perf record: Make per-cpu mmaps the default.

This affects the -p, -t and -u options that previously defaulted to
per-thread mmaps.

Consequently add an option to select per-thread mmaps to support the old
behaviour.

Note that per-thread can be used with a workload-only (i.e. none of -p,
-t, -u, -a or -C is selected) to get a per-thread mmap with no
inheritance.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/5286271D.3020808@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This commit is contained in:
Adrian Hunter 2013-11-15 15:52:29 +02:00 committed by Arnaldo Carvalho de Melo
parent e944d3d7d1
commit 3aa5939d71
7 changed files with 29 additions and 14 deletions

View File

@ -201,11 +201,11 @@ abort events and some memory events in precise mode on modern Intel CPUs.
--transaction::
Record transaction flags for transaction related events.
--force-per-cpu::
Force the use of per-cpu mmaps. By default, when tasks are specified (i.e. -p,
-t or -u options) per-thread mmaps are created. This option overrides that and
forces per-cpu mmaps. A side-effect of that is that inheritance is
automatically enabled. Add the -i option also to disable inheritance.
--per-thread::
Use per-thread mmaps. By default per-cpu mmaps are created. This option
overrides that and uses per-thread mmaps. A side-effect of that is that
inheritance is automatically disabled. --per-thread is ignored with a warning
if combined with -a or -C options.
SEE ALSO
--------

View File

@ -800,6 +800,7 @@ static struct perf_record record = {
.freq = 4000,
.target = {
.uses_mmap = true,
.default_per_cpu = true,
},
},
};
@ -888,8 +889,8 @@ const struct option record_options[] = {
"sample by weight (on special events only)"),
OPT_BOOLEAN(0, "transaction", &record.opts.sample_transaction,
"sample transaction flags (special events only)"),
OPT_BOOLEAN(0, "force-per-cpu", &record.opts.target.force_per_cpu,
"force the use of per-cpu mmaps"),
OPT_BOOLEAN(0, "per-thread", &record.opts.target.per_thread,
"use per-thread mmaps"),
OPT_END()
};

View File

@ -3,5 +3,5 @@ command = record
args = -i kill >/dev/null 2>&1
[event:base-record]
sample_type=259
sample_type=263
inherit=0

View File

@ -819,8 +819,10 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
if (evlist->threads == NULL)
return -1;
if (target->force_per_cpu)
evlist->cpus = cpu_map__new(target->cpu_list);
if (target->default_per_cpu)
evlist->cpus = target->per_thread ?
cpu_map__dummy_new() :
cpu_map__new(target->cpu_list);
else if (target__has_task(target))
evlist->cpus = cpu_map__dummy_new();
else if (!target__has_cpu(target) && !target->uses_mmap)

View File

@ -574,6 +574,7 @@ void perf_evsel__config(struct perf_evsel *evsel,
struct perf_evsel *leader = evsel->leader;
struct perf_event_attr *attr = &evsel->attr;
int track = !evsel->idx; /* only the first counter needs these */
bool per_cpu = opts->target.default_per_cpu && !opts->target.per_thread;
attr->sample_id_all = perf_missing_features.sample_id_all ? 0 : 1;
attr->inherit = !opts->no_inherit;
@ -647,7 +648,7 @@ void perf_evsel__config(struct perf_evsel *evsel,
}
}
if (target__has_cpu(&opts->target) || opts->target.force_per_cpu)
if (target__has_cpu(&opts->target))
perf_evsel__set_sample_bit(evsel, CPU);
if (opts->period)
@ -655,7 +656,7 @@ void perf_evsel__config(struct perf_evsel *evsel,
if (!perf_missing_features.sample_id_all &&
(opts->sample_time || !opts->no_inherit ||
target__has_cpu(&opts->target) || opts->target.force_per_cpu))
target__has_cpu(&opts->target) || per_cpu))
perf_evsel__set_sample_bit(evsel, TIME);
if (opts->raw_samples) {

View File

@ -55,6 +55,13 @@ enum target_errno target__validate(struct target *target)
ret = TARGET_ERRNO__UID_OVERRIDE_SYSTEM;
}
/* THREAD and SYSTEM/CPU are mutually exclusive */
if (target->per_thread && (target->system_wide || target->cpu_list)) {
target->per_thread = false;
if (ret == TARGET_ERRNO__SUCCESS)
ret = TARGET_ERRNO__SYSTEM_OVERRIDE_THREAD;
}
return ret;
}
@ -100,6 +107,7 @@ static const char *target__error_str[] = {
"UID switch overriding CPU",
"PID/TID switch overriding SYSTEM",
"UID switch overriding SYSTEM",
"SYSTEM/CPU switch overriding PER-THREAD",
"Invalid User: %s",
"Problems obtaining information for user %s",
};
@ -131,7 +139,8 @@ int target__strerror(struct target *target, int errnum,
msg = target__error_str[idx];
switch (errnum) {
case TARGET_ERRNO__PID_OVERRIDE_CPU ... TARGET_ERRNO__UID_OVERRIDE_SYSTEM:
case TARGET_ERRNO__PID_OVERRIDE_CPU ...
TARGET_ERRNO__SYSTEM_OVERRIDE_THREAD:
snprintf(buf, buflen, "%s", msg);
break;

View File

@ -12,7 +12,8 @@ struct target {
uid_t uid;
bool system_wide;
bool uses_mmap;
bool force_per_cpu;
bool default_per_cpu;
bool per_thread;
};
enum target_errno {
@ -33,6 +34,7 @@ enum target_errno {
TARGET_ERRNO__UID_OVERRIDE_CPU,
TARGET_ERRNO__PID_OVERRIDE_SYSTEM,
TARGET_ERRNO__UID_OVERRIDE_SYSTEM,
TARGET_ERRNO__SYSTEM_OVERRIDE_THREAD,
/* for target__parse_uid() */
TARGET_ERRNO__INVALID_UID,