Commit 1a991488 authored Aug 09, 2019 by Eric Dumazet Committed by David S. Miller Aug 09, 2019

tcp: batch calls to sk_flush_backlog()



Starting from commit d41a69f1 ("tcp: make tcp_sendmsg() aware of socket backlog")
loopback flows got hurt, because for each skb sent, the socket receives an
immediate ACK and sk_flush_backlog() causes extra work.

Intent was to not let the backlog grow too much, but we went a bit too far.

We can check the backlog every 16 skbs (about 1MB chunks)
to increase TCP over loopback performance by about 15 %

Note that the call to sk_flush_backlog() handles a single ACK,
thanks to coalescing done on backlog, but cleans the 16 skbs
found in rtx rb-tree.

Reported-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

parent fcc32a21

net/ipv4/tcp.c

+6 −5

Original line number	Diff line number	Diff line
		@@ -1162,7 +1162,7 @@ int tcp_sendmsg_locked(struct sock sk, struct msghdr msg, size_t size)
		struct sockcm_cookie sockc;
		int flags, err, copied = 0;
		int mss_now = 0, size_goal, copied_syn = 0;
		bool process_backlog = false;
		int process_backlog = 0;
		bool zc = false;
		long timeo;

		@@ -1254,8 +1254,9 @@ new_segment:
		if (!sk_stream_memory_free(sk))
		goto wait_for_sndbuf;

		if (process_backlog && sk_flush_backlog(sk)) {
		process_backlog = false;
		if (unlikely(process_backlog >= 16)) {
		process_backlog = 0;
		if (sk_flush_backlog(sk))
		goto restart;
		}
		first_skb = tcp_rtx_and_write_queues_empty(sk);
		@@ -1264,7 +1265,7 @@ new_segment:
		if (!skb)
		goto wait_for_memory;

		process_backlog = true;
		process_backlog++;
		skb->ip_summed = CHECKSUM_PARTIAL;

		skb_entail(sk, skb);

Admin message