Revision [774]
Last edited on 2006-04-11 19:55:20 by MatthewToselandAdditions:
===Congestion Control===
==Timeout Prevention by Pre-emptive Rejection==
==Data Transfers==
==Timeout Prevention by Pre-emptive Rejection==
==Data Transfers==
Deletions:
=Timeout Prevention by Pre-emptive Rejection=
=Data Transfers=
Revision [773]
Edited on 2006-04-11 19:55:05 by MatthewToselandAdditions:
==Congestion Control==
=Timeout Prevention by Pre-emptive Rejection=
=Data Transfers=
=Timeout Prevention by Pre-emptive Rejection=
=Data Transfers=
Revision [772]
Edited on 2006-04-11 19:54:13 by MatthewToselandAdditions:
Additionally, data transfers (32kB blocks divided into 1kB packets) are limited using the same AIMD algorithm described in LoadBalancing.
Revision [769]
Edited on 2006-04-11 19:51:44 by MatthewToselandDeletions:
Additions:
If the geometric mean of the round-trip times of all connected peers is less than 500ms, we accept all requests. If it is over 1000ms, we accept no requests. If it is between the two then we accept requests randomly proportional to the round-trip time.
Deletions:
Revision [767]
Edited on 2006-04-11 19:50:34 by MatthewToselandAdditions:
If this is less than 1000ms, we accept all requests. If it is more than 2000ms, we accept no requests (actually we accept one every 10 seconds anyway just to ensure that we don't get "stuck" with too high an old average). If it's in between we accept some requests, as above.