From f5ff7f311055a967350fa376601f8e20440bbcf4 Mon Sep 17 00:00:00 2001 From: Willy Tarreau Date: Tue, 13 Jan 2009 16:04:36 -0800 Subject: tcp: splice as many packets as possible at once [ Upstream commit 33966dd0e2f68f26943cd9ee93ec6abbc6547a8e ] As spotted by Willy Tarreau, current splice() from tcp socket to pipe is not optimal. It processes at most one segment per call. This results in low performance and very high overhead due to syscall rate when splicing from interfaces which do not support LRO. Willy provided a patch inside tcp_splice_read(), but a better fix is to let tcp_read_sock() process as many segments as possible, so that tcp_rcv_space_adjust() and tcp_cleanup_rbuf() are called less often. With this change, splice() behaves like tcp_recvmsg(), being able to consume many skbs in one system call. With typical 1460 bytes of payload per frame, that means splice(SPLICE_F_NONBLOCK) can return 16*1460 = 23360 bytes. Signed-off-by: Willy Tarreau Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/tcp.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index f57d57681348..8a69163451d9 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -518,8 +518,12 @@ static int tcp_splice_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, unsigned int offset, size_t len) { struct tcp_splice_state *tss = rd_desc->arg.data; + int ret; - return skb_splice_bits(skb, offset, tss->pipe, tss->len, tss->flags); + ret = skb_splice_bits(skb, offset, tss->pipe, rd_desc->count, tss->flags); + if (ret > 0) + rd_desc->count -= ret; + return ret; } static int __tcp_splice_read(struct sock *sk, struct tcp_splice_state *tss) @@ -527,6 +531,7 @@ static int __tcp_splice_read(struct sock *sk, struct tcp_splice_state *tss) /* Store TCP splice context information in read_descriptor_t. */ read_descriptor_t rd_desc = { .arg.data = tss, + .count = tss->len, }; return tcp_read_sock(sk, &rd_desc, tcp_splice_data_recv); @@ -611,11 +616,13 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos, tss.len -= ret; spliced += ret; + if (!timeo) + break; release_sock(sk); lock_sock(sk); if (sk->sk_err || sk->sk_state == TCP_CLOSE || - (sk->sk_shutdown & RCV_SHUTDOWN) || !timeo || + (sk->sk_shutdown & RCV_SHUTDOWN) || signal_pending(current)) break; } -- cgit v1.2.3