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: Kan Liang <kan.liang@intel.com>
Signed-off-by: Peter 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: Ingo Molnar <mingo@kernel.org>
{
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);
[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",
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",
u64 lost;
};
+struct lost_samples_event {
+ struct perf_event_header header;
+ u64 lost;
+};
+
/*
* PERF_FORMAT_ENABLED | PERF_FORMAT_RUNNING | PERF_FORMAT_ID
*/
* 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
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;
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;
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,
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)
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;
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,
tool->exit = process_event_stub;
if (tool->lost == NULL)
tool->lost = perf_event__process_lost;
+ if (tool->lost_samples == NULL)
+ tool->lost_samples = perf_event__process_lost_samples;
if (tool->aux == NULL)
tool->aux = perf_event__process_aux;
if (tool->itrace_start == NULL)
[PERF_RECORD_SAMPLE] = perf_event__all64_swap,
[PERF_RECORD_AUX] = perf_event__aux_swap,
[PERF_RECORD_ITRACE_START] = perf_event__itrace_start_swap,
+ [PERF_RECORD_LOST_SAMPLES] = perf_event__all64_swap,
[PERF_RECORD_HEADER_ATTR] = perf_event__hdr_attr_swap,
[PERF_RECORD_HEADER_EVENT_TYPE] = perf_event__event_type_swap,
[PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap,
if (tool->lost == perf_event__process_lost)
evlist->stats.total_lost += event->lost.lost;
return tool->lost(tool, event, sample, machine);
+ case PERF_RECORD_LOST_SAMPLES:
+ if (tool->lost_samples == perf_event__process_lost_samples)
+ evlist->stats.total_lost_samples += event->lost_samples.lost;
+ return tool->lost_samples(tool, event, sample, machine);
case PERF_RECORD_READ:
return tool->read(tool, event, sample, evsel, machine);
case PERF_RECORD_THROTTLE:
stats->nr_events[PERF_RECORD_LOST]);
}
+ if (session->tool->lost_samples == perf_event__process_lost_samples) {
+ double drop_rate;
+
+ drop_rate = (double)stats->total_lost_samples /
+ (double) (stats->nr_events[PERF_RECORD_SAMPLE] + stats->total_lost_samples);
+ if (drop_rate > 0.05) {
+ ui__warning("Processed %lu samples and lost %3.2f%% samples!\n\n",
+ stats->nr_events[PERF_RECORD_SAMPLE] + stats->total_lost_samples,
+ drop_rate * 100.0);
+ }
+ }
+
if (stats->nr_unknown_events != 0) {
ui__warning("Found %u unknown events!\n\n"
"Is this an older tool processing a perf.data "
fork,
exit,
lost,
+ lost_samples,
aux,
itrace_start,
throttle,