X-Recipient: archive-cygwin AT delorie DOT com
X-SWARE-Spam-Status: No, hits=-2.3 required=5.0 	tests=AWL,BAYES_00,SPF_PASS
X-Spam-Check-By: sourceware.org
X-Authority-Analysis: v=1.0 c=1 a=w_pzkKWiAAAA:8 a=rMz_2MCF1mFbbE5xY1UA:9 a=VUS7VCYclwZSOH0a87V3G5bK96MA:4 a=buB1NfXUTBUA:10 a=IfQ-iFkkCvMA:10
Message-ID: <4B54CA85.8030901@columbus.rr.com>
Date: Mon, 18 Jan 2010 15:54:29 -0500
From: Paul McFerrin <pmcferrin AT columbus DOT rr DOT com>
Reply-To: pmcferrin AT columbus DOT rr DOT com
User-Agent: Thunderbird 2.0.0.23 (Windows/20090812)
MIME-Version: 1.0
To: Cygwin <cygwin AT cygwin DOT com>
Subject: Re: slowdown in "mv" operation
References: <4B53759C DOT 9040405 AT columbus DOT rr DOT com>
In-Reply-To: <4B53759C.9040405@columbus.rr.com>
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Content-Transfer-Encoding: 7bit
X-IsSubscribed: yes
Mailing-List: contact cygwin-help AT cygwin DOT com; run by ezmlm
List-Id: <cygwin.cygwin.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

Since I've already opened my mouth on this subject, I thought I would 
elaborate some on this subject: performance.

I have setup two tests to execute on each of 1.5 and 1.7 cygwin 
systems.  In each of these tests, they are not exhaustive as they should 
be.  I developed these tests based upon a typical task that I would do.

They are scripting task's involving the movement of 4,178 music files 
each to another directory on the same file system.  In one script, it 
uses the "basename" program to create the next script which executes the 
"ln" command to link files to look different.  For each filename, there 
are a total of two commands for each file:  1) basename and 2) ln.   The 
total execution times for each are:
     _Cygwin 1.5_                 _Cygwin1.7_
       996** secs                         1222 secs       (for the 
'basename')
       898 secs                               900 secs       (for the "ln")
** The system "time" command was
    not used.  Just unobserved clock
    awareness time.  For "ln" time, I'm
    calling it a dead-heat.

So it looks like the I/O times in my book for 1.7 compares closely to 
1.5.  There was no physical movement of data for these tests.
                      
Paul McFerrin wrote:
> I have over 12,000 music files I frequently move around using the "mv" 
> command with both source & destination on the same FS.  Under Cygwin 
> 1.5, this script would act amazedly fast that it would be impossible 
> to read your screen..  I do have trace turned on.
>
> Now under Cygwin 1.7, my trace output scrools about 2 lines / second.  
> Much slower than Cygwin 1.5.  Has anyone noticed this slow-down.  It 
> is so slow that it is very obvious.  I've already destroyed my 1.5 
> installation.
>
> -- 
> 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