Update on Buffer Sizing in Internet Routers
by Yashar Ganjali and Nick McKeown
In the past two years, several papers have proposed rules that suggest two to five orders of magnitude reduction in Internet core router buffers.
Others present scenarios where buffer sizes need to be significantly increased. So why the different rules? In this paper we briefly compare the different results and proposals, and summarize some recent preliminary experiments to validate the proposals. We’ll see that different results apply to different parts of the network, and depend on several assumptions. For example, we believe that buffers can be safely reduced by an order of magnitude in the routers in service provider backbone networks; but it would be premature to reduce them in routers closer to the edge.
| Attachment | Size |
|---|---|
| p67-ganjali.pdf | 80.65 KB |

does scanning traffic bothers buffer occupancy measurements ?
In some measurements of one-way delays at a stub network we found evidence
of large bursts of packets originated by high-rate sequential scanners (see http://userver.ftw.at/~ricciato/darwin/FTW-TR-2007-001.pdf).
I wonder weather such traffic might be bothering in some way the measurements related to buffer occupancy in the real networks (e.g. delay statistics),
including those aimed at validating buffer sizing criteria.
What's your opinion ?
Fabio (ricciato@ftw.at)