Date: Wed, 21 Nov 2012 03:32:17 +0100 From: Ingo Flaschberger <if@xip.at> To: Barney Cordoba <barney_cordoba@yahoo.com> Cc: freebsd-net@freebsd.org Subject: Re: FreeBSD boxes as a 'router'... Message-ID: <50AC3D31.1070905@xip.at> In-Reply-To: <1353454215.20382.YahooMailClassic@web121601.mail.ne1.yahoo.com> References: <1353454215.20382.YahooMailClassic@web121601.mail.ne1.yahoo.com>
next in thread | previous in thread | raw e-mail | index | archive | help
Am 21.11.2012 00:30, schrieb Barney Cordoba:
>
> --- On Tue, 11/20/12, Ingo Flaschberger <if@xip.at> wrote:
>
>> stems (Intel 82541GI) polling prevent live-locks.
>>
>> Best test:
>> Loop a GigE Switch, inject a Packet and plug it into the
>> test-box.
> Yeah, thats a good real-world test.
>
> To me "performance" is not "burning a cpu" to get some extra pps.
> Performance is not dropping buckets of packets. Performance is using
> less cpu to do the same amount of work.
>
> Is a machine that benchmarks at 998Mb/s at 95% cpu really a "higher
> performance" system than one that does 970Mb/s and uses 50% of the cpu?
Talking about Mb/s is definitly the wrong way - forwarding performance
is measured in pps.
> The measure of performance is to manage an entire load without dropping
> any packets. If your machine goes into live-lock, then you need more
> machine. Hacking it so that it drops packets is hardly a solution.
No, because standard internet traffic has not 100% 64b packets - but
when a hacker attacks - it has (dos).
Then it's important to know - who is the attacker and keep the box up
even if it drops packets.
If you don't like packet drops - go - buy some juniper (which also use
FreeBSD).
Kind regards,
Ingo Flaschberger
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?50AC3D31.1070905>