linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Namhyung Kim <namhyung@kernel.org>
To: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Ingo Molnar <mingo@kernel.org>,
	Peter Zijlstra <a.p.zijlstra@chello.nl>,
	Jiri Olsa <jolsa@redhat.com>, LKML <linux-kernel@vger.kernel.org>,
	David Ahern <dsahern@gmail.com>,
	Frederic Weisbecker <fweisbec@gmail.com>,
	Andi Kleen <andi@firstfloor.org>,
	Stephane Eranian <eranian@google.com>,
	Adrian Hunter <adrian.hunter@intel.com>
Subject: [PATCH/RFC 15/16] perf top: Add --num-thread option
Date: Thu, 10 Dec 2015 16:53:34 +0900	[thread overview]
Message-ID: <1449734015-9148-16-git-send-email-namhyung@kernel.org> (raw)
In-Reply-To: <1449734015-9148-1-git-send-email-namhyung@kernel.org>

The --num-thread option is to set number of reader thread.  Default
value is 0 which will be converted to 1/4 of number of mmaps.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/builtin-top.c | 49 +++++++++++++++++++++++++++++++++++-------------
 tools/perf/util/top.h    |  1 +
 2 files changed, 37 insertions(+), 13 deletions(-)

diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index f3ab46b234b6..fc9715b046b3 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -838,10 +838,10 @@ struct collector_arg {
 
 static void collect_hists(struct perf_top *top, struct hists *hists)
 {
-	int i, k;
+	unsigned int i, k;
 	struct perf_evsel *evsel;
 
-	for (i = 0, k = 0; i < top->evlist->nr_mmaps; i++) {
+	for (i = 0, k = 0; i < top->nr_threads; i++) {
 		evlist__for_each(top->evlist, evsel) {
 			struct hists *src_hists = &hists[k++];
 			struct hists *dst_hists = evsel__hists(evsel);
@@ -900,6 +900,7 @@ static int hist_iter__top_callback(struct hist_entry_iter *iter,
 
 struct reader_arg {
 	int			idx;
+	int			nr_idx;
 	struct perf_top		*top;
 	struct hists		*hists;
 	struct perf_top_stats	stats;
@@ -993,7 +994,7 @@ static void perf_event__process_sample(struct reader_arg *rarg,
 	addr_location__put(&al);
 }
 
-static void perf_top__mmap_read(struct reader_arg *rarg)
+static void perf_top__mmap_read_idx(struct reader_arg *rarg, int idx)
 {
 	struct perf_sample sample;
 	struct perf_evsel *evsel;
@@ -1001,7 +1002,6 @@ static void perf_top__mmap_read(struct reader_arg *rarg)
 	struct perf_session *session = top->session;
 	union perf_event *event;
 	struct machine *machine;
-	int idx = rarg->idx;
 	u8 origin;
 	int ret;
 
@@ -1067,6 +1067,14 @@ static void perf_top__mmap_read(struct reader_arg *rarg)
 	}
 }
 
+static void perf_top__mmap_read(struct reader_arg *rarg)
+{
+	int i;
+
+	for (i = 0; i < rarg->nr_idx; i++)
+		perf_top__mmap_read_idx(rarg, rarg->idx + i);
+}
+
 static void *mmap_read_worker(void *arg)
 {
 	struct reader_arg *rarg = arg;
@@ -1160,7 +1168,8 @@ static int __cmd_top(struct perf_top *top)
 	struct reader_arg *rargs = NULL;
 	struct collector_arg carg;
 	int ret;
-	int i;
+	unsigned int i;
+	int idx, nr_idx, rem;
 
 	top->session = perf_session__new(NULL, false, NULL);
 	if (top->session == NULL)
@@ -1211,34 +1220,47 @@ static int __cmd_top(struct perf_top *top)
 	/* Wait for a minimal set of events before starting the snapshot */
 	perf_evlist__poll(top->evlist, 100);
 
+	if (top->nr_threads == 0)
+		top->nr_threads = top->evlist->nr_mmaps / 4 ?: 1;
+	if ((int)top->nr_threads > top->evlist->nr_mmaps)
+		top->nr_threads = top->evlist->nr_mmaps;
+
+	nr_idx = top->evlist->nr_mmaps / top->nr_threads;
+	rem = top->evlist->nr_mmaps % top->nr_threads;
+
 	ret = -1;
-	readers = calloc(sizeof(pthread_t), top->evlist->nr_mmaps);
+	readers = calloc(sizeof(pthread_t), top->nr_threads);
 	if (readers == NULL)
 		goto out_delete;
 
-	rargs = calloc(sizeof(*rargs), top->evlist->nr_mmaps);
+	rargs = calloc(sizeof(*rargs), top->nr_threads);
 	if (rargs == NULL)
 		goto out_free;
 
-	hists = calloc(sizeof(*hists), top->evlist->nr_mmaps * top->evlist->nr_entries);
+	hists = calloc(sizeof(*hists), top->nr_threads * top->evlist->nr_entries);
 	if (hists == NULL)
 		goto out_free;
 
-	for (i = 0; i < top->evlist->nr_mmaps * top->evlist->nr_entries; i++)
+	for (i = 0; i < top->nr_threads * top->evlist->nr_entries; i++)
 		__hists__init(&hists[i]);
 
-	for (i = 0; i < top->evlist->nr_mmaps; i++) {
+	for (i = 0, idx = 0; i < top->nr_threads; i++) {
 		struct reader_arg *rarg = &rargs[i];
 
-		rarg->idx = i;
 		rarg->top = top;
 		rarg->hists = &hists[i * top->evlist->nr_entries];
 
+		rarg->idx = idx;
+		rarg->nr_idx = nr_idx;
+		if (rem-- > 0)
+			rarg->nr_idx++;
+		idx += rarg->nr_idx;
+
 		perf_top__mmap_read(rarg);
 	}
 	collect_hists(top, hists);
 
-	for (i = 0; i < top->evlist->nr_mmaps; i++) {
+	for (i = 0; i < top->nr_threads; i++) {
 		if (pthread_create(&readers[i], NULL, mmap_read_worker, &rargs[i]))
 			goto out_join;
 	}
@@ -1259,7 +1281,7 @@ static int __cmd_top(struct perf_top *top)
 out_join:
 	pthread_join(ui_thread, NULL);
 	pthread_join(collector, NULL);
-	for (i = 0; i < top->evlist->nr_mmaps; i++) {
+	for (i = 0; i < top->nr_threads; i++) {
 		pthread_join(readers[i], NULL);
 	}
 
@@ -1458,6 +1480,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_CALLBACK('j', "branch-filter", &opts->branch_stack,
 		     "branch filter mask", "branch stack filter modes",
 		     parse_branch_stack),
+	OPT_UINTEGER(0, "num-thread", &top.nr_threads, "number of thread to run"),
 	OPT_END()
 	};
 	const char * const top_usage[] = {
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index 55eb5aebae59..916ba36b0ac0 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -43,6 +43,7 @@ struct perf_top {
 	int		   sym_pcnt_filter;
 	const char	   *sym_filter;
 	float		   min_percent;
+	unsigned int	   nr_threads;
 };
 
 #define CONSOLE_CLEAR "^[[H^[[2J"
-- 
2.6.2


  parent reply	other threads:[~2015-12-10  7:54 UTC|newest]

Thread overview: 55+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-12-10  7:53 [PATCHSET 00/16] perf top: Add multi-thread support (v1) Namhyung Kim
2015-12-10  7:53 ` [PATCH/RFC 01/16] perf top: Delete half-processed hist entries when exit Namhyung Kim
2015-12-10  9:55   ` 平松雅巳 / HIRAMATU,MASAMI
2015-12-10 18:57     ` Arnaldo Carvalho de Melo
2015-12-14  8:15   ` [tip:perf/core] " tip-bot for Namhyung Kim
2015-12-10  7:53 ` [PATCH/RFC 02/16] perf top: Fix and cleanup perf_top__record_precise_ip() Namhyung Kim
2015-12-10 19:04   ` Arnaldo Carvalho de Melo
2015-12-11  2:27     ` Namhyung Kim
2015-12-10  7:53 ` [PATCH/RFC 03/16] perf top: Factor out warnings about kernel addresses and symbols Namhyung Kim
2015-12-10 19:07   ` Arnaldo Carvalho de Melo
2015-12-14  1:44     ` Namhyung Kim
2015-12-14  2:02       ` Namhyung Kim
2015-12-10  7:53 ` [PATCH/RFC 04/16] perf top: Factor out warnings in perf_top__record_precise_ip() Namhyung Kim
2015-12-10  7:53 ` [PATCH/RFC 05/16] perf top: Show warning messages in the display thread Namhyung Kim
2015-12-10  7:53 ` [PATCH/RFC 06/16] perf top: Get rid of access to hists->lock in perf_top__record_precise_ip() Namhyung Kim
2015-12-10  7:53 ` [PATCH/RFC 07/16] perf hists: Pass hists struct to hist_entry_iter struct Namhyung Kim
2015-12-13 23:15   ` Jiri Olsa
2015-12-14  1:45     ` Namhyung Kim
2015-12-10  7:53 ` [PATCH/RFC 08/16] perf tools: Export a couple of hist functions Namhyung Kim
2015-12-13 23:17   ` Jiri Olsa
2015-12-10  7:53 ` [PATCH/RFC 09/16] perf tools: Update hist entry's hists pointer Namhyung Kim
2015-12-13 23:23   ` Jiri Olsa
2015-12-13 23:28     ` Jiri Olsa
2015-12-14  1:51       ` Namhyung Kim
2015-12-10  7:53 ` [PATCH/RFC 10/16] perf hist: Add events_stats__add() and hists__add_stats() Namhyung Kim
2015-12-10  7:53 ` [PATCH/RFC 11/16] perf top: Implement basic parallel processing Namhyung Kim
2015-12-14  9:23   ` Jiri Olsa
2015-12-14  9:35     ` Jiri Olsa
2015-12-15  2:08       ` Namhyung Kim
2015-12-10  7:53 ` [PATCH/RFC 12/16] perf tools: Reduce lock contention when processing events Namhyung Kim
2015-12-14  8:43   ` Jiri Olsa
2015-12-15  2:03     ` Namhyung Kim
2015-12-10  7:53 ` [PATCH/RFC 13/16] perf top: Protect the seen list using mutex Namhyung Kim
2015-12-10  7:53 ` [PATCH/RFC 14/16] perf top: Separate struct perf_top_stats Namhyung Kim
2015-12-10  7:53 ` Namhyung Kim [this message]
2015-12-10  7:53 ` [PATCH/RFC 16/16] perf tools: Skip dso front cache for multi-threaded lookup Namhyung Kim
2015-12-10  8:01 ` [PATCHSET 00/16] perf top: Add multi-thread support (v1) Ingo Molnar
2015-12-10  8:49   ` Namhyung Kim
2015-12-11  8:11     ` Ingo Molnar
2015-12-11 15:01       ` David Ahern
2015-12-14  1:12         ` Namhyung Kim
2015-12-14  9:26         ` Peter Zijlstra
2015-12-14  9:38           ` Ingo Molnar
2015-12-14 14:55             ` David Ahern
2015-12-14 16:26               ` Arnaldo Carvalho de Melo
2015-12-14 16:41                 ` Peter Zijlstra
2015-12-14 17:52                   ` Arnaldo Carvalho de Melo
2015-12-14 16:38             ` Namhyung Kim
2015-12-14 16:56               ` Peter Zijlstra
2015-12-14 17:11                 ` Namhyung Kim
2015-12-14 14:46           ` David Ahern
2015-12-14 17:06             ` Namhyung Kim
2015-12-14 17:54               ` Arnaldo Carvalho de Melo
2015-12-14 16:25           ` Namhyung Kim
2015-12-14 16:44             ` Peter Zijlstra

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=1449734015-9148-16-git-send-email-namhyung@kernel.org \
    --to=namhyung@kernel.org \
    --cc=a.p.zijlstra@chello.nl \
    --cc=acme@kernel.org \
    --cc=adrian.hunter@intel.com \
    --cc=andi@firstfloor.org \
    --cc=dsahern@gmail.com \
    --cc=eranian@google.com \
    --cc=fweisbec@gmail.com \
    --cc=jolsa@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.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 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).