Date: Mon, 23 Nov 2009 13:04:09 +0100
From: Ingo Molnar <mingo@elte.hu>
To: Alan Cox <alan@lxorguk.ukuu.org.uk>
Cc: Mike Galbraith <efault@gmx.de>, Robert Swan <swan.r.l@gmail.com>,
       Linus Torvalds <torvalds@linux-foundation.org>,
       linux-kernel@vger.kernel.org
Subject: Re: [bisected] pty performance problem
Message-ID: <20091123120409.GA32009@elte.hu>
References: <20091121222319.GA3905@swanrl.gmail.com>
 <20091122063926.GA18224@elte.hu>
 <20091122122312.71a343d9@lxorguk.ukuu.org.uk>
 <1258952431.6261.38.camel@marge.simson.net>
 <20091123113110.15063a0a@lxorguk.ukuu.org.uk>
 <20091123114845.GC25575@elte.hu>
 <20091123115949.29bcf89d@lxorguk.ukuu.org.uk>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20091123115949.29bcf89d@lxorguk.ukuu.org.uk>
User-Agent: Mutt/1.5.20 (2009-08-17)
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1003
Lines: 29


* Alan Cox <alan@lxorguk.ukuu.org.uk> wrote:

> > > Another possibility is to do
> > > 
> > > 	if (tty->low_latency)
> > > 		schedule_delayed_work(&tty->buf.work, 0);
> > > 	else
> > > 		schedule_delayed_work(&tty->buf.work, 1);
> > 
> > Flaggery for low latency is kind of lame though - especially if it 
> > defaults to off in most drivers as you say.
> 
> So you'd prefer to detect devices that are byte based or message based 
> by what method ?

I'd not delay the worklet by default - i.e. i'd do Mike's patch.

Havent tested all effects of it though - do you have any estimation 
about negative effects from such a change? We do have hard numbers 
(latencies in the millisecs range) from the opposite direction and those 
numbers arent pretty.

	Ingo
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/