LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Riccardo Mancini <rickyman7@gmail.com>
To: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Ian Rogers <irogers@google.com>,
	Namhyung Kim <namhyung@kernel.org>,
	Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	Mark Rutland <mark.rutland@arm.com>, Jiri Olsa <jolsa@redhat.com>,
	linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org,
	Riccardo Mancini <rickyman7@gmail.com>
Subject: [RFC PATCH v1 28/37] perf evlist: add multithreading to evlist__open
Date: Sat, 21 Aug 2021 11:19:34 +0200	[thread overview]
Message-ID: <313458a08272272b00efa6b5581a1cdbaca0ef84.1629490974.git.rickyman7@gmail.com> (raw)
In-Reply-To: <cover.1629490974.git.rickyman7@gmail.com>

This patch enables multithreading in evlist__open using the new
evsel__open_per_cpu_no_fallback function.

The multithreaded version tries to open everything in parallel. Once
workers are done, it checks their result and, in case of error, it
tries the fallback mechanisms present in evsel__open_cpu and restarts
the workers from were they've left.

Signed-off-by: Riccardo Mancini <rickyman7@gmail.com>
---
 tools/perf/util/evlist.c | 189 +++++++++++++++++++++++++++++++++++++--
 1 file changed, 183 insertions(+), 6 deletions(-)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index f0a839107e8849bf..3472038d719ec7d4 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -19,6 +19,8 @@
 #include "units.h"
 #include "bpf_counter.h"
 #include <internal/lib.h> // page_size
+#include <internal/cpumap.h>
+#include <internal/threadmap.h>
 #include "affinity.h"
 #include "../perf.h"
 #include "asm/bug.h"
@@ -1403,11 +1405,184 @@ static int evlist__create_syswide_maps(struct evlist *evlist)
 	return err;
 }
 
-int evlist__open(struct evlist *evlist)
+static int evlist__open_singlethreaded(struct evlist *evlist)
 {
 	struct evsel *evsel;
 	int err;
 
+	evlist__for_each_entry(evlist, evsel) {
+		err = evsel__open(evsel, evsel->core.cpus, evsel->core.threads);
+		if (err < 0)
+			return err;
+	}
+
+	return 0;
+}
+
+struct evlist_open_work {
+	struct work_struct work;
+	struct evlist *evlist;
+	int cpu;
+	union {
+		int cpu_resume;
+		int cpu_err;
+	};
+	union {
+		struct evsel *evsel_resume;
+		struct evsel *evsel_err;
+	};
+	struct evsel_open_result res;	// this is also used to resume work
+	bool progress;			// did the worker do any progress?
+};
+
+static void evlist__open_multithreaded_func(struct work_struct *_work)
+{
+	struct evlist_open_work *work = container_of(_work, struct evlist_open_work, work);
+	struct evsel *evsel = work->evsel_resume;
+	int cpu_idx, thread_resume = work->res.thread;
+
+	work->res.peo_res.err = PEO_SUCCESS;
+	work->progress = false;
+
+	if (!evsel)	// nothing to do
+		return;
+
+	work->evsel_err = NULL;
+
+	evlist__for_each_entry_from(work->evlist, evsel) {
+		cpu_idx = evsel__find_cpu(evsel, work->cpu);
+		if (cpu_idx < work->cpu_resume)
+			continue;
+
+		work->res = evsel__open_per_cpu_no_fallback(evsel,
+					evsel->core.cpus,
+					evsel->core.threads,
+					cpu_idx, thread_resume);
+		work->progress |= work->res.thread != thread_resume;
+		if (work->res.peo_res.err != PEO_SUCCESS) {
+			work->evsel_err = evsel;
+			work->cpu_err = cpu_idx;
+			break;
+		}
+
+		thread_resume = 0;
+	}
+}
+
+static int evlist__open_multithreaded(struct evlist *evlist)
+{
+	int cpu, cpuid, cpuidx, thread, err;
+	struct evlist_open_work *works;
+	char errbuf[WORKQUEUE_STRERR_BUFSIZE];
+	struct perf_event_open_result peo_res;
+	struct evsel *evsel;
+	struct perf_cpu_map *cpus;
+	struct perf_thread_map *threads;
+	enum rlimit_action set_rlimit = NO_CHANGE;
+	bool progress;
+
+	works = calloc(perf_cpu_map__nr(evlist->core.all_cpus), sizeof(*works));
+	if (!works)
+		return -ENOMEM;
+
+	perf_cpu_map__for_each_cpu(cpuid, cpuidx, evlist->core.all_cpus) {
+		init_work(&works[cpuidx].work);
+		works[cpuidx].work.func = evlist__open_multithreaded_func;
+		works[cpuidx].evlist = evlist;
+		works[cpuidx].cpu = cpuid;
+		works[cpuidx].evsel_resume = evlist__first(evlist);
+	}
+
+reprepare:
+	evlist__for_each_entry(evlist, evsel) {
+		err = evsel__prepare_open(evsel, evsel->core.cpus,
+				evsel->core.threads);
+		if (err)
+			goto out;
+	}
+retry:
+	perf_cpu_map__for_each_cpu(cpuid, cpuidx, evlist->core.all_cpus) {
+		err = schedule_work_on(cpuid, &works[cpuidx].work);
+		if (err) {
+			workqueue_strerror(global_wq, err, errbuf, sizeof(errbuf));
+			pr_debug("schedule_work: %s\n", errbuf);
+			goto out;
+		}
+	}
+
+	err = flush_scheduled_work();
+	if (err) {
+		workqueue_strerror(global_wq, err, errbuf, sizeof(errbuf));
+		pr_debug("flush_scheduled_work: %s\n", errbuf);
+		goto out;
+	}
+
+	// check if any event was opened (progress = true)
+	progress = false;
+	perf_cpu_map__for_each_cpu(cpuid, cpuidx, evlist->core.all_cpus) {
+		if (works[cpuidx].progress) {
+			progress = true;
+			break;
+		}
+	}
+
+	perf_cpu_map__for_each_cpu(cpuid, cpuidx, evlist->core.all_cpus) {
+		peo_res = works[cpuidx].res.peo_res;
+
+		switch (peo_res.err) {
+		case PEO_SUCCESS:
+			continue;
+		case PEO_FALLBACK:
+			err = peo_res.rc;
+			break;
+		default:
+		case PEO_ERROR:
+			err = peo_res.rc;
+			goto out;
+		}
+
+		// fallback
+		evsel = works[cpuidx].evsel_err;
+		cpus = evsel->core.cpus;
+		cpu = works[cpuidx].cpu_err;
+		threads = evsel->core.threads;
+		thread = works[cpuidx].res.thread;
+
+		if (evsel__precise_ip_fallback(evsel))
+			goto retry;
+
+		if (evsel__ignore_missing_thread(evsel, cpus->nr, cpu,
+						threads, thread, err))
+			goto retry;
+
+		// increase rlimit only if no progress was made
+		if (progress)
+			set_rlimit = NO_CHANGE;
+		if (err == -EMFILE && evsel__increase_rlimit(&set_rlimit))
+			goto retry;
+
+		if (err != -EINVAL || cpu > 0 || thread > 0)
+			goto out;
+
+		if (evsel__detect_missing_features(evsel))
+			goto reprepare;
+
+		// no fallback worked, return the error
+		goto out;
+	}
+
+	err = 0;
+
+out:
+	free(works);
+
+	return err;
+}
+
+int evlist__open(struct evlist *evlist)
+{
+	int err;
+
 	/*
 	 * Default: one fd per CPU, all threads, aka systemwide
 	 * as sys_perf_event_open(cpu = -1, thread = -1) is EINVAL
@@ -1420,11 +1595,13 @@ int evlist__open(struct evlist *evlist)
 
 	evlist__update_id_pos(evlist);
 
-	evlist__for_each_entry(evlist, evsel) {
-		err = evsel__open(evsel, evsel->core.cpus, evsel->core.threads);
-		if (err < 0)
-			goto out_err;
-	}
+	if (perf_singlethreaded)
+		err = evlist__open_singlethreaded(evlist);
+	else
+		err = evlist__open_multithreaded(evlist);
+
+	if (err)
+		goto out_err;
 
 	return 0;
 out_err:
-- 
2.31.1


  parent reply	other threads:[~2021-08-21  9:22 UTC|newest]

Thread overview: 63+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-08-21  9:19 [RFC PATCH v1 00/37] perf: use workqueue for evlist operations Riccardo Mancini
2021-08-21  9:19 ` [RFC PATCH v1 01/37] libperf cpumap: improve idx function Riccardo Mancini
2021-08-31 18:46   ` Arnaldo Carvalho de Melo
2021-10-08 14:29   ` Arnaldo Carvalho de Melo
2021-08-21  9:19 ` [RFC PATCH v1 02/37] libperf cpumap: improve max function Riccardo Mancini
2021-08-31 18:47   ` Arnaldo Carvalho de Melo
2021-08-31 19:16     ` Arnaldo Carvalho de Melo
2021-08-21  9:19 ` [RFC PATCH v1 03/37] perf evlist: replace evsel__cpu_iter* functions with evsel__find_cpu Riccardo Mancini
2021-10-08 14:38   ` [RFC PATCH v1 03/37] perf evlist: replace evsel__cpu_iter* functions with evsel__find_cpu() Arnaldo Carvalho de Melo
2021-12-11  0:20   ` [RFC PATCH v1 03/37] perf evlist: replace evsel__cpu_iter* functions with evsel__find_cpu Ian Rogers
2021-08-21  9:19 ` [RFC PATCH v1 04/37] perf util: add mmap_cpu_mask__duplicate function Riccardo Mancini
2021-08-31 19:21   ` Arnaldo Carvalho de Melo
2021-08-21  9:19 ` [RFC PATCH v1 05/37] perf util/mmap: add missing bitops.h header Riccardo Mancini
2021-08-31 19:22   ` Arnaldo Carvalho de Melo
2021-08-21  9:19 ` [RFC PATCH v1 06/37] perf workqueue: add affinities to threadpool Riccardo Mancini
2021-08-21  9:19 ` [RFC PATCH v1 07/37] perf workqueue: add support for setting affinities to workers Riccardo Mancini
2021-08-21  9:19 ` [RFC PATCH v1 08/37] perf workqueue: add method to execute work on specific CPU Riccardo Mancini
2021-08-21  9:19 ` [RFC PATCH v1 09/37] perf python: add workqueue dependency Riccardo Mancini
2021-08-21  9:19 ` [RFC PATCH v1 10/37] perf evlist: add multithreading helper Riccardo Mancini
2021-08-21  9:19 ` [RFC PATCH v1 11/37] perf evlist: add multithreading to evlist__disable Riccardo Mancini
2021-08-21  9:19 ` [RFC PATCH v1 12/37] perf evlist: add multithreading to evlist__enable Riccardo Mancini
2021-08-21  9:19 ` [RFC PATCH v1 13/37] perf evlist: add multithreading to evlist__close Riccardo Mancini
2021-08-21  9:19 ` [RFC PATCH v1 14/37] perf evsel: remove retry_sample_id goto label Riccardo Mancini
2021-08-31 19:25   ` Arnaldo Carvalho de Melo
2021-08-21  9:19 ` [RFC PATCH v1 15/37] perf evsel: separate open preparation from open itself Riccardo Mancini
2021-08-31 19:27   ` Arnaldo Carvalho de Melo
2021-08-21  9:19 ` [RFC PATCH v1 16/37] perf evsel: save open flags in evsel Riccardo Mancini
2021-08-31 19:31   ` Arnaldo Carvalho de Melo
2021-08-21  9:19 ` [RFC PATCH v1 17/37] perf evsel: separate missing feature disabling from evsel__open_cpu Riccardo Mancini
2021-08-31 19:35   ` Arnaldo Carvalho de Melo
2021-08-21  9:19 ` [RFC PATCH v1 18/37] perf evsel: add evsel__prepare_open function Riccardo Mancini
2021-08-31 19:36   ` Arnaldo Carvalho de Melo
2021-08-21  9:19 ` [RFC PATCH v1 19/37] perf evsel: separate missing feature detection from evsel__open_cpu Riccardo Mancini
2021-08-31 19:39   ` Arnaldo Carvalho de Melo
2021-08-21  9:19 ` [RFC PATCH v1 20/37] perf evsel: separate rlimit increase " Riccardo Mancini
2021-08-31 19:41   ` Arnaldo Carvalho de Melo
2021-08-21  9:19 ` [RFC PATCH v1 21/37] perf evsel: move ignore_missing_thread to fallback code Riccardo Mancini
2021-08-31 19:44   ` Arnaldo Carvalho de Melo
2021-08-21  9:19 ` [RFC PATCH v1 22/37] perf evsel: move test_attr__open to success path in evsel__open_cpu Riccardo Mancini
2021-08-31 19:47   ` Arnaldo Carvalho de Melo
2021-08-21  9:19 ` [RFC PATCH v1 23/37] perf evsel: move bpf_counter__install_pe " Riccardo Mancini
2021-08-31 19:50   ` Arnaldo Carvalho de Melo
2021-08-21  9:19 ` [RFC PATCH v1 24/37] perf evsel: handle precise_ip fallback " Riccardo Mancini
2021-08-31 19:52   ` Arnaldo Carvalho de Melo
2021-08-21  9:19 ` [RFC PATCH v1 25/37] perf evsel: move event open in evsel__open_cpu to separate function Riccardo Mancini
2021-08-31 19:54   ` Arnaldo Carvalho de Melo
2021-09-03 21:52     ` Riccardo Mancini
2021-09-11 19:10       ` Arnaldo Carvalho de Melo
2021-08-21  9:19 ` [RFC PATCH v1 26/37] perf evsel: add evsel__open_per_cpu_no_fallback function Riccardo Mancini
2021-08-21  9:19 ` [RFC PATCH v1 27/37] perf evlist: add evlist__for_each_entry_from macro Riccardo Mancini
2021-08-31 20:06   ` Arnaldo Carvalho de Melo
2021-08-21  9:19 ` Riccardo Mancini [this message]
2021-08-21  9:19 ` [RFC PATCH v1 29/37] perf evlist: add custom fallback to evlist__open Riccardo Mancini
2021-08-21  9:19 ` [RFC PATCH v1 30/37] perf record: use evlist__open_custom Riccardo Mancini
2021-08-21  9:19 ` [RFC PATCH v1 31/37] tools lib/subcmd: add OPT_UINTEGER_OPTARG option type Riccardo Mancini
2021-08-31 18:44   ` Arnaldo Carvalho de Melo
2021-08-21  9:19 ` [RFC PATCH v1 32/37] perf record: add --threads option Riccardo Mancini
2021-08-21  9:19 ` [RFC PATCH v1 33/37] perf record: pin threads to monitored cpus if enough threads available Riccardo Mancini
2021-08-21  9:19 ` [RFC PATCH v1 34/37] perf record: apply multithreading in init and fini phases Riccardo Mancini
2021-08-21  9:19 ` [RFC PATCH v1 35/37] perf test/evlist-open-close: add multithreading Riccardo Mancini
2021-08-21  9:19 ` [RFC PATCH v1 36/37] perf test/evlist-open-close: use inline func to convert timeval to usec Riccardo Mancini
2021-10-08 14:46   ` Arnaldo Carvalho de Melo
2021-08-21  9:19 ` [RFC PATCH v1 37/37] perf test/evlist-open-close: add detailed output mode Riccardo Mancini

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=313458a08272272b00efa6b5581a1cdbaca0ef84.1629490974.git.rickyman7@gmail.com \
    --to=rickyman7@gmail.com \
    --cc=acme@kernel.org \
    --cc=irogers@google.com \
    --cc=jolsa@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=mingo@redhat.com \
    --cc=namhyung@kernel.org \
    --cc=peterz@infradead.org \
    --subject='Re: [RFC PATCH v1 28/37] perf evlist: add multithreading to evlist__open' \
    /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
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).