Commit 02275a2e authored Dec 02, 2012 by Willy Tarreau Committed by David S. Miller Dec 02, 2012

tcp: don't abort splice() after small transfers



TCP coalescing added a regression in splice(socket->pipe) performance,
for some workloads because of the way tcp_read_sock() is implemented.

The reason for this is the break when (offset + 1 != skb->len).

As we released the socket lock, this condition is possible if TCP stack
added a fragment to the skb, which can happen with TCP coalescing.

So let's go back to the beginning of the loop when this happens,
to give a chance to splice more frags per system call.

Doing so fixes the issue and makes GRO 10% faster than LRO
on CPU-bound splice() workloads instead of the opposite.

Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

parent 077b393d

net/ipv4/tcp.c

+8 −4

Original line number	Diff line number	Diff line
		@@ -1494,15 +1494,19 @@ int tcp_read_sock(struct sock sk, read_descriptor_t desc,
		copied += used;
		offset += used;
		}
		/*
		* If recv_actor drops the lock (e.g. TCP splice
		/* If recv_actor drops the lock (e.g. TCP splice
		* receive) the skb pointer might be invalid when
		* getting here: tcp_collapse might have deleted it
		* while aggregating skbs from the socket queue.
		*/
		skb = tcp_recv_skb(sk, seq - 1, &offset);
		if (!skb \|\| (offset+1 != skb->len))
		if (!skb)
		break;
		/* TCP coalescing might have appended data to the skb.
		* Try to splice more frags
		*/
		if (offset + 1 != skb->len)
		continue;
		}
		if (tcp_hdr(skb)->fin) {
		sk_eat_skb(sk, skb, false);

Admin message