Messages in this thread | | | From | (Alan Cox) | Subject | Re: 2.1.90 network layer again not responsive | Date | Sat, 21 Mar 1998 09:01:42 +0000 (GMT) |
| |
> >Actually you arent supposed to delay the initial ack to <mss sized frame > >because you may otherwise delay the other end quite materially as it will > >be doing Nagle at the time. > > Is that really true?
It is a bit simplistic but thats what some peoples view point is.
> Isn't one of the benefits of delayed ack that the acks get sent back with the > character echo (or other display update) for interactive sessions?
Yes. Its one of the bigger ones.
> Maybe acks for short (<mss) frames should be delayed _less_ than long (=mss) > frames.
Well Dave appears to have his own magic formula now and it works rather well in testing here. Who needs theory with a Dave Miller around ;)
Alan
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu
| |