Mailing-List: contact cygwin-help AT cygwin DOT com; run by ezmlm List-Subscribe: List-Archive: List-Post: List-Help: , Sender: cygwin-owner AT cygwin DOT com Mail-Followup-To: cygwin AT cygwin DOT com Delivered-To: mailing list cygwin AT cygwin DOT com To: cygwin AT cygwin DOT com From: "Anonymous" Subject: Re: Serious performance problems (new snapshot has some performance improvement) Date: Mon, 30 May 2005 23:52:24 -0400 Lines: 20 Message-ID: References: <4298F195 DOT 9090600 AT familiehaase DOT de> <20050529000152 DOT GE3094 AT trixie DOT casa DOT cgf DOT cx> <20050529001846 DOT GG3094 AT trixie DOT casa DOT cgf DOT cx> <20050529030523 DOT GA10263 AT trixie DOT casa DOT cgf DOT cx> <20050529171324 DOT GA26603 AT trixie DOT casa DOT cgf DOT cx> <429A19EC DOT 9080905 AT familiehaase DOT de> <20050529201431 DOT GB28340 AT trixie DOT casa DOT cgf DOT cx> <429B78A5 DOT 2050107 AT familiehaase DOT de> <20050531001246 DOT GA17217 AT trixie DOT casa DOT cgf DOT cx> Mime-Version: 1.0 Content-Type: text/plain; format=flowed; charset="iso-8859-1"; reply-type=original Content-Transfer-Encoding: 7bit X-IsSubscribed: yes > There is no reason to expect any improvement in mingw programs from my > change. > Yeah i figured that one out. ;) I was just trying to rationalize the change that I did show in the original report. My timings don't show great improvement, and a 1 second margin of error due to windows caching does not make it look that much better. Perhaps there is something else to account for the difference. The patch saved 6 +/- 1 second from the execution of the unopimized testcase. the most interesting numbers are Old DLL: 19.60 seconds snapshot DLL: 13.32 seconds Mingw: ~3 seconds. OT: I wonder what the performance is like with Interix (Windows Services for UNIX 3.5). Do they have a similar showdown problem? -- 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/