From mboxrd@z Thu Jan 1 00:00:00 1970 From: Gerrit Renker Date: Thu, 16 Nov 2006 17:45:19 +0000 Subject: Re: [BUG] DCCP performance stops on CCID3 at times Message-Id: <200611161745.20056@strip-the-willow> List-Id: References: <200611161055.31036.ian.mcdonald@jandi.co.nz> In-Reply-To: <200611161055.31036.ian.mcdonald@jandi.co.nz> MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable To: dccp@vger.kernel.org Quoting Ian McDonald: | I'm still working on it but anybody else can feel free to help! It is great to see that this is picked up. It is one of the items which I h= ad put onto the ToDo list as well, the thread starting this began on=20 http://www.mail-archive.com/dccp%40vger.kernel.org/msg00446.html | And now I get these subcases: | Nov 2 21:22:21 localhost kernel: [26564.665163] ccid3_hc_rx_calc_first_= li: p =3D 0, fval =3D 7046 | This is due to the computed x_recv being very, very low I believe. So it= sets it to ~0 | =20 | Nov 2 21:22:21 localhost kernel: [26564.665381] dccp_li_hist_calc_i_mea= n: w_tot =3D 0 | Nov 3 02:27:46 localhost kernel: [44880.646467] ccid3_hc_rx_calc_first_= li: server, sk=DC04b16c, Could not find a win_count interval > 0. Defaultin= g to 1 | Nov 3 02:27:46 localhost kernel: [44880.646538] tmp2 =3D 0 ccid3_hc_rx_= calc_first_li: x_recv =3D 0, rtt =3D1 I wonder whether this is due to the RTT, due to the following statement in = ccid3_hc_rx_calc_first_li: if (rtt =3D 0) rtt =3D 1; Maybe it would be good to print out when the RTT estimate is zero (with reg= ard to the other email, I am still puzzled about the Receiver-RTT measurement). The same statement re-appears = in tfrc_calc_x (to avoid division-by-zero),=20 without warning.=20 I think that a warning message could bring in some light: maybe it is the c= ase here that the RTT measurement is just at rock bottom, always returns 0, and thus always stays at 1.=20 It would be great if you could come up with something, you know this code b= est. I have put it into my `TBD' folder and may just pester with emails later ;-)=20 There is another thread which I think may be of relevance, incidentally aga= in at the rx_packet_recv function: http://www.mail-archive.com/dccp%40vger.kernel.org/msg00118.html I put this also into the ToDo list, but I am still stuck with other work. M= aybe we could kill all those ToDos in=20 one swoop? -- Gerrit =20