diff options
| author | David S. Miller <davem@davemloft.net> | 2016-09-21 07:23:09 +0300 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2016-09-21 07:23:09 +0300 |
| commit | a624f93ce6623d452e87d8dcf557e7c680822991 (patch) | |
| tree | f6d7ecddbe3fd16a6a48374f2c647d40f25b77e5 /include/linux | |
| parent | 94d308d060cd3ee65152b8ebd7a1c24fa86eee82 (diff) | |
| parent | 0f8782ea14974ce992618b55f0c041ef43ed0b78 (diff) | |
| download | linux-a624f93ce6623d452e87d8dcf557e7c680822991.tar.xz | |
Merge branch 'tcp-bbr'
Neal Cardwell says:
====================
tcp: BBR congestion control algorithm
This patch series implements a new TCP congestion control algorithm:
BBR (Bottleneck Bandwidth and RTT). A paper with a detailed
description of BBR will be published in ACM Queue, September-October
2016, as "BBR: Congestion-Based Congestion Control". BBR is widely
deployed in production at Google.
The patch series starts with a set of supporting infrastructure
changes, including a few that extend the congestion control
framework. The last patch adds BBR as a TCP congestion control
module. Please see individual patches for the details.
- v3 -> v4:
- Updated tcp_bbr.c in "tcp_bbr: add BBR congestion control"
to use const to qualify all the constant parameters.
Thanks to Stephen Hemminger.
- In "tcp_bbr: add BBR congestion control", remove the bbr_rate_kbps()
function, which had a 64-bit divide that would be problematic on some
architectures, and just use bbr_rate_bytes_per_sec() directly.
Thanks to Kenneth Klette Jonassen for suggesting this.
- In "tcp: switch back to proper tcp_skb_cb size check in tcp_init()",
switched from sizeof(skb->cb) to FIELD_SIZEOF.
Thanks to Lance Richardson for suggesting this.
- Updated "tcp_bbr: add BBR congestion control" commit message with
performance data, more details about deployment at Google, and
another reminder to use fq with BBR.
- Updated tcp_bbr.c in "tcp_bbr: add BBR congestion control"
to use MODULE_LICENSE("Dual BSD/GPL").
- v2 -> v3: fix another issue caught by build bots:
- adjust rate_sample struct initialization syntax to allow gcc-4.4 to compile
the "tcp: track data delivery rate for a TCP connection" patch; also
adjusted some similar syntax in "tcp_bbr: add BBR congestion control"
- v1 -> v2: fix issues caught by build bots:
- fix "tcp: export data delivery rate" to use rate64 instead of rate,
so there is a 64-bit numerator for the do_div call
- fix conflicting definitions for minmax caused by
"tcp: use windowed min filter library for TCP min_rtt estimation"
with a new commit:
tcp: cdg: rename struct minmax in tcp_cdg.c to avoid a naming conflict
- fix warning about the use of __packed in
"tcp: track data delivery rate for a TCP connection",
which involves the addition of a new commit:
tcp: switch back to proper tcp_skb_cb size check in tcp_init()
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'include/linux')
| -rw-r--r-- | include/linux/tcp.h | 14 | ||||
| -rw-r--r-- | include/linux/win_minmax.h | 37 |
2 files changed, 47 insertions, 4 deletions
diff --git a/include/linux/tcp.h b/include/linux/tcp.h index c723a465125d..a17ae7b85218 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -19,6 +19,7 @@ #include <linux/skbuff.h> +#include <linux/win_minmax.h> #include <net/sock.h> #include <net/inet_connection_sock.h> #include <net/inet_timewait_sock.h> @@ -212,7 +213,8 @@ struct tcp_sock { u8 reord; /* reordering detected */ } rack; u16 advmss; /* Advertised MSS */ - u8 unused; + u8 rate_app_limited:1, /* rate_{delivered,interval_us} limited? */ + unused:7; u8 nonagle : 4,/* Disable Nagle algorithm? */ thin_lto : 1,/* Use linear timeouts for thin streams */ thin_dupack : 1,/* Fast retransmit on first dupack */ @@ -234,9 +236,7 @@ struct tcp_sock { u32 mdev_max_us; /* maximal mdev for the last rtt period */ u32 rttvar_us; /* smoothed mdev_max */ u32 rtt_seq; /* sequence number to update rttvar */ - struct rtt_meas { - u32 rtt, ts; /* RTT in usec and sampling time in jiffies. */ - } rtt_min[3]; + struct minmax rtt_min; u32 packets_out; /* Packets which are "in flight" */ u32 retrans_out; /* Retransmitted packets out */ @@ -268,6 +268,12 @@ struct tcp_sock { * receiver in Recovery. */ u32 prr_out; /* Total number of pkts sent during Recovery. */ u32 delivered; /* Total data packets delivered incl. rexmits */ + u32 lost; /* Total data packets lost incl. rexmits */ + u32 app_limited; /* limited until "delivered" reaches this val */ + struct skb_mstamp first_tx_mstamp; /* start of window send phase */ + struct skb_mstamp delivered_mstamp; /* time we reached "delivered" */ + u32 rate_delivered; /* saved rate sample: packets delivered */ + u32 rate_interval_us; /* saved rate sample: time elapsed */ u32 rcv_wnd; /* Current receiver window */ u32 write_seq; /* Tail(+1) of data held in tcp send buffer */ diff --git a/include/linux/win_minmax.h b/include/linux/win_minmax.h new file mode 100644 index 000000000000..56569604278f --- /dev/null +++ b/include/linux/win_minmax.h @@ -0,0 +1,37 @@ +/** + * lib/minmax.c: windowed min/max tracker by Kathleen Nichols. + * + */ +#ifndef MINMAX_H +#define MINMAX_H + +#include <linux/types.h> + +/* A single data point for our parameterized min-max tracker */ +struct minmax_sample { + u32 t; /* time measurement was taken */ + u32 v; /* value measured */ +}; + +/* State for the parameterized min-max tracker */ +struct minmax { + struct minmax_sample s[3]; +}; + +static inline u32 minmax_get(const struct minmax *m) +{ + return m->s[0].v; +} + +static inline u32 minmax_reset(struct minmax *m, u32 t, u32 meas) +{ + struct minmax_sample val = { .t = t, .v = meas }; + + m->s[2] = m->s[1] = m->s[0] = val; + return m->s[0].v; +} + +u32 minmax_running_max(struct minmax *m, u32 win, u32 t, u32 meas); +u32 minmax_running_min(struct minmax *m, u32 win, u32 t, u32 meas); + +#endif |
