Commit 562b1fdf authored by Haiyang Zhang's avatar Haiyang Zhang Committed by Jakub Kicinski
Browse files

tcp: Set pingpong threshold via sysctl 



TCP pingpong threshold is 1 by default. But some applications, like SQL DB
may prefer a higher pingpong threshold to activate delayed acks in quick
ack mode for better performance.

The pingpong threshold and related code were changed to 3 in the year
2019 in:
  commit 4a41f453 ("tcp: change pingpong threshold to 3")
And reverted to 1 in the year 2022 in:
  commit 4d8f24ee ("Revert "tcp: change pingpong threshold to 3"")

There is no single value that fits all applications.
Add net.ipv4.tcp_pingpong_thresh sysctl tunable, so it can be tuned for
optimal performance based on the application needs.

Signed-off-by: default avatarHaiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: default avatarSimon Horman <horms@kernel.org>
Reviewed-by: default avatarEric Dumazet <edumazet@google.com>
Acked-by: default avatarNeal Cardwell <ncardwell@google.com>
Reviewed-by: default avatarKuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/1697056244-21888-1-git-send-email-haiyangz@microsoft.com


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parent 39d08b91

Documentation/networking/ip-sysctl.rst

+13 −0
Original line number Diff line number Diff line
@@ -1183,6 +1183,19 @@ tcp_plb_cong_thresh - INTEGER 


	Default: 128



tcp_pingpong_thresh - INTEGER

	The number of estimated data replies sent for estimated incoming data

	requests that must happen before TCP considers that a connection is a

	"ping-pong" (request-response) connection for which delayed

	acknowledgments can provide benefits.



	This threshold is 1 by default, but some applications may need a higher

	threshold for optimal performance.



	Possible Values: 1 - 255



	Default: 1



UDP variables

=============

include/net/inet_connection_sock.h

+12 −4
Original line number Diff line number Diff line
@@ -328,11 +328,10 @@ void inet_csk_update_fastreuse(struct inet_bind_bucket *tb, 


struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu);



#define TCP_PINGPONG_THRESH	1



static inline void inet_csk_enter_pingpong_mode(struct sock *sk)

{

	inet_csk(sk)->icsk_ack.pingpong = TCP_PINGPONG_THRESH;

	inet_csk(sk)->icsk_ack.pingpong =

		READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_pingpong_thresh);

}



static inline void inet_csk_exit_pingpong_mode(struct sock *sk)
@@ -342,7 +341,16 @@ static inline void inet_csk_exit_pingpong_mode(struct sock *sk) 


static inline bool inet_csk_in_pingpong_mode(struct sock *sk)

{

	return inet_csk(sk)->icsk_ack.pingpong >= TCP_PINGPONG_THRESH;

	return inet_csk(sk)->icsk_ack.pingpong >=

	       READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_pingpong_thresh);

}



static inline void inet_csk_inc_pingpong_cnt(struct sock *sk)

{

	struct inet_connection_sock *icsk = inet_csk(sk);



	if (icsk->icsk_ack.pingpong < U8_MAX)

		icsk->icsk_ack.pingpong++;

}



static inline bool inet_csk_has_ulp(const struct sock *sk)

include/net/netns/ipv4.h

+2 −0
Original line number Diff line number Diff line
@@ -133,6 +133,8 @@ struct netns_ipv4 { 
	u8 sysctl_tcp_migrate_req;

	u8 sysctl_tcp_comp_sack_nr;

	u8 sysctl_tcp_backlog_ack_defer;

	u8 sysctl_tcp_pingpong_thresh;



	int sysctl_tcp_reordering;

	u8 sysctl_tcp_retries1;

	u8 sysctl_tcp_retries2;

net/ipv4/sysctl_net_ipv4.c

+8 −0
Original line number Diff line number Diff line
@@ -1498,6 +1498,14 @@ static struct ctl_table ipv4_net_table[] = { 
		.extra1		= SYSCTL_ZERO,

		.extra2		= SYSCTL_ONE,

	},

	{

		.procname	= "tcp_pingpong_thresh",

		.data		= &init_net.ipv4.sysctl_tcp_pingpong_thresh,

		.maxlen		= sizeof(u8),

		.mode		= 0644,

		.proc_handler	= proc_dou8vec_minmax,

		.extra1		= SYSCTL_ONE,

	},

	{ }

};

net/ipv4/tcp_ipv4.c

+2 −0
Original line number Diff line number Diff line
@@ -3288,6 +3288,8 @@ static int __net_init tcp_sk_init(struct net *net) 
	net->ipv4.sysctl_tcp_syn_linear_timeouts = 4;

	net->ipv4.sysctl_tcp_shrink_window = 0;



	net->ipv4.sysctl_tcp_pingpong_thresh = 1;



	return 0;

}