X-Recipient:	archive-cygwin AT delorie DOT com
X-SWARE-Spam-Status:	No, hits=-0.6 required=5.0 tests=AWL,BAYES_00,DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,FREEMAIL_FROM,RCVD_IN_DNSWL_LOW
X-Spam-Check-By:	sourceware.org
MIME-Version:	1.0
In-Reply-To:	<CADs2-=SoNva+kU3C94L5ri6Avv278v_sg=Mipa6j_bBFtOyvXA@mail.gmail.com>
References:	<CALRo7LtHGrbXC-S2ZuJfg+hvYJtPid0SQYLgEANHsSjyrQ8PQA AT mail DOT gmail DOT com> <4F2FEDD0 DOT 8040102 AT gmail DOT com> <CADs2-=SoNva+kU3C94L5ri6Avv278v_sg=Mipa6j_bBFtOyvXA AT mail DOT gmail DOT com>
Date:	Fri, 10 Feb 2012 17:01:30 +0530
Message-ID:	<CALRo7LthmqWcaUwz995wUJttD4+EG4MQTLDh_rO3edOdiVpnAw@mail.gmail.com>
Subject:	Re: Performance degradation between Cygwin 1.7.7-1 and 1.5.24-2
From:	Jaswinder Bhamra <jbhamra AT gmail DOT com>
To:	cygwin <cygwin AT cygwin DOT com>
Mailing-List:	contact cygwin-help AT cygwin DOT com; run by ezmlm
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
X-MIME-Autoconverted:	from quoted-printable to 8bit by delorie.com id q1ABVrJa013956

Thanks for correcting the math. I wanted to mention 'count' instead of 'times'.

I tried the suggestion of trying out with 1.7.10 and found no
performance gain by doing this. I am getting the same reading with
1.7.10 as I got with 1.7.7.

Any other suggestions/insights on improving the performance are welcome.

Thanks,
Jaswinder

> On 2/6/2012 2:08 PM, Jaswinder Bhamra wrote:
>>
>> Hi,
>>
>> We are experiencing performance degradation between Cygwin version
>> 1.7.7-1 and 1.5.24-2.
>>
>> Recently, we have upgraded from Cygwin version 1.5.24-2 to version
>> 1.7.7-1. The simple test brings forward the performance degradation in
>> version 1.7.7-1 over 1.5.24-2.
>>
>> <On Cygwin version 1.5.24-2>
>> bash-3.2$ while [ 1 ]; do date; done | uniq -c
>>   40 Mon Feb  6 17:58:13 2012
>>   65 Mon Feb  6 17:58:14 2012
>>   66 Mon Feb  6 17:58:15 2012
>>   65 Mon Feb  6 17:58:16 2012
>>   66 Mon Feb  6 17:58:17 2012
>>   65 Mon Feb  6 17:58:18 2012
>>   66 Mon Feb  6 17:58:19 2012
>>   65 Mon Feb  6 17:58:20 2012
>>   65 Mon Feb  6 17:58:21 2012
>>   66 Mon Feb  6 17:58:22 2012
>>   65 Mon Feb  6 17:58:23 2012
>>   66 Mon Feb  6 17:58:24 2012
>>   64 Mon Feb  6 17:58:25 2012
>>   65 Mon Feb  6 17:58:26 2012
>>   66 Mon Feb  6 17:58:27 2012
>>   66 Mon Feb  6 17:58:28 2012
>>   65 Mon Feb  6 17:58:29 2012
>>   65 Mon Feb  6 17:58:30 2012
>>
>> bash-3.2$
>>
>> <On Cygwin version 1.7.7-1>
>> # while [ 1 ]; do date; done | uniq -c
>>      16 Mon Feb  6 17:58:41 IST 2012
>>      49 Mon Feb  6 17:58:42 IST 2012
>>      50 Mon Feb  6 17:58:43 IST 2012
>>      50 Mon Feb  6 17:58:44 IST 2012
>>      49 Mon Feb  6 17:58:45 IST 2012
>>      50 Mon Feb  6 17:58:46 IST 2012
>>      50 Mon Feb  6 17:58:47 IST 2012
>>      49 Mon Feb  6 17:58:48 IST 2012
>>      49 Mon Feb  6 17:58:49 IST 2012
>>      49 Mon Feb  6 17:58:50 IST 2012
>>      50 Mon Feb  6 17:58:51 IST 2012
>>      50 Mon Feb  6 17:58:52 IST 2012
>>      49 Mon Feb  6 17:58:53 IST 2012
>>      50 Mon Feb  6 17:58:54 IST 2012
>>      50 Mon Feb  6 17:58:55 IST 2012
>>      49 Mon Feb  6 17:58:56 IST 2012
>>      50 Mon Feb  6 17:58:57 IST 2012
>>      50 Mon Feb  6 17:58:58 IST 2012
>>      49 Mon Feb  6 17:58:59 IST 2012
>>      51 Mon Feb  6 17:59:00 IST 2012
>>      49 Mon Feb  6 17:59:01 IST 2012
>>      51 Mon Feb  6 17:59:02 IST 2012
>>
>> #
>>
>> As you can see the version 1.5.24-2 executes date command
>> approximately 15-16 times more than in version 1.7.7-1.
>>
>> The above test is done on MS Windows XP Professional version 2002 SP3, v.5857.
>> i7-2620M CPU @ 2.70GHz, 3.16 GB of RAM. Care has been taken to perform
>> the above 2 tests one at a time under the same load average on the
>> machine.
>>
>> Is this performance degradation a known issue and does anyone knows if
>> this is already addressed in any Cygwin version higher than 1.7.7-1?
>>
>> Thanks,
>> Jaswinder
>
>
> Dear Jaswinder,
> your math looks strange
>
> 50/65 = 77 %  so you are losing as performance 23% not 15 times
>
> For 15 times you should have 4-5 instead of 50 as result.
>
> Try last 1.7.10 and see if yo have any change.
>
> Regards
> Marco
>
>
> --
> 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

--
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

- Raw text -