All of lore.kernel.org
 help / color / mirror / Atom feed
From: Andi Kleen <andi@firstfloor.org>
To: acme@kernel.org
Cc: linux-kernel@vger.kernel.org, jolsa@kernel.org,
	eranian@google.com, kan.liang@linux.intel.com,
	peterz@infradead.org, Andi Kleen <ak@linux.intel.com>
Subject: [PATCH v2 9/9] perf stat: Use affinity for enabling/disabling events
Date: Sun, 20 Oct 2019 10:52:02 -0700	[thread overview]
Message-ID: <20191020175202.32456-10-andi@firstfloor.org> (raw)
In-Reply-To: <20191020175202.32456-1-andi@firstfloor.org>

From: Andi Kleen <ak@linux.intel.com>

Restructure event enabling/disabling to use affinity, which
minimizes the number of IPIs needed.

Before on a large test case with 94 CPUs:

% time     seconds  usecs/call     calls    errors syscall
------ ----------- ----------- --------- --------- ----------------
 54.65    1.899986          22     84812       660 ioctl

after:

 39.21    0.930451          10     84796       644 ioctl

Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/lib/evsel.c              | 49 ++++++++++++++++++++--------
 tools/perf/lib/include/perf/evsel.h |  2 ++
 tools/perf/util/evlist.c            | 50 ++++++++++++++++++++++++++---
 tools/perf/util/evsel.c             | 13 ++++++++
 tools/perf/util/evsel.h             |  2 ++
 5 files changed, 98 insertions(+), 18 deletions(-)

diff --git a/tools/perf/lib/evsel.c b/tools/perf/lib/evsel.c
index ea775dacbd2d..89ddfade0b96 100644
--- a/tools/perf/lib/evsel.c
+++ b/tools/perf/lib/evsel.c
@@ -198,38 +198,61 @@ int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
 }
 
 static int perf_evsel__run_ioctl(struct perf_evsel *evsel,
-				 int ioc,  void *arg)
+				 int ioc,  void *arg,
+				 int cpu)
 {
-	int cpu, thread;
+	int thread;
 
-	for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) {
-		for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {
-			int fd = FD(evsel, cpu, thread),
-			    err = ioctl(fd, ioc, arg);
+	for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {
+		int fd = FD(evsel, cpu, thread),
+		    err = ioctl(fd, ioc, arg);
 
-			if (err)
-				return err;
-		}
+		if (err)
+			return err;
 	}
 
 	return 0;
 }
 
+int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu)
+{
+	return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, 0, cpu);
+}
+
 int perf_evsel__enable(struct perf_evsel *evsel)
 {
-	return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, 0);
+	int i;
+	int err = 0;
+
+	for (i = 0; i < evsel->cpus->nr && !err; i++)
+		err = perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, 0, i);
+	return err;
+}
+
+int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu)
+{
+	return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, 0, cpu);
 }
 
 int perf_evsel__disable(struct perf_evsel *evsel)
 {
-	return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, 0);
+	int i;
+	int err = 0;
+
+	for (i = 0; i < evsel->cpus->nr && !err; i++)
+		err = perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, 0, i);
+	return err;
 }
 
 int perf_evsel__apply_filter(struct perf_evsel *evsel, const char *filter)
 {
-	return perf_evsel__run_ioctl(evsel,
+	int err = 0, i;
+
+	for (i = 0; i < evsel->cpus->nr && !err; i++)
+		err = perf_evsel__run_ioctl(evsel,
 				     PERF_EVENT_IOC_SET_FILTER,
-				     (void *)filter);
+				     (void *)filter, i);
+	return err;
 }
 
 struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel)
diff --git a/tools/perf/lib/include/perf/evsel.h b/tools/perf/lib/include/perf/evsel.h
index ed10a914cd3f..db31e512a120 100644
--- a/tools/perf/lib/include/perf/evsel.h
+++ b/tools/perf/lib/include/perf/evsel.h
@@ -32,7 +32,9 @@ LIBPERF_API void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu);
 LIBPERF_API int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
 				 struct perf_counts_values *count);
 LIBPERF_API int perf_evsel__enable(struct perf_evsel *evsel);
+LIBPERF_API int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu);
 LIBPERF_API int perf_evsel__disable(struct perf_evsel *evsel);
+LIBPERF_API int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu);
 LIBPERF_API struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel);
 LIBPERF_API struct perf_thread_map *perf_evsel__threads(struct perf_evsel *evsel);
 LIBPERF_API struct perf_event_attr *perf_evsel__attr(struct perf_evsel *evsel);
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index bcb8a3670f3f..55f38a71ad30 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -378,26 +378,66 @@ void evlist__cpu_iter_next(struct evsel *ev)
 void evlist__disable(struct evlist *evlist)
 {
 	struct evsel *pos;
+	struct affinity affinity;
+	struct perf_cpu_map *cpus;
+	int i;
 
+	if (affinity__setup(&affinity) < 0)
+		return;
+
+	cpus = evlist__cpu_iter_start(evlist);
+	for (i = 0; i < cpus->nr; i++) {
+		int cpu = cpus->map[i];
+		affinity__set(&affinity, cpu);
+
+		evlist__for_each_entry(evlist, pos) {
+			if (evlist__cpu_iter_skip(pos, cpu))
+				continue;
+			if (pos->disabled || !perf_evsel__is_group_leader(pos) || !pos->core.fd)
+				continue;
+			evsel__disable_cpu(pos, pos->cpu_index);
+			evlist__cpu_iter_next(pos);
+		}
+	}
+	affinity__cleanup(&affinity);
 	evlist__for_each_entry(evlist, pos) {
-		if (pos->disabled || !perf_evsel__is_group_leader(pos) || !pos->core.fd)
+		if (!perf_evsel__is_group_leader(pos) || !pos->core.fd)
 			continue;
-		evsel__disable(pos);
+		pos->disabled = true;
 	}
-
 	evlist->enabled = false;
 }
 
 void evlist__enable(struct evlist *evlist)
 {
 	struct evsel *pos;
+	struct affinity affinity;
+	struct perf_cpu_map *cpus;
+	int i;
+
+	if (affinity__setup(&affinity) < 0)
+		return;
+
+	cpus = evlist__cpu_iter_start(evlist);
+	for (i = 0; i < cpus->nr; i++) {
+		int cpu = cpus->map[i];
+		affinity__set(&affinity, cpu);
 
+		evlist__for_each_entry(evlist, pos) {
+			if (evlist__cpu_iter_skip(pos, cpu))
+				continue;
+			if (!perf_evsel__is_group_leader(pos) || !pos->core.fd)
+				continue;
+			evsel__enable_cpu(pos, pos->cpu_index);
+			evlist__cpu_iter_next(pos);
+		}
+	}
+	affinity__cleanup(&affinity);
 	evlist__for_each_entry(evlist, pos) {
 		if (!perf_evsel__is_group_leader(pos) || !pos->core.fd)
 			continue;
-		evsel__enable(pos);
+		pos->disabled = false;
 	}
-
 	evlist->enabled = true;
 }
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 7106f9a067df..79050a6f4991 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1205,13 +1205,26 @@ int perf_evsel__append_addr_filter(struct evsel *evsel, const char *filter)
 	return perf_evsel__append_filter(evsel, "%s,%s", filter);
 }
 
+/* Caller has to clear disabled after going through all CPUs. */
+int evsel__enable_cpu(struct evsel *evsel, int cpu)
+{
+	int err = perf_evsel__enable_cpu(&evsel->core, cpu);
+	return err;
+}
+
 int evsel__enable(struct evsel *evsel)
 {
 	int err = perf_evsel__enable(&evsel->core);
 
 	if (!err)
 		evsel->disabled = false;
+	return err;
+}
 
+/* Caller has to set disabled after going through all CPUs. */
+int evsel__disable_cpu(struct evsel *evsel, int cpu)
+{
+	int err = perf_evsel__disable_cpu(&evsel->core, cpu);
 	return err;
 }
 
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 9fc9f6698aa4..15977bbe7b63 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -222,8 +222,10 @@ int perf_evsel__set_filter(struct evsel *evsel, const char *filter);
 int perf_evsel__append_tp_filter(struct evsel *evsel, const char *filter);
 int perf_evsel__append_addr_filter(struct evsel *evsel,
 				   const char *filter);
+int evsel__enable_cpu(struct evsel *evsel, int cpu);
 int evsel__enable(struct evsel *evsel);
 int evsel__disable(struct evsel *evsel);
+int evsel__disable_cpu(struct evsel *evsel, int cpu);
 
 int perf_evsel__open_per_cpu(struct evsel *evsel,
 			     struct perf_cpu_map *cpus,
-- 
2.21.0


  parent reply	other threads:[~2019-10-20 17:52 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-10-20 17:51 Optimize perf stat for large number of events/cpus v2 Andi Kleen
2019-10-20 17:51 ` [PATCH v2 1/9] perf evsel: Always preserve errno while cleaning up perf_event_open failures Andi Kleen
2019-10-22  8:01   ` Jiri Olsa
2019-11-12 11:18   ` [tip: perf/core] " tip-bot2 for Andi Kleen
2019-10-20 17:51 ` [PATCH v2 2/9] perf evsel: Avoid close(-1) Andi Kleen
2019-10-22  8:01   ` Jiri Olsa
2019-11-12 11:18   ` [tip: perf/core] " tip-bot2 for Andi Kleen
2019-10-20 17:51 ` [PATCH v2 3/9] perf pmu: Use file system cache to optimize sysfs access Andi Kleen
2019-10-23  9:47   ` Jiri Olsa
2019-10-20 17:51 ` [PATCH v2 4/9] perf affinity: Add infrastructure to save/restore affinity Andi Kleen
2019-10-23  9:59   ` Jiri Olsa
2019-10-23 13:02     ` Andi Kleen
2019-10-23 14:30       ` Jiri Olsa
2019-10-23 14:52         ` Andi Kleen
2019-10-23 16:16           ` Alexey Budankov
2019-10-23 17:19             ` Andi Kleen
2019-10-23 18:08               ` Alexey Budankov
2019-10-23 22:37                 ` Andi Kleen
2019-10-24  8:46                   ` Alexey Budankov
2019-10-20 17:51 ` [PATCH v2 5/9] perf evsel: Add iterator to iterate over events ordered by CPU Andi Kleen
2019-10-20 17:51 ` [PATCH v2 6/9] perf stat: Use affinity for closing file descriptors Andi Kleen
2019-10-20 17:52 ` [PATCH v2 7/9] perf stat: Use affinity for opening events Andi Kleen
2019-10-20 17:52 ` [PATCH v2 8/9] perf stat: Use affinity for reading Andi Kleen
2019-10-20 17:52 ` Andi Kleen [this message]
2019-10-23 10:30   ` [PATCH v2 9/9] perf stat: Use affinity for enabling/disabling events Jiri Olsa
2019-10-23 13:07     ` Andi Kleen
2019-10-22  8:02 ` Optimize perf stat for large number of events/cpus v2 Jiri Olsa
2019-10-22 14:11   ` 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=20191020175202.32456-10-andi@firstfloor.org \
    --to=andi@firstfloor.org \
    --cc=acme@kernel.org \
    --cc=ak@linux.intel.com \
    --cc=eranian@google.com \
    --cc=jolsa@kernel.org \
    --cc=kan.liang@linux.intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=peterz@infradead.org \
    /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
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.