From c1d5674f8313b9f8e683c265f1c00a2582cf5fc5 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Wed, 16 Jan 2019 15:05:35 -0800 Subject: tcp: less aggressive window probing on local congestion Previously when the sender fails to send (original) data packet or window probes due to congestion in the local host (e.g. throttling in qdisc), it'll retry within an RTO or two up to 500ms. In low-RTT networks such as data-centers, RTO is often far below the default minimum 200ms. Then local host congestion could trigger a retry storm pouring gas to the fire. Worse yet, the probe counter (icsk_probes_out) is not properly updated so the aggressive retry may exceed the system limit (15 rounds) until the packet finally slips through. On such rare events, it's wise to retry more conservatively (500ms) and update the stats properly to reflect these incidents and follow the system limit. Note that this is consistent with the behaviors when a keep-alive probe or RTO retry is dropped due to local congestion. Signed-off-by: Yuchung Cheng Signed-off-by: Eric Dumazet Reviewed-by: Neal Cardwell Reviewed-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- net/ipv4/tcp_output.c | 22 +++++++--------------- 1 file changed, 7 insertions(+), 15 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index d2d494c74811..6527f61f59ff 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3749,7 +3749,7 @@ void tcp_send_probe0(struct sock *sk) struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); - unsigned long probe_max; + unsigned long timeout; int err; err = tcp_write_wakeup(sk, LINUX_MIB_TCPWINPROBE); @@ -3761,26 +3761,18 @@ void tcp_send_probe0(struct sock *sk) return; } + icsk->icsk_probes_out++; if (err <= 0) { if (icsk->icsk_backoff < net->ipv4.sysctl_tcp_retries2) icsk->icsk_backoff++; - icsk->icsk_probes_out++; - probe_max = TCP_RTO_MAX; + timeout = tcp_probe0_when(sk, TCP_RTO_MAX); } else { /* If packet was not sent due to local congestion, - * do not backoff and do not remember icsk_probes_out. - * Let local senders to fight for local resources. - * - * Use accumulated backoff yet. + * Let senders fight for local resources conservatively. */ - if (!icsk->icsk_probes_out) - icsk->icsk_probes_out = 1; - probe_max = TCP_RESOURCE_PROBE_INTERVAL; - } - tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, - tcp_probe0_when(sk, probe_max), - TCP_RTO_MAX, - NULL); + timeout = TCP_RESOURCE_PROBE_INTERVAL; + } + tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, timeout, TCP_RTO_MAX, NULL); } int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) -- cgit v1.2.3-59-g8ed1b