perf record: Add an option to force per-cpu mmaps

By default, when tasks are specified (i.e. -p, -t or -u options)
per-thread mmaps are created.

Add an option to override that and force per-cpu mmaps.

Further comments by peterz:

So this option allows -t/-p/-u to create one buffer per cpu and attach
all the various thread/process/user tasks' their counters to that one
buffer?

As opposed to the current state where each such counter would have its
own buffer.

Signed-off-by: Adrian Hunter <[email protected]>
Tested-by: Sukadev Bhattiprolu <[email protected]>
Acked-by: Peter Zijlstra <[email protected]>
Cc: David Ahern <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Mike Galbraith <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Paul Mackerras <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Stephane Eranian <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>

diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 052f7c4dc00c25a47dbe6355f0f762744ad5a79a..43b42c4f4a915ad96be76c737b63feee12925de2 100644 (file)
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -201,6 +201,12 @@ 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.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1]

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 4d644fe2d5b78315f6d00f0d66560ae5836e7b02..7c8020a32784abcd6d44223dc3a5586f7ba7f3f0 100644 (file)
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -888,6 +888,8 @@ 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_END()
 };
 

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 5ce2ace2d6c103b8e1f8fc37e6b76a6bbdd3496f..bbc746aa571663d92e989bb5f3f2703c31c9a193 100644 (file)
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -819,7 +819,9 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
        if (evlist->threads == NULL)
                return -1;
 
-       if (target__has_task(target))
+       if (target->force_per_cpu)
+               evlist->cpus = 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)
                evlist->cpus = cpu_map__dummy_new();

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 18f7c188ff632816376c26b9f5a3594df4571fac..46dd4c2a41ce7e0a844e0b691c134e3ce23f55e6 100644 (file)
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -645,7 +645,7 @@ void perf_evsel__config(struct perf_evsel *evsel,
                }
        }
 
-       if (target__has_cpu(&opts->target))
+       if (target__has_cpu(&opts->target) || opts->target.force_per_cpu)
                perf_evsel__set_sample_bit(evsel, CPU);
 
        if (opts->period)
@@ -653,7 +653,7 @@ 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)))
+            target__has_cpu(&opts->target) || opts->target.force_per_cpu))
                perf_evsel__set_sample_bit(evsel, TIME);
 
        if (opts->raw_samples) {

diff --git a/tools/perf/util/target.h b/tools/perf/util/target.h
index 89bab7129de4a3c92b74ca037787431c155f251f..2d0c506908926f6fce822adc45a39e76911edd10 100644 (file)
--- a/tools/perf/util/target.h
+++ b/tools/perf/util/target.h
@@ -12,6 +12,7 @@ struct target {
        uid_t        uid;
        bool         system_wide;
        bool         uses_mmap;
+       bool         force_per_cpu;
 };
 
 enum target_errno {