[e2e] Queue size of routers

[Jon Crowcroft]

in the old days, routers were quiote small because a packet could be
stored as electrons - nowadays, photons are used which are much
bigger, so the average 1500 byte packet takes around 10,000 photons,
which at 0.42 meters per photon means that you need a lot of real
estate for a packet - basically, only the US and Commonwealth of
Indpeendnat states and China have enough land to have more than 1
router each.

luckily, in todays overphotonic networks, queue sizes are only [0-1]
packets - if we ran the networks the way we used to with a
bandwidth*delay product of buffer a gmpls optical router would have
be about the size of the earth-moon orbit....

this is of course some of the motivation behind the inter-planetarey
internetwork project- most people havnt noticed, but Vint Cerf in his
wisdom has managed to pursuade NASA to re-direct some of theior funds
to allow us to use the earth-moon orbit to keep ipv6 headers in
In message <20030125140110.20275.qmail at web15107.mail.bjs.yahoo.com>, =?gb2312?q
?Jing=20Shen?= typed:

 >>--0-1891598806-1043503270=:16934
 >>Content-Type: text/plain; charset=gb2312
 >>Content-Transfer-Encoding: quoted-printable
 >>X-MIME-Autoconverted: from 8bit to quoted-printable by boreas.isi.edu id h0PE5AH01984
 >>
 >>
 >>Is there any paper/report on the observation core router behavior ?
 >>=20
 >> Long Le <le at cs.unc.edu> wrote:Hi Dennis,
 >>
 >>Thanks for your interesting email.
 >>
 >>On Fri, 17 Jan 2003, Dennis Ferguson wrote:
 >>
 >>> Greg,
 >>>=20
 >>> I believe (based solely on a single long-ago observation that an M/M/1/=
 >>K
 >>> queuing model seemed to predict the measured behaviour of core routers
 >>> with short buffers pretty accurately) that the speculation in your thir=
 >>d
 >>> sentence above may in fact be true.
 >>
 >>This sounds intriguing. Does anyone have a pointer to this work?
 >>
 >>Thanks,
 >>-- long
 >>
 >>
 >>Jing Shen
 >>
 >>State Key Lab of CAD&CG
 >>ZheJiang University(YuQuan)
 >>HangZhou, ZheJiang Province 310027
 >>P.R.China
 >>
 >>
 >>---------------------------------
 >>Do You Yahoo!?
 >>"=BF=EE=BF=EE=B8=DF=B9=F3=B5=E4=D1=C5=A3=AC=B5=E3=BB=F7=B2=CE=BC=D3=C6=FB=
 >>=B3=B5=B5=F7=B2=E9!"
 >>--0-1891598806-1043503270=:16934
 >>Content-Type: text/html; charset=gb2312
 >>Content-Transfer-Encoding: quoted-printable
 >>X-MIME-Autoconverted: from 8bit to quoted-printable by boreas.isi.edu id h0PE5AH01984
 >>
 >><P>Is there any paper/report on the observation core router behavior ?
 >><P>&nbsp;
 >><P>&nbsp;<B><I>Long Le &lt;le at cs.unc.edu&gt;</I></B> wrote:
 >><BLOCKQUOTE style=3D"PADDING-LEFT: 5px; MARGIN-LEFT: 5px; BORDER-LEFT: #1=
 >>010ff 2px solid">Hi Dennis,<BR><BR>Thanks for your interesting email.<BR>=
 >><BR>On Fri, 17 Jan 2003, Dennis Ferguson wrote:<BR><BR>&gt; Greg,<BR>&gt;=
 >> <BR>&gt; I believe (based solely on a single long-ago observation that a=
 >>n M/M/1/K<BR>&gt; queuing model seemed to predict the measured behaviour =
 >>of core routers<BR>&gt; with short buffers pretty accurately) that the sp=
 >>eculation in your third<BR>&gt; sentence above may in fact be true.<BR><B=
 >>R>This sounds intriguing. Does anyone have a pointer to this work?<BR><BR=
 >>>Thanks,<BR>-- long<BR></BLOCKQUOTE><BR><BR>Jing Shen<br><br>State Key La=
 >>b of CAD&amp;CG<br>ZheJiang University(YuQuan)<br>HangZhou, ZheJiiang Pro=
 >>vince 310027<br>P.R.China<p><br><hr size=3D1><b>Do You Yahoo!?</b><br>
 >><a href=3D"http://rd.yahoo.com/mail_cn/tag?http://cn.surveys.yahoo.com/gm=
 >>_campaign_evaluation">"=BF=EE=BF=EE=B8=DF=B9=F3=B5=E4=D1=C5=A3=AC=B5=E3=BB=
 >>=F7=B2=CE=BC=D3=C6=FB=B3=B5=B5=F7=B2=E9!"</a>
 >>--0-1891598806-1043503270=:16934--
 >>

 cheers

   jon