From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner+w=401wt.eu-S1753396AbXDUQ7i@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
	id S1753396AbXDUQ7i (ORCPT <rfc822;w@1wt.eu>);
	Sat, 21 Apr 2007 12:59:38 -0400
Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753400AbXDUQ7i
	(ORCPT <rfc822;linux-kernel-outgoing>);
	Sat, 21 Apr 2007 12:59:38 -0400
Received: from 1wt.eu ([62.212.114.60]:2137 "EHLO 1wt.eu"
	rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S1753396AbXDUQ7h (ORCPT <rfc822;linux-kernel@vger.kernel.org>);
	Sat, 21 Apr 2007 12:59:37 -0400
Date: Sat, 21 Apr 2007 18:57:02 +0200
From: Willy Tarreau <w@1wt.eu>
To: Ingo Molnar <mingo@elte.hu>
Cc: Linus Torvalds <torvalds@linux-foundation.org>,
       Con Kolivas <kernel@kolivas.org>, linux-kernel@vger.kernel.org,
       Andrew Morton <akpm@linux-foundation.org>,
       Nick Piggin <npiggin@suse.de>, Mike Galbraith <efault@gmx.de>,
       Arjan van de Ven <arjan@infradead.org>,
       Peter Williams <pwil3058@bigpond.net.au>,
       Thomas Gleixner <tglx@linutronix.de>, caglar@pardus.org.tr,
       Gene Heskett <gene.heskett@gmail.com>
Subject: Re: [REPORT] cfs-v4 vs sd-0.44
Message-ID: <20070421165702.GE7840@1wt.eu>
References: <20070420140457.GA14017@elte.hu> <20070421121235.GA2044@1wt.eu> <20070421154614.GA26169@elte.hu> <20070421161818.GC7840@1wt.eu> <alpine.LFD.0.98.0704210931370.9964@woody.linux-foundation.org> <20070421165347.GA26903@elte.hu>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20070421165347.GA26903@elte.hu>
User-Agent: Mutt/1.5.11
Sender: linux-kernel-owner@vger.kernel.org
X-Mailing-List: linux-kernel@vger.kernel.org

On Sat, Apr 21, 2007 at 06:53:47PM +0200, Ingo Molnar wrote:
> 
> * Linus Torvalds <torvalds@linux-foundation.org> wrote:
> 
> > It would be even better to simply have the rule:
> >  - child gets almost no points at startup
> >  - but when a parent does a "waitpid()" call and blocks, it will spread 
> >    out its points to the childred (the "vfork()" blocking is another case 
> >    that is really the same).
> > 
> > This is a very special kind of "priority inversion" logic: you give 
> > higher priority to the things you wait for. Not because of holding any 
> > locks, but simply because a blockign waitpid really is a damn big hint 
> > that "ok, the child now works for the parent".
> 
> yeah. One problem i can see with the implementation of this though is 
> that shells typically do nonspecific waits - for example bash does this 
> on a simple 'ls' command:
> 
>   21310 clone(child_stack=0,  ...) = 21399
>   ...
>   21399 execve("/bin/ls", 
>   ...
>   21310 waitpid(-1, <unfinished ...>
> 
> the PID is -1 so we dont actually know which task we are waiting for. We 
> could use the first entry from the p->children list, but that looks too 
> specific of a hack to me. It should catch most of the 
> synchronous-helper-task cases though.

The last one should be more appropriate IMHO. If you waitpid(), it's very
likely that you're waiting for the result of the very last fork().

Willy