diff options
| author | Neal Cardwell <ncardwell@google.com> | 2015-03-10 17:17:03 -0400 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2015-03-11 16:51:51 -0400 |
| commit | 9949afa42be0b76f5832db112ce51bb6b35b2abb (patch) | |
| tree | dded55a25200f202f9904369f39ccad9769da00d /net | |
| parent | 366c1bd191c49380d81b15b96cf7d4e3528a82a2 (diff) | |
| download | linux-9949afa42be0b76f5832db112ce51bb6b35b2abb.tar.gz | |
tcp: fix tcp_cong_avoid_ai() credit accumulation bug with decreases in w
The recent change to tcp_cong_avoid_ai() to handle stretch ACKs
introduced a bug where snd_cwnd_cnt could accumulate a very large
value while w was large, and then if w was reduced snd_cwnd could be
incremented by a large delta, leading to a large burst and high packet
loss. This was tickled when CUBIC's bictcp_update() sets "ca->cnt =
100 * cwnd".
This bug crept in while preparing the upstream version of
814d488c6126.
Testing: This patch has been tested in datacenter netperf transfers
and live youtube.com and google.com servers.
Fixes: 814d488c6126 ("tcp: fix the timid additive increase on stretch ACKs")
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
| -rw-r--r-- | net/ipv4/tcp_cong.c | 6 |
1 files changed, 6 insertions, 0 deletions
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index d694088214cd..62856e185a93 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -378,6 +378,12 @@ EXPORT_SYMBOL_GPL(tcp_slow_start); */ void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked) { + /* If credits accumulated at a higher w, apply them gently now. */ + if (tp->snd_cwnd_cnt >= w) { + tp->snd_cwnd_cnt = 0; + tp->snd_cwnd++; + } + tp->snd_cwnd_cnt += acked; if (tp->snd_cwnd_cnt >= w) { u32 delta = tp->snd_cwnd_cnt / w; |