diff options
| author | David S. Miller | 2005-07-06 00:43:58 +0200 |
|---|---|---|
| committer | David S. Miller | 2005-07-06 00:43:58 +0200 |
| commit | 908a75c17a9e5a888347c2c1d3572203d1b1c7db (patch) | |
| tree | 9741bc479cedc00dec3eb123ed834527af7f3974 /net/ipv4 | |
| parent | [PKT_SCHED]: Blackhole queueing discipline (diff) | |
| download | kernel-qcow2-linux-908a75c17a9e5a888347c2c1d3572203d1b1c7db.tar.gz kernel-qcow2-linux-908a75c17a9e5a888347c2c1d3572203d1b1c7db.tar.xz kernel-qcow2-linux-908a75c17a9e5a888347c2c1d3572203d1b1c7db.zip | |
[TCP]: Never TSO defer under periods of congestion.
Congestion window recover after loss depends upon the fact
that if we have a full MSS sized frame at the head of the
send queue, we will send it. TSO deferral can defeat the
ACK clocking necessary to exit cleanly from recovery.
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/ipv4')
| -rw-r--r-- | net/ipv4/tcp_output.c | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index fd3ce38184ae..e041d057ec86 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -909,6 +909,9 @@ static int tcp_tso_should_defer(struct sock *sk, struct tcp_sock *tp, struct sk_ if (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN) return 0; + if (tp->ca_state != TCP_CA_Open) + return 0; + in_flight = tcp_packets_in_flight(tp); BUG_ON(tcp_skb_pcount(skb) <= 1 || |