Store -k clockid frequency into Perf trace to enable timestamps
derived metrics conversion into wall clock time on reporting stage.
Below is the example of perf report output:
tools/perf/perf record -k raw -- ../../matrix/linux/matrix.gcc
...
[ perf record: Captured and wrote 31.222 MB perf.data (818054 samples) ]
tools/perf/perf report --header
# ========
...
# event : name = cycles:ppp, , size = 112, { sample_period, sample_freq } = 4000, sample_type = IP|TID|TIME|PERIOD, disabled = 1, inherit = 1, mmap = 1, comm = 1, freq = 1, enable_on_exec = 1, task = 1, precise_ip = 3, sample_id_all = 1, exclude_guest = 1, mmap2 = 1, comm_exec = 1, use_clockid = 1, clockid = 4
...
# clockid frequency: 1000 MHz
...
# ========
Signed-off-by: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/23a4a1dc-b160-85a0-347d-40a2ed6d007b@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
if (!rec->opts.full_auxtrace)
perf_header__clear_feat(&session->header, HEADER_AUXTRACE);
+ if (!(rec->opts.use_clockid && rec->opts.clockid_res_ns))
+ perf_header__clear_feat(&session->header, HEADER_CLOCKID);
+
perf_header__clear_feat(&session->header, HEADER_STAT);
}
record__init_features(rec);
+ if (rec->opts.use_clockid && rec->opts.clockid_res_ns)
+ session->header.env.clockid_res_ns = rec->opts.clockid_res_ns;
+
if (forks) {
err = perf_evlist__prepare_workload(rec->evlist, &opts->target,
argv, data->is_pipe,
CLOCKID_END,
};
+static int get_clockid_res(clockid_t clk_id, u64 *res_ns)
+{
+ struct timespec res;
+
+ *res_ns = 0;
+ if (!clock_getres(clk_id, &res))
+ *res_ns = res.tv_nsec + res.tv_sec * NSEC_PER_SEC;
+ else
+ pr_warning("WARNING: Failed to determine specified clock resolution.\n");
+
+ return 0;
+}
+
static int parse_clockid(const struct option *opt, const char *str, int unset)
{
struct record_opts *opts = (struct record_opts *)opt->value;
/* if its a number, we're done */
if (sscanf(str, "%d", &opts->clockid) == 1)
- return 0;
+ return get_clockid_res(opts->clockid, &opts->clockid_res_ns);
/* allow a "CLOCK_" prefix to the name */
if (!strncasecmp(str, "CLOCK_", 6))
for (cm = clockids; cm->name; cm++) {
if (!strcasecmp(str, cm->name)) {
opts->clockid = cm->clockid;
- return 0;
+ return get_clockid_res(opts->clockid,
+ &opts->clockid_res_ns);
}
}
unsigned initial_delay;
bool use_clockid;
clockid_t clockid;
+ u64 clockid_res_ns;
unsigned int proc_map_timeout;
};
struct numa_node *numa_nodes;
struct memory_node *memory_nodes;
unsigned long long memory_bsize;
+ u64 clockid_res_ns;
};
extern struct perf_env perf_env;
return err;
}
+static int write_clockid(struct feat_fd *ff,
+ struct perf_evlist *evlist __maybe_unused)
+{
+ return do_write(ff, &ff->ph->env.clockid_res_ns,
+ sizeof(ff->ph->env.clockid_res_ns));
+}
+
static int cpu_cache_level__sort(const void *a, const void *b)
{
struct cpu_cache_level *cache_a = (struct cpu_cache_level *)a;
fprintf(fp, "# Core ID and Socket ID information is not available\n");
}
+static void print_clockid(struct feat_fd *ff, FILE *fp)
+{
+ fprintf(fp, "# clockid frequency: %"PRIu64" MHz\n",
+ ff->ph->env.clockid_res_ns * 1000);
+}
+
static void free_event_desc(struct perf_evsel *events)
{
struct perf_evsel *evsel;
return ret;
}
+static int process_clockid(struct feat_fd *ff,
+ void *data __maybe_unused)
+{
+ if (do_read_u64(ff, &ff->ph->env.clockid_res_ns))
+ return -1;
+
+ return 0;
+}
+
struct feature_ops {
int (*write)(struct feat_fd *ff, struct perf_evlist *evlist);
void (*print)(struct feat_fd *ff, FILE *fp);
FEAT_OPN(CACHE, cache, true),
FEAT_OPR(SAMPLE_TIME, sample_time, false),
FEAT_OPR(MEM_TOPOLOGY, mem_topology, true),
+ FEAT_OPR(CLOCKID, clockid, false)
};
struct header_print_data {
HEADER_CACHE,
HEADER_SAMPLE_TIME,
HEADER_MEM_TOPOLOGY,
+ HEADER_CLOCKID,
HEADER_LAST_FEATURE,
HEADER_FEAT_BITS = 256,
};