From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751319AbeBDIoO (ORCPT ); Sun, 4 Feb 2018 03:44:14 -0500 Received: from cloudserver094114.home.pl ([79.96.170.134]:60677 "EHLO cloudserver094114.home.pl" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750796AbeBDIoH (ORCPT ); Sun, 4 Feb 2018 03:44:07 -0500 From: "Rafael J. Wysocki" To: Mel Gorman Cc: Srinivas Pandruvada , Peter Zijlstra , Mike Galbraith , Matt Fleming , LKML Subject: Re: [PATCH 4/4] sched/fair: Use a recently used CPU as an idle candidate and the basis for SIS Date: Sun, 04 Feb 2018 09:42:28 +0100 Message-ID: <2563202.Cx1TqSeWJa@aspire.rjw.lan> In-Reply-To: <20180202194801.mhvuwzbz6pauf63f@techsingularity.net> References: <20180130104555.4125-1-mgorman@techsingularity.net> <1517583264.18051.60.camel@linux.intel.com> <20180202194801.mhvuwzbz6pauf63f@techsingularity.net> MIME-Version: 1.0 Content-Transfer-Encoding: 7Bit Content-Type: text/plain; charset="us-ascii" Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Friday, February 2, 2018 8:48:01 PM CET Mel Gorman wrote: > On Fri, Feb 02, 2018 at 06:54:24AM -0800, Srinivas Pandruvada wrote: > > > > > No idea, desired would be the one I would start with, it matches > > > > > with > > > > > the intent here. But I've no idea what our current HWP > > > > > implementation > > > > > actually does with it. > > > > Desired !=0 will disable HWP autonomous mode of frequency > > > > selection. > > > But I don't think it will just run at "desired" then, will it? > > HWP all are these hints only not a guarantee. > > Sure, but the lack on detection when tasks are low utilisation but still > latency/throughput sensitive is problematic. Users shouldn't have to > know they need to disable HWP or set performance goernor out of the box. > It's only going to get worse as sockets get larger. OK, so that's the case I was thinking about when the kernel actually knows more about what's going on than the HW-based logic. That's when it makes sense to provide hints, of course. > > There are totally different way HWP is handled in client an servers. > > If you set desired all heuristics they collected will be dumped, so > > they suggest don't set desired when you are in autonomous mode. If we > > really want a boost set the EPP. We know that EPP makes lots of > > measurable difference. > > > > Sure boosting EPP makes a difference -- it's essentially what the performance > goveror does and I know that can be done by a user but it's still basically a > cop-out. Default performance for low utilisation or lightly loaded machines > is poor. Maybe it should be set based on the ACPI preferred profile but > that information is not always available. It would be nice if *some* > sort of hint about new migrations or tasks waking from IO would be desirable. Agreed, we only need to figure out a clean way to do that.