Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit c4937a91 authored by Kan Liang's avatar Kan Liang Committed by Ingo Molnar
Browse files

perf tools: handle PERF_RECORD_LOST_SAMPLES 



This patch modifies the perf tool to handle the new RECORD type,
PERF_RECORD_LOST_SAMPLES.

The number of lost-sample events is stored in
.nr_events[PERF_RECORD_LOST_SAMPLES]. The exact number of samples
which the kernel dropped is stored in total_lost_samples.

When the percentage of dropped samples is greater than 5%, a warning
is printed.

Here are some examples:

Eg 1, Recording different frequently-occurring events is safe with the
      patch. Only a very low drop rate is associated with such actions.

$ perf record -e '{cycles:p,instructions:p}' -c 20003 --no-time ~/tchain ~/tchain

$ perf report -D | tail
          SAMPLE events:     120243
           MMAP2 events:          5
    LOST_SAMPLES events:         24
  FINISHED_ROUND events:         15
cycles:p stats:
           TOTAL events:      59348
          SAMPLE events:      59348
instructions:p stats:
           TOTAL events:      60895
          SAMPLE events:      60895

$ perf report --stdio --group
 # To display the perf.data header info, please use --header/--header-only options.
 #
 #
 # Total Lost Samples: 24
 #
 # Samples: 120K of event 'anon group { cycles:p, instructions:p }'
 # Event count (approx.): 24048600000
 #
 #         Overhead  Command      Shared Object     Symbol
 # ................  ...........  ................
 ..................................
 #
    99.74%  99.86%  tchain_edit  tchain_edit       [.] f3
     0.09%   0.02%  tchain_edit  tchain_edit       [.] f2
     0.04%   0.00%  tchain_edit  [kernel.vmlinux]  [k] ixgbe_read_reg

Eg 2, Recording the same thing multiple times can lead to high drop
      rate, but it is not a useful configuration.

$ perf record -e '{cycles:p,cycles:p}' -c 20003 --no-time ~/tchain
Warning: Processed 600592 samples and lost 99.73% samples!
[perf record: Woken up 148 times to write data]
[perf record: Captured and wrote 36.922 MB perf.data (1206322 samples)]
[perf record: Woken up 1 times to write data]
[perf record: Captured and wrote 0.121 MB perf.data (1629 samples)]

Signed-off-by: default avatarKan Liang <kan.liang@intel.com>
Signed-off-by: default avatarPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: acme@infradead.org
Cc: eranian@google.com
Link: http://lkml.kernel.org/r/1431285195-14269-9-git-send-email-kan.liang@intel.com


Signed-off-by: default avatarIngo Molnar <mingo@kernel.org>
parent f38b0dbb

tools/perf/builtin-report.c

+1 −0
Original line number Diff line number Diff line
@@ -320,6 +320,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist, 
{

	struct perf_evsel *pos;



	fprintf(stdout, "#\n# Total Lost Samples: %lu\n#\n", evlist->stats.total_lost_samples);

	evlist__for_each(evlist, pos) {

		struct hists *hists = evsel__hists(pos);

		const char *evname = perf_evsel__name(pos);

tools/perf/util/event.c

+9 −0
Original line number Diff line number Diff line
@@ -25,6 +25,7 @@ static const char *perf_event__names[] = { 
	[PERF_RECORD_SAMPLE]			= "SAMPLE",

	[PERF_RECORD_AUX]			= "AUX",

	[PERF_RECORD_ITRACE_START]		= "ITRACE_START",

	[PERF_RECORD_LOST_SAMPLES]		= "LOST_SAMPLES",

	[PERF_RECORD_HEADER_ATTR]		= "ATTR",

	[PERF_RECORD_HEADER_EVENT_TYPE]		= "EVENT_TYPE",

	[PERF_RECORD_HEADER_TRACING_DATA]	= "TRACING_DATA",
@@ -712,6 +713,14 @@ int perf_event__process_itrace_start(struct perf_tool *tool __maybe_unused, 
	return machine__process_itrace_start_event(machine, event);

}



int perf_event__process_lost_samples(struct perf_tool *tool __maybe_unused,

				     union perf_event *event,

				     struct perf_sample *sample,

				     struct machine *machine)

{

	return machine__process_lost_samples_event(machine, event, sample);

}



size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp)

{

	return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %c %s\n",

tools/perf/util/event.h

+17 −0
Original line number Diff line number Diff line
@@ -52,6 +52,11 @@ struct lost_event { 
	u64 lost;

};



struct lost_samples_event {

	struct perf_event_header header;

	u64 lost;

};



/*

 * PERF_FORMAT_ENABLED | PERF_FORMAT_RUNNING | PERF_FORMAT_ID

 */
@@ -235,6 +240,12 @@ enum auxtrace_error_type { 
 * total_lost tells exactly how many events the kernel in fact lost, i.e. it is

 * the sum of all struct lost_event.lost fields reported.

 *

 * The kernel discards mixed up samples and sends the number in a

 * PERF_RECORD_LOST_SAMPLES event. The number of lost-samples events is stored

 * in .nr_events[PERF_RECORD_LOST_SAMPLES] while total_lost_samples tells

 * exactly how many samples the kernel in fact dropped, i.e. it is the sum of

 * all struct lost_samples_event.lost fields reported.

 *

 * The total_period is needed because by default auto-freq is used, so

 * multipling nr_events[PERF_EVENT_SAMPLE] by a frequency isn't possible to get

 * the total number of low level events, it is necessary to to sum all struct
@@ -244,6 +255,7 @@ struct events_stats { 
	u64 total_period;

	u64 total_non_filtered_period;

	u64 total_lost;

	u64 total_lost_samples;

	u64 total_invalid_chains;

	u32 nr_events[PERF_RECORD_HEADER_MAX];

	u32 nr_non_filtered_samples;
@@ -342,6 +354,7 @@ union perf_event { 
	struct comm_event		comm;

	struct fork_event		fork;

	struct lost_event		lost;

	struct lost_samples_event	lost_samples;

	struct read_event		read;

	struct throttle_event		throttle;

	struct sample_event		sample;
@@ -390,6 +403,10 @@ int perf_event__process_lost(struct perf_tool *tool, 
			     union perf_event *event,

			     struct perf_sample *sample,

			     struct machine *machine);

int perf_event__process_lost_samples(struct perf_tool *tool,

				     union perf_event *event,

				     struct perf_sample *sample,

				     struct machine *machine);

int perf_event__process_aux(struct perf_tool *tool,

			    union perf_event *event,

			    struct perf_sample *sample,

tools/perf/util/machine.c

+10 −0
Original line number Diff line number Diff line
@@ -482,6 +482,14 @@ int machine__process_lost_event(struct machine *machine __maybe_unused, 
	return 0;

}



int machine__process_lost_samples_event(struct machine *machine __maybe_unused,

					union perf_event *event, struct perf_sample *sample)

{

	dump_printf(": id:%" PRIu64 ": lost samples :%" PRIu64 "\n",

		    sample->id, event->lost_samples.lost);

	return 0;

}



static struct dso*

machine__module_dso(struct machine *machine, struct kmod_path *m,

		    const char *filename)
@@ -1419,6 +1427,8 @@ int machine__process_event(struct machine *machine, union perf_event *event, 
		ret = machine__process_aux_event(machine, event); break;

	case PERF_RECORD_ITRACE_START:

		ret = machine__process_itrace_start_event(machine, event);

	case PERF_RECORD_LOST_SAMPLES:

		ret = machine__process_lost_samples_event(machine, event, sample); break;

		break;

	default:

		ret = -1;

tools/perf/util/machine.h

+2 −0
Original line number Diff line number Diff line
@@ -81,6 +81,8 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event 
				struct perf_sample *sample);

int machine__process_lost_event(struct machine *machine, union perf_event *event,

				struct perf_sample *sample);

int machine__process_lost_samples_event(struct machine *machine, union perf_event *event,

					struct perf_sample *sample);

int machine__process_aux_event(struct machine *machine,

			       union perf_event *event);

int machine__process_itrace_start_event(struct machine *machine,