From mboxrd@z Thu Jan 1 00:00:00 1970 Message-ID: <4D9D4E30.3020804@domain.hid> Date: Thu, 07 Apr 2011 07:40:00 +0200 From: Gilles Chanteperdrix MIME-Version: 1.0 References: <4D9CA930.3000204@domain.hid> <1302128785.2030.90.camel@domain.hid> In-Reply-To: <1302128785.2030.90.camel@domain.hid> Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit Subject: Re: [Xenomai-core] Backfire: User <-> Kernel latancy mesurement tool on Xenomai List-Id: Xenomai life and development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Philippe Gerum Cc: xenomai@xenomai.org Philippe Gerum wrote: > On Wed, 2011-04-06 at 19:31 +0100, krishna murthy j s wrote: >> Thanks for the reply. Can you please tell me why my questions are >> useless. Such attitude will take Xenomai user group no where. > > So, don't take what was said earlier personally. It is just that > sometimes, people may have tuned their bullshit deflector a bit eagerly. > Mine is totally busted btw, so you never know. My apologies for losing my temper. There are valid reasons to choose preempt_rt over Xenomai, but each time we test, we see that we get lower latencies with Xenomai, so, lower latencies is not among those valid reasons. But, by the way, if you are into choosing preempt_rt or Xenomai, you should ponder these other reasons. Notably the fact that it is much easier to write a real-time application with preempt_rt without understanding its inner workings, than it is with Xenomai. I wonder if we should not make a wiki page which dispassionately document the dual-kernel vs native preemption issue. -- Gilles.