aboutsummaryrefslogtreecommitdiffstats
path: root/tools/perf/builtin-record.c
diff options
context:
space:
mode:
Diffstat (limited to 'tools/perf/builtin-record.c')
-rw-r--r--tools/perf/builtin-record.c74
1 files changed, 57 insertions, 17 deletions
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 882285fb9f64..f3f7f3100336 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -23,7 +23,6 @@
#include "util/evlist.h"
#include "util/evsel.h"
#include "util/debug.h"
-#include "util/drv_configs.h"
#include "util/session.h"
#include "util/tool.h"
#include "util/symbol.h"
@@ -39,8 +38,10 @@
#include "util/bpf-loader.h"
#include "util/trigger.h"
#include "util/perf-hooks.h"
+#include "util/cpu-set-sched.h"
#include "util/time-utils.h"
#include "util/units.h"
+#include "util/bpf-event.h"
#include "asm/bug.h"
#include <errno.h>
@@ -81,12 +82,17 @@ struct record {
bool timestamp_boundary;
struct switch_output switch_output;
unsigned long long samples;
+ cpu_set_t affinity_mask;
};
static volatile int auxtrace_record__snapshot_started;
static DEFINE_TRIGGER(auxtrace_snapshot_trigger);
static DEFINE_TRIGGER(switch_output_trigger);
+static const char *affinity_tags[PERF_AFFINITY_MAX] = {
+ "SYS", "NODE", "CPU"
+};
+
static bool switch_output_signal(struct record *rec)
{
return rec->switch_output.signal &&
@@ -531,9 +537,13 @@ static int record__mmap_evlist(struct record *rec,
struct record_opts *opts = &rec->opts;
char msg[512];
+ if (opts->affinity != PERF_AFFINITY_SYS)
+ cpu__setup_cpunode_map();
+
if (perf_evlist__mmap_ex(evlist, opts->mmap_pages,
opts->auxtrace_mmap_pages,
- opts->auxtrace_snapshot_mode, opts->nr_cblocks) < 0) {
+ opts->auxtrace_snapshot_mode,
+ opts->nr_cblocks, opts->affinity) < 0) {
if (errno == EPERM) {
pr_err("Permission error mapping pages.\n"
"Consider increasing "
@@ -566,7 +576,6 @@ static int record__open(struct record *rec)
struct perf_evlist *evlist = rec->evlist;
struct perf_session *session = rec->session;
struct record_opts *opts = &rec->opts;
- struct perf_evsel_config_term *err_term;
int rc = 0;
/*
@@ -619,14 +628,6 @@ try_again:
goto out;
}
- if (perf_evlist__apply_drv_configs(evlist, &pos, &err_term)) {
- pr_err("failed to set config \"%s\" on event %s with %d (%s)\n",
- err_term->val.drv_cfg, perf_evsel__name(pos), errno,
- str_error_r(errno, msg, sizeof(msg)));
- rc = -1;
- goto out;
- }
-
rc = record__mmap(rec);
if (rc)
goto out;
@@ -659,10 +660,9 @@ static int process_sample_event(struct perf_tool *tool,
static int process_buildids(struct record *rec)
{
- struct perf_data *data = &rec->data;
struct perf_session *session = rec->session;
- if (data->size == 0)
+ if (perf_data__size(&rec->data) == 0)
return 0;
/*
@@ -722,6 +722,16 @@ static struct perf_event_header finished_round_event = {
.type = PERF_RECORD_FINISHED_ROUND,
};
+static void record__adjust_affinity(struct record *rec, struct perf_mmap *map)
+{
+ if (rec->opts.affinity != PERF_AFFINITY_SYS &&
+ !CPU_EQUAL(&rec->affinity_mask, &map->affinity_mask)) {
+ CPU_ZERO(&rec->affinity_mask);
+ CPU_OR(&rec->affinity_mask, &rec->affinity_mask, &map->affinity_mask);
+ sched_setaffinity(0, sizeof(rec->affinity_mask), &rec->affinity_mask);
+ }
+}
+
static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evlist,
bool overwrite)
{
@@ -749,6 +759,7 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli
struct perf_mmap *map = &maps[i];
if (map->base) {
+ record__adjust_affinity(rec, map);
if (!record__aio_enabled(rec)) {
if (perf_mmap__push(map, rec, record__pushfn) != 0) {
rc = -1;
@@ -839,7 +850,7 @@ record__finish_output(struct record *rec)
return;
rec->session->header.data_size += rec->bytes_written;
- data->size = lseek(perf_data__fd(data), 0, SEEK_CUR);
+ data->file.size = lseek(perf_data__fd(data), 0, SEEK_CUR);
if (!rec->no_buildid) {
process_buildids(rec);
@@ -907,7 +918,7 @@ record__switch_output(struct record *rec, bool at_exit)
if (!quiet)
fprintf(stderr, "[ perf record: Dump %s.%s ]\n",
- data->file.path, timestamp);
+ data->path, timestamp);
/* Output tracking events */
if (!at_exit) {
@@ -1082,6 +1093,11 @@ static int record__synthesize(struct record *rec, bool tail)
return err;
}
+ err = perf_event__synthesize_bpf_events(tool, process_synthesized_event,
+ machine, opts);
+ if (err < 0)
+ pr_warning("Couldn't synthesize bpf events.\n");
+
err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->threads,
process_synthesized_event, opts->sample_address,
1);
@@ -1445,7 +1461,7 @@ out_child:
fprintf(stderr, "[ perf record: Captured and wrote %.3f MB %s%s%s ]\n",
perf_data__size(data) / 1024.0 / 1024.0,
- data->file.path, postfix, samples);
+ data->path, postfix, samples);
}
out_delete_session:
@@ -1639,6 +1655,21 @@ static int parse_clockid(const struct option *opt, const char *str, int unset)
return -1;
}
+static int record__parse_affinity(const struct option *opt, const char *str, int unset)
+{
+ struct record_opts *opts = (struct record_opts *)opt->value;
+
+ if (unset || !str)
+ return 0;
+
+ if (!strcasecmp(str, "node"))
+ opts->affinity = PERF_AFFINITY_NODE;
+ else if (!strcasecmp(str, "cpu"))
+ opts->affinity = PERF_AFFINITY_CPU;
+
+ return 0;
+}
+
static int record__parse_mmap_pages(const struct option *opt,
const char *str,
int unset __maybe_unused)
@@ -1831,7 +1862,7 @@ static struct option __record_options[] = {
OPT_STRING('C', "cpu", &record.opts.target.cpu_list, "cpu",
"list of cpus to monitor"),
OPT_U64('c', "count", &record.opts.user_interval, "event period to sample"),
- OPT_STRING('o', "output", &record.data.file.path, "file",
+ OPT_STRING('o', "output", &record.data.path, "file",
"output file name"),
OPT_BOOLEAN_SET('i', "no-inherit", &record.opts.no_inherit,
&record.opts.no_inherit_set,
@@ -1839,6 +1870,7 @@ static struct option __record_options[] = {
OPT_BOOLEAN(0, "tail-synthesize", &record.opts.tail_synthesize,
"synthesize non-sample events at the end of output"),
OPT_BOOLEAN(0, "overwrite", &record.opts.overwrite, "use overwrite mode"),
+ OPT_BOOLEAN(0, "bpf-event", &record.opts.bpf_event, "record bpf events"),
OPT_BOOLEAN(0, "strict-freq", &record.opts.strict_freq,
"Fail if the specified frequency can't be used"),
OPT_CALLBACK('F', "freq", &record.opts, "freq or 'max'",
@@ -1946,6 +1978,9 @@ static struct option __record_options[] = {
&nr_cblocks_default, "n", "Use <n> control blocks in asynchronous trace writing mode (default: 1, max: 4)",
record__aio_parse),
#endif
+ OPT_CALLBACK(0, "affinity", &record.opts, "node|cpu",
+ "Set affinity mask of trace reading thread to NUMA node cpu mask or cpu of processed mmap buffer",
+ record__parse_affinity),
OPT_END()
};
@@ -1980,6 +2015,9 @@ int cmd_record(int argc, const char **argv)
# undef REASON
#endif
+ CPU_ZERO(&rec->affinity_mask);
+ rec->opts.affinity = PERF_AFFINITY_SYS;
+
rec->evlist = perf_evlist__new();
if (rec->evlist == NULL)
return -ENOMEM;
@@ -2143,6 +2181,8 @@ int cmd_record(int argc, const char **argv)
if (verbose > 0)
pr_info("nr_cblocks: %d\n", rec->opts.nr_cblocks);
+ pr_debug("affinity: %s\n", affinity_tags[rec->opts.affinity]);
+
err = __cmd_record(&record, argc, argv);
out:
perf_evlist__delete(rec->evlist);
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.