Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753137AbbDPPiv (ORCPT ); Thu, 16 Apr 2015 11:38:51 -0400 Received: from mx1.redhat.com ([209.132.183.28]:55244 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752024AbbDPPid (ORCPT ); Thu, 16 Apr 2015 11:38:33 -0400 From: Petr Holasek To: linux-kernel@vger.kernel.org Cc: Arnaldo Carvalho de Melo , Jiri Olsa , Ingo Molnar , Petr Holasek Subject: [PATCH 3/3] perf bench numa: fix immediate meeting of convergence condition Date: Thu, 16 Apr 2015 17:38:19 +0200 Message-Id: <1429198699-25039-4-git-send-email-pholasek@redhat.com> In-Reply-To: <1429198699-25039-1-git-send-email-pholasek@redhat.com> References: <1429198699-25039-1-git-send-email-pholasek@redhat.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1469 Lines: 48 This patch fixes the race in the beginning of benchmark run when some threads hasn't got assigned curr_cpu yet so they don't occur in nodes-of-process stats and benchmark concludes that all remaining threads are converged already. The race can be reproduced with small amount of threads and some bigger amount of shared process memory, e.g. one process, two threads and 5GB of process memory. Signed-off-by: Petr Holasek --- tools/perf/bench/numa.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index 72edc49..1704929 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -832,6 +832,9 @@ static int count_process_nodes(int process_nr) td = g->threads + task_nr; node = numa_node_of_cpu(td->curr_cpu); + if (node < 0) /* curr_cpu was likely still -1 */ + return 0; + node_present[node] = 1; } @@ -886,6 +889,11 @@ static void calc_convergence_compression(int *strong) for (p = 0; p < g->p.nr_proc; p++) { unsigned int nodes = count_process_nodes(p); + if (!nodes) { + *strong = 0; + return; + } + nodes_min = min(nodes, nodes_min); nodes_max = max(nodes, nodes_max); } -- 2.1.0 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/