Full Throttle Nagios

[patrick.morris at hp.com]

Hi Marcel!

On Tue, 18 May 2010, Marcel wrote:

> Hi list,
> 
> Several times I'm asked about Nagios latency when the number of services go over a certain number.
> 
> Is there any tweak to have nagios scale checkings more than it would after tweaking every configuration option for boosting performance?
> 
> It seems that nagios don't do the best job at taking the hardware to its real limits.
> 
> When I have more than, say, 10k checks, I start seen check latency rises and there just isn't anything that could be done, even distributed monitoring have the nagios.cmd write-lock bottleneck.
> 
> I'm asking if there is by design that nagios don't thrases the server when the number of checks reaches certain limits.

In my experience, the single biggest bottleneck in the number of checks
Nagios can perform without going belly-up is the OS pipe size.

In particular, this has been an issue for me on Linux, where it's not
hard to have check results overflow a 4K pipe (the Linux kernel default)
faster than Nagios can be configured to empty it out.

The good news for me has been that it's relatively easy to make that
bottleneck go away by recompiling a kernel that supports larger pipes.

------------------------------------------------------------------------------

_______________________________________________
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