Commit 9b5cbf46 authored by David S. Miller's avatar David S. Miller
Browse files

Merge branch 'tcp-exponential-backoff-in-tcp_send_ack' 



Eric Dumazet says:

====================
tcp: exponential backoff in tcp_send_ack()

We had outages caused by repeated skb allocation failures in tcp_send_ack()

It is time to add exponential backoff to reduce number of attempts.
Before doing so, first patch removes icsk_ack.blocked to make
room for a new field (icsk_ack.retry)
====================

Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parents 20c168be a37c2134

include/net/inet_connection_sock.h

+3 −2
Original line number Diff line number Diff line
@@ -110,7 +110,7 @@ struct inet_connection_sock { 
		__u8		  pending;	 /* ACK is pending			   */

		__u8		  quick;	 /* Scheduled number of quick acks	   */

		__u8		  pingpong;	 /* The session is interactive		   */

		__u8		  blocked;	 /* Delayed ACK was blocked by socket lock */

		__u8		  retry;	 /* Number of attempts			   */

		__u32		  ato;		 /* Predicted tick of soft clock	   */

		unsigned long	  timeout;	 /* Currently scheduled timeout		   */

		__u32		  lrcvtime;	 /* timestamp of last received data packet */
@@ -198,7 +198,8 @@ static inline void inet_csk_clear_xmit_timer(struct sock *sk, const int what) 
		sk_stop_timer(sk, &icsk->icsk_retransmit_timer);

#endif

	} else if (what == ICSK_TIME_DACK) {

		icsk->icsk_ack.blocked = icsk->icsk_ack.pending = 0;

		icsk->icsk_ack.pending = 0;

		icsk->icsk_ack.retry = 0;

#ifdef INET_CSK_CLEAR_TIMERS

		sk_stop_timer(sk, &icsk->icsk_delack_timer);

#endif

net/dccp/timer.c

+0 −1
Original line number Diff line number Diff line
@@ -176,7 +176,6 @@ static void dccp_delack_timer(struct timer_list *t) 
	bh_lock_sock(sk);

	if (sock_owned_by_user(sk)) {

		/* Try again later. */

		icsk->icsk_ack.blocked = 1;

		__NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED);

		sk_reset_timer(sk, &icsk->icsk_delack_timer,

			       jiffies + TCP_DELACK_MIN);

net/ipv4/inet_connection_sock.c

+1 −1
Original line number Diff line number Diff line
@@ -564,7 +564,7 @@ void inet_csk_clear_xmit_timers(struct sock *sk) 
{

	struct inet_connection_sock *icsk = inet_csk(sk);



	icsk->icsk_pending = icsk->icsk_ack.pending = icsk->icsk_ack.blocked = 0;

	icsk->icsk_pending = icsk->icsk_ack.pending = 0;



	sk_stop_timer(sk, &icsk->icsk_retransmit_timer);

	sk_stop_timer(sk, &icsk->icsk_delack_timer);

net/ipv4/tcp.c

+2 −4
Original line number Diff line number Diff line
@@ -1538,10 +1538,8 @@ void tcp_cleanup_rbuf(struct sock *sk, int copied) 


	if (inet_csk_ack_scheduled(sk)) {

		const struct inet_connection_sock *icsk = inet_csk(sk);

		   /* Delayed ACKs frequently hit locked sockets during bulk

		    * receive. */

		if (icsk->icsk_ack.blocked ||

		    /* Once-per-two-segments ACK was not sent by tcp_input.c */



		if (/* Once-per-two-segments ACK was not sent by tcp_input.c */

		    tp->rcv_nxt - tp->rcv_wup > icsk->icsk_ack.rcv_mss ||

		    /*

		     * If this read emptied read buffer, we send ACK, if

net/ipv4/tcp_output.c

+10 −8
Original line number Diff line number Diff line
@@ -3911,11 +3911,8 @@ void tcp_send_delayed_ack(struct sock *sk) 


	/* Use new timeout only if there wasn't a older one earlier. */

	if (icsk->icsk_ack.pending & ICSK_ACK_TIMER) {

		/* If delack timer was blocked or is about to expire,

		 * send ACK now.

		 */

		if (icsk->icsk_ack.blocked ||

		    time_before_eq(icsk->icsk_ack.timeout, jiffies + (ato >> 2))) {

		/* If delack timer is about to expire, send ACK now. */

		if (time_before_eq(icsk->icsk_ack.timeout, jiffies + (ato >> 2))) {

			tcp_send_ack(sk);

			return;

		}
@@ -3944,10 +3941,15 @@ void __tcp_send_ack(struct sock *sk, u32 rcv_nxt) 
	buff = alloc_skb(MAX_TCP_HEADER,

			 sk_gfp_mask(sk, GFP_ATOMIC | __GFP_NOWARN));

	if (unlikely(!buff)) {

		struct inet_connection_sock *icsk = inet_csk(sk);

		unsigned long delay;



		delay = TCP_DELACK_MAX << icsk->icsk_ack.retry;

		if (delay < TCP_RTO_MAX)

			icsk->icsk_ack.retry++;

		inet_csk_schedule_ack(sk);

		inet_csk(sk)->icsk_ack.ato = TCP_ATO_MIN;

		inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,

					  TCP_DELACK_MAX, TCP_RTO_MAX);

		icsk->icsk_ack.ato = TCP_ATO_MIN;

		inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, delay, TCP_RTO_MAX);

		return;

	}