[15013] in North American Network Operators' Group
Re: MTU of the Internet?
daemon@ATHENA.MIT.EDU (Frank Kastenholz)
Thu Feb 5 10:29:55 1998
Date: Thu, 05 Feb 1998 09:57:02 -0500
To: Eric Osborne <osborne@notcom.com>, jdd@vbc.net (Jim Dixon)
From: Frank Kastenholz <kasten@argon.com>
Cc: perry@piermont.com, nanog@merit.edu
In-Reply-To: <199802051411.JAA00536@micron.notcom.com>
At 09:11 AM 2/5/98 -0500, Eric Osborne wrote:
>
>I think that "triple" is perhaps an oversimplification. This assumes that
>without a 576-byte MTU, all packets would be 1500-byte MTUs. 1500/576 ~=~ 3.
>
>Remember, there's three kinds of average: mean, median, mode. While the mean
>packet size may be 200-250 bytes, the mode and median are probably different.
>I don't have any statistics on this, but I'd be willing to guess that if you
>plotted the packet sizes frequency you'd see something like a bimodal curve,
>with a small peak at around 64 (ping) and a larger one near 1500 (10Mbit
>Ethernet/T1 MTU). As to median packet size, I have no idea. It's probably
>somewhere in the middle. :)
the real data sez...
packet size distribution is roughly tri-modal
the 25-jun-97 numbers show
- roughly 38% at 40bytes (tcp acks mostly)
- .6 41
- 6% 44 (syn+mss)
- 1 52
- 10% 55
- .6 56
- .7 61
- 5% 576
- 12% 1500
nothing else accounts for >0.5% of the packets
and for those that really care
- 40 byte packets represent ~ 4% of the bytes-on-the-fiber
- 552 16
- 576 8%
- 1500 49%
the median packet size is 56 bytes
(http://www.nlanr.net/NA/Learn/packetsizes.html)
