X-Recipient: archive-cygwin AT delorie DOT com
X-SWARE-Spam-Status: No, hits=-1.6 required=5.0	tests=AWL,BAYES_00,RCVD_IN_DNSWL_NONE,UNPARSEABLE_RELAY
X-Spam-Check-By: sourceware.org
X-Yahoo-SMTP: jenXL62swBAWhMTL3wnej93oaS0ClBQOAKs8jbEbx_o-
Date: Sat, 30 Jul 2011 17:09:08 -0400
From: Christopher Faylor <cgf-use-the-mailinglist-please AT cygwin DOT com>
To: cygwin AT cygwin DOT com
Subject: Re: Slow performance Win7/64
Message-ID: <20110730210908.GA31747@ednor.casa.cgf.cx>
Reply-To: cygwin AT cygwin DOT com
Mail-Followup-To: cygwin AT cygwin DOT com
References: <loom DOT 20110727T120025-601 AT post DOT gmane DOT org> <j0tc8u$slo$1 AT dough DOT gmane DOT org> <loom DOT 20110729T103121-380 AT post DOT gmane DOT org> <20110729092602 DOT GB19240 AT calimero DOT vinschen DOT de> <loom DOT 20110729T144701-436 AT post DOT gmane DOT org> <20110729130645 DOT GA28223 AT ednor DOT casa DOT cgf DOT cx>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20110729130645.GA28223@ednor.casa.cgf.cx>
User-Agent: Mutt/1.5.20 (2009-06-14)
Mailing-List: contact cygwin-help AT cygwin DOT com; run by ezmlm
Precedence: bulk
List-Id: <cygwin.cygwin.com>
List-Unsubscribe: <mailto:cygwin-unsubscribe-archive-cygwin=delorie DOT com AT cygwin DOT com>
List-Subscribe: <mailto:cygwin-subscribe AT cygwin DOT com>
List-Archive: <http://sourceware.org/ml/cygwin/>
List-Post: <mailto:cygwin AT cygwin DOT com>
List-Help: <mailto:cygwin-help AT cygwin DOT com>, <http://sourceware.org/ml/#faqs>
Sender: cygwin-owner AT cygwin DOT com
Mail-Followup-To: cygwin AT cygwin DOT com
Delivered-To: mailing list cygwin AT cygwin DOT com

On Fri, Jul 29, 2011 at 09:06:45AM -0400, Christopher Faylor wrote:
>On Fri, Jul 29, 2011 at 12:52:47PM +0000, Heiko Elger wrote:
>>Hello,
>>
>>Corinna Vinschen writes:
>>> 
>>> The slowdown of the code was the result of a patch which was supposed
>>> to fix a potential race condition.  Jojelino's patch looks nice, but
>>> it might reintroduce a new race.  Handle with care.
>>Oops - what king of race condition do you mean.
>>
>>OK - that's a new information for me.
>>So the current slow implementation is a workaround for another race condition.
>
>The signal startup has been very carefully crafted.  Starting wait_sig
>asynchronously could create inability to send signals.
>
>I can't check this right now.  I should be back near my Windows system on the
>weekend.

I've checked in a change which uses QueueUserAPC to create threads like
the signal thread.  As everyone has noted this seems to have a salutory
effect on the OP's test case.

I don't entirely understand why the code which already existed in Cygwin
to deal with the "slow performance on win7/64" didn't fix the problem but
using QueueUserAPC seems to solve the problem so I guess won't lose too
much sleep over this.

Thanks jojelino for the idea.  Much appreciated.

cgf

--
Problem reports:       http://cygwin.com/problems.html
FAQ:                   http://cygwin.com/faq/
Documentation:         http://cygwin.com/docs.html
Unsubscribe info:      http://cygwin.com/ml/#unsubscribe-simple