[bittorrent] Open letter to the BBC

Elliott Mitchell ehem at m5p.com
Sat Jun 25 01:48:21 EDT 2005


>From: Joseph Ashwood <ashwood at msn.com>
> the overhead because the protocol messages are smaller. As for a running 
> system performing a variety of uploads on a variety of torrents (a recipe 
> for high protocol overhead), I am currently connected to 135 peers 

Why are you using such a ludicrusly large number of peers?

50 peers is the conventional number to cite for statistics because it
presents a worst case scenario. I'm in favor of BT clients burying the
option to change number of peers deep in some menu where this can be
mentioned. By contrast queue depth is an important tuning parameter that
should be easily available.

> (including seeds) and overhead in the last few seconds has been 4.9% 
> download, 1.2%upload, with variances between about 2% and 7% for download 
> and 0.3% and 4% for upload, spontaneous share ratio is 1:2 (half as much 
> upload as download), across the entire session which is at about 2 days, 3% 
> download overhead, 1% upload overhead, share ratio of 1.2:1 (1.2 bytes 

Incredibly small given the number of peers. 135 peers is horrendously bad
for the BT protocol.

> upload for each one downloaded). These numbers indicate that there is a 
> client or group of clients that is being actually quite chatty, but I don't 
> feel like tracing it down, it's probably one of the older ones though..

Wild guess, I'd say the seeds are being quiet (they tell their entire
story with the BITFIELD), the ones being chatty are the ones actually
downloading (they need to send HAVEs).


-- 
(\___(\___(\______          --=> 8-) EHM <=--          ______/)___/)___/)
 \BS (    |         EHeM at gremlin.m5p.com PGP 8881EF59         |    )   /
  \_CS\   |  _____  -O #include <stddisclaimer.h> O-   _____  |   /  _/
    \___\_|_/82 04 A1 3C C7 B1 37 2A*E3 6E 84 DA 97 4C 40 E6\_|_/___/





More information about the BitTorrent mailing list