From mboxrd@z Thu Jan 1 00:00:00 1970 From: Steven Rostedt Subject: Re: [PATCH][RT][RFC] irq_work: Have non HARD_IRQ irq work just run from ticks Date: Tue, 23 Jun 2015 12:30:57 -0400 Message-ID: <20150623123057.0bf8fc58@gandalf.local.home> References: <20150622150959.44055b32@gandalf.local.home> <5589694D.4040504@siemens.com> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Cc: Jan Kiszka , Sebastian Andrzej Siewior , LKML , linux-rt-users , Thomas Gleixner , Peter Zijlstra To: Gary Robertson Return-path: Received: from smtprelay0033.hostedemail.com ([216.40.44.33]:40252 "EHLO smtprelay.hostedemail.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S932629AbbFWQbB (ORCPT ); Tue, 23 Jun 2015 12:31:01 -0400 In-Reply-To: Sender: linux-rt-users-owner@vger.kernel.org List-ID: On Tue, 23 Jun 2015 11:20:38 -0500 Gary Robertson wrote: > I am concerned about interactions with the evolving 'full tickless' operations. I'm concerned about more than just full tickless. But like you, I don't currently have any concrete examples to show there's a possible issue. > > While I have no concrete use cases to show, I can conceive that > an I/O data processing application running on an isolated core > operating in 'full tickless' mode might benefit from allowing interrupts > on that same core so long as they service hardware involved with > the data flow being processed by the application. > Let's further assume that for hardware-related reasons we still want > to run the irq work from a softirq context rather than a hardirq context. > > In such circumstances we obviously don't want the irq work done from a > timer tick - > so adding another irq work queue independent of the lazy flag and > unconditionally raising a softirq on the first addition to that queue > would seem to be the most flexible and compatible answer. > Irq work queued with the lazy bit set could be deferred until the next > tick interrupt > for efficiency and compatibility, and 'normal' irq work > would no longer be potentially stalled > by being enqueued with 'lazy' work. 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. -- Steve