Always allow the two first skbs in write queue to be sent,
regardless of sk_wmem_alloc/sk_pacing_rate values.
This helps a lot in situations where TX completions are delayed either
because of driver latencies or softirq latencies.
Test is done with no cache line misses.
Signed-off-by: Eric Dumazet <eduma...@google.com>
---
net/ipv4/tcp_output.c | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 0db63efe5b8b..d5c46749adab 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2091,6 +2091,15 @@ static bool tcp_small_queue_check(struct sock *sk, const
struct sk_buff *skb,
limit <<= factor;
if (atomic_read(&sk->sk_wmem_alloc) > limit) {
+ /* Always send the 1st or 2nd skb in write queue.
+ * No need to wait for TX completion to call us back,
+ * after softirq/tasklet schedule.
+ * This helps when TX completions are delayed too much.
+ */
+ if (skb == sk->sk_write_queue.next ||
+ skb->prev == sk->sk_write_queue.next)
+ return false;
+
set_bit(TSQ_THROTTLED, &tcp_sk(sk)->tsq_flags);
/* It is possible TX completion already happened
* before we set TSQ_THROTTLED, so we must
--
2.8.0.rc3.226.g39d4020
