tcp: instrument how long TCP is busy sending

This patch measures TCP busy time, which is defined as the period
of time when sender has data (or FIN) to send. The time starts when
data is buffered and stops when the write queue is flushed by ACKs
or error events.

Note the busy time does not include SYN time, unless data is
included in SYN (i.e. Fast Open). It does include FIN time even
if the FIN carries no payload. Excluding pure FIN is possible but
would incur one additional test in the fast path, which may not
be worth it.

Signed-off-by: Francis Yan <francisyyan@gmail.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 24 insertions, 4 deletions

diff --git a/include/net/tcp.h b/include/net/tcp.h
index e5ff4083870d..3e097e39d4d2 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1535,6 +1535,7 @@ static inline void tcp_write_queue_purge(struct sock *sk)
 {
 	struct sk_buff *skb;
 
+	tcp_chrono_stop(sk, TCP_CHRONO_BUSY);
 	while ((skb = __skb_dequeue(&sk->sk_write_queue)) != NULL)
 		sk_wmem_free_skb(sk, skb);
 	sk_mem_reclaim(sk);
@@ -1593,8 +1594,10 @@ static inline void tcp_advance_send_head(struct sock *sk, const struct sk_buff *
 
 static inline void tcp_check_send_head(struct sock *sk, struct sk_buff *skb_unlinked)
 {
-	if (sk->sk_send_head == skb_unlinked)
+	if (sk->sk_send_head == skb_unlinked) {
 		sk->sk_send_head = NULL;
+		tcp_chrono_stop(sk, TCP_CHRONO_BUSY);
+	}
 	if (tcp_sk(sk)->highest_sack == skb_unlinked)
 		tcp_sk(sk)->highest_sack = NULL;
 }
@@ -1616,6 +1619,7 @@ static inline void tcp_add_write_queue_tail(struct sock *sk, struct sk_buff *skb
 	/* Queue it, remembering where we must start sending. */
 	if (sk->sk_send_head == NULL) {
 		sk->sk_send_head = skb;
+		tcp_chrono_start(sk, TCP_CHRONO_BUSY);
 
 		if (tcp_sk(sk)->highest_sack == NULL)
 			tcp_sk(sk)->highest_sack = skb;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 22e6a2097ff6..a5d172761610 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3178,6 +3178,9 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 			tp->lost_skb_hint = NULL;
 	}
 
+	if (!skb)
+		tcp_chrono_stop(sk, TCP_CHRONO_BUSY);
+
 	if (likely(between(tp->snd_up, prior_snd_una, tp->snd_una)))
 		tp->snd_up = tp->snd_una;
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 34f751776a01..e8ea584106e0 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2096,8 +2096,8 @@ void tcp_chrono_start(struct sock *sk, const enum tcp_chrono type)
 	struct tcp_sock *tp = tcp_sk(sk);
 
 	/* If there are multiple conditions worthy of tracking in a
-	 * chronograph then the highest priority enum takes precedence over
-	 * the other conditions. So that if something "more interesting"
+	 * chronograph then the highest priority enum takes precedence
+	 * over the other conditions. So that if something "more interesting"
 	 * starts happening, stop the previous chrono and start a new one.
 	 */
 	if (type > tp->chrono_type)
@@ -2108,7 +2108,18 @@ void tcp_chrono_stop(struct sock *sk, const enum tcp_chrono type)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	tcp_chrono_set(tp, TCP_CHRONO_UNSPEC);
+
+	/* There are multiple conditions worthy of tracking in a
+	 * chronograph, so that the highest priority enum takes
+	 * precedence over the other conditions (see tcp_chrono_start).
+	 * If a condition stops, we only stop chrono tracking if
+	 * it's the "most interesting" or current chrono we are
+	 * tracking and starts busy chrono if we have pending data.
+	 */
+	if (tcp_write_queue_empty(sk))
+		tcp_chrono_set(tp, TCP_CHRONO_UNSPEC);
+	else if (type == tp->chrono_type)
+		tcp_chrono_set(tp, TCP_CHRONO_BUSY);
 }
 
 /* This routine writes packets to the network.  It advances the
@@ -3328,6 +3339,8 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 	fo->copied = space;
 
 	tcp_connect_queue_skb(sk, syn_data);
+	if (syn_data->len)
+		tcp_chrono_start(sk, TCP_CHRONO_BUSY);
 
 	err = tcp_transmit_skb(sk, syn_data, 1, sk->sk_allocation);