[PATCH 05/14] perf tools: handle PERF_RECORD_OVERHEAD record type

From: kan . liang
Date: Wed Nov 23 2016 - 12:47:43 EST

Next message: kan . liang: "[PATCH 01/14] perf/x86: Introduce PERF_RECORD_OVERHEAD"
Previous message: kan . liang: "[PATCH 04/14] perf/x86: output side-band events overhead"
In reply to: Peter Zijlstra: "Re: [PATCH 04/14] perf/x86: output side-band events overhead"
Next in thread: Jiri Olsa: "Re: [PATCH 05/14] perf tools: handle PERF_RECORD_OVERHEAD record type"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

From: Kan Liang <kan.liang@xxxxxxxxx>

The infrastructure to handle PERF_RECORD_OVERHEAD record type. A new
perf report option is also introduced as a knob to show the overhead
information.

Signed-off-by: Kan Liang <kan.liang@xxxxxxxxx>
---
tools/include/uapi/linux/perf_event.h | 33 ++++++++++++++++++++++++++++++++
tools/perf/Documentation/perf-report.txt | 3 +++
tools/perf/builtin-report.c | 6 ++++++
tools/perf/util/event.c | 9 +++++++++
tools/perf/util/event.h | 11 +++++++++++
tools/perf/util/machine.c | 8 ++++++++
tools/perf/util/machine.h | 2 ++
tools/perf/util/session.c | 5 +++++
tools/perf/util/symbol.h | 3 ++-
tools/perf/util/tool.h | 1 +
10 files changed, 80 insertions(+), 1 deletion(-)

diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index c66a485..5e7c522 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -862,6 +862,17 @@ enum perf_event_type {
*/
PERF_RECORD_SWITCH_CPU_WIDE = 15,

+ /*
+ * Records perf overhead
+ * struct {
+ * struct perf_event_header header;
+ * u32 type;
+ * struct perf_overhead_entry entry;
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_OVERHEAD = 16,
+
PERF_RECORD_MAX, /* non-ABI */
};

@@ -980,4 +991,26 @@ struct perf_branch_entry {
reserved:44;
};

+enum perf_record_overhead_type {
+ PERF_NMI_OVERHEAD = 0,
+ PERF_MUX_OVERHEAD,
+ PERF_SB_OVERHEAD,
+
+ PERF_OVERHEAD_MAX,
+};
+
+/*
+ * single overhead record layout:
+ *
+ * cpu: The cpu which overhead occues
+ * nr: Times of overhead happens.
+ * E.g. for NMI, nr == times of NMI handler are called.
+ * time: Total overhead cost(ns)
+ */
+struct perf_overhead_entry {
+ __u32 cpu;
+ __u64 nr;
+ __u64 time;
+};
+
#endif /* _UAPI_LINUX_PERF_EVENT_H */
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 2d17462..fea8bea 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -412,6 +412,9 @@ include::itrace.txt[]
--hierarchy::
Enable hierarchical output.

+--show-overhead::
+ Show extra overhead which perf brings during monitoring
+
include::callchain-overhead-calculation.txt[]

SEE ALSO
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 3dfbfff..1416c39 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -368,6 +368,10 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
struct perf_evsel *pos;

fprintf(stdout, "#\n# Total Lost Samples: %" PRIu64 "\n#\n", evlist->stats.total_lost_samples);
+ if (symbol_conf.show_overhead) {
+ fprintf(stdout, "# Overhead:\n");
+ fprintf(stdout, "#\n");
+ }
evlist__for_each_entry(evlist, pos) {
struct hists *hists = evsel__hists(pos);
const char *evname = perf_evsel__name(pos);
@@ -830,6 +834,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
OPT_CALLBACK_DEFAULT(0, "stdio-color", NULL, "mode",
"'always' (default), 'never' or 'auto' only applicable to --stdio mode",
stdio__config_color, "always"),
+ OPT_BOOLEAN(0, "show-overhead", &symbol_conf.show_overhead,
+ "Show perf overhead"),
OPT_END()
};
struct perf_data_file file = {
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 8ab0d7d..ca98c4c 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -31,6 +31,7 @@ static const char *perf_event__names[] = {
[PERF_RECORD_LOST_SAMPLES] = "LOST_SAMPLES",
[PERF_RECORD_SWITCH] = "SWITCH",
[PERF_RECORD_SWITCH_CPU_WIDE] = "SWITCH_CPU_WIDE",
+ [PERF_RECORD_OVERHEAD] = "OVERHEAD",
[PERF_RECORD_HEADER_ATTR] = "ATTR",
[PERF_RECORD_HEADER_EVENT_TYPE] = "EVENT_TYPE",
[PERF_RECORD_HEADER_TRACING_DATA] = "TRACING_DATA",
@@ -1056,6 +1057,14 @@ int perf_event__process_switch(struct perf_tool *tool __maybe_unused,
return machine__process_switch_event(machine, event);
}

+int perf_event__process_overhead(struct perf_tool *tool __maybe_unused,
+ union perf_event *event,
+ struct perf_sample *sample __maybe_unused,
+ struct machine *machine)
+{
+ return machine__process_overhead_event(machine, event);
+}
+
size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp)
{
return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %c %s\n",
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index c735c53..d1b179b 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -480,6 +480,12 @@ struct time_conv_event {
u64 time_zero;
};

+struct perf_overhead {
+ struct perf_event_header header;
+ u32 type;
+ struct perf_overhead_entry entry;
+};
+
union perf_event {
struct perf_event_header header;
struct mmap_event mmap;
@@ -509,6 +515,7 @@ union perf_event {
struct stat_event stat;
struct stat_round_event stat_round;
struct time_conv_event time_conv;
+ struct perf_overhead overhead;
};

void perf_event__print_totals(void);
@@ -587,6 +594,10 @@ int perf_event__process_switch(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
struct machine *machine);
+int perf_event__process_overhead(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct machine *machine);
int perf_event__process_mmap(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 9b33bef..1101757 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -555,6 +555,12 @@ int machine__process_switch_event(struct machine *machine __maybe_unused,
return 0;
}

+int machine__process_overhead_event(struct machine *machine __maybe_unused,
+ union perf_event *event __maybe_unused)
+{
+ return 0;
+}
+
static void dso__adjust_kmod_long_name(struct dso *dso, const char *filename)
{
const char *dup_filename;
@@ -1536,6 +1542,8 @@ int machine__process_event(struct machine *machine, union perf_event *event,
case PERF_RECORD_SWITCH:
case PERF_RECORD_SWITCH_CPU_WIDE:
ret = machine__process_switch_event(machine, event); break;
+ case PERF_RECORD_OVERHEAD:
+ ret = machine__process_overhead_event(machine, event); break;
default:
ret = -1;
break;
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 354de6e..ec2dd4d 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -97,6 +97,8 @@ int machine__process_itrace_start_event(struct machine *machine,
union perf_event *event);
int machine__process_switch_event(struct machine *machine,
union perf_event *event);
+int machine__process_overhead_event(struct machine *machine,
+ union perf_event *event);
int machine__process_mmap_event(struct machine *machine, union perf_event *event,
struct perf_sample *sample);
int machine__process_mmap2_event(struct machine *machine, union perf_event *event,
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index f268201..bc0bc21 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -373,6 +373,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
tool->itrace_start = perf_event__process_itrace_start;
if (tool->context_switch == NULL)
tool->context_switch = perf_event__process_switch;
+ if (tool->overhead == NULL)
+ tool->overhead = perf_event__process_overhead;
if (tool->read == NULL)
tool->read = process_event_sample_stub;
if (tool->throttle == NULL)
@@ -786,6 +788,7 @@ static perf_event__swap_op perf_event__swap_ops[] = {
[PERF_RECORD_LOST_SAMPLES] = perf_event__all64_swap,
[PERF_RECORD_SWITCH] = perf_event__switch_swap,
[PERF_RECORD_SWITCH_CPU_WIDE] = perf_event__switch_swap,
+ [PERF_RECORD_OVERHEAD] = 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,
@@ -1267,6 +1270,8 @@ static int machines__deliver_event(struct machines *machines,
case PERF_RECORD_SWITCH:
case PERF_RECORD_SWITCH_CPU_WIDE:
return tool->context_switch(tool, event, sample, machine);
+ case PERF_RECORD_OVERHEAD:
+ return tool->overhead(tool, event, sample, machine);
default:
++evlist->stats.nr_unknown_events;
return -1;
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 2d0a905..2d96bdb 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -117,7 +117,8 @@ struct symbol_conf {
show_ref_callgraph,
hide_unresolved,
raw_trace,
- report_hierarchy;
+ report_hierarchy,
+ show_overhead;
const char *vmlinux_name,
*kallsyms_name,
*source_prefix,
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index ac2590a..c5bbb34 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -47,6 +47,7 @@ struct perf_tool {
aux,
itrace_start,
context_switch,
+ overhead,
throttle,
unthrottle;
event_attr_op attr;
--
2.5.5

Next message: kan . liang: "[PATCH 01/14] perf/x86: Introduce PERF_RECORD_OVERHEAD"
Previous message: kan . liang: "[PATCH 04/14] perf/x86: output side-band events overhead"
In reply to: Peter Zijlstra: "Re: [PATCH 04/14] perf/x86: output side-band events overhead"
Next in thread: Jiri Olsa: "Re: [PATCH 05/14] perf tools: handle PERF_RECORD_OVERHEAD record type"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]