Mailing-List: contact cygwin-help@cygwin.com; run by ezmlm List-Subscribe: List-Archive: List-Post: List-Help: , Sender: cygwin-owner@cygwin.com Mail-Followup-To: cygwin@cygwin.com Delivered-To: mailing list cygwin@cygwin.com Date: Thu, 28 Nov 2002 15:07:40 +0100 From: thomas Reply-To: thomas X-Priority: 3 (Normal) Message-ID: <1988826218.20021128150740@huno.net> To: thomas Subject: Re: pipe performance problem In-Reply-To: <6654089625.20021128033745@huno.net> References: <777770015.20021122040845@huno.net> <007301c291ff$eb9ce050$78d96f83@pomello> <21545718.20021122114035@huno.net> <12415481703.20021122220059@huno.net> <20021122210856.GA10679@redhat.com> <5.1.0.14.2.20021122143402.00fdc148@pop3.cris.com> <10824453046.20021123003030@huno.net> <14936170000.20021127223905@huno.net> <20021127233624.GK17798@redhat.com> <1245871093.20021128012046@huno.net> <20021128003443.GD21457@redhat.com> <5549457171.20021128022032@huno.net> <6654089625.20021128033745@huno.net> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Ok now i really found the problem. If i always return from fhandler_base::ready_for_read with 1 at the first line and skip all the checks in there everything works. $ time cat test.iso | nice -0 dd of=/dev/null 352512+0 records in 352512+0 records out real 0m5.528s user 0m2.155s sys 0m3.342s $ time cat test.iso | nice --1 dd of=/dev/null 352512+0 records in 352512+0 records out real 0m4.188s user 0m1.592s sys 0m2.452s nice --1 is faster like it should be. Just to be on the safe side i also did: $ cat test.iso | nice --1 dd of=test1 $ cat test.iso | nice -0 dd of=test0 $ diff -q -s --binary test0 test1 Files test0 and test1 are identical $ diff -q -s --binary test0 test.iso Files test0 and test.iso are identical So that workaround works perfectly for my purposes. But i guess the checks were put in there for good reason to fix sth. that happened on the way. Just that it broke sth. else. I already did some mkisofs | cdrecord checks and it also works perfectly! thomas -- Unsubscribe info: http://cygwin.com/ml/#unsubscribe-simple Bug reporting: http://cygwin.com/bugs.html Documentation: http://cygwin.com/docs.html FAQ: http://cygwin.com/faq/