From mboxrd@z Thu Jan  1 00:00:00 1970
From: Willy Tarreau <w@1wt.eu>
Subject: Re: Major network performance regression in 3.7
Date: Sun, 6 Jan 2013 22:52:00 +0100
Message-ID: <20130106215200.GV16031@1wt.eu>
References: <1357490393.6919.267.camel@edumazet-glaptop> <20130106164416.GF16031@1wt.eu> <1357492255.6919.336.camel@edumazet-glaptop> <20130106173543.GB22432@1wt.eu> <1357497541.6919.519.camel@edumazet-glaptop> <1357497809.6919.529.camel@edumazet-glaptop> <1357498276.6919.547.camel@edumazet-glaptop> <1357498815.6919.570.camel@edumazet-glaptop> <20130106193410.GL16031@1wt.eu> <20713.61807.385486.594545@quad.stoffel.home>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Cc: Eric Dumazet <eric.dumazet@gmail.com>, netdev@vger.kernel.org,
	linux-kernel@vger.kernel.org
To: John Stoffel <john@stoffel.org>
Return-path: <netdev-owner@vger.kernel.org>
Received: from 1wt.eu ([62.212.114.60]:37753 "EHLO 1wt.eu"
	rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S1753018Ab3AFVwT (ORCPT <rfc822;netdev@vger.kernel.org>);
	Sun, 6 Jan 2013 16:52:19 -0500
Content-Disposition: inline
In-Reply-To: <20713.61807.385486.594545@quad.stoffel.home>
Sender: netdev-owner@vger.kernel.org
List-ID: <netdev.vger.kernel.org>

On Sun, Jan 06, 2013 at 04:49:35PM -0500, John Stoffel wrote:
> >>>>> "Willy" == Willy Tarreau <w@1wt.eu> writes:
> 
> Willy> On Sun, Jan 06, 2013 at 11:00:15AM -0800, Eric Dumazet wrote:
> >> On Sun, 2013-01-06 at 10:51 -0800, Eric Dumazet wrote:
> >> > > 
> >> > > (sd->len is usually 4096, which is expected, but sd->total_len value is
> >> > > huge in your case, so we always set the flag in fs/splice.c)
> >> > 
> >> > I am testing :
> >> > 
> >> >        if (sd->len < sd->total_len && pipe->nrbufs > 1)
> >> >                 more |= MSG_SENDPAGE_NOTLAST;
> >> > 
> >> 
> >> Yes, this should fix the problem :
> >> 
> >> If there is no following buffer in the pipe, we should not set NOTLAST.
> >> 
> >> diff --git a/fs/splice.c b/fs/splice.c
> >> index 8890604..6909d89 100644
> >> --- a/fs/splice.c
> >> +++ b/fs/splice.c
> >> @@ -696,8 +696,10 @@ static int pipe_to_sendpage(struct pipe_inode_info *pipe,
> >> return -EINVAL;
> >> 
> >> more = (sd->flags & SPLICE_F_MORE) ? MSG_MORE : 0;
> >> -	if (sd->len < sd->total_len)
> >> +
> >> +	if (sd->len < sd->total_len && pipe->nrbufs > 1)
> >> more |= MSG_SENDPAGE_NOTLAST;
> >> +
> >> return file->f_op->sendpage(file, buf->page, buf->offset,
> sd-> len, &pos, more);
> >> }
>  
> Willy> OK it works like a charm here now ! I can't break it anymore, so it
> Willy> looks like you finally got it !
> 
> It's still broken, there's no comments in the code to explain all this
> magic to mere mortals!  *grin*

I would generally agree, but when Eric fixes such a thing, he
generally goes with lengthy details in the commit message.

Willy