Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753200AbbGaNyx (ORCPT ); Fri, 31 Jul 2015 09:54:53 -0400 Received: from terminus.zytor.com ([198.137.202.10]:57168 "EHLO terminus.zytor.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751231AbbGaNyv (ORCPT ); Fri, 31 Jul 2015 09:54:51 -0400 Date: Fri, 31 Jul 2015 06:54:35 -0700 From: tip-bot for Jiri Olsa Message-ID: Cc: namhyung@kernel.org, linux-kernel@vger.kernel.org, mingo@kernel.org, ak@linux.intel.com, kan.liang@intel.com, acme@redhat.com, hpa@zytor.com, jolsa@kernel.org, tglx@linutronix.de Reply-To: hpa@zytor.com, acme@redhat.com, kan.liang@intel.com, ak@linux.intel.com, linux-kernel@vger.kernel.org, mingo@kernel.org, namhyung@kernel.org, tglx@linutronix.de, jolsa@kernel.org In-Reply-To: <1438162936-59698-3-git-send-email-kan.liang@intel.com> References: <1438162936-59698-3-git-send-email-kan.liang@intel.com> To: linux-tip-commits@vger.kernel.org Subject: [tip:perf/core] perf tools: Force period term to overload global settings Git-Commit-ID: ee4c75887d12bcd6ecd897291797d969256f39ca X-Mailer: tip-git-log-daemon Robot-ID: Robot-Unsubscribe: Contact to get blacklisted from these emails MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset=UTF-8 Content-Disposition: inline Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 5615 Lines: 147 Commit-ID: ee4c75887d12bcd6ecd897291797d969256f39ca Gitweb: http://git.kernel.org/tip/ee4c75887d12bcd6ecd897291797d969256f39ca Author: Jiri Olsa AuthorDate: Wed, 29 Jul 2015 05:42:11 -0400 Committer: Arnaldo Carvalho de Melo CommitDate: Wed, 29 Jul 2015 16:18:21 -0300 perf tools: Force period term to overload global settings Currently the command line option settings beats the per event period settings: With no global settings, we get per-event configuration: $ perf record -e 'cpu/instructions,period=20000/' sleep 1 $ perf evlist -v ... { sample_period, sample_freq }: 20000 ... With 'c' option period setup, we get 'c' option value: $ perf record -e 'cpu/instructions,period=20000/' -c 1000 sleep 1 $ perf evlist -v ... { sample_period, sample_freq }: 1000 ... This patch makes the per-event settings overload the global 'c' option setup: $ perf record -e 'cpu/instructions,period=20000/' -c 1000 sleep 1 $ perf evlist -v ... { sample_period, sample_freq }: 20000 ... I think the making the per-event settings to overload any other config makes more sense than current state. However it breaks the current 'period' term handling, which might cause some noise.. so let's see ;-). Also fixing parse event tests with the new behaviour. Signed-off-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Andi Kleen Cc: Kan Liang Cc: Namhyung Kim Link: http://lkml.kernel.org/r/1438162936-59698-3-git-send-email-kan.liang@intel.com Signed-off-by: Kan Liang Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-record.txt | 2 +- tools/perf/tests/parse-events.c | 12 ++++++++++-- tools/perf/util/evsel.c | 2 ++ tools/perf/util/evsel.h | 1 + tools/perf/util/parse-events.c | 3 ++- 5 files changed, 16 insertions(+), 4 deletions(-) diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 63ee040..ac41350 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -46,7 +46,7 @@ OPTIONS /sys/bus/event_sources/devices//format/* There are also some params which are not defined in ...//format/*. - These params can be used to set event defaults. + These params can be used to overload default config values per event. Here is a list of the params. - 'period': Set event sampling period diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index d76963f..f65bb89 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -82,8 +82,12 @@ static int test__checkevent_symbolic_name_config(struct perf_evlist *evlist) TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); TEST_ASSERT_VAL("wrong config", PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config); + /* + * The period value gets configured within perf_evlist__config, + * while this test executes only parse events method. + */ TEST_ASSERT_VAL("wrong period", - 100000 == evsel->attr.sample_period); + 0 == evsel->attr.sample_period); TEST_ASSERT_VAL("wrong config1", 0 == evsel->attr.config1); TEST_ASSERT_VAL("wrong config2", @@ -406,7 +410,11 @@ static int test__checkevent_pmu(struct perf_evlist *evlist) TEST_ASSERT_VAL("wrong config", 10 == evsel->attr.config); TEST_ASSERT_VAL("wrong config1", 1 == evsel->attr.config1); TEST_ASSERT_VAL("wrong config2", 3 == evsel->attr.config2); - TEST_ASSERT_VAL("wrong period", 1000 == evsel->attr.sample_period); + /* + * The period value gets configured within perf_evlist__config, + * while this test executes only parse events method. + */ + TEST_ASSERT_VAL("wrong period", 0 == evsel->attr.sample_period); return 0; } diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 048d61d..7d3acba 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -594,6 +594,8 @@ static void apply_config_terms(struct perf_event_attr *attr __maybe_unused, list_for_each_entry(term, config_terms, list) { switch (term->type) { + case PERF_EVSEL__CONFIG_TERM_PERIOD: + attr->sample_period = term->val.period; default: break; } diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 0339819..a7d2175 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -38,6 +38,7 @@ struct cgroup_sel; * perf_evsel::config_terms list head. */ enum { + PERF_EVSEL__CONFIG_TERM_PERIOD, PERF_EVSEL__CONFIG_TERM_MAX, }; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 3271d13..09bee93 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -596,7 +596,6 @@ do { \ break; case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD: CHECK_TYPE_VAL(NUM); - attr->sample_period = term->val.num; break; case PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE: /* @@ -649,6 +648,8 @@ do { \ list_for_each_entry(term, head_config, list) { switch (term->type_term) { + case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD: + ADD_CONFIG_TERM(PERIOD, period, term->val.num); default: break; } -- 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/