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_recovery.c | |
| parent | c4b2bf6b4a35348fe6d1eb06928eb68d7b9d99a9 (diff) | |
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_recovery.c')
| -rw-r--r-- | net/ipv4/tcp_recovery.c | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c index fe9a493d0208..449cd914d58e 100644 --- a/net/ipv4/tcp_recovery.c +++ b/net/ipv4/tcp_recovery.c @@ -113,7 +113,7 @@ void tcp_rack_mark_lost(struct sock *sk) tp->rack.advanced = 0; tcp_rack_detect_loss(sk, &timeout); if (timeout) { - timeout = usecs_to_jiffies(timeout + TCP_REO_TIMEOUT_MIN); + timeout = usecs_to_jiffies(timeout) + TCP_TIMEOUT_MIN; inet_csk_reset_xmit_timer(sk, ICSK_TIME_REO_TIMEOUT, timeout, inet_csk(sk)->icsk_rto); } |