From ab32ea5d8a760e7dd4339634e95d7be24ee5b842 Mon Sep 17 00:00:00 2001 From: Brian Haley Date: Fri, 22 Sep 2006 14:15:41 -0700 Subject: [NET/IPV4/IPV6]: Change some sysctl variables to __read_mostly Change net/core, ipv4 and ipv6 sysctl variables to __read_mostly. Couldn't actually measure any performance increase while testing (.3% I consider noise), but seems like the right thing to do. Signed-off-by: Brian Haley Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 36 ++++++++++++++++++------------------ 1 file changed, 18 insertions(+), 18 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 159fa3f1ba6..caf3c41dcc8 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -72,24 +72,24 @@ #include #include -int sysctl_tcp_timestamps = 1; -int sysctl_tcp_window_scaling = 1; -int sysctl_tcp_sack = 1; -int sysctl_tcp_fack = 1; -int sysctl_tcp_reordering = TCP_FASTRETRANS_THRESH; -int sysctl_tcp_ecn; -int sysctl_tcp_dsack = 1; -int sysctl_tcp_app_win = 31; -int sysctl_tcp_adv_win_scale = 2; - -int sysctl_tcp_stdurg; -int sysctl_tcp_rfc1337; -int sysctl_tcp_max_orphans = NR_FILE; -int sysctl_tcp_frto; -int sysctl_tcp_nometrics_save; - -int sysctl_tcp_moderate_rcvbuf = 1; -int sysctl_tcp_abc; +int sysctl_tcp_timestamps __read_mostly = 1; +int sysctl_tcp_window_scaling __read_mostly = 1; +int sysctl_tcp_sack __read_mostly = 1; +int sysctl_tcp_fack __read_mostly = 1; +int sysctl_tcp_reordering __read_mostly = TCP_FASTRETRANS_THRESH; +int sysctl_tcp_ecn __read_mostly; +int sysctl_tcp_dsack __read_mostly = 1; +int sysctl_tcp_app_win __read_mostly = 31; +int sysctl_tcp_adv_win_scale __read_mostly = 2; + +int sysctl_tcp_stdurg __read_mostly; +int sysctl_tcp_rfc1337 __read_mostly; +int sysctl_tcp_max_orphans __read_mostly = NR_FILE; +int sysctl_tcp_frto __read_mostly; +int sysctl_tcp_nometrics_save __read_mostly; + +int sysctl_tcp_moderate_rcvbuf __read_mostly = 1; +int sysctl_tcp_abc __read_mostly; #define FLAG_DATA 0x01 /* Incoming frame contained data. */ #define FLAG_WIN_UPDATE 0x02 /* Incoming ACK was a window update. */ -- cgit v1.2.3-70-g09d2 From ff9b5e0f08cb650d113eef0c654f931c0a7ae730 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Thu, 31 Aug 2006 15:11:02 -0700 Subject: [TCP]: Fix rcv mss estimate for LRO By passing a Linux-generated TSO packet straight back into Linux, Xen becomes our first LRO user :) Unfortunately, there is at least one spot in our stack that needs to be changed to cope with this. The receive MSS estimate is computed from the raw packet size. This is broken if the packet is GSO/LRO. Fortunately the real MSS can be found in gso_size so we simply need to use that if it is non-zero. Real LRO NICs should of course set the gso_size field in future. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index caf3c41dcc8..511b738f118 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -127,7 +127,7 @@ static void tcp_measure_rcv_mss(struct sock *sk, /* skb->len may jitter because of SACKs, even if peer * sends good full-sized frames. */ - len = skb->len; + len = skb_shinfo(skb)->gso_size ?: skb->len; if (len >= icsk->icsk_ack.rcv_mss) { icsk->icsk_ack.rcv_mss = len; } else { -- cgit v1.2.3-70-g09d2 From 1ef9696c909060ccdae3ade245ca88692b49285b Mon Sep 17 00:00:00 2001 From: Alexey Kuznetsov Date: Tue, 19 Sep 2006 12:52:50 -0700 Subject: [TCP]: Send ACKs each 2nd received segment. It does not affect either mss-sized connections (obviously) or connections controlled by Nagle (because there is only one small segment in flight). The idea is to record the fact that a small segment arrives on a connection, where one small segment has already been received and still not-ACKed. In this case ACK is forced after tcp_recvmsg() drains receive buffer. In other words, it is a "soft" each-2nd-segment ACK, which is enough to preserve ACK clock even when ABC is enabled. Signed-off-by: Alexey Kuznetsov Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 3 ++- net/ipv4/tcp.c | 7 +++++-- net/ipv4/tcp_input.c | 2 ++ 3 files changed, 9 insertions(+), 3 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 9bf73fe5094..de4e83b6da4 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -147,7 +147,8 @@ extern struct sock *inet_csk_clone(struct sock *sk, enum inet_csk_ack_state_t { ICSK_ACK_SCHED = 1, ICSK_ACK_TIMER = 2, - ICSK_ACK_PUSHED = 4 + ICSK_ACK_PUSHED = 4, + ICSK_ACK_PUSHED2 = 8 }; extern void inet_csk_init_xmit_timers(struct sock *sk, diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 29e3d606db7..66e9a729f6d 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -955,8 +955,11 @@ void tcp_cleanup_rbuf(struct sock *sk, int copied) * receive buffer and there was a small segment * in queue. */ - (copied > 0 && (icsk->icsk_ack.pending & ICSK_ACK_PUSHED) && - !icsk->icsk_ack.pingpong && !atomic_read(&sk->sk_rmem_alloc))) + (copied > 0 && + ((icsk->icsk_ack.pending & ICSK_ACK_PUSHED2) || + ((icsk->icsk_ack.pending & ICSK_ACK_PUSHED) && + !icsk->icsk_ack.pingpong)) && + !atomic_read(&sk->sk_rmem_alloc))) time_to_ack = 1; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 511b738f118..b3def0df14f 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -156,6 +156,8 @@ static void tcp_measure_rcv_mss(struct sock *sk, return; } } + if (icsk->icsk_ack.pending & ICSK_ACK_PUSHED) + icsk->icsk_ack.pending |= ICSK_ACK_PUSHED2; icsk->icsk_ack.pending |= ICSK_ACK_PUSHED; } } -- cgit v1.2.3-70-g09d2