On Tue, 15 Feb 2000, Keith Plourd wrote:
> Question 6: You will need to be careful about a few things.
>
> I recently did a study of the "burden" that rapid polling does on CPU
> performance. SNMP daemons responding to queries place a higher burden (via
> the number of lines of code) than, for example, simple system calls.
Lucky for me (and our SUNs) I only poll routers,
I hope those have a more direct and optimised method of answering.
For single-variable PDUs, they must have: I've never seen MRTG bring down
a network when it polls loads of variables from all the routers...
To inspect the the impact of multi-variable getnext requests is a good
idea.
> In my situation, I had 30 to 50 hosts to poll in under one second timing. I
> polled each for one OID, processed, then did it again with another OID, etc.
> I maintained close watch over how often I was asking questions of each
> host/architecture type.
Did you make statistics about the CPU utilisation of a polling process on
the poller host itself?
Are there any studies on this available?
Thank you for the ideas:
Szocske
-- !! This message is brought to you via the `tkined & scotty' mailing list. !! Please do not reply to this message to unsubscribe. To subscribe or !! unsubscribe, send a mail message to <tkined-request@ibr.cs.tu-bs.de>. !! See http://wwwsnmp.cs.utwente.nl/~schoenw/scotty/ for more information.
This archive was generated by hypermail 2b29 : Mon Jan 08 2001 - 15:27:35 MET