From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753055AbbJYKmb (ORCPT ); Sun, 25 Oct 2015 06:42:31 -0400 Received: from imap.thunk.org ([74.207.234.97]:42624 "EHLO imap.thunk.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750802AbbJYKm3 (ORCPT ); Sun, 25 Oct 2015 06:42:29 -0400 Date: Sun, 25 Oct 2015 06:41:45 -0400 From: "Theodore Ts'o" To: Ingo Molnar Cc: Linus Torvalds , Tejun Heo , Mike Galbraith , Paul Turner , Peter Zijlstra , Ingo Molnar , Johannes Weiner , Li Zefan , cgroups , LKML , kernel-team , Andrew Morton Subject: Re: [PATCH 3/3] sched: Implement interface for cgroup unified hierarchy Message-ID: <20151025104145.GE27558@thunk.org> Mail-Followup-To: Theodore Ts'o , Ingo Molnar , Linus Torvalds , Tejun Heo , Mike Galbraith , Paul Turner , Peter Zijlstra , Ingo Molnar , Johannes Weiner , Li Zefan , cgroups , LKML , kernel-team , Andrew Morton References: <20150912144007.GA8942@htj.duckdns.org> <20151001184629.GB26498@mtj.duckdns.org> <20151023222110.GA4390@mtj.duckdns.org> <1445661367.3218.62.camel@gmail.com> <20151025021829.GA15471@mtj.duckdns.org> <20151025093331.GA4834@gmail.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20151025093331.GA4834@gmail.com> User-Agent: Mutt/1.5.24 (2015-08-30) X-SA-Exim-Connect-IP: X-SA-Exim-Mail-From: tytso@thunk.org X-SA-Exim-Scanned: No (on imap.thunk.org); SAEximRunCond expanded to false Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Sun, Oct 25, 2015 at 10:33:32AM +0100, Ingo Molnar wrote: > > Hm, that's weird - all our sched_*() system call APIs that set task scheduling > priorities are fundamentally per thread, not per process. Same goes for the old > sys_nice() interface. The scheduler has no real notion of 'process', and certainly > not at the system call level. > I suspect the main issue is that the games programmers were trying to access it via libc / pthreads, which hides a lot of the power available at the raw syscall level. This is probably more of a "tutorial needed for userspace programmers" issue, at a guess. - Ted