tcp: fix cwnd limited checking to improve congestion control
Yuchung discovered tcp_is_cwnd_limited() was returning false in
slow start phase even if the application filled the socket write queue.
All congestion modules take into account tcp_is_cwnd_limited()
before increasing cwnd, so this behavior limits slow start from
probing the bandwidth at full speed.
The problem is that even if write queue is full (aka we are _not_
application limited), cwnd can be under utilized if TSO should auto
defer or TCP Small queues decided to hold packets.
So the in_flight can be kept to smaller value, and we can get to the
point tcp_is_cwnd_limited() returns false.
With TCP Small Queues and FQ/pacing, this issue is more visible.
We fix this by having tcp_cwnd_validate(), which is supposed to track
such things, take into account unsent_segs, the number of segs that we
are not sending at the moment due to TSO or TSQ, but intend to send
real soon. Then when we are cwnd-limited, remember this fact while we
are processing the window of ACKs that comes back.
For example, suppose we have a brand new connection with cwnd=10; we
are in slow start, and we send a flight of 9 packets. By the time we
have received ACKs for all 9 packets we want our cwnd to be 18.
We implement this by setting tp->lsnd_pending to 9, and
considering ourselves to be cwnd-limited while cwnd is less than
twice tp->lsnd_pending (2*9 -> 18).
This makes tcp_is_cwnd_limited() more understandable, by removing
the GSO/TSO kludge, that tried to work around the issue.
Note the in_flight parameter can be removed in a followup cleanup
patch.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 20847de..f9181a1 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1402,12 +1402,13 @@
tp->snd_cwnd_stamp = tcp_time_stamp;
}
-/* Congestion window validation. (RFC2861) */
-static void tcp_cwnd_validate(struct sock *sk)
+static void tcp_cwnd_validate(struct sock *sk, u32 unsent_segs)
{
struct tcp_sock *tp = tcp_sk(sk);
- if (tp->packets_out >= tp->snd_cwnd) {
+ tp->lsnd_pending = tp->packets_out + unsent_segs;
+
+ if (tcp_is_cwnd_limited(sk, 0)) {
/* Network is feed fully. */
tp->snd_cwnd_used = 0;
tp->snd_cwnd_stamp = tcp_time_stamp;
@@ -1880,7 +1881,7 @@
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
- unsigned int tso_segs, sent_pkts;
+ unsigned int tso_segs, sent_pkts, unsent_segs = 0;
int cwnd_quota;
int result;
@@ -1924,7 +1925,7 @@
break;
} else {
if (!push_one && tcp_tso_should_defer(sk, skb))
- break;
+ goto compute_unsent_segs;
}
/* TCP Small Queues :
@@ -1949,8 +1950,14 @@
* there is no smp_mb__after_set_bit() yet
*/
smp_mb__after_clear_bit();
- if (atomic_read(&sk->sk_wmem_alloc) > limit)
+ if (atomic_read(&sk->sk_wmem_alloc) > limit) {
+ u32 unsent_bytes;
+
+compute_unsent_segs:
+ unsent_bytes = tp->write_seq - tp->snd_nxt;
+ unsent_segs = DIV_ROUND_UP(unsent_bytes, mss_now);
break;
+ }
}
limit = mss_now;
@@ -1990,7 +1997,7 @@
/* Send one loss probe per tail loss episode. */
if (push_one != 2)
tcp_schedule_loss_probe(sk);
- tcp_cwnd_validate(sk);
+ tcp_cwnd_validate(sk, unsent_segs);
return false;
}
return (push_one == 2) || (!tp->packets_out && tcp_send_head(sk));