Date: Fri, 30 Jul 2010 21:45:53 +0000 (UTC) From: Andre Oppermann <andre@FreeBSD.org> To: src-committers@freebsd.org, svn-src-all@freebsd.org, svn-src-head@freebsd.org Subject: svn commit: r210666 - head/sys/netinet Message-ID: <201007302145.o6ULjr3k083665@svn.freebsd.org>
next in thread | raw e-mail | index | archive | help
Author: andre Date: Fri Jul 30 21:45:53 2010 New Revision: 210666 URL: http://svn.freebsd.org/changeset/base/210666 Log: Fix a bug in syncache where the initial CWND for new incoming connections was limited to one segment under the faulty assumption of a retransmit. Due to this the opportunity to initialize the increased congestion window according to RFC3390 was missed. Support for RFC3465 introduced in r187289 uncovered the bug as the ACK to SYN/ACK no longer caused snd_cwnd increase by MSS (actually, this increase shouldn't happen as it's explicitly forbidden by RFC3390, but it's another issue). Snd_cwnd remains really small (1*MSS + 1) and this causes really bad interaction with delayed acks on other side. The variable name sc_rxmits is a bit misleading as it counts all transmits, not just retransmits. Submitted by: Maxim Dounin <mdounin-at-mdounin-dot-ru> MFC after: 10 days Modified: head/sys/netinet/tcp_syncache.c Modified: head/sys/netinet/tcp_syncache.c ============================================================================== --- head/sys/netinet/tcp_syncache.c Fri Jul 30 21:39:28 2010 (r210665) +++ head/sys/netinet/tcp_syncache.c Fri Jul 30 21:45:53 2010 (r210666) @@ -804,8 +804,9 @@ syncache_socket(struct syncache *sc, str /* * If the SYN,ACK was retransmitted, reset cwnd to 1 segment. + * NB: sc_rxmits counts all SYN,ACK transmits, not just retransmits. */ - if (sc->sc_rxmits) + if (sc->sc_rxmits > 1) tp->snd_cwnd = tp->t_maxseg; tcp_timer_activate(tp, TT_KEEP, tcp_keepinit);
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?201007302145.o6ULjr3k083665>