[Beowulf] photonic buffer bloat

[Eugen Leitl]

Relevant for future clusters, see the PPT presentation linked
in below URL.

----- Forwarded message from Masataka Ohta <mohta at necom830.hpcl.titech.ac.jp> -----

From: Masataka Ohta <mohta at necom830.hpcl.titech.ac.jp>
Date: Sat, 28 Jan 2012 21:42:13 +0900
To: nanog at nanog.org
Subject: Re: photonic buffer bloat
User-Agent: Mozilla/5.0 (Windows NT 5.1;
	rv:9.0) Gecko/20111222 Thunderbird/9.0.1

Eugen Leitl wrote:

> In future photonic networks (which will do relativistic cut-through
> directly in a photonic crossbar without converting photons to electrons
> and back) the fiber is not just a transport channel but also a photonic
> buffer

Yes.

> (e.g. at 10 GBit/s Ethernet a short reach fiber already buffers
> a standard 1500 MTU).

Wrong. 10Gbps is too slow for optical buffering.

At 1Tbps, you can use 100 times less lengthy fiber than at 10Gbps
to buffer packets.

A 1Tbps packet can be constructed by simultaneously encoding
100 wavelengths at 10Gbps.

> Of course photonic gates are expensive, individual delays do add up
> so even with slow light buffers

Don't try to make light slower. Slow light buffers have resonators,
which means they have very very very narrow bandwidth.

Instead, make communication speed faster, which shortens fiber
length of fiber delay line buffers.

> or optical delay loops taken into consideration
> current TCP/IP header layout has not been optimized for leading edge
> containing most significant switching/routing information, or even
> local-knowledge routing (with no global routes). It's too bad IPv6
> was not radical enough, so today's legacy protocols have to be tunneled
> through the networks of the future.

Considering that, in practice, packet headers must be processed
electrically, IPv4 at the photonic backbone is just fine, if most
routing table entries are aggregated at /24 or better, which is
the current practice. You only have to read a 16M entry SRAM.

A problem of IPv6 with 128bit addresses is that route look up
can not be performed within a constant time of a few nano
seconds, which means packets have overrun fiber delay lines.

> I presume this future is some 20-30 years away still.

Not so much. Moore's law requires much rapid bandwidth
increase.

My slides presented at IEEE photonics society 2009 summer topical

	ftp://chacha.hpcl.titech.ac.jp/IEEE-ST.ppt

might be interesting for you.

						Masataka Ohta

----- End forwarded message -----
-- 
Eugen* Leitl <a href="http://leitl.org">leitl</a> http://leitl.org
______________________________________________________________
ICBM: 48.07100, 11.36820 http://www.ativel.com http://postbiota.org
8B29F6BE: 099D 78BA 2FD3 B014 B08A  7779 75B0 2443 8B29 F6BE