diff options
| author | Eric Dumazet <[email protected]> | 2011-09-22 20:02:19 +0000 |
|---|---|---|
| committer | David S. Miller <[email protected]> | 2011-09-27 04:58:44 +0000 |
| commit | 7a269ffad72f3604b8982fa09c387670e0d2ee14 (patch) | |
| tree | 3655a22066bcb1011e5e1b717a00a108143dfd85 /net/ipv4/tcp_output.c | |
| parent | sky2: manage irq better on single port card (diff) | |
| download | kernel-7a269ffad72f3604b8982fa09c387670e0d2ee14.tar.gz kernel-7a269ffad72f3604b8982fa09c387670e0d2ee14.zip | |
tcp: ECN blackhole should not force quickack mode
While playing with a new ADSL box at home, I discovered that ECN
blackhole can trigger suboptimal quickack mode on linux : We send one
ACK for each incoming data frame, without any delay and eventual
piggyback.
This is because TCP_ECN_check_ce() considers that if no ECT is seen on a
segment, this is because this segment was a retransmit.
Refine this heuristic and apply it only if we seen ECT in a previous
segment, to detect ECN blackhole at IP level.
Signed-off-by: Eric Dumazet <[email protected]>
CC: Jamal Hadi Salim <[email protected]>
CC: Jerry Chu <[email protected]>
CC: Ilpo Järvinen <[email protected]>
CC: Jim Gettys <[email protected]>
CC: Dave Taht <[email protected]>
Acked-by: Ilpo Järvinen <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
Diffstat (limited to 'net/ipv4/tcp_output.c')
0 files changed, 0 insertions, 0 deletions