diff options
author | smh <smh@FreeBSD.org> | 2017-04-24 16:31:28 +0000 |
---|---|---|
committer | smh <smh@FreeBSD.org> | 2017-04-24 16:31:28 +0000 |
commit | 5f7e779f9ffada568a00fd3d20896316ecf69996 (patch) | |
tree | fe6aba59a930b30016ee7d2ec96ff36628b01719 /sys/netinet/tcp_input.c | |
parent | e7481cb7514ab48287a87757be4290e9ce05b949 (diff) | |
download | FreeBSD-src-5f7e779f9ffada568a00fd3d20896316ecf69996.zip FreeBSD-src-5f7e779f9ffada568a00fd3d20896316ecf69996.tar.gz |
Partial MFC r316676 and the required r313045
MFC r316676:
Use estimated RTT for receive buffer auto resizing instead of timestamps.
This is a partial MFC as stable/10 doesn't include the TCP stack
modularisation.
MFC r313045:
Add an mbuf to ipinfo_t translator to finish cleanup of mbuf passing to TCP
probes. This is a partial MFC (missing debug__output & debug__drop changes)
due to the massive amount of additional dtrace changes that would be
required for a full MFC.
Relnotes: Yes
Sponsored by: Multiplay
Diffstat (limited to 'sys/netinet/tcp_input.c')
-rw-r--r-- | sys/netinet/tcp_input.c | 121 |
1 files changed, 63 insertions, 58 deletions
diff --git a/sys/netinet/tcp_input.c b/sys/netinet/tcp_input.c index 254454f..95c4d53 100644 --- a/sys/netinet/tcp_input.c +++ b/sys/netinet/tcp_input.c @@ -1469,6 +1469,68 @@ drop: m_freem(m); } +/* + * Automatic sizing of receive socket buffer. Often the send + * buffer size is not optimally adjusted to the actual network + * conditions at hand (delay bandwidth product). Setting the + * buffer size too small limits throughput on links with high + * bandwidth and high delay (eg. trans-continental/oceanic links). + * + * On the receive side the socket buffer memory is only rarely + * used to any significant extent. This allows us to be much + * more aggressive in scaling the receive socket buffer. For + * the case that the buffer space is actually used to a large + * extent and we run out of kernel memory we can simply drop + * the new segments; TCP on the sender will just retransmit it + * later. Setting the buffer size too big may only consume too + * much kernel memory if the application doesn't read() from + * the socket or packet loss or reordering makes use of the + * reassembly queue. + * + * The criteria to step up the receive buffer one notch are: + * 1. Application has not set receive buffer size with + * SO_RCVBUF. Setting SO_RCVBUF clears SB_AUTOSIZE. + * 2. the number of bytes received during the time it takes + * one timestamp to be reflected back to us (the RTT); + * 3. received bytes per RTT is within seven eighth of the + * current socket buffer size; + * 4. receive buffer size has not hit maximal automatic size; + * + * This algorithm does one step per RTT at most and only if + * we receive a bulk stream w/o packet losses or reorderings. + * Shrinking the buffer during idle times is not necessary as + * it doesn't consume any memory when idle. + * + * TODO: Only step up if the application is actually serving + * the buffer to better manage the socket buffer resources. + */ +int +tcp_autorcvbuf(struct mbuf *m, struct tcphdr *th, struct socket *so, + struct tcpcb *tp, int tlen) +{ + int newsize = 0; + + if (V_tcp_do_autorcvbuf && (so->so_rcv.sb_flags & SB_AUTOSIZE) && + tp->t_srtt != 0 && tp->rfbuf_ts != 0 && + TCP_TS_TO_TICKS(tcp_ts_getticks() - tp->rfbuf_ts) > + (tp->t_srtt >> TCP_RTT_SHIFT)) { + if (tp->rfbuf_cnt > (so->so_rcv.sb_hiwat / 8 * 7) && + so->so_rcv.sb_hiwat < V_tcp_autorcvbuf_max) { + newsize = min(so->so_rcv.sb_hiwat + + V_tcp_autorcvbuf_inc, V_tcp_autorcvbuf_max); + } + TCP_PROBE6(receive__autoresize, NULL, tp, m, tp, th, newsize); + + /* Start over with next RTT. */ + tp->rfbuf_ts = 0; + tp->rfbuf_cnt = 0; + } else { + tp->rfbuf_cnt += tlen; /* add up */ + } + + return (newsize); +} + static void tcp_do_segment(struct mbuf *m, struct tcphdr *th, struct socket *so, struct tcpcb *tp, int drop_hdrlen, int tlen, uint8_t iptos, @@ -1811,60 +1873,7 @@ tcp_do_segment(struct mbuf *m, struct tcphdr *th, struct socket *so, tcp_trace(TA_INPUT, ostate, tp, (void *)tcp_saveipgen, &tcp_savetcp, 0); #endif - /* - * Automatic sizing of receive socket buffer. Often the send - * buffer size is not optimally adjusted to the actual network - * conditions at hand (delay bandwidth product). Setting the - * buffer size too small limits throughput on links with high - * bandwidth and high delay (eg. trans-continental/oceanic links). - * - * On the receive side the socket buffer memory is only rarely - * used to any significant extent. This allows us to be much - * more aggressive in scaling the receive socket buffer. For - * the case that the buffer space is actually used to a large - * extent and we run out of kernel memory we can simply drop - * the new segments; TCP on the sender will just retransmit it - * later. Setting the buffer size too big may only consume too - * much kernel memory if the application doesn't read() from - * the socket or packet loss or reordering makes use of the - * reassembly queue. - * - * The criteria to step up the receive buffer one notch are: - * 1. the number of bytes received during the time it takes - * one timestamp to be reflected back to us (the RTT); - * 2. received bytes per RTT is within seven eighth of the - * current socket buffer size; - * 3. receive buffer size has not hit maximal automatic size; - * - * This algorithm does one step per RTT at most and only if - * we receive a bulk stream w/o packet losses or reorderings. - * Shrinking the buffer during idle times is not necessary as - * it doesn't consume any memory when idle. - * - * TODO: Only step up if the application is actually serving - * the buffer to better manage the socket buffer resources. - */ - if (V_tcp_do_autorcvbuf && - (to.to_flags & TOF_TS) && - to.to_tsecr && - (so->so_rcv.sb_flags & SB_AUTOSIZE)) { - if (TSTMP_GT(to.to_tsecr, tp->rfbuf_ts) && - to.to_tsecr - tp->rfbuf_ts < hz) { - if (tp->rfbuf_cnt > - (so->so_rcv.sb_hiwat / 8 * 7) && - so->so_rcv.sb_hiwat < - V_tcp_autorcvbuf_max) { - newsize = - min(so->so_rcv.sb_hiwat + - V_tcp_autorcvbuf_inc, - V_tcp_autorcvbuf_max); - } - /* Start over with next RTT. */ - tp->rfbuf_ts = 0; - tp->rfbuf_cnt = 0; - } else - tp->rfbuf_cnt += tlen; /* add up */ - } + newsize = tcp_autorcvbuf(m, th, so, tp, tlen); /* Add data to socket buffer. */ SOCKBUF_LOCK(&so->so_rcv); @@ -1905,10 +1914,6 @@ tcp_do_segment(struct mbuf *m, struct tcphdr *th, struct socket *so, win = 0; tp->rcv_wnd = imax(win, (int)(tp->rcv_adv - tp->rcv_nxt)); - /* Reset receive buffer auto scaling when not in bulk receive mode. */ - tp->rfbuf_ts = 0; - tp->rfbuf_cnt = 0; - switch (tp->t_state) { /* |