diff options
| author |   Yuchung Cheng <ycheng@google.com> | 2017-07-19 15:41:26 -0700 |
|---|---|---|
| committer |   David S. Miller <davem@davemloft.net> | 2017-07-19 16:14:10 -0700 |
| commit | bb4d991a28cc86a2dfbeefeff32911ca9f779c18 (patch) | |
| tree | 6fd415a7d0b54a9e639067375013fe8f2c3a48b7 /net/ipv4/tcp_output.c | |
| parent | openvswitch: Optimize operations for OvS flow_stats. (diff) | |
| download | linux-dev-bb4d991a28cc86a2dfbeefeff32911ca9f779c18.tar.xz linux-dev-bb4d991a28cc86a2dfbeefeff32911ca9f779c18.zip | |
tcp: adjust tail loss probe timeout
This patch adjusts the timeout formula to schedule the TCP loss probe
(TLP). The previous formula uses 2*SRTT or 1.5*RTT + DelayACKMax if
only one packet is in flight. It keeps a lower bound of 10 msec which
is too large for short RTT connections (e.g. within a data-center).
The new formula = 2*RTT + (inflight == 1 ? 200ms : 2ticks) which
performs better for short and fast connections.
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/ipv4/tcp_output.c')
| -rw-r--r-- | net/ipv4/tcp_output.c | 17 |
1 files changed, 10 insertions, 7 deletions
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 4e985dea1dd2..886d874775df 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2377,7 +2377,6 @@ bool tcp_schedule_loss_probe(struct sock *sk) struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); u32 timeout, tlp_time_stamp, rto_time_stamp; - u32 rtt = usecs_to_jiffies(tp->srtt_us >> 3); /* No consecutive loss probes. */ if (WARN_ON(icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)) { @@ -2406,15 +2405,19 @@ bool tcp_schedule_loss_probe(struct sock *sk) tcp_send_head(sk)) return false; - /* Probe timeout is at least 1.5*rtt + TCP_DELACK_MAX to account + /* Probe timeout is 2*rtt. Add minimum RTO to account * for delayed ack when there's one outstanding packet. If no RTT * sample is available then probe after TCP_TIMEOUT_INIT. */ - timeout = rtt << 1 ? : TCP_TIMEOUT_INIT; - if (tp->packets_out == 1) - timeout = max_t(u32, timeout, - (rtt + (rtt >> 1) + TCP_DELACK_MAX)); - timeout = max_t(u32, timeout, msecs_to_jiffies(10)); + if (tp->srtt_us) { + timeout = usecs_to_jiffies(tp->srtt_us >> 2); + if (tp->packets_out == 1) + timeout += TCP_RTO_MIN; + else + timeout += TCP_TIMEOUT_MIN; + } else { + timeout = TCP_TIMEOUT_INIT; + } /* If RTO is shorter, just schedule TLP in its place. */ tlp_time_stamp = tcp_jiffies32 + timeout; |