Date: Tue, 5 May 2009 07:25:27 GMT From: Andre Oppermann <andre@FreeBSD.org> To: Perforce Change Reviews <perforce@freebsd.org> Subject: PERFORCE change 161596 for review Message-ID: <200905050725.n457PR7o003321@repoman.freebsd.org>
next in thread | raw e-mail | index | archive | help
http://perforce.freebsd.org/chv.cgi?CH=161596 Change 161596 by andre@andre_t61 on 2009/05/05 07:25:27 Update comments. Affected files ... .. //depot/projects/tcp_new/netinet/tcp_cc_newreno.c#3 edit Differences ... ==== //depot/projects/tcp_new/netinet/tcp_cc_newreno.c#3 (text+ko) ==== @@ -93,6 +93,7 @@ * avoid capping cwnd. * * NB: Make sure to lower bound cwnd to one (two?) segments. + * XXXAO: Upper bound to link-speed to avoid CWND overshooting. */ if (tp->snd_cwnd > tp->snd_ssthresh) { /* Congestion avoidance */ @@ -150,14 +151,14 @@ newreno_post_lr(struct tcpcb *tp, struct tcphdr *th) { /* - * Out of fast recovery. - * Window inflation should have left us - * with approximately snd_ssthresh - * outstanding data. - * But in case we would be inclined to - * send a burst, better to do it via - * the slow start mechanism. - */ + * Out of fast recovery. + * Window inflation should have left us + * with approximately snd_ssthresh + * outstanding data. + * But in case we would be inclined to + * send a burst, better to do it via + * the slow start mechanism. + */ if (th && SEQ_GT(th->th_ack + tp->snd_ssthresh, tp->snd_nxt)) tp->snd_cwnd = tp->snd_nxt - th->th_ack + tp->snd_mss; else
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200905050725.n457PR7o003321>