From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752289Ab0JTN32 (ORCPT ); Wed, 20 Oct 2010 09:29:28 -0400 Received: from smtp-out.google.com ([74.125.121.35]:19972 "EHLO smtp-out.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751078Ab0JTN31 (ORCPT ); Wed, 20 Oct 2010 09:29:27 -0400 DomainKey-Signature: a=rsa-sha1; c=nofws; d=google.com; s=beta; h=message-id:from:date:to:reply-to:cc:subject; b=wjCSSsPhW2ZXub+vsTjH1Fx9md3b0gyyALpT1013ViM29vgpmB+SqciZcga/Vq+ug3 ihZJjD8I4fgkin5ZfUTg== Message-ID: <4cbeeeb2.1e07e30a.317f.0daa@mx.google.com> From: Stephane Eranian Date: Wed, 20 Oct 2010 15:25:01 +0200 To: linux-kernel@vger.kernel.org Reply-to: eranian@google.com Cc: peterz@infradead.org, mingo@elte.hu, paulus@samba.org, davem@davemloft.net, fweisbec@gmail.com, perfmon2-devel@lists.sf.net, eranian@gmail.com, eranian@google.com, robert.richter@amd.com Subject: [PATCH 0/2] perf_events: fix the fix for transaction recovery in group_sched_in() (v2) X-System-Of-Record: true Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org This is a new version of the patch to fix the way timing is handled in group_sched_in(). Although the patch solved the issue with time_running, time_enabled for all events in a group, it had one flaw in case the group could never be scheduled. It would cause time_enabled to get negative. The issue was that tstamp_stopped was never updated, even though tstamp_enabled was. This new version is much simpler and ensures that in case of error in group_sched_in() during event_sched_in(), the events up to the failed event go through regular event_sched_out(). But the failed event and the remaining events in the group have their timings adjusted as if they had also gone through event_sched_in() and event_sched_out(). This ensures timing uniformity across all events in a group. This also takes care of the tstamp_stopped problem in case the group could never be scheduled. The tstamp_stopped is updated as if the event had actually run. With this patch, the following now reports correct time_enabled, in case the NMI watchdog is active: $ task -e unhalted_core_cycles,instructions_retired,baclears,baclears noploop 1 noploop for 1 seconds 0 unhalted_core_cycles (100.00% scaling, ena=997,552,872, run=0) 0 instructions_retired (100.00% scaling, ena=997,552,872, run=0) 0 baclears (100.00% scaling, ena=997,552,872, run=0) 0 baclears (100.00% scaling, ena=997,552,872, run=0) [PATCH 0/2] : introduction [PATCH 1/2] : revert commit 8e5fc1a [PATCH 2/2] : the actual fix Signed-off-by: Stephane Eranian --