From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932131AbXB1KQJ (ORCPT ); Wed, 28 Feb 2007 05:16:09 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S932134AbXB1KQI (ORCPT ); Wed, 28 Feb 2007 05:16:08 -0500 Received: from relay00.pair.com ([209.68.5.9]:3356 "HELO relay00.pair.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with SMTP id S932133AbXB1KQH (ORCPT ); Wed, 28 Feb 2007 05:16:07 -0500 X-pair-Authenticated: 24.241.238.207 Message-ID: <45E55664.90407@cybsft.com> Date: Wed, 28 Feb 2007 04:16:04 -0600 From: "K.R. Foley" Organization: Cybersoft Solutions, Inc. User-Agent: Thunderbird 2.0b2 (X11/20070116) MIME-Version: 1.0 To: Ingo Molnar CC: linux-kernel@vger.kernel.org, linux-rt-users@vger.kernel.org Subject: Re: v2.6.20-rt1, yum/rpm References: <20070205065636.GA1652@elte.hu> <45E46CB4.1080009@cybsft.com> <20070228081132.GA32405@elte.hu> In-Reply-To: <20070228081132.GA32405@elte.hu> X-Enigmail-Version: 0.94.2.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Ingo Molnar wrote: > * K.R. Foley wrote: > >> Ingo Molnar wrote: >>> i have released the v2.6.20-rt1 kernel, which can be downloaded from the >>> usual place: >>> >> I have a couple of questions regarding priorities of the softirqs, IRQ >> handlers, etc. >> >> With some exceptions, back in 2.6.18 and prior patches the IRQ threads >> were prioritized between 50 and 25 and the most of the softirqs were >> prioritized at 1? In newer patches it looks like they are all >> prioritized at 50? >> >> I was just curious what went into making these choices? I am just >> trying to better understand these decisions. > > The basically random order-of-request_irq() prioritization was causing > problems (it worked for some but didnt work for others), so i got rid of > trying to auto-guess some priority order. Also, now that we've got > tools/scripts like set_kthread_prio and rtprio it seemed more consistent > to just not attempt to prioritize interrupts and softirqs at all, but to > keep them all 'in the middle' of the RT priority range. > > Ingo > Thanks. -- kr