diff for duplicates of <9dfc3c5eb811f2774b378fce0158b3e7@localhost> diff --git a/a/1.txt b/N1/1.txt index b2b60dd..cd76233 100644 --- a/a/1.txt +++ b/N1/1.txt @@ -2,43 +2,22 @@ On Mon, 05 Dec 2011 11:59:34 +0100, Eric Dumazet wrote: - - - > Adding a time limit is possible, all we need is a proper design and - > implementation :) - > - > Here is my suggestion : - > - > Design a new tfifo/tred qdisc, with following properties : - > - > Adaptative RED, (ECN enabled + head drop), but instead of using - > bytes/packet qlen average, use time_in_queue average. - - Question one: is anything wrong with sfb or choke as the basis, instead of - RED? - - Question two: I submitted pfast_head_drop to drop more outdated data - instead of new data. Back in time I thought TCP _may_ experience benefits - because more up-to-date SACK data packets are saved. Are there any other - TCP advantages with head drop policy? - - Hagen diff --git a/a/content_digest b/N1/content_digest index 41d21a4..19844eb 100644 --- a/a/content_digest +++ b/N1/content_digest @@ -1,59 +1,37 @@ "ref\0CAA93jw7kQYONQiAozatRmdRRJeK0GB9eNDWtRZ3AL+OVKn0OpA@mail.gmail.com\0" "ref\01323082774.2670.40.camel@edumazet-HP-Compaq-6005-Pro-SFF-PC\0" - "From\0Hagen Paul Pfeifer <hagen@jauu.net>\0" - "Subject\0Re: [Bloat] Time in Queue, bufferbloat, and... our accidentally interplanetary network\0" + "From\0Hagen Paul Pfeifer <hagen-GvnIQ6b/HdU@public.gmane.org>\0" + "Subject\0Re: Time in Queue, bufferbloat, and... our accidentally interplanetary network\0" "Date\0Wed, 07 Dec 2011 11:15:38 +0100\0" - "To\0Eric Dumazet <eric.dumazet@gmail.com>\0" - "Cc\0Dave Taht <dave.taht@gmail.com>" - linux-wireless <linux-wireless@vger.kernel.org> - <netdev@vger.kernel.org> - bloat-devel <bloat-devel@lists.bufferbloat.net> - " bloat <bloat@lists.bufferbloat.net>\0" + "To\0Eric Dumazet <eric.dumazet-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>\0" + "Cc\0bloat-devel <bloat-devel-JXvr2/1DY2fm6VMwtOF2vx4hnT+Y9+D1@public.gmane.org>" + netdev-u79uwXL29TY76Z2rM5mHXA@public.gmane.org + linux-wireless <linux-wireless-u79uwXL29TY76Z2rM5mHXA@public.gmane.org> + " bloat <bloat-JXvr2/1DY2fm6VMwtOF2vx4hnT+Y9+D1@public.gmane.org>\0" "\00:1\0" "b\0" "\n" "On Mon, 05 Dec 2011 11:59:34 +0100, Eric Dumazet wrote:\n" "\n" "\n" - "\n" - "\n" - "\n" "> Adding a time limit is possible, all we need is a proper design and\n" - "\n" "> implementation :)\n" - "\n" "> \n" - "\n" "> Here is my suggestion :\n" - "\n" "> \n" - "\n" "> Design a new tfifo/tred qdisc, with following properties :\n" - "\n" "> \n" - "\n" "> Adaptative RED, (ECN enabled + head drop), but instead of using\n" - "\n" "> bytes/packet qlen average, use time_in_queue average.\n" "\n" - "\n" - "\n" "Question one: is anything wrong with sfb or choke as the basis, instead of\n" - "\n" "RED?\n" "\n" - "\n" - "\n" "Question two: I submitted pfast_head_drop to drop more outdated data\n" - "\n" "instead of new data. Back in time I thought TCP _may_ experience benefits\n" - "\n" "because more up-to-date SACK data packets are saved. Are there any other\n" - "\n" "TCP advantages with head drop policy?\n" "\n" - "\n" - "\n" Hagen -e52262a2f31d9afc7103b4028bf8028123f2cbc4d276b8fba715ad27aaf827ed +6cfc45f1bc4fd74e029cc5b4c55d6f7ca29c0fd6cb36bddfb669229e5919a845
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.