summaryrefslogtreecommitdiff
path: root/net/ipv4/tcp_input.c
diff options
context:
space:
mode:
authorYuchung Cheng <ycheng@google.com>2013-08-12 16:41:25 -0700
committerDavid S. Miller <davem@davemloft.net>2013-08-13 16:08:33 -0700
commit74c181d528bd8b5989f424a489262d0742ca31ae (patch)
treedb72e02385e949e1b3a9c305e661db65a27f639b /net/ipv4/tcp_input.c
parent98f1b7f3820a50a42e51f9bd3e7014cf9b2688a8 (diff)
tcp: reset reordering est. selectively on timeout
On timeout the TCP sender unconditionally resets the estimated degree of network reordering (tp->reordering). The idea behind this is that the estimate is too large to trigger fast recovery (e.g., due to a IP path change). But for example if the sender only had 2 packets outstanding, then a timeout doesn't tell much about reordering. A sender that learns about reordering on big writes and loses packets on small writes will end up falsely retransmitting again and again, especially when reordering is more likely on big writes. Therefore the sender should only suspect that tp->reordering is too high if it could have gone into fast recovery with the (lower) default estimate. Signed-off-by: Yuchung Cheng <ycheng@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/ipv4/tcp_input.c')
-rw-r--r--net/ipv4/tcp_input.c9
1 files changed, 7 insertions, 2 deletions
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index b61274b666f6..e965cc7b87ff 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1877,8 +1877,13 @@ void tcp_enter_loss(struct sock *sk, int how)
}
tcp_verify_left_out(tp);
- tp->reordering = min_t(unsigned int, tp->reordering,
- sysctl_tcp_reordering);
+ /* Timeout in disordered state after receiving substantial DUPACKs
+ * suggests that the degree of reordering is over-estimated.
+ */
+ if (icsk->icsk_ca_state <= TCP_CA_Disorder &&
+ tp->sacked_out >= sysctl_tcp_reordering)
+ tp->reordering = min_t(unsigned int, tp->reordering,
+ sysctl_tcp_reordering);
tcp_set_ca_state(sk, TCP_CA_Loss);
tp->high_seq = tp->snd_nxt;
TCP_ECN_queue_cwr(tp);