Date: Fri, 5 Jul 2013 14:50:06 +0000 (UTC) From: Andre Oppermann <andre@FreeBSD.org> To: src-committers@freebsd.org, svn-src-all@freebsd.org, svn-src-stable@freebsd.org, svn-src-stable-9@freebsd.org Subject: svn commit: r252788 - stable/9/sys/netinet Message-ID: <201307051450.r65Eo79t063625@svn.freebsd.org>
next in thread | raw e-mail | index | archive | help
Author: andre Date: Fri Jul 5 14:50:06 2013 New Revision: 252788 URL: http://svnweb.freebsd.org/changeset/base/252788 Log: MFC r226447: Remove the ss_fltsz and ss_fltsz_local sysctl's which have long been superseded by the RFC3390 initial CWND sizing. Also remove the remnants of TCP_METRICS_CWND which used the TCP hostcache to set the initial CWND in a non-RFC compliant way. MFC r242249: Adjust the initial default CWND upon connection establishment to the new and increased values specified by RFC5681 Section 3.1. The even larger initial CWND per RFC3390, if enabled, is not affected. MFC r242250: When SYN or SYN/ACK had to be retransmitted RFC5681 requires us to reduce the initial CWND to one segment. This reduction got lost some time ago due to a change in initialization ordering. Additionally in tcp_timer_rexmt() avoid entering fast recovery when we're still in TCPS_SYN_SENT state. MFC r242255: Allow arbitrary MSS sizes and don't mind about the cluster size anymore. We've got more cluster sizes for quite some time now and the orginally imposed limits and the previously codified thoughts on efficiency gains are no longer true. Modified: stable/9/sys/netinet/tcp_input.c stable/9/sys/netinet/tcp_output.c stable/9/sys/netinet/tcp_syncache.c stable/9/sys/netinet/tcp_timer.c stable/9/sys/netinet/tcp_var.h Directory Properties: stable/9/sys/ (props changed) Modified: stable/9/sys/netinet/tcp_input.c ============================================================================== --- stable/9/sys/netinet/tcp_input.c Fri Jul 5 14:30:54 2013 (r252787) +++ stable/9/sys/netinet/tcp_input.c Fri Jul 5 14:50:06 2013 (r252788) @@ -304,9 +304,6 @@ cc_conn_init(struct tcpcb *tp) struct hc_metrics_lite metrics; struct inpcb *inp = tp->t_inpcb; int rtt; -#ifdef INET6 - int isipv6 = ((inp->inp_vflag & INP_IPV6) != 0) ? 1 : 0; -#endif INP_WLOCK_ASSERT(tp->t_inpcb); @@ -340,49 +337,29 @@ cc_conn_init(struct tcpcb *tp) } /* - * Set the slow-start flight size depending on whether this - * is a local network or not. + * Set the initial slow-start flight size. * - * Extend this so we cache the cwnd too and retrieve it here. - * Make cwnd even bigger than RFC3390 suggests but only if we - * have previous experience with the remote host. Be careful - * not make cwnd bigger than remote receive window or our own - * send socket buffer. Maybe put some additional upper bound - * on the retrieved cwnd. Should do incremental updates to - * hostcache when cwnd collapses so next connection doesn't - * overloads the path again. + * RFC5681 Section 3.1 specifies the default conservative values. + * RFC3390 specifies slightly more aggressive values. * - * XXXAO: Initializing the CWND from the hostcache is broken - * and in its current form not RFC conformant. It is disabled - * until fixed or removed entirely. - * - * RFC3390 says only do this if SYN or SYN/ACK didn't got lost. - * We currently check only in syncache_socket for that. - */ -/* #define TCP_METRICS_CWND */ -#ifdef TCP_METRICS_CWND - if (metrics.rmx_cwnd) - tp->snd_cwnd = max(tp->t_maxseg, min(metrics.rmx_cwnd / 2, - min(tp->snd_wnd, so->so_snd.sb_hiwat))); - else -#endif - if (V_tcp_do_rfc3390) + * If a SYN or SYN/ACK was lost and retransmitted, we have to + * reduce the initial CWND to one segment as congestion is likely + * requiring us to be cautious. + */ + if (tp->snd_cwnd == 1) + tp->snd_cwnd = tp->t_maxseg; /* SYN(-ACK) lost */ + else if (V_tcp_do_rfc3390) tp->snd_cwnd = min(4 * tp->t_maxseg, max(2 * tp->t_maxseg, 4380)); -#ifdef INET6 - else if (isipv6 && in6_localaddr(&inp->in6p_faddr)) - tp->snd_cwnd = tp->t_maxseg * V_ss_fltsz_local; -#endif -#if defined(INET) && defined(INET6) - else if (!isipv6 && in_localaddr(inp->inp_faddr)) - tp->snd_cwnd = tp->t_maxseg * V_ss_fltsz_local; -#endif -#ifdef INET - else if (in_localaddr(inp->inp_faddr)) - tp->snd_cwnd = tp->t_maxseg * V_ss_fltsz_local; -#endif - else - tp->snd_cwnd = tp->t_maxseg * V_ss_fltsz; + else { + /* Per RFC5681 Section 3.1 */ + if (tp->t_maxseg > 2190) + tp->snd_cwnd = 2 * tp->t_maxseg; + else if (tp->t_maxseg > 1095) + tp->snd_cwnd = 3 * tp->t_maxseg; + else + tp->snd_cwnd = 4 * tp->t_maxseg; + } if (CC_ALGO(tp)->conn_init != NULL) CC_ALGO(tp)->conn_init(tp->ccv); @@ -3389,10 +3366,8 @@ tcp_xmit_timer(struct tcpcb *tp, int rtt /* * Determine a reasonable value for maxseg size. * If the route is known, check route for mtu. - * If none, use an mss that can be handled on the outgoing - * interface without forcing IP to fragment; if bigger than - * an mbuf cluster (MCLBYTES), round down to nearest multiple of MCLBYTES - * to utilize large mbufs. If no route is found, route has no mtu, + * If none, use an mss that can be handled on the outgoing interface + * without forcing IP to fragment. If no route is found, route has no mtu, * or the destination isn't local, use a default, hopefully conservative * size (usually 512 or the default IP max size, but no more than the mtu * of the interface), as we can't discover anything about intervening @@ -3573,13 +3548,6 @@ tcp_mss_update(struct tcpcb *tp, int off (tp->t_flags & TF_RCVD_TSTMP) == TF_RCVD_TSTMP)) mss -= TCPOLEN_TSTAMP_APPA; -#if (MCLBYTES & (MCLBYTES - 1)) == 0 - if (mss > MCLBYTES) - mss &= ~(MCLBYTES-1); -#else - if (mss > MCLBYTES) - mss = mss / MCLBYTES * MCLBYTES; -#endif tp->t_maxseg = mss; } Modified: stable/9/sys/netinet/tcp_output.c ============================================================================== --- stable/9/sys/netinet/tcp_output.c Fri Jul 5 14:30:54 2013 (r252787) +++ stable/9/sys/netinet/tcp_output.c Fri Jul 5 14:50:06 2013 (r252788) @@ -92,16 +92,6 @@ SYSCTL_VNET_INT(_net_inet_tcp, OID_AUTO, &VNET_NAME(path_mtu_discovery), 1, "Enable Path MTU Discovery"); -VNET_DEFINE(int, ss_fltsz) = 1; -SYSCTL_VNET_INT(_net_inet_tcp, OID_AUTO, slowstart_flightsize, CTLFLAG_RW, - &VNET_NAME(ss_fltsz), 1, - "Slow start flight size"); - -VNET_DEFINE(int, ss_fltsz_local) = 4; -SYSCTL_VNET_INT(_net_inet_tcp, OID_AUTO, local_slowstart_flightsize, - CTLFLAG_RW, &VNET_NAME(ss_fltsz_local), 1, - "Slow start flight size for local networks"); - VNET_DEFINE(int, tcp_do_tso) = 1; #define V_tcp_do_tso VNET(tcp_do_tso) SYSCTL_VNET_INT(_net_inet_tcp, OID_AUTO, tso, CTLFLAG_RW, Modified: stable/9/sys/netinet/tcp_syncache.c ============================================================================== --- stable/9/sys/netinet/tcp_syncache.c Fri Jul 5 14:30:54 2013 (r252787) +++ stable/9/sys/netinet/tcp_syncache.c Fri Jul 5 14:50:06 2013 (r252788) @@ -852,11 +852,12 @@ syncache_socket(struct syncache *sc, str tcp_mss(tp, sc->sc_peer_mss); /* - * If the SYN,ACK was retransmitted, reset cwnd to 1 segment. + * If the SYN,ACK was retransmitted, indicate that CWND to be + * limited to one segment in cc_conn_init(). * NB: sc_rxmits counts all SYN,ACK transmits, not just retransmits. */ if (sc->sc_rxmits > 1) - tp->snd_cwnd = tp->t_maxseg; + tp->snd_cwnd = 1; #ifdef TCP_OFFLOAD /* Modified: stable/9/sys/netinet/tcp_timer.c ============================================================================== --- stable/9/sys/netinet/tcp_timer.c Fri Jul 5 14:30:54 2013 (r252787) +++ stable/9/sys/netinet/tcp_timer.c Fri Jul 5 14:50:06 2013 (r252788) @@ -545,7 +545,13 @@ tcp_timer_rexmt(void * xtp) } INP_INFO_RUNLOCK(&V_tcbinfo); headlocked = 0; - if (tp->t_rxtshift == 1) { + if (tp->t_state == TCPS_SYN_SENT) { + /* + * If the SYN was retransmitted, indicate CWND to be + * limited to 1 segment in cc_conn_init(). + */ + tp->snd_cwnd = 1; + } else if (tp->t_rxtshift == 1) { /* * first retransmit; record ssthresh and cwnd so they can * be recovered if this turns out to be a "bad" retransmit. Modified: stable/9/sys/netinet/tcp_var.h ============================================================================== --- stable/9/sys/netinet/tcp_var.h Fri Jul 5 14:30:54 2013 (r252787) +++ stable/9/sys/netinet/tcp_var.h Fri Jul 5 14:50:06 2013 (r252788) @@ -623,8 +623,6 @@ VNET_DECLARE(int, tcp_minmss); VNET_DECLARE(int, tcp_delack_enabled); VNET_DECLARE(int, tcp_do_rfc3390); VNET_DECLARE(int, path_mtu_discovery); -VNET_DECLARE(int, ss_fltsz); -VNET_DECLARE(int, ss_fltsz_local); VNET_DECLARE(int, tcp_do_rfc3465); VNET_DECLARE(int, tcp_abc_l_var); #define V_tcb VNET(tcb) @@ -635,8 +633,6 @@ VNET_DECLARE(int, tcp_abc_l_var); #define V_tcp_delack_enabled VNET(tcp_delack_enabled) #define V_tcp_do_rfc3390 VNET(tcp_do_rfc3390) #define V_path_mtu_discovery VNET(path_mtu_discovery) -#define V_ss_fltsz VNET(ss_fltsz) -#define V_ss_fltsz_local VNET(ss_fltsz_local) #define V_tcp_do_rfc3465 VNET(tcp_do_rfc3465) #define V_tcp_abc_l_var VNET(tcp_abc_l_var)
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?201307051450.r65Eo79t063625>