From mboxrd@z Thu Jan 1 00:00:00 1970 Message-ID: <4EEB3614.4080805@domain.hid> Date: Fri, 16 Dec 2011 13:14:12 +0100 From: Anders Blomdell MIME-Version: 1.0 References: <4EE9FD4A.1090202@domain.hid> <4EEB304B.2010108@domain.hid> In-Reply-To: Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: quoted-printable Subject: Re: [Xenomai-help] Big differences in analogy interrupt handling time List-Id: Help regarding installation and common use of Xenomai List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: =?UTF-8?B?RmVybmFuZG8gSGVycmVybyBDYXJyw7Nu?= Cc: "xenomai@xenomai.org" On 12/16/2011 12:57 PM, Fernando Herrero Carr=C3=B3n wrote: > [...] > >> Nice that somebody has already tested this. >> > > >> Nobody that has any insight on what might slow down execution with 20% >> (curious mind wants to know)? >> > > Dear Anders, > > I am afraid I don't understand your question. 20% with respect to what? > Indeed, the "sync_dma" function performs some copy between kernel/user > space. The old code performs exactly the same copy ten times, which > multiplies the time spent in the interrupt handler tenfold, and adds 10= us > in idle wait. Besides that, I believe that the most time spent in an > interrupt handler is in the i-pipe dispatching mechanism itself. 20% difference in execution time in identical code paths (attachment 'A'=20 and 'B'), where executing the same codepath in 'B' takes 20% longer time=20 than in 'A' > > There are for sure other people in the list more knowledgeable than me = on > this subject. And me, obviously. --=20 Anders Blomdell Email: anders.blomdell@domain.hid Department of Automatic Control Lund University Phone: +46 46 222 4625 P.O. Box 118 Fax: +46 46 138118 SE-221 00 Lund, Sweden