On Tue, 2017-01-03 at 10:22 -0500, Soheil Hassas Yeganeh wrote:
> On Mon, Jan 2, 2017 at 3:23 PM, Soheil Hassas Yeganeh <soh...@google.com>
> wrote:
> > On Mon, Jan 2, 2017 at 3:20 PM, Soheil Hassas Yeganeh
> > <soheil.k...@gmail.com> wrote:
> >> From: Soheil Hassas Yeganeh <soh...@google.com>
> >>
> >> For TCP sockets, tx timestamps are only captured when the user data
> >> is successfully and fully written to the socket. In many cases,
> >> however, TCP writes can be partial for which no timestamp is
> >> collected.
> >>
> >> Collect timestamps when the user data is partially copied into
> >> the socket.
> >>
> >> Signed-off-by: Soheil Hassas Yeganeh <soh...@google.com>
> >> Cc: Willem de Bruijn <will...@google.com>
> >> Cc: Yuchung Cheng <ych...@google.com>
> >> Cc: Eric Dumazet <eduma...@google.com>
> >> Cc: Neal Cardwell <ncardw...@google.com>
> >> Cc: Martin KaFai Lau <ka...@fb.com>
> >> ---
> >> net/ipv4/tcp.c | 8 ++++++--
> >> 1 file changed, 6 insertions(+), 2 deletions(-)
> >>
> >> diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
> >> index 2e3807d..c207b16 100644
> >> --- a/net/ipv4/tcp.c
> >> +++ b/net/ipv4/tcp.c
> >> @@ -992,8 +992,10 @@ static ssize_t do_tcp_sendpages(struct sock *sk,
> >> struct page *page, int offset,
> >> return copied;
> >>
> >> do_error:
> >> - if (copied)
> >> + if (copied) {
> >> + tcp_tx_timestamp(sk, sk->sk_tsflags,
> >> tcp_write_queue_tail(sk));
> >> goto out;
> >> + }
> >> out_err:
> >> /* make sure we wake any epoll edge trigger waiter */
> >> if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 &&
> >> @@ -1329,8 +1331,10 @@ int tcp_sendmsg(struct sock *sk, struct msghdr
> >> *msg, size_t size)
> >> }
> >>
> >> do_error:
> >> - if (copied + copied_syn)
> >> + if (copied + copied_syn) {
> >> + tcp_tx_timestamp(sk, sk->sk_tsflags,
> >> tcp_write_queue_tail(sk));
>
> Thanks to Willem for noting that this should be sockc.tsflags and not
> sk->sk_tsflags. I'll send V2 to fix.
Also, why not factorizing a bit and have a single point calling
tcp_tx_timestamp() ?
This would ease code review quite a bit.
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index
4a044964da6670829e5c47fef52d2cd76360b59f..11357f3bd1f82fa29129dd3ecf4d270feb4a6b1d
100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -958,10 +958,8 @@ static ssize_t do_tcp_sendpages(struct sock *sk, struct
page *page, int offset,
copied += copy;
offset += copy;
size -= copy;
- if (!size) {
- tcp_tx_timestamp(sk, sk->sk_tsflags, skb);
+ if (!size)
goto out;
- }
if (skb->len < size_goal || (flags & MSG_OOB))
continue;
@@ -987,8 +985,11 @@ static ssize_t do_tcp_sendpages(struct sock *sk, struct
page *page, int offset,
}
out:
- if (copied && !(flags & MSG_SENDPAGE_NOTLAST))
- tcp_push(sk, flags, mss_now, tp->nonagle, size_goal);
+ if (copied) {
+ tcp_tx_timestamp(sk, sk->sk_tsflags, tcp_write_queue_tail(sk));
+ if (!(flags & MSG_SENDPAGE_NOTLAST))
+ tcp_push(sk, flags, mss_now, tp->nonagle, size_goal);
+ }
return copied;
do_error:
@@ -1281,7 +1282,6 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg,
size_t size)
copied += copy;
if (!msg_data_left(msg)) {
- tcp_tx_timestamp(sk, sockc.tsflags, skb);
if (unlikely(flags & MSG_EOR))
TCP_SKB_CB(skb)->eor = 1;
goto out;
@@ -1312,8 +1312,10 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg,
size_t size)
}
out:
- if (copied)
+ if (copied) {
+ tcp_tx_timestamp(sk, sockc.tsflags, tcp_write_queue_tail(sk));
tcp_push(sk, flags, mss_now, tp->nonagle, size_goal);
+ }
out_nopush:
release_sock(sk);
return copied + copied_syn;
