|To:||Thomas Graf <tgraf@xxxxxxx>|
|Subject:||Re: dummy as IMQ replacement|
|From:||Andy Furniss <andy.furniss@xxxxxxxxxxxxx>|
|Date:||Tue, 01 Feb 2005 01:02:12 +0000|
|Cc:||jamal <hadi@xxxxxxxxxx>, netdev@xxxxxxxxxxx, Nguyen Dinh Nam <nguyendinhnam@xxxxxxxxx>, Remus <rmocius@xxxxxxxxxxxxxx>, Andre Tomt <andre@xxxxxxxx>, syrius.ml@xxxxxxxxxx, Damion de Soto <damion@xxxxxxxxxxxx>|
|References:||<email@example.com> <20050131135810.GC31837@postel.suug.ch> <firstname.lastname@example.org> <20050131151532.GE31837@postel.suug.ch>|
|User-agent:||Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.3a) Gecko/20021212|
Thomas Graf wrote:
Or dropping packets. TCP will adjust itself either way; at least thats true according to this formula [rfc3448] (originally derived from Reno, but people are finding it works fine with all other variants of TCP CC):
WRT policers I never figured out where you would put the effects of playing with the burst size parameter and it's effects with few/many connections and any burstiness caused into an equasion like that.
This sounds cool. For me in someways I think it could be nicer (in the case of shaping from the wrong end of a slow link) to delay the real packets - that way the tcps of the clients get to see the smoothed version of the traffic and you can delay udp aswell.
How intelligent and how much, if any, per connection state do you/could you keep? I think being able to set a class that behaves as full before it is, removing the s from sfq, de piggybacking acks and singling out and handling slowstart connections specially could really help the world of shaping from the wrong end of slow links.
There's always playing with rwin, but maybe that's abit OTT :-)
|<Prev in Thread]||Current Thread||[Next in Thread>|
|Previous by Date:||[PATCH][NET] Add PPC440SP support to IBM EMAC driver, Matt Porter|
|Next by Date:||[PATCH 2.6] e100: remove reference to NAPI config option, Scott Feldman|
|Previous by Thread:||Re: dummy as IMQ replacement, David S. Miller|
|Next by Thread:||Re: dummy as IMQ replacement, Andre Correa|
|Indexes:||[Date] [Thread] [Top] [All Lists]|