perf record: Add --synth option
Add an option to control the synthesizing behavior.
--synth <no|all|task|mmap|cgroup>
Fine-tune event synthesis: default=all
This can be useful when we know it doesn't need some synthesis like
in a specific usecase and/or when using pipe:
$ perf record -a --all-cgroups --synth cgroup -o- sleep 1 | \
> perf report -i- -s cgroup
Committer notes:
Added a clarification to the man page entry for --synth that this is
about pre-existing threads.
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https //lore.kernel.org/r/20210811044658.1313391-2-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 0263e383..41bb884 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1255,6 +1255,7 @@ static int record__synthesize_workload(struct record *rec, bool tail)
{
int err;
struct perf_thread_map *thread_map;
+ bool needs_mmap = rec->opts.synth & PERF_SYNTH_MMAP;
if (rec->opts.tail_synthesize != tail)
return 0;
@@ -1266,7 +1267,7 @@ static int record__synthesize_workload(struct record *rec, bool tail)
err = perf_event__synthesize_thread_map(&rec->tool, thread_map,
process_synthesized_event,
&rec->session->machines.host,
- true,
+ needs_mmap,
rec->opts.sample_address);
perf_thread_map__put(thread_map);
return err;
@@ -1471,20 +1472,26 @@ static int record__synthesize(struct record *rec, bool tail)
if (err < 0)
pr_warning("Couldn't synthesize bpf events.\n");
- err = perf_event__synthesize_cgroups(tool, process_synthesized_event,
- machine);
- if (err < 0)
- pr_warning("Couldn't synthesize cgroup events.\n");
+ if (rec->opts.synth & PERF_SYNTH_CGROUP) {
+ err = perf_event__synthesize_cgroups(tool, process_synthesized_event,
+ machine);
+ if (err < 0)
+ pr_warning("Couldn't synthesize cgroup events.\n");
+ }
if (rec->opts.nr_threads_synthesize > 1) {
perf_set_multithreaded();
f = process_locked_synthesized_event;
}
- err = __machine__synthesize_threads(machine, tool, &opts->target,
- rec->evlist->core.threads,
- f, true, opts->sample_address,
- rec->opts.nr_threads_synthesize);
+ if (rec->opts.synth & PERF_SYNTH_TASK) {
+ bool needs_mmap = rec->opts.synth & PERF_SYNTH_MMAP;
+
+ err = __machine__synthesize_threads(machine, tool, &opts->target,
+ rec->evlist->core.threads,
+ f, needs_mmap, opts->sample_address,
+ rec->opts.nr_threads_synthesize);
+ }
if (rec->opts.nr_threads_synthesize > 1)
perf_set_singlethreaded();
@@ -2393,6 +2400,26 @@ static int process_timestamp_boundary(struct perf_tool *tool,
return 0;
}
+static int parse_record_synth_option(const struct option *opt,
+ const char *str,
+ int unset __maybe_unused)
+{
+ struct record_opts *opts = opt->value;
+ char *p = strdup(str);
+
+ if (p == NULL)
+ return -1;
+
+ opts->synth = parse_synth_opt(p);
+ free(p);
+
+ if (opts->synth < 0) {
+ pr_err("Invalid synth option: %s\n", str);
+ return -1;
+ }
+ return 0;
+}
+
/*
* XXX Ideally would be local to cmd_record() and passed to a record__new
* because we need to have access to it in record__exit, that is called
@@ -2418,6 +2445,7 @@ static struct record record = {
.nr_threads_synthesize = 1,
.ctl_fd = -1,
.ctl_fd_ack = -1,
+ .synth = PERF_SYNTH_ALL,
},
.tool = {
.sample = process_sample_event,
@@ -2633,6 +2661,8 @@ static struct option __record_options[] = {
"\t\t\t Optionally send control command completion ('ack\\n') to ack-fd descriptor.\n"
"\t\t\t Alternatively, ctl-fifo / ack-fifo will be opened and used as ctl-fd / ack-fd.",
parse_control_option),
+ OPT_CALLBACK(0, "synth", &record.opts, "no|all|task|mmap|cgroup",
+ "Fine-tune event synthesis: default=all", parse_record_synth_option),
OPT_END()
};