linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: "tip-bot2 for Andi Kleen" <tip-bot2@linutronix.de>
To: linux-tip-commits@vger.kernel.org
Cc: Andi Kleen <ak@linux.intel.com>, Jiri Olsa <jolsa@kernel.org>,
	Arnaldo Carvalho de Melo <acme@redhat.com>, x86 <x86@kernel.org>,
	LKML <linux-kernel@vger.kernel.org>
Subject: [tip: perf/urgent] perf evlist: Maintain evlist->all_cpus
Date: Wed, 04 Dec 2019 07:53:55 -0000	[thread overview]
Message-ID: <157544603545.21853.16342096532124116230.tip-bot2@tip-bot2> (raw)
In-Reply-To: <20191121001522.180827-5-andi@firstfloor.org>

The following commit has been merged into the perf/urgent branch of tip:

Commit-ID:     a2408a70368ade9c99de27da78d49416313b8833
Gitweb:        https://git.kernel.org/tip/a2408a70368ade9c99de27da78d49416313b8833
Author:        Andi Kleen <ak@linux.intel.com>
AuthorDate:    Wed, 20 Nov 2019 16:15:14 -08:00
Committer:     Arnaldo Carvalho de Melo <acme@redhat.com>
CommitterDate: Fri, 29 Nov 2019 12:20:45 -03:00

perf evlist: Maintain evlist->all_cpus

Maintain a cpumap in the evlist that is the union of all the cpus of the
events.

This needs a cpumap merge operation, which is added together with tests.

v2:
Add tests for cpu map merge
Fix handling of duplicates
Rename _update to _merge
Factor out sorting.
Fix handling of NULL maps in merge

v3:
Add comments and empty lines to _merge

Committer testing:

  # perf test "Merge cpu map"
  52: Merge cpu map                                         : Ok
  #

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Link: http://lore.kernel.org/lkml/20191121001522.180827-5-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/lib/cpumap.c                  | 57 +++++++++++++++++++++++-
 tools/perf/lib/evlist.c                  |  1 +-
 tools/perf/lib/include/internal/evlist.h |  1 +-
 tools/perf/lib/include/perf/cpumap.h     |  2 +-
 tools/perf/tests/builtin-test.c          |  5 ++-
 tools/perf/tests/cpumap.c                | 16 ++++++-
 tools/perf/tests/tests.h                 |  1 +-
 7 files changed, 83 insertions(+)

diff --git a/tools/perf/lib/cpumap.c b/tools/perf/lib/cpumap.c
index d81656b..f93f4e7 100644
--- a/tools/perf/lib/cpumap.c
+++ b/tools/perf/lib/cpumap.c
@@ -286,3 +286,60 @@ int perf_cpu_map__max(struct perf_cpu_map *map)
 
 	return max;
 }
+
+/*
+ * Merge two cpumaps
+ *
+ * orig either gets freed and replaced with a new map, or reused
+ * with no reference count change (similar to "realloc")
+ * other has its reference count increased.
+ */
+
+struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
+					 struct perf_cpu_map *other)
+{
+	int *tmp_cpus;
+	int tmp_len;
+	int i, j, k;
+	struct perf_cpu_map *merged;
+
+	if (!orig && !other)
+		return NULL;
+	if (!orig) {
+		perf_cpu_map__get(other);
+		return other;
+	}
+	if (!other)
+		return orig;
+	if (orig->nr == other->nr &&
+	    !memcmp(orig->map, other->map, orig->nr * sizeof(int)))
+		return orig;
+
+	tmp_len = orig->nr + other->nr;
+	tmp_cpus = malloc(tmp_len * sizeof(int));
+	if (!tmp_cpus)
+		return NULL;
+
+	/* Standard merge algorithm from wikipedia */
+	i = j = k = 0;
+	while (i < orig->nr && j < other->nr) {
+		if (orig->map[i] <= other->map[j]) {
+			if (orig->map[i] == other->map[j])
+				j++;
+			tmp_cpus[k++] = orig->map[i++];
+		} else
+			tmp_cpus[k++] = other->map[j++];
+	}
+
+	while (i < orig->nr)
+		tmp_cpus[k++] = orig->map[i++];
+
+	while (j < other->nr)
+		tmp_cpus[k++] = other->map[j++];
+	assert(k <= tmp_len);
+
+	merged = cpu_map__trim_new(k, tmp_cpus);
+	free(tmp_cpus);
+	perf_cpu_map__put(orig);
+	return merged;
+}
diff --git a/tools/perf/lib/evlist.c b/tools/perf/lib/evlist.c
index 205ddbb..ae9e65a 100644
--- a/tools/perf/lib/evlist.c
+++ b/tools/perf/lib/evlist.c
@@ -54,6 +54,7 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
 
 	perf_thread_map__put(evsel->threads);
 	evsel->threads = perf_thread_map__get(evlist->threads);
+	evlist->all_cpus = perf_cpu_map__merge(evlist->all_cpus, evsel->cpus);
 }
 
 static void perf_evlist__propagate_maps(struct perf_evlist *evlist)
diff --git a/tools/perf/lib/include/internal/evlist.h b/tools/perf/lib/include/internal/evlist.h
index a2fbccf..74dc8c3 100644
--- a/tools/perf/lib/include/internal/evlist.h
+++ b/tools/perf/lib/include/internal/evlist.h
@@ -18,6 +18,7 @@ struct perf_evlist {
 	int			 nr_entries;
 	bool			 has_user_cpus;
 	struct perf_cpu_map	*cpus;
+	struct perf_cpu_map	*all_cpus;
 	struct perf_thread_map	*threads;
 	int			 nr_mmaps;
 	size_t			 mmap_len;
diff --git a/tools/perf/lib/include/perf/cpumap.h b/tools/perf/lib/include/perf/cpumap.h
index ac9aa49..6a17ad7 100644
--- a/tools/perf/lib/include/perf/cpumap.h
+++ b/tools/perf/lib/include/perf/cpumap.h
@@ -12,6 +12,8 @@ LIBPERF_API struct perf_cpu_map *perf_cpu_map__dummy_new(void);
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list);
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__read(FILE *file);
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map);
+LIBPERF_API struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
+						     struct perf_cpu_map *other);
 LIBPERF_API void perf_cpu_map__put(struct perf_cpu_map *map);
 LIBPERF_API int perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx);
 LIBPERF_API int perf_cpu_map__nr(const struct perf_cpu_map *cpus);
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 7115aa3..82d19a8 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -260,6 +260,11 @@ static struct test generic_tests[] = {
 		.func = test__cpu_map_print,
 	},
 	{
+		.desc = "Merge cpu map",
+		.func = test__cpu_map_merge,
+	},
+
+	{
 		.desc = "Probe SDT events",
 		.func = test__sdt_event,
 	},
diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c
index 8a0d236..4ac5674 100644
--- a/tools/perf/tests/cpumap.c
+++ b/tools/perf/tests/cpumap.c
@@ -120,3 +120,19 @@ int test__cpu_map_print(struct test *test __maybe_unused, int subtest __maybe_un
 	TEST_ASSERT_VAL("failed to convert map", cpu_map_print("1-10,12-20,22-30,32-40"));
 	return 0;
 }
+
+int test__cpu_map_merge(struct test *test __maybe_unused, int subtest __maybe_unused)
+{
+	struct perf_cpu_map *a = perf_cpu_map__new("4,2,1");
+	struct perf_cpu_map *b = perf_cpu_map__new("4,5,7");
+	struct perf_cpu_map *c = perf_cpu_map__merge(a, b);
+	char buf[100];
+
+	TEST_ASSERT_VAL("failed to merge map: bad nr", c->nr == 5);
+	cpu_map__snprint(c, buf, sizeof(buf));
+	TEST_ASSERT_VAL("failed to merge map: bad result", !strcmp(buf, "1-2,4-5,7"));
+	perf_cpu_map__put(a);
+	perf_cpu_map__put(b);
+	perf_cpu_map__put(c);
+	return 0;
+}
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 25aea38..4f9ae6a 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -98,6 +98,7 @@ int test__event_update(struct test *test, int subtest);
 int test__event_times(struct test *test, int subtest);
 int test__backward_ring_buffer(struct test *test, int subtest);
 int test__cpu_map_print(struct test *test, int subtest);
+int test__cpu_map_merge(struct test *test, int subtest);
 int test__sdt_event(struct test *test, int subtest);
 int test__is_printable_array(struct test *test, int subtest);
 int test__bitmap_print(struct test *test, int subtest);

  reply	other threads:[~2019-12-04  7:54 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-11-21  0:15 Optimize perf stat for large number of events/cpus Andi Kleen
2019-11-21  0:15 ` [PATCH 01/12] perf pmu: Use file system cache to optimize sysfs access Andi Kleen
2019-11-29  6:02   ` [tip: perf/urgent] " tip-bot2 for Andi Kleen
2019-11-21  0:15 ` [PATCH 02/12] perf affinity: Add infrastructure to save/restore affinity Andi Kleen
2019-11-29  6:02   ` [tip: perf/urgent] " tip-bot2 for Andi Kleen
2019-11-21  0:15 ` [PATCH 03/12] perf cpumap: Maintain cpumaps ordered and without dups Andi Kleen
2019-12-04  7:53   ` [tip: perf/urgent] " tip-bot2 for Andi Kleen
2019-11-21  0:15 ` [PATCH 04/12] perf evlist: Maintain evlist->all_cpus Andi Kleen
2019-12-04  7:53   ` tip-bot2 for Andi Kleen [this message]
2019-11-21  0:15 ` [PATCH 05/12] perf evsel: Add iterator to iterate over events ordered by CPU Andi Kleen
2019-12-04  7:53   ` [tip: perf/urgent] " tip-bot2 for Andi Kleen
2019-11-21  0:15 ` [PATCH 06/12] perf evsel: Add functions to close evsel on a CPU Andi Kleen
2019-12-04  7:53   ` [tip: perf/urgent] " tip-bot2 for Andi Kleen
2019-11-21  0:15 ` [PATCH 07/12] perf stat: Use affinity for closing file descriptors Andi Kleen
2019-12-04  7:53   ` [tip: perf/urgent] " tip-bot2 for Andi Kleen
2019-11-21  0:15 ` [PATCH 08/12] perf stat: Factor out open error handling Andi Kleen
2019-12-04  7:53   ` [tip: perf/urgent] " tip-bot2 for Andi Kleen
2019-11-21  0:15 ` [PATCH 09/12] perf stat: Use affinity for opening events Andi Kleen
2019-12-04  7:53   ` [tip: perf/urgent] " tip-bot2 for Andi Kleen
2019-12-18  9:29   ` [perf stat] cc9cdf40ae: perf-sanity-tests.Event_times.fail kernel test robot
2019-11-21  0:15 ` [PATCH 10/12] perf stat: Use affinity for reading Andi Kleen
2019-12-04  7:53   ` [tip: perf/urgent] " tip-bot2 for Andi Kleen
2019-11-21  0:15 ` [PATCH 11/12] perf evsel: Add functions to enable/disable for a specific CPU Andi Kleen
2019-12-04  7:53   ` [tip: perf/urgent] " tip-bot2 for Andi Kleen
2019-11-21  0:15 ` [PATCH 12/12] perf stat: Use affinity for enabling/disabling events Andi Kleen
2019-12-04  7:53   ` [tip: perf/urgent] " tip-bot2 for Andi Kleen
2019-11-21 12:47 ` Optimize perf stat for large number of events/cpus Andi Kleen
2019-11-21 14:32   ` Arnaldo Carvalho de Melo
2019-11-27 15:16 ` Arnaldo Carvalho de Melo
2019-11-27 15:43   ` Arnaldo Carvalho de Melo
2019-11-27 23:26     ` Andi Kleen
2019-11-28  0:01       ` Arnaldo Carvalho de Melo

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=157544603545.21853.16342096532124116230.tip-bot2@tip-bot2 \
    --to=tip-bot2@linutronix.de \
    --cc=acme@redhat.com \
    --cc=ak@linux.intel.com \
    --cc=jolsa@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-tip-commits@vger.kernel.org \
    --cc=x86@kernel.org \
    --subject='Re: [tip: perf/urgent] perf evlist: Maintain evlist->all_cpus' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
on how to clone and mirror all data and code used for this inbox