X-Spam-Check-By: sourceware.org
To: cygwin AT cygwin DOT com
From: "J.D. Liau" <jliau AT cisco DOT com>
Subject:  Windows system performance and Cygwin
Date:  Mon, 14 Aug 2006 15:27:01 -0500
Lines: 21
Message-ID: <ebqmam$o1k$1@sea.gmane.org>
X-IsSubscribed: yes
Mailing-List: contact cygwin-help AT cygwin DOT com; run by ezmlm
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

Hi:

We have two idnetical Windows 2000 Server SP4 machines with all hotfixes 
from Microsoft.  After we install openSSH on machineA and reboot the server, 
it outperforms machineB by 200%~300%.  We traced into openSSH, it basically 
runs "cygrunserv.exe" as a service.  So, if cygrunsrv.exe starts, machineA 
runs two to three times faster based on our benchmark program.  If we stop 
cygrunserv.exe then both machines have the same performance.  BTW, our 
benchmark program is heavy on inter-thread communication.

However, a plain Windows 2000 Server SP4 machine WITHOUT any Microsoft 
hotfixes or cygrunserv.exe runs as fast as machineA with cygrunserv.exe 
running.

There appears to have been an OS changes due to those hotfixes, but how does 
Cygwin work around the issue to keep interthread communication  performance? 
Is there a Win32 API hooks internally to change thread or process resources?

Thanks!




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