>- People will enable it which will lead to more congestion because of
>more packets.
Did you read my thought about the congestion issue? I think that we could
eventually end up wasting more bandwith with delayed-acks because if the
net drops an delayed-ack, the other end could have to retransmit _two_
packets _full_ of data.
>- A global sysctl is not fine grained enough, if you need it make it at
>least a per route attribute (like mss or window)
This is a good reason. I just thought about it.
>Because of the first reason I would prefer to not implement it.
Since I didn' t know if it would accepted I didn' t implemented as a per
route flag. For my needs a sysctl is good enough and doesn' t break any
kind of RFC or tcp-impl draft AFIK.
Andrea Arcangeli
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/