Service check latency rises when service notification event occurs frequently

Yu Watanabe yu.watanabe at jp.fujitsu.com
Tue Oct 18 13:23:24 CEST 2011


Andreas Ericsson さんは書きました:
>On 10/18/2011 04:19 AM, Yu Watanabe wrote:
>> Hi all!
>> 
>> We are doing some performance test with nagios 3.3.1 in following
>> environement.
>> 
>> Server 1
>> 
>> RHEL 5.5 64 bit
>> 1CPU Xeon E3-1220 3.10 GHz
>> Memory    8GB
>> Disk      450GB (Raid 1)
>> 
>> Server 2
>> 
>> RHEL 5.5 64 bit
>> 2CPU Xeon E5630 2.53 GHz
>> Memory    8GB
>> Disk      300GB (Raid 5)
>> 
>> 3011 hosts
>> 6173 services (3011 ping check)
>> 
>> Also putting some loads on the background,
>> 
>> 1. 347 syslog msg per sec
>> 2. 1 passvie service check per sec for notification event to two contact group
>> 3. 30 ms of network traffic latency
>> 4. cacti polling
>> 
>> I have realized that Server 1 has service check latency for average 80 second but
>> server 2 has average below 10 second.
>> 
>
>Server 2 has Raid 5 (superior to Raid 1) and an extra CPU. I'm not very
>surprised that it performs better than server 1. What happens if you
>put spool directories and objects.cache and status.sav on ramdisk?

  We didnt have time to do your suggestions , sorry about that...
  However, when I take off the notification event, the average service latency 
  goes down below 1 sec in both servers. This was very strange.

>
>> Does notification process naturally effect the service check scheduling?
>> 
>
>Not by much, no.
>
>-- 
>Andreas Ericsson                   andreas.ericsson at op5.se
>OP5 AB                             www.op5.se
>Tel: +46 8-230225                  Fax: +46 8-230231
>
>Considering the successes of the wars on alcohol, poverty, drugs and
>terror, I think we should give some serious thought to declaring war
>on peace.
>


------------------------------------------------------------------------------
All the data continuously generated in your IT infrastructure contains a
definitive record of customers, application performance, security
threats, fraudulent activity and more. Splunk takes this data and makes
sense of it. Business sense. IT sense. Common sense.
http://p.sf.net/sfu/splunk-d2d-oct
_______________________________________________
Nagios-users mailing list
Nagios-users at lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/nagios-users
::: Please include Nagios version, plugin version (-v) and OS when reporting any issue. 
::: Messages without supporting info will risk being sent to /dev/null





More information about the Users mailing list