tcp: improve latencies of timer triggered events
Modern TCP stack highly depends on tcp_write_timer() having a small
latency, but current implementation doesn't exactly meet the
expectations.
When a timer fires but finds the socket is owned by the user, it rearms
itself for an additional delay hoping next run will be more
successful.
tcp_write_timer() for example uses a 50ms delay for next try, and it
defeats many attempts to get predictable TCP behavior in term of
latencies.
Use the recently introduced tcp_release_cb(), so that the user owning
the socket will call various handlers right before socket release.
This will permit us to post a followup patch to address the
tcp_tso_should_defer() syndrome (some deferred packets have to wait
RTO timer to be transmitted, while cwnd should allow us to send them
sooner)
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Tom Herbert <therbert@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Nandita Dukkipati <nanditad@google.com>
Cc: H.K. Jerry Chu <hkchu@google.com>
Cc: John Heffner <johnwheffner@gmail.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 27a32ac..950aebf 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -837,6 +837,13 @@
};
static DEFINE_PER_CPU(struct tsq_tasklet, tsq_tasklet);
+static void tcp_tsq_handler(struct sock *sk)
+{
+ if ((1 << sk->sk_state) &
+ (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_CLOSING |
+ TCPF_CLOSE_WAIT | TCPF_LAST_ACK))
+ tcp_write_xmit(sk, tcp_current_mss(sk), 0, 0, GFP_ATOMIC);
+}
/*
* One tasklest per cpu tries to send more skbs.
* We run in tasklet context but need to disable irqs when
@@ -864,16 +871,10 @@
bh_lock_sock(sk);
if (!sock_owned_by_user(sk)) {
- if ((1 << sk->sk_state) &
- (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 |
- TCPF_CLOSING | TCPF_CLOSE_WAIT | TCPF_LAST_ACK))
- tcp_write_xmit(sk,
- tcp_current_mss(sk),
- 0, 0,
- GFP_ATOMIC);
+ tcp_tsq_handler(sk);
} else {
/* defer the work to tcp_release_cb() */
- set_bit(TSQ_OWNED, &tp->tsq_flags);
+ set_bit(TCP_TSQ_DEFERRED, &tp->tsq_flags);
}
bh_unlock_sock(sk);
@@ -882,6 +883,9 @@
}
}
+#define TCP_DEFERRED_ALL ((1UL << TCP_TSQ_DEFERRED) | \
+ (1UL << TCP_WRITE_TIMER_DEFERRED) | \
+ (1UL << TCP_DELACK_TIMER_DEFERRED))
/**
* tcp_release_cb - tcp release_sock() callback
* @sk: socket
@@ -892,16 +896,24 @@
void tcp_release_cb(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
+ unsigned long flags, nflags;
- if (test_and_clear_bit(TSQ_OWNED, &tp->tsq_flags)) {
- if ((1 << sk->sk_state) &
- (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 |
- TCPF_CLOSING | TCPF_CLOSE_WAIT | TCPF_LAST_ACK))
- tcp_write_xmit(sk,
- tcp_current_mss(sk),
- 0, 0,
- GFP_ATOMIC);
- }
+ /* perform an atomic operation only if at least one flag is set */
+ do {
+ flags = tp->tsq_flags;
+ if (!(flags & TCP_DEFERRED_ALL))
+ return;
+ nflags = flags & ~TCP_DEFERRED_ALL;
+ } while (cmpxchg(&tp->tsq_flags, flags, nflags) != flags);
+
+ if (flags & (1UL << TCP_TSQ_DEFERRED))
+ tcp_tsq_handler(sk);
+
+ if (flags & (1UL << TCP_WRITE_TIMER_DEFERRED))
+ tcp_write_timer_handler(sk);
+
+ if (flags & (1UL << TCP_DELACK_TIMER_DEFERRED))
+ tcp_delack_timer_handler(sk);
}
EXPORT_SYMBOL(tcp_release_cb);