From mboxrd@z Thu Jan 1 00:00:00 1970 From: Sebastian Andrzej Siewior Subject: Re: [PATCH][RT][RFC] irq_work: Have non HARD_IRQ irq work just run from ticks Date: Tue, 23 Jun 2015 20:45:35 +0200 Message-ID: <5589A94F.9010209@linutronix.de> References: <20150622150959.44055b32@gandalf.local.home> <5589694D.4040504@siemens.com> <20150623123057.0bf8fc58@gandalf.local.home> Mime-Version: 1.0 Content-Type: text/plain; charset=windows-1252 Content-Transfer-Encoding: 7bit Cc: Jan Kiszka , LKML , linux-rt-users , Thomas Gleixner , Peter Zijlstra To: Steven Rostedt , Gary Robertson Return-path: Received: from www.linutronix.de ([62.245.132.108]:41649 "EHLO Galois.linutronix.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752298AbbFWSpj (ORCPT ); Tue, 23 Jun 2015 14:45:39 -0400 In-Reply-To: <20150623123057.0bf8fc58@gandalf.local.home> Sender: linux-rt-users-owner@vger.kernel.org List-ID: On 06/23/2015 06:30 PM, Steven Rostedt wrote: > I'd be sleeping better at night with a third queue. I'll write up a > patch and post that as an RFC as well. This will at a minimum keep with > the paradigm of mainline linux. We had three queues. We are down to two and I think this is a good thing. We only deal with FULL_NOHZ in hardirq context (looking at v4.0-RT). Before that (FULL_NOHZ) everything was handled in softirq and nobody was concerned (saw a problem). It would be good if we would address a regression or a bug or something like that. > > -- Steve Sebastian