crt”
key_path = SysconfDir + “/icinga2/pki/” + NodeName + “.key”
ca_path = SysconfDir + “/icinga2/pki/ca.crt”
ticket_salt = TicketSalt
accept_config = true
accept_commands = true
}
# service icinga2 restart
配置endopoint,zone
EndPoint 需要与NodeName一致。
# vim /etc/icinga2/zones.conf
object Endpoint “node-master” {
host = “192.168.19.77”
}
object Endpoint “node-45” {
host = “192.168.19.45”
}
object Endpoint “node-30” {
host = “192.168.19.30”
}
object Zone “zone-master” {
endpoints = [ “node-master” ]
}
object Zone “zone-45” {
parent = “zone-master”
endpoints = [ “node-45” ]
}
object Zone “zone-30” {
parent = “zone-master”
endpoints = [ “node-30” ]
}
object Zone “global-templates” {
global = true
}
这里配置了4个区域，分别是zone-master,zone-45,zone-30,global-templates。global-templates区域中的配置会分发到所有的区域。
配置文件管理
创建配置目录，目录名要与区域名一致。
在192.168.77上执行
# mkdir /etc/icinga2/zones.d/global-templates/
# mkdir /etc/icinga2/zones.d/zone-30/
# mkdir /etc/icinga2/zones.d/zone-45/
# mkdir /etc/icinga2/zones.d/zone-master/
将/etc/icinga2/conf.d中的文件复制到/etc/icinga2/zones.d/global-templates/
# cp -rf /etc/icinga2/conf.d/* /etc/icinga2/zones.d/global-templates/
注释掉3台服务器上conf.d目录
# vim /etc/icinga2/icinga2.conf
#include_recursive "conf.d"
配置master将空两个子节点
# vim /etc/icinga2/zones.d/hosts.conf
object Host NodeName {
import "generic-host"
address = "127.0.0.1"
vars.os = "Linux"
vars.disks["disk"] = {
}
vars.notification["mail"] = {
groups = [ "icingaadmins" ]
}
/*NIC dell2950 */
vars.interfaces["eth0"]={
interface_speed = 100
}
}
object Host "node-45" {
import "generic-host"
address = "192.168.19.45"
vars.os = "Linux"
vars.disks["disk"] = {
}
vars.notification["mail"] = {
groups = [ "icingaadmins" ]
}
/*NIC*/
vars.interfaces["em1"]={
interface_speed = 1000
}
/* openstack */
vars.openstack_controller_listen="192.168.19.45"
vars.openstack["keystone"]="controller"
vars.openstack["cinder"]="controller"
vars.openstack["glance"]="controller"
vars.openstack["heat"]="controller"
vars.openstack["nova"]="controller"
}
object Host "node-30" {
import "generic-host"
address = "192.168.19.30"
vars.os = "Linux"
vars.disks["disk"] = {
}
vars.notification["mail"] = {
groups = [ "icingaadmins" ]
}
/*NIC*/
vars.interfaces["em1"]={
interface_speed = 1000
}
}
重启icinga2，查看结果
# service icinga2 restart
打开http://192.168.19.77/icinga2-classicui/
配置正确的话，应该可以看到77，45，39服务器的监控信息
使用nrpe监控服务器
源码安装
不用apt的原因是apt安装的nrpe不接受监控命令传参。
编译安装
# apt-get install build-essential libssl-dev libssl0.9.8 libssl-dev unzip make -y
# cd /usr/local/src
# wget http://sourceforge.net/projects/nagios/files/nrpe-2.x/nrpe-2.15/nrpe-2.15.tar.gz/download -O nrpe-2.15.tar.gz
# tar -xf nrpe-2.15.tar.gz
# cd nrpe-2.15
# ./configure --enable-command-args --with-ssl=/usr/bin/openssl --with-ssl-lib=/usr/lib/x86_64-linux-gnu
# make all
# make install-daemon
添加配置文件
# mkdir /etc/nagios
# vim /etc/nagios/nrpe.cfg
log_facility=daemon
pid_file=/var/run/nrpe.pid
server_port=5666
nrpe_user=nagios
nrpe_group=nagios
allowed_hosts=127.0.0.1,192.168.19.30,192.168.19.45,192.168.19.77
dont_blame_nrpe=1
debug=0
command_timeout=60
connection_timeout=300
command[check_load]=/usr/lib/nagios/libexec/check_load -w 20,15,10 -c 50,40,30
command[check_disk]=/usr/lib/nagios/libexec/check_disk -w 10% -c 5% -W 10% -K 5% -A
command[check_mem]=/usr/lib/nagios/libexec/check_mem -u -C -w 85 -c 90
command[check_proc_num]=/usr/lib/nagios/libexec/check_procs -m PROCS -w 1500:1000 -c 300000:1500
command[check_zombie_procs]=/usr/lib/nagios/libexec/check_procs -w 5 -c 10 -s Z
command[check_swap]=/usr/lib/nagios/libexec/check_swap -a -w 30% -c 15%
command[check_local_port]=/usr/lib/nagios/libexec/check_tcp -H localhost -p $ARG1$ -w 2 -c 5
command[check_linux_raid]=/usr/lib/nagios/libexec/check_linux_raid
command[check_md_raid]=/usr/lib/nagios/libexec/check_md_raid
command[check_icmp]=/usr/lib/nagios/libexec/check_icmp $ARG1$
command[check_lvs]=/usr/lib/nagios/libexec/check_ipvsadm
command[check_backup]=/usr/lib/nagios/libexec/check_backup
command[check_dns]=/usr/lib/nagios/libexec/check_dns
command[check_http]=/usr/lib/nagios/libexec/check_http
command[check_rsyncd]=/usr/lib/nagios/libexec/check_rsyncd
command[check_monitorwebbackup]=/usr/lib/nagios/libexec/check_monitorwebbackup
command[check_monitormysqlbackup]=/usr/lib/nagios/libexec/check_monitormysqlbackup
command[check_diskhealth]=/usr/lib/nagios/libexec/check_openmanage --check storage -b ctrl_fw=all/ctrl_driver=all/ctrl_stdr=all/bat_charge=all/encl=all/ps=all -t 30
command[check_safe]=/usr/lib/nagios/libexec/check_safe $ARG1$
command[check_tcptraffic]=/usr/lib/nagios/plugins/contrib/check_tcptraffic -w $ARG1$ -c $ARG2$ -s $ARG3$ -i $ARG4$
在rc.local加入启动命令
# vim /etc/rc.local
/usr/local/nagios/bin/nrpe -c /etc/nagios/nrpe.cfg -d
安装通用plugin
# apt-get install nagios-plugins nagios-plugins-basic nagios-plugins-standard nagios-nrpe-plugin -y
从其他服务器拷贝libexec文件夹
文件夹位置:/usr/lib/nagios/libexec
启动nrpe
# /usr/local/nagios/bin/nrpe -c /etc/nagios/nrpe.cfg -d
在icinga2中启用nrpe
配置checkcommand模板
# vim /etc/icinga2/zones.d/global-templates/nrpe_base.conf
template CheckCommand "nrpe-common" {
import "plugin-check-command"
command = [ PluginDir + "/check_nrpe" ]
arguments = {
"-H" = "$nrpe_address$"
"-p" = "$nrpe_port$"
"-c" = "$nrpe_command$"
"-a" = {
value = "$nrpe_args$"
repeat_key = false
order = 1
}
}
vars.nrpe_address = "$address$"
vars.nrpe_port = 5666
}
配置常用linux检测命令
# vim /etc/icinga2/zones.d/global-templates/nrpe_linux.conf
object CheckCommand "nrpe-disk" {
import "nrpe-common"
#vars.nrpe_args = [ "$disk_wfree$%", "$disk_cfree$%"]
vars.nrpe_command = "check_disk"
#vars.disk_wfree = 20
#vars.disk_cfree = 10
}
object CheckCommand "nrpe-diskhealth" {
import "nrpe-common"
vars.nrpe_command = "check_diskhealth"
}
object CheckCommand "nrpe-tcptraffic" {
import "nrpe-common"
vars.nrpe_args = [ "$tcptraffic_wbytes$", "$tcptraffic_cbytes$","$interface_speed$","$interface_name$"]
vars.nrpe_command = "check_tcptraffic"
vars.tcptraffic_wbytes = 10485760 /*10M=10*1024*1024*/
vars.tcptraffic_cbytes = 20971520 /*20M=20*1024*1024*/
#vars.tcptraffic_wbytes = 1 /*10M=10*1024*1024*/
#vars.tcptraffic_cbytes = 2 /*20M=20*1024*1024*/
}
object CheckCommand "nrpe-load" {
import "nrpe-common"
vars.nrpe_command = "check_load"
}
object CheckCommand "nrpe-mem" {
import "nrpe-common"
vars.nrpe_command = "check_mem"
}
object CheckCommand "nrpe-proc_num" {
import "nrpe-common"
vars.nrpe_command = "check_proc_num"
}
object CheckCommand "nrpe-zombie_procs" {
import "nrpe-common"
vars.nrpe_command = "check_zombie_procs"
}
object CheckCommand "nrpe-swap" {
import "nrpe-common"
vars.nrpe_command = "check_swap"
}
object CheckCommand "nrpe-dns" {
import "nrpe-common"
vars.nrpe_command = "check_dns"
}
object CheckCommand "nrpe-safe" {
import "nrpe-common"
vars.nrpe_command = "check_safe"
}
apply Service"check_nrpe:" for (disk_nrpe_linux => config in host.vars.disks) {
import "generic-service"
display_name = "Check Nrpe:" + disk_nrpe_linux
check_command = "nrpe-disk"
vars += config
assign where host.vars.os == "Linux"
}
Storage Error! No controllers found on ubuntu15.04 dell r720
apply Service"check_nrpe:diskhealth"{
import "generic-service"
display_name = "Check Nrpe: Diskhealth"
check_command = "nrpe-diskhealth"
assign where host.vars.os == "Linux"
}
apply Service"check_nrpe:tcptraffic" for (interface_name =>interface_info in host.vars.interfaces){
import "generic-service"
display_name = "Check Nrpe: Tcptraffic "+ interface_name
check_command = "nrpe-tcptraffic"
vars.interface_name = interface_name
vars+=interface_info
assign where host.vars.interfaces && host.vars.os == "Linux"
}
apply Service"check_nrpe:load"{
import "generic-service"
display_name = "Check Nrpe: Load"
check_command = "nrpe-load"
assign where host.vars.os == "Linux"
}
apply Service"check_nrpe:mem"{
import "generic-service"
display_name = "Check Nrpe: Mem"
check_command = "nrpe-mem"
assign where host.vars.os == "Linux"
}
apply Service"check_nrpe:proc_num"{
import "generic-service"
display_name = "Check Nrpe: proc_num"
check_command = "nrpe-proc_num"
assign where host.vars.os == "Linux"
}
apply Service"check_nrpe:zombie_procs"{
import "generic-service"
display_name = "Check Nrpe: zombie_procs"
check_command = "nrpe-zombie_procs"
assign where host.vars.os == "Linux"
}
apply Service"check_nrpe:swap"{
import "generic-service"
display_name = "Check Nrpe: swap"
check_command = "nrpe-swap"
assign where host.vars.os == "Linux"
}
apply Service"check_nrpe:dns"{
import "generic-service"
display_name = "Check Nrpe: dns"
check_command = "nrpe-dns"
assign where host.vars.os == "Linux"
}
apply Service"check_nrpe:safe"{
import "generic-service"
display_name = "Check Nrpe: safe"
check_command = "nrpe-safe"
assign where host.vars.os == "Linux"
}
配置常用window检测命令
# vim /etc/icinga2/zones.d/global-templates/nrpe_windows.conf
object CheckCommand "windows-nrpe-cpu" {
import "nrpe-common"
vars.nrpe_args = []
vars.nrpe_command = "alias_cpu"
}
object CheckCommand "windows-nrpe-disk" {
import "nrpe-common"
vars.nrpe_args = []
vars.nrpe_command = "alias_disk"
}
object CheckCommand "windows-nrpe-uptime" {
import "nrpe-common"
vars.nrpe_args = []
vars.nrpe_command = "uptime"
}
object CheckCommand "windows-nrpe-mem" {
import "nrpe-common"
vars.nrpe_args = []
vars.nrpe_command = "alias_mem"
}
apply Service"windows_check_nrpe:cpu"{
import "generic-service"
display_name = "Windows-Check Nrpe: CPU"
check_command = "windows-nrpe-cpu"
assign where host.vars.os == "Windows"
}
apply Service"windows_check_nrpe:disk"{
import "generic-service"
display_name = "Windows-Check Nrpe: Disk"
check_command = "windows-nrpe-disk"
assign where host.vars.os == "Windows"
}
apply Service"windows_check_nrpe:uptime"{
import "generic-service"
display_name = "Windows-Check Nrpe: Uptime"
check_command = "windows-nrpe-uptime"
assign where host.vars.os == "Windows"
}
apply Service"windows_check_nrpe:Mem"{
import "generic-service"
display_name = "Windows-Check Nrpe: Mem"
check_command = "windows-nrpe-mem"
assign where host.vars.os == "Windows"
}
重载icinga2
在reload后，master会自动分发配置给两个子节点，从而做到统一配置，统一分发。
# service icinga2 reload
Ubuntu15.04单机/伪分布式安装配置Hadoop与Hive试验机：http://www.linuxdiyf.com/linux/11858.html
Ubuntu和CentOS中分布式配置Hadoop-2.2.0：http://www.linuxdiyf.com/linux/11401.html
Ubuntu14.04安装配置Hadoop2.6.0（完全分布式）与wordcount实例：http://www.linuxdiyf.com/linux/10226.html
Ubuntu14.04下Hadoop2.4.1单机/伪分布式安装配置教程：http://www.linuxdiyf.com/linux/10156.html
虚拟机下Linux系统Hadoop单机/伪分布式配置:Hadoop2.5.2+Ubuntu1：http://www.linuxdiyf.com/linux/11350.html