From mboxrd@z Thu Jan 1 00:00:00 1970 From: Yuchung Cheng Subject: [net-next 12/13] tcp: remove thin_dupack feature Date: Thu, 12 Jan 2017 22:03:53 -0800 Message-ID: <20170113060354.85234-13-ycheng@google.com> References: <20170113060354.85234-1-ycheng@google.com> Cc: netdev@vger.kernel.org, edumazet@google.com, ncardwell@google.com, nanditad@google.com, Yuchung Cheng To: davem@davemloft.net Return-path: Received: from mail-pf0-f171.google.com ([209.85.192.171]:35455 "EHLO mail-pf0-f171.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751146AbdAMGEm (ORCPT ); Fri, 13 Jan 2017 01:04:42 -0500 Received: by mail-pf0-f171.google.com with SMTP id f144so25782462pfa.2 for ; Thu, 12 Jan 2017 22:04:42 -0800 (PST) In-Reply-To: <20170113060354.85234-1-ycheng@google.com> Sender: netdev-owner@vger.kernel.org List-ID: Thin stream DUPACK is to start fast recovery on only one DUPACK provided the connection is a thin stream (i.e., low inflight). But this older feature is now subsumed with RACK. If a connection receives only a single DUPACK, RACK would arm a reordering timer and soon starts fast recovery instead of timeout if no further ACKs are received. The socket option (THIN_DUPACK) is kept as a nop for compatibility. Note that this patch does not change another thin-stream feature which enables linear RTO. Although it might be good to generalize that in the future (i.e., linear RTO for the first say 3 retries). Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Acked-by: Eric Dumazet --- Documentation/networking/ip-sysctl.txt | 12 ------------ include/linux/tcp.h | 2 +- net/ipv4/sysctl_net_ipv4.c | 7 ------- net/ipv4/tcp.c | 6 ++---- net/ipv4/tcp_input.c | 13 ------------- 5 files changed, 3 insertions(+), 37 deletions(-) diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 7de2cf79e16f..aa1bb49f1dc6 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -703,18 +703,6 @@ tcp_thin_linear_timeouts - BOOLEAN Documentation/networking/tcp-thin.txt Default: 0 -tcp_thin_dupack - BOOLEAN - Enable dynamic triggering of retransmissions after one dupACK - for thin streams. If set, a check is performed upon reception - of a dupACK to determine if the stream is thin (less than 4 - packets in flight). As long as the stream is found to be thin, - data is retransmitted on the first received dupACK. This - improves retransmission latency for non-aggressive thin - streams, often found to be time-dependent. - For more information on thin streams, see - Documentation/networking/tcp-thin.txt - Default: 0 - tcp_limit_output_bytes - INTEGER Controls TCP Small Queue limit per tcp socket. TCP bulk sender tends to increase packets in flight until it diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 4733368f953a..6c22332afb75 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -220,7 +220,7 @@ struct tcp_sock { unused:5; u8 nonagle : 4,/* Disable Nagle algorithm? */ thin_lto : 1,/* Use linear timeouts for thin streams */ - thin_dupack : 1,/* Fast retransmit on first dupack */ + unused1 : 1, repair : 1, frto : 1;/* F-RTO (RFC5682) activated in CA_Loss */ u8 repair_queue; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 0f2d37e8e983..c8d283615c6f 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -537,13 +537,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .procname = "tcp_thin_dupack", - .data = &sysctl_tcp_thin_dupack, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { .procname = "tcp_early_retrans", .data = &sysctl_tcp_early_retrans, .maxlen = sizeof(int), diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index d9023e8ed53e..aba6ea76338e 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2474,9 +2474,6 @@ static int do_tcp_setsockopt(struct sock *sk, int level, case TCP_THIN_DUPACK: if (val < 0 || val > 1) err = -EINVAL; - else { - tp->thin_dupack = val; - } break; case TCP_REPAIR: @@ -2966,8 +2963,9 @@ static int do_tcp_getsockopt(struct sock *sk, int level, case TCP_THIN_LINEAR_TIMEOUTS: val = tp->thin_lto; break; + case TCP_THIN_DUPACK: - val = tp->thin_dupack; + val = 0; break; case TCP_REPAIR: diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 87315ab1ab1a..39ebc20ca1b2 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -95,9 +95,6 @@ int sysctl_tcp_rfc1337 __read_mostly; int sysctl_tcp_max_orphans __read_mostly = NR_FILE; int sysctl_tcp_frto __read_mostly = 2; int sysctl_tcp_min_rtt_wlen __read_mostly = 300; - -int sysctl_tcp_thin_dupack __read_mostly; - int sysctl_tcp_moderate_rcvbuf __read_mostly = 1; int sysctl_tcp_early_retrans __read_mostly = 3; int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2; @@ -2170,16 +2167,6 @@ static bool tcp_time_to_recover(struct sock *sk, int flag) if (tcp_dupack_heuristics(tp) > tp->reordering) return true; - /* If a thin stream is detected, retransmit after first - * received dupack. Employ only if SACK is supported in order - * to avoid possible corner-case series of spurious retransmissions - * Use only if there are no unsent data. - */ - if ((tp->thin_dupack || sysctl_tcp_thin_dupack) && - tcp_stream_is_thin(tp) && tcp_dupack_heuristics(tp) > 1 && - tcp_is_sack(tp) && !tcp_send_head(sk)) - return true; - return false; } -- 2.11.0.483.g087da7b7c-goog