perf record: Enable off-cpu analysis with BPF
Add --off-cpu option to enable the off-cpu profiling with BPF. It'd
use a bpf_output event and rename it to "offcpu-time". Samples will
be synthesized at the end of the record session using data from a BPF
map which contains the aggregated off-cpu time at context switches.
So it needs root privilege to get the off-cpu profiling.
Each sample will have a separate user stacktrace so it will skip
kernel threads. The sample ip will be set from the stacktrace and
other sample data will be updated accordingly. Currently it only
handles some basic sample types.
The sample timestamp is set to a dummy value just not to bother with
other events during the sorting. So it has a very big initial value
and increase it on processing each samples.
Good thing is that it can be used together with regular profiling like
cpu cycles. If you don't want to that, you can use a dummy event to
enable off-cpu profiling only.
Example output:
$ sudo perf record --off-cpu perf bench sched messaging -l 1000
$ sudo perf report --stdio --call-graph=no
# Total Lost Samples: 0
#
# Samples: 41K of event 'cycles'
# Event count (approx.): 42137343851
...
# Samples: 1K of event 'offcpu-time'
# Event count (approx.): 587990831640
#
# Children Self Command Shared Object Symbol
# ........ ........ ............... .................. .........................
#
81.66% 0.00% sched-messaging libc-2.33.so [.] __libc_start_main
81.66% 0.00% sched-messaging perf [.] cmd_bench
81.66% 0.00% sched-messaging perf [.] main
81.66% 0.00% sched-messaging perf [.] run_builtin
81.43% 0.00% sched-messaging perf [.] bench_sched_messaging
40.86% 40.86% sched-messaging libpthread-2.33.so [.] __read
37.66% 37.66% sched-messaging libpthread-2.33.so [.] __write
2.91% 2.91% sched-messaging libc-2.33.so [.] __poll
...
As you can see it spent most of off-cpu time in read and write in
bench_sched_messaging(). The --call-graph=no was added just to make
the output concise here.
It uses perf hooks facility to control BPF program during the record
session rather than adding new BPF/off-cpu specific calls.
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Ian Rogers <irogers@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Blake Jones <blakejones@google.com>
Cc: Hao Luo <haoluo@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Song Liu <songliubraving@fb.com>
Cc: bpf@vger.kernel.org
Link: https://lore.kernel.org/r/20220518224725.742882-3-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 cf9a7ce..b76f57e 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -49,6 +49,7 @@
#include "util/clockid.h"
#include "util/pmu-hybrid.h"
#include "util/evlist-hybrid.h"
+#include "util/off_cpu.h"
#include "asm/bug.h"
#include "perf.h"
#include "cputopo.h"
@@ -162,6 +163,7 @@ struct record {
bool buildid_mmap;
bool timestamp_filename;
bool timestamp_boundary;
+ bool off_cpu;
struct switch_output switch_output;
unsigned long long samples;
unsigned long output_max_size; /* = 0: unlimited */
@@ -888,6 +890,11 @@ static int record__config_text_poke(struct evlist *evlist)
return 0;
}
+static int record__config_off_cpu(struct record *rec)
+{
+ return off_cpu_prepare(rec->evlist);
+}
+
static bool record__kcore_readable(struct machine *machine)
{
char kcore[PATH_MAX];
@@ -2591,6 +2598,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
} else
status = err;
+ if (rec->off_cpu)
+ rec->bytes_written += off_cpu_write(rec->session);
+
record__synthesize(rec, true);
/* this will be recalculated during process_buildids() */
rec->samples = 0;
@@ -3315,6 +3325,7 @@ static struct option __record_options[] = {
OPT_CALLBACK_OPTARG(0, "threads", &record.opts, NULL, "spec",
"write collected trace data into several data files using parallel threads",
record__parse_threads),
+ OPT_BOOLEAN(0, "off-cpu", &record.off_cpu, "Enable off-cpu analysis"),
OPT_END()
};
@@ -3736,6 +3747,12 @@ int cmd_record(int argc, const char **argv)
# undef REASON
#endif
+#ifndef HAVE_BPF_SKEL
+# define set_nobuild(s, l, m, c) set_option_nobuild(record_options, s, l, m, c)
+ set_nobuild('\0', "off-cpu", "no BUILD_BPF_SKEL=1", true);
+# undef set_nobuild
+#endif
+
rec->opts.affinity = PERF_AFFINITY_SYS;
rec->evlist = evlist__new();
@@ -3972,6 +3989,14 @@ int cmd_record(int argc, const char **argv)
}
}
+ if (rec->off_cpu) {
+ err = record__config_off_cpu(rec);
+ if (err) {
+ pr_err("record__config_off_cpu failed, error %d\n", err);
+ goto out;
+ }
+ }
+
if (record_opts__config(&rec->opts)) {
err = -EINVAL;
goto out;
