[179842] in North American Network Operators' Group
RE: Thousands of hosts on a gigabit LAN, maybe not
daemon@ATHENA.MIT.EDU (Brian R)
Fri May 8 16:20:36 2015
X-Original-To: nanog@nanog.org
From: Brian R <briansupport@hotmail.com>
To: John Levine <johnl@iecc.com>, "nanog@nanog.org" <nanog@nanog.org>
Date: Fri, 8 May 2015 13:16:03 -0700
In-Reply-To: <20150508185303.55159.qmail@ary.lan>
Errors-To: nanog-bounces@nanog.org
Agree with many of the other comments. Smaller subnets (the /23 suggestion=
sounds good) with L3 between the subnets.
=20
<off topic>
The first thing that came to mind was "Bitcoin farm!" then "Ask Bitmaintech=
" and then "I'd be more worried about the number of fans and A/C units".
</off topic>
=20
Brian
=20
> Date: Fri=2C 8 May 2015 18:53:03 +0000
> From: johnl@iecc.com
> To: nanog@nanog.org
> Subject: Thousands of hosts on a gigabit LAN=2C maybe not
>=20
> Some people I know (yes really) are building a system that will have
> several thousand little computers in some racks. Each of the
> computers runs Linux and has a gigabit ethernet interface. It occurs
> to me that it is unlikely that I can buy an ethernet switch with
> thousands of ports=2C and even if I could=2C would I want a Linux system
> to have 10=2C000 entries or more in its ARP table.
>=20
> Most of the traffic will be from one node to another=2C with
> considerably less to the outside. Physical distance shouldn't be a
> problem since everything's in the same room=2C maybe the same rack.
>=20
> What's the rule of thumb for number of hosts per switch=2C cascaded
> switches vs. routers=2C and whatever else one needs to design a dense
> network like this? TIA
>=20
> R's=2C
> John
=
