[191351] in North American Network Operators' Group
Re: Looking for recommendations for a dedicated ping responder
daemon@ATHENA.MIT.EDU (Christopher Morrow)
Fri Sep 9 16:42:55 2016
X-Original-To: nanog@nanog.org
In-Reply-To: <A6290B62-3467-4287-BE3C-CA93EE769382@puck.nether.net>
From: Christopher Morrow <morrowc.lists@gmail.com>
Date: Fri, 9 Sep 2016 16:42:51 -0400
To: Jared Mauch <jared@puck.nether.net>
Cc: NANOG <nanog@nanog.org>
Errors-To: nanog-bounces@nanog.org
On Fri, Sep 9, 2016 at 4:17 PM, Jared Mauch <jared@puck.nether.net> wrote:
>
> > On Sep 9, 2016, at 4:08 PM, Dan White <dwhite@olp.net> wrote:
> >
> > We're being caught up in some sort of peering dispute between Level 3 and
> > Google (in the Dallas area), and we've fielded several calls from larger
> > customers complaining of 40-50% packet loss (to 8.8.8.8) when there
> appears
> > to be no actual service impacting loss.
> >
> > We currently suggest customers use a Linux server to ping against, or
> > another public host.
> >
> > Ideally we'd like to use a hardware based ICMP system for customer use -
> > Accedian NIDs are good at this (exceptionally low jitter) accept they
> > throttle at 500 pings per second.
>
> I know that the NETNOD folks did NTP in a FPGA that can do 4x 10GE,
> perhaps that card and code could be used to do 40G ICMP responder?
>
>
or, alternately test some useful application instead? I mean, 'wget' will
tell you stats about the bw/etc... apache-bench will as well, and you can
probably whip up some custom python/etc that'd do the same sort of thing.
