linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Namhyung Kim <namhyung@kernel.org>
To: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>,
	Jiri Olsa <jolsa@redhat.com>,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	linux-kernel <linux-kernel@vger.kernel.org>,
	Andi Kleen <ak@linux.intel.com>,
	Adrian Hunter <adrian.hunter@intel.com>,
	Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com>,
	Alexander Antonov <alexander.antonov@linux.intel.com>
Subject: Re: [PATCH v3 07/12] perf record: init data file at mmap buffer object
Date: Fri, 20 Nov 2020 19:49:42 +0900	[thread overview]
Message-ID: <20201120104942.GF94830@google.com> (raw)
In-Reply-To: <ad205903-41a6-5041-f4f3-6f57d83cbd3a@linux.intel.com>

On Mon, Nov 16, 2020 at 03:19:41PM +0300, Alexey Budankov wrote:
> 
> Initialize data files located at mmap buffer objects so trace data
> can be written into several data file located at data directory.
> 
> Signed-off-by: Alexey Budankov <alexey.budankov@linux.intel.com>
> ---
>  tools/perf/builtin-record.c | 41 ++++++++++++++++++++++++++++++-------
>  tools/perf/util/record.h    |  1 +
>  2 files changed, 35 insertions(+), 7 deletions(-)
> 
> diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
> index 779676531edf..f5e5175da6a1 100644
> --- a/tools/perf/builtin-record.c
> +++ b/tools/perf/builtin-record.c
> @@ -158,6 +158,11 @@ static const char *affinity_tags[PERF_AFFINITY_MAX] = {
>  	"SYS", "NODE", "CPU"
>  };
>  
> +static int record__threads_enabled(struct record *rec)
> +{
> +	return rec->opts.threads_spec;
> +}
> +
>  static bool switch_output_signal(struct record *rec)
>  {
>  	return rec->switch_output.signal &&
> @@ -1060,7 +1065,7 @@ static int record__free_thread_data(struct record *rec)
>  static int record__mmap_evlist(struct record *rec,
>  			       struct evlist *evlist)
>  {
> -	int ret;
> +	int i, ret;
>  	struct record_opts *opts = &rec->opts;
>  	bool auxtrace_overwrite = opts->auxtrace_snapshot_mode ||
>  				  opts->auxtrace_sample_mode;
> @@ -1099,6 +1104,18 @@ static int record__mmap_evlist(struct record *rec,
>  	if (ret)
>  		return ret;
>  
> +	if (record__threads_enabled(rec)) {
> +		ret = perf_data__create_dir(&rec->data, evlist->core.nr_mmaps);
> +		if (ret)
> +			return ret;
> +		for (i = 0; i < evlist->core.nr_mmaps; i++) {
> +			if (evlist->mmap)
> +				evlist->mmap[i].file = &rec->data.dir.files[i];
> +			if (evlist->overwrite_mmap)
> +				evlist->overwrite_mmap[i].file = &rec->data.dir.files[i];
> +		}
> +	}
> +
>  	return 0;
>  }
>  
> @@ -1400,8 +1417,12 @@ static int record__mmap_read_evlist(struct record *rec, struct evlist *evlist,
>  	/*
>  	 * Mark the round finished in case we wrote
>  	 * at least one event.
> +	 *
> +	 * No need for round events in directory mode,
> +	 * because per-cpu maps and files have data
> +	 * sorted by kernel.

But it's not just for single cpu since task can migrate so we need to
look at other cpu's data too.  Thus we use the ordered events queue
and round events help to determine when to flush the data.  Without
the round events, it'd consume huge amount of memory during report.

If we separate tracking records and process them first, we should be
able to process samples immediately without sorting them in the
ordered event queue.  This will save both cpu cycles and memory
footprint significantly IMHO.

Thanks,
Namhyung


>  	 */
> -	if (bytes_written != rec->bytes_written)
> +	if (!record__threads_enabled(rec) && bytes_written != rec->bytes_written)
>  		rc = record__write(rec, NULL, &finished_round_event, sizeof(finished_round_event));
>  
>  	if (overwrite)
> @@ -1514,7 +1535,9 @@ static void record__init_features(struct record *rec)
>  	if (!rec->opts.use_clockid)
>  		perf_header__clear_feat(&session->header, HEADER_CLOCK_DATA);
>  
> -	perf_header__clear_feat(&session->header, HEADER_DIR_FORMAT);
> +	if (!record__threads_enabled(rec))
> +		perf_header__clear_feat(&session->header, HEADER_DIR_FORMAT);
> +
>  	if (!record__comp_enabled(rec))
>  		perf_header__clear_feat(&session->header, HEADER_COMPRESSED);
>  
> @@ -1525,15 +1548,21 @@ static void
>  record__finish_output(struct record *rec)
>  {
>  	struct perf_data *data = &rec->data;
> -	int fd = perf_data__fd(data);
> +	int i, fd = perf_data__fd(data);
>  
>  	if (data->is_pipe)
>  		return;
>  
>  	rec->session->header.data_size += rec->bytes_written;
>  	data->file.size = lseek(perf_data__fd(data), 0, SEEK_CUR);
> +	if (record__threads_enabled(rec)) {
> +		for (i = 0; i < data->dir.nr; i++)
> +			data->dir.files[i].size = lseek(data->dir.files[i].fd, 0, SEEK_CUR);
> +	}
>  
>  	if (!rec->no_buildid) {
> +		/* this will be recalculated during process_buildids() */
> +		rec->samples = 0;
>  		process_buildids(rec);
>  
>  		if (rec->buildid_all)
> @@ -2438,8 +2467,6 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
>  		status = err;
>  
>  	record__synthesize(rec, true);
> -	/* this will be recalculated during process_buildids() */
> -	rec->samples = 0;
>  
>  	if (!err) {
>  		if (!rec->timestamp_filename) {
> @@ -3179,7 +3206,7 @@ int cmd_record(int argc, const char **argv)
>  
>  	}
>  
> -	if (rec->opts.kcore)
> +	if (rec->opts.kcore || record__threads_enabled(rec))
>  		rec->data.is_dir = true;
>  
>  	if (rec->opts.comp_level != 0) {
> diff --git a/tools/perf/util/record.h b/tools/perf/util/record.h
> index 266760ac9143..9c13a39cc58f 100644
> --- a/tools/perf/util/record.h
> +++ b/tools/perf/util/record.h
> @@ -74,6 +74,7 @@ struct record_opts {
>  	int	      ctl_fd;
>  	int	      ctl_fd_ack;
>  	bool	      ctl_fd_close;
> +	int	      threads_spec;
>  };
>  
>  extern const char * const *record_usage;
> -- 
> 2.24.1
> 

  reply	other threads:[~2020-11-20 10:49 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-11-16 12:12 [PATCH v3 00/12] Introduce threaded trace streaming for basic perf record operation Alexey Budankov
2020-11-16 12:14 ` [PATCH v3 01/12] perf record: introduce thread affinity and mmap masks Alexey Budankov
2020-11-20 10:01   ` Namhyung Kim
2020-11-16 12:15 ` [PATCH v3 02/12] perf record: introduce thread specific data array Alexey Budankov
2020-11-20 10:14   ` Namhyung Kim
2020-11-16 12:16 ` [PATCH v3 03/12] perf record: introduce thread local variable Alexey Budankov
2020-11-20 10:20   ` Namhyung Kim
2020-11-16 12:17 ` [PATCH v3 04/12] perf record: stop threads in the end of trace streaming Alexey Budankov
2020-11-16 12:18 ` [PATCH v3 05/12] perf record: start threads in the beginning " Alexey Budankov
2020-11-16 12:18 ` [PATCH v3 06/12] perf record: introduce data file at mmap buffer object Alexey Budankov
2020-11-20 10:28   ` Namhyung Kim
2020-11-16 12:19 ` [PATCH v3 07/12] perf record: init " Alexey Budankov
2020-11-20 10:49   ` Namhyung Kim [this message]
2021-03-01 11:16     ` Bayduraev, Alexey V
2021-03-01 11:44       ` Namhyung Kim
2021-03-01 13:33         ` Bayduraev, Alexey V
2021-03-01 14:20           ` Namhyung Kim
2020-11-16 12:20 ` [PATCH v3 08/12] perf record: introduce --threads=<spec> command line option Alexey Budankov
2020-11-20 11:09   ` Namhyung Kim
2020-11-16 12:21 ` [PATCH v3 09/12] perf record: document parallel data streaming mode Alexey Budankov
2020-11-16 12:22 ` [PATCH v3 10/12] perf report: output data file name in raw trace dump Alexey Budankov
2020-11-16 12:22 ` [PATCH v3 11/12] perf session: load data directory files for analysis Alexey Budankov
2020-11-16 12:25 ` [PATCH v3 12/12] perf session: use reader functions to load perf data file Alexey Budankov
2020-11-20  9:45 ` [PATCH v3 00/12] Introduce threaded trace streaming for basic perf record operation Namhyung Kim
2020-12-15 15:05   ` Alexei Budankov

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=20201120104942.GF94830@google.com \
    --to=namhyung@kernel.org \
    --cc=acme@kernel.org \
    --cc=adrian.hunter@intel.com \
    --cc=ak@linux.intel.com \
    --cc=alexander.antonov@linux.intel.com \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=alexey.budankov@linux.intel.com \
    --cc=alexey.v.bayduraev@linux.intel.com \
    --cc=jolsa@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --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 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).