Leo Bicknell wrote: > On Thu, Jul 12, 2001 at 08:17:14PM -0600, Drew Eckhardt wrote: > > You can reduce the window size with each ACK, although this is frowned > > upon. > > There's "frowned upon" and "frowned upon". :-) For instance, if > the only reason it's discouraged is because it causes connections > to start running slower, then I would consider that something worth > rethinking. If there are cases where it actively causes issues > for the far end stack, then it probably should be avoided. > > That RFC is old enough that it's worth double checking that the > recommendations still make sence today. You can congest intermediate hop routers as a result of them buffering more data than you are now willing to accept. Julian's approach was much better, and much cleverer... -- Terry To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-hackers" in the body of the message
- Re: Network performance tuning. Leo Bicknell
- Re: Network performance tuning. Leo Bicknell
- Re: Network performance tuning. E.B. Dreger
- Re: Network performance tuning. Matt Dillon
- Re: Network performance tuning. Drew Eckhardt
- Re: Network performance tuning. Alfred Perlstein
- Re: Network performance tuning. Mike Silbersack
- Re: Network performance tuning. Mike Silbersack
- Re: Network performance tuning. Leo Bicknell
- Re: Network performance tuning. Leo Bicknell
- Re: Network performance tuning. Terry Lambert
- Re: Network performance tuning. Rik van Riel
- Re: Network performance tuning. Dan Nelson
- Re: Network performance tuning. Leo Bicknell
- Re: Network performance tuning. Paul Robinson
- Re: Network performance tuning. Matt Dillon
- Re: Network performance tuning. Leo Bicknell
- Re: Network performance tuning. E.B. Dreger
- Re: Network performance tuning. Terry Lambert
- Re: Network performance tuning. Leo Bicknell
- Re: Network performance tuning. Terry Lambert

