Nagios 性能分析圖示的作用
Nagios對服務或主機監控的是一個瞬時狀态,有時候系統管理者需要了解主機在一段時間内的性能及服務的響應狀态,并且形成圖表,這就需要通過檢視日志資料來分析。但是這種方式不僅煩瑣,而且抽象。為了能更直覺的檢視主機運作狀态,這裡采用PNP 來實作此功能。PNP 是一個小巧的開源軟體包,它是基于 PHP 和 Perl 腳本編寫,PNP 可以利用 rrdtool 工具将 Nagios采集的資料繪制成圖表,然後顯示主機或者服務在一段時間内運作的狀況。以下詳細介紹 PNP 安裝配置流程:
安裝 RRDtool 工具可以編譯安裝 RRDtool,也可以直接yum安裝
#yum install rrdtool -y
編譯安裝 PNP
下載下傳站點:http://docs.pnp4nagios.org/start版本分為 0.6.x和0.4.x兩個版本
#tar zxvf pnp-0.4.13.tar.gz
#cd pnp-0.4.13
#./configure\
--with-nagios-user=nagios \
--with-nagios-group=nagios \
--with-rrdtoul=/usr/local/rrdtool/bin/rrdtool \
--with-perfdata-dir=/usr/local/nagios/share/perfdata
編譯的時候會報
checking for PerlModule Time::HiRes... no
configure: error:Perl Module Time::HiRes not available
錯誤,需要安裝#perl-Time-HiRes
#makeall
#make install
#make install-config
#make install-init
1. PNP配置檔案定義
在 PNP安裝完成後, 預設安裝目錄下回自帶相應的模闆配置檔案, 是以隻需要參考相應的模闆檔案進行修改即可,
PNP 配置檔案定義
# cd/usr/local/nagios/etc/pnp/
# cp process_perfdata.cfg-sample process_perfdata.cfg
# cp npcd.cfg-sample npcd.cfg
# cp rra.cfg-sample rra.cfg
# chown -R nagios:nagios /usr/local/nagios/etc/pnp
2.修改process_perfdata.cfg 檔案
打開 Nagios下的 process_perfdata.cfg 檔案,修改相關内容。可從下圖的注釋資訊了解到
将數字 0 變更為2 是開啟了日志的調試功能,操作如下:
開啟日志調試功能
# vim/usr/local/nagios/etc/pnp/process_perfdata.cfg
LOG_FILE =/usr/local/nagios/var/perfdata.log
#
# Loglevel 0=silent1=normal 2=debug
LOG_LEVEL = 2
3.修改Nagios 相關配置檔案
- 增加流量圖圖示
修改templates.cfg,增加一個定義 PNP 的 host 和 service,詳細見下圖 :
PNP 配置與設定
# vim /usr/local/nagios/etc/objects/templates.cfg #添加下面兩行
define host{
name hosts-pnp
register 0
action_url/nagios/pnp/index.php?host=$HOSTNAME$
#process_perf_data 1
}
define service{
name services-pnp
register 0
action_url /nagios/pnp/index.php?host=$HOSTNAME$&srv=$SERVICEDESC$
- 修改 nagios.cfg
如果想讓nagios 将資料輸出,首先要修改 nagios 的主配置檔案 nagios.cfg,找到如下幾項,如有注釋的将其去掉。修改後的資訊如下:
增加 nagios 資料輸出設定
#vim/usr/local/nagios/etc/nagios.cfg
process_performance_data=1
host_perfdata_command=process-host-perfdata
service_perfdata_command=process-service-perfdata
- 修改 commands.cfg
process-host-perfdata和 process-service-perfdata 指令聲明了 nagios 輸出哪些值到輸出檔案中。 不過這些定義相對簡單,而 PNP 提供了一個Perl 腳本,非常詳細地定義了一個輸出資料的方法,process_perfdata.pl 其實是 PNP 自帶的一個腳本,這個腳本在 PNP安裝完成後會自動生成。是以,可以将 process-host-perfdata 和 process-service-perfdata指令中對應的執行指令的内容替換成此腳本。增加下圖的内容:
在 commands.cfg 檔案中增加性能圖檔配置
# vim /usr/local/nagios/etc/objects/commands.cfg #首先注釋掉下面的兩個,然後添加下面這個
define command{
command_name process-host-perfdata
command_line $USER1$/process_perfdata.pl -d HOSTPERFDATA
}
command_name process-service-perfdata
command_line $USER1$/process_perfdata.pl
- 修改 hosts.cfg 與 services.cfg
将hosts-pnp 和 services-pnp 引用到 hosts.cfg 和 services.cfg 中,修改後的 hosts.cfg 内容如圖 13和圖 14 所示:
在給三個主機的配置檔案中增加性能圖檔配置
# vim/usr/local/nagios/etc/objects/localhost.cfg
define host{
use linux-server,hosts-pnp
host_name localhost
alias localhost
address 127.0.0.1
process_perf_data 1
}
# vim/usr/local/nagios/etc/objects/windows.cfg
define host{
use windows-server,hosts-pnp
host_name winserver
alias My Windows Server
address 192.168.0.5
}
# vim/usr/local/nagios/etc/objects/linuxserver.cfg
define host{
use linux-server,hosts-pnp
host_name linuxserver
alias My linux Server
address 192.168.0.3
}
在主機配置檔案内給這三個主機的服務增加性能圖檔配置
# vim /usr/local/nagios/etc/objects/linuxserver.cfg
define service{
use generic-service,services-pnp
host_name linuxserver
service_description CHECK USERS
check_command check_nrpe!check_users
}
define service{
use generic-service,services-pnp
host_name linuxserver
service_description Load
check_command check_nrpe!check_load
}
define service{
use generic-service,services-pnp
host_name linuxserver
service_description SDA1
check_command check_nrpe!check_sda1
}
define service{
use generic-service,services-pnp
host_name linuxserver
service_description SDA2
check_command check_nrpe!check_sda2
}
define service{
use generic-service,services-pnp
host_name linuxserver
service_description Zombie
check_command check_nrpe!check_zombie_procs
}
define service{
use generic-service,services-pnp
host_name linuxserver
service_description Total_procs
check_command check_nrpe!check_total_procs
}
define service{
use generic-service,services-pnp
host_name linuxserver
service_description Swap
check_command check_nrpe!check_swap
}
define service{
use generic-service,services-pnp
host_name linuxserver
service_description Rootdisk
check_command check_nrpe!check_rootdisk
}
# vim /usr/local/nagios/etc/objects/windows.cfg
define service{
use generic-service,services-pnp
host_name winserver
service_description NSClient++ Version
check_command check_nt!CLIENTVERSION
}
define service{
use generic-service,services-pnp
host_name winserver
service_description Uptime
check_command check_nt!UPTIME
}
define service{
use generic-service,services-pnp
host_name winserver
service_description CPU Load
check_command check_nt!CPULOAD!-l 5,80,90
}
define service{
use generic-service,services-pnp
host_name winserver
service_description Memory Usage
check_command check_nt!MEMUSE!-w 80 -c 90
}
use generic-service,services-pnp
host_name winserver
service_description C:\ Drive Space
check_command check_nt!USEDDISKSPACE!-l c -w 80 -c90
}
define service{
use generic-service,services-pnp
host_name winserver
service_description W3SVC
check_command check_nt!SERVICESTATE!-d SHOWALL -lW3SVC
}
define service{
use generic-service,services-pnp
host_name winserver
service_description Explorer
check_command check_nt!PROCSTATE!-d SHOWALL -lExplorer.exe
}
define service{
use generic-service,services-pnp
host_name winserver
service_description Web_server
check_command check_http
}
# vim /usr/local/nagios/etc/objects/localhost.cfg
define service{
host_name localhost
service_description PING
check_command check_ping!100.0,20%!500.0,60%
}
define service{
host_name localhost
service_description Root Partition
check_command check_local_disk!20%!10%!/
}
# if > 50 users.
host_name localhost
service_description Current Users
check_command check_local_users!20!50
}
define service{
host_name localhost
service_description Total Processes
check_command check_local_procs!250!400!RSZDT
}
# Define a service tocheck the load on the local machine.
host_name localhost
service_description Current Load
}
host_name localhost
service_description Swap Usage
check_command check_local_swap!20!10
}
define service{
use local-service,services-pnp ; Name of service template to use
host_name localhost
service_description SSH
check_command check_ssh
notifications_enabled 0
}
define service{
use local-service,services-pnp ; Name of service template to use
host_name localhost
service_description HTTP
check_command check_http
notifications_enabled 0
}
#/usr/local/nagios/bin/nagios -v /usr/local/nagios/etc/nagios.cfg
…………………………...
Total Warnings: 0
Total Errors: 0
然後重新開機服務
# service nagiosrestart
Running configurationcheck...done.
Stopping nagios:done.
Starting nagios:done.
然後登陸nagios管理界面,你就可看到主機和服務前面的性能圖示
點選圖示的時候如果你沒有安裝php-gd的話,就會提示“php gd support not found”,直接yum安裝就可以
剛開始的時候,你點選那個流量圖示,可能會提示錯誤,如下,這隻是rrd資料庫還沒有生成,是以沒有發現,等一會就不會有這個提示了
過一段時間以後,你點主機和服務的性能圖示的話就會有流量圖顯示;