[16966] in North American Network Operators' Group
Re: cpu impact of netflow export ?
daemon@ATHENA.MIT.EDU (Al Reuben)
Mon May 18 10:45:31 1998
Date: Mon, 18 May 1998 10:23:20 -0400 (EDT)
From: Al Reuben <alex@nac.net>
To: Dave Curado <davec@navinet.net>
cc: nanog@merit.edu
In-Reply-To: <199805160253.WAA06246@drama.navinet.net>
We noticed a *minor* increase in CPU. Ie, a 7206 moving around about 10 to
12 mb/s on average, with 8 ethers, 8 T1', 2 HSSIs, and one fast ether, on
a NPE-150 with 128 Megs, about 12 peers (5 of which are fairly active),
two full views, running 11.1.17CA, was doing around 30% on average. With
NetFlow on every interface, it moved up to about 36%. FYI, CEF was about
24%.
'sho proc c' shows most of the CPU going to IP Input:
CPU utilization for five seconds: 34%/32%; one minute: 36%; five minutes: 36%
PID Runtime(ms) Invoked uSecs 5Sec 1Min 5Min TTY Process
17 150791508 36649565 4114 0.32% 0.46% 0.48% 0 IP Input
On Fri, 15 May 1998, Dave Curado wrote:
>
> Does anyone have any data points they'd share regarding
> the impact of netflow export on cpu load? I'd like to
> capture all of my netflow stats, but I'm worried about
> scalability.
>
> Thanks,
> davec
>
>
-- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- --
Atheism is a non-prophet organization.
I route, therefore I am.
Alex Rubenstein, alex@nac.net, KC2BUO, ISP/C Charter Member
Father of the Network and Head Bottle-Washer
Net Access Corporation, 9 Mt. Pleasant Tpk., Denville, NJ 07834
Don't choose a spineless ISP! We have more backbone! http://www.nac.net
-- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- --
