From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753428AbbDPQoI (ORCPT ); Thu, 16 Apr 2015 12:44:08 -0400 Received: from foss.arm.com ([217.140.101.70]:38522 "EHLO foss.arm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751597AbbDPQoC (ORCPT ); Thu, 16 Apr 2015 12:44:02 -0400 Date: Thu, 16 Apr 2015 17:43:57 +0100 From: Mark Rutland To: Kan Liang Cc: "acme@kernel.org" , "a.p.zijlstra@chello.nl" , "eranian@google.com" , "andi@firstfloor.org" , "linux-kernel@vger.kernel.org" Subject: Re: [PATCH V2 1/6] perf,core: allow invalid context events to be part of sw/hw groups Message-ID: <20150416164356.GD19775@leverpostej> References: <1429084576-1078-1-git-send-email-kan.liang@intel.com> <20150416163140.GA19775@leverpostej> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20150416163140.GA19775@leverpostej> User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org > Even if you ignore the fundamental semantics of groups, there are other > problems with allowing shared contexts: > > * The *_txn functions only get called on the group leader's PMU. If your > system PMU has these functions, they are not called. > > * Event rotation is per ctx, but now you could have some events in a CPU > PMU's context, and some in the uncore PMU's context. So those can race > with each other. > > * Throttling is also per-context. So those can race with each other too. There's also a break down of behaviour: events in the uncore context will get migrated to another CPU in the event of a hot unplug, while events that are grouped with CPU events (and hence live in the CPU context) will be destroyed. Mark.