From mboxrd@z Thu Jan  1 00:00:00 1970
From: Eric Dumazet <eric.dumazet@gmail.com>
Subject: Re: Stable regression with 'tcp: allow splice() to build full TSO
 packets'
Date: Thu, 17 May 2012 23:50:10 +0200
Message-ID: <1337291410.3403.52.camel@edumazet-glaptop>
References: <20120517121800.GA18052@1wt.eu>
	 <1337287279.3403.44.camel@edumazet-glaptop> <20120517211414.GP14498@1wt.eu>
	 <1337290822.3403.47.camel@edumazet-glaptop>
Mime-Version: 1.0
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: 7bit
Cc: netdev@vger.kernel.org
To: Willy Tarreau <w@1wt.eu>
Return-path: <netdev-owner@vger.kernel.org>
Received: from mail-wi0-f178.google.com ([209.85.212.178]:48950 "EHLO
	mail-wi0-f178.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with ESMTP id S1761163Ab2EQVuO (ORCPT
	<rfc822;netdev@vger.kernel.org>); Thu, 17 May 2012 17:50:14 -0400
Received: by wibhn6 with SMTP id hn6so2273152wib.1
        for <netdev@vger.kernel.org>; Thu, 17 May 2012 14:50:13 -0700 (PDT)
In-Reply-To: <1337290822.3403.47.camel@edumazet-glaptop>
Sender: netdev-owner@vger.kernel.org
List-ID: <netdev.vger.kernel.org>

On Thu, 2012-05-17 at 23:40 +0200, Eric Dumazet wrote:

> I dont understand why we should tcp_push() if we sent 0 bytes in this
> splice() call.
> 
> The push() should have be done already by prior splice() call, dont you
> think ?
> 
> out:
> 	if (copied && !(flags & MSG_SENDPAGE_NOTLAST))
> 		tcp_push(sk, flags, mss_now, tp->nonagle);
> 

I think I now understand

One splice() syscall actually calls do_tcp_sendpages() several times
(N).

Problem is N-1 calls are done with MSG_SENDPAGE_NOTLAST set

And last one with MSG_SENDPAGE_NOTLAST unset

So maybe we should replace this test by :

	if (!(flags & MSG_SENDPAGE_NOTLAST))
		tcp_push(...);