perf record: Split --data-mmap option

Currently -d/--data option controls both PERF_SAMPLE_ADDR bit and
perf_event_attr.mmap_data flag.  Separate them using new --data-mmap
option to support recording only one of them.

For data-type profiling, data MMAP is unnecessary but it wastes a lot
of space in the ring buffer and data file.

Committer testing:

On an idle system:

  root@x1:~# perf record -d -a sleep 1
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 5.672 MB perf.data (1075 samples) ]
  root@x1:~# ls -la perf.data
  -rw-------. 1 root root 5982480 Dec 16 15:34 perf.data
  root@x1:~# perf evlist -v
  cpu_atom/cycles/P: type: 0 (PERF_TYPE_HARDWARE), size: 144, config: 0xa00000000 (cpu_atom/PERF_COUNT_HW_CPU_CYCLES/), { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|ADDR|CPU|PERIOD|IDENTIFIER|DATA_SRC, read_format: ID|LOST, disabled: 1, freq: 1, precise_ip: 3, sample_id_all: 1
  cpu_core/cycles/P: type: 0 (PERF_TYPE_HARDWARE), size: 144, config: 0x400000000 (cpu_core/PERF_COUNT_HW_CPU_CYCLES/), { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|ADDR|CPU|PERIOD|IDENTIFIER|DATA_SRC, read_format: ID|LOST, disabled: 1, freq: 1, precise_ip: 3, sample_id_all: 1
  dummy:u: type: 1 (PERF_TYPE_SOFTWARE), size: 144, config: 0x9 (PERF_COUNT_SW_DUMMY), { sample_period, sample_freq }: 1, sample_type: IP|TID|TIME|ADDR|CPU|IDENTIFIER|DATA_SRC, read_format: ID|LOST, exclude_kernel: 1, exclude_hv: 1, mmap: 1, comm: 1, task: 1, mmap_data: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, ksymbol: 1, bpf_event: 1, build_id: 1
  root@x1:~#

Now with just --data-mmap we will not save that much, as only DATA_SRC
will not be enabled in sample_type:

  root@x1:~# perf record --data-mmap -a sleep 1
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 5.576 MB perf.data (716 samples) ]
  root@x1:~# ls -la perf.data
  -rw-------. 1 root root 5880112 Dec 16 15:37 perf.data
  root@x1:~# perf evlist -v
  cpu_atom/cycles/P: type: 0 (PERF_TYPE_HARDWARE), size: 144, config: 0xa00000000 (cpu_atom/PERF_COUNT_HW_CPU_CYCLES/), { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CPU|PERIOD|IDENTIFIER, read_format: ID|LOST, disabled: 1, freq: 1, precise_ip: 3, sample_id_all: 1
  cpu_core/cycles/P: type: 0 (PERF_TYPE_HARDWARE), size: 144, config: 0x400000000 (cpu_core/PERF_COUNT_HW_CPU_CYCLES/), { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CPU|PERIOD|IDENTIFIER, read_format: ID|LOST, disabled: 1, freq: 1, precise_ip: 3, sample_id_all: 1
  dummy:u: type: 1 (PERF_TYPE_SOFTWARE), size: 144, config: 0x9 (PERF_COUNT_SW_DUMMY), { sample_period, sample_freq }: 1, sample_type: IP|TID|TIME|CPU|IDENTIFIER, read_format: ID|LOST, exclude_kernel: 1, exclude_hv: 1, mmap: 1, comm: 1, task: 1, mmap_data: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, ksymbol: 1, bpf_event: 1, build_id: 1
  root@x1:~#

To complete, just with DATA_SRC, no mmap_data:

  root@x1:~# perf record --sample-mem-info -a sleep 1
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 1.407 MB perf.data (1311 samples) ]
  root@x1:~# ls -la perf.data
  -rw-------. 1 root root 1509224 Dec 16 15:40 perf.data
  root@x1:~# perf evlist -v
  cpu_atom/cycles/P: type: 0 (PERF_TYPE_HARDWARE), size: 144, config: 0xa00000000 (cpu_atom/PERF_COUNT_HW_CPU_CYCLES/), { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CPU|PERIOD|IDENTIFIER|DATA_SRC, read_format: ID|LOST, disabled: 1, freq: 1, precise_ip: 3, sample_id_all: 1
  cpu_core/cycles/P: type: 0 (PERF_TYPE_HARDWARE), size: 144, config: 0x400000000 (cpu_core/PERF_COUNT_HW_CPU_CYCLES/), { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CPU|PERIOD|IDENTIFIER|DATA_SRC, read_format: ID|LOST, disabled: 1, freq: 1, precise_ip: 3, sample_id_all: 1
  dummy:u: type: 1 (PERF_TYPE_SOFTWARE), size: 144, config: 0x9 (PERF_COUNT_SW_DUMMY), { sample_period, sample_freq }: 1, sample_type: IP|TID|TIME|CPU|IDENTIFIER|DATA_SRC, read_format: ID|LOST, exclude_kernel: 1, exclude_hv: 1, mmap: 1, comm: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, ksymbol: 1, bpf_event: 1, build_id: 1
  root@x1:~#

Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index e8b9aadbbfa5057411f0fdcda7aae7186b795fc2..c402e74172f6a22d157c7ee78f41621c796bb4a9 100644 (file)
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -344,7 +344,8 @@ OPTIONS
 
 -d::
 --data::
-       Record the sample virtual addresses.  Implies --sample-mem-info.
+       Record the sample virtual addresses.  Implies --sample-mem-info and
+       --data-mmap.
 
 --phys-data::
        Record the sample physical addresses.
@@ -861,6 +862,11 @@ filtered through the mask provided by -C option.
        Prepare BPF filter to be used by regular users.  The action should be
        either "pin" or "unpin".  The filter can be used after it's pinned.
 
+--data-mmap::
+       Enable recording MMAP events for non-executable mappings.  Basically
+       perf only records executable mappings but data mmaping can be useful
+       when you analyze data access with sample addresses.  So using -d option
+       would enable this unless you specify --no-data-mmap manually.
 
 include::intel-hybrid.txt[]
 

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 2584d0d8bc820676da60bdf5f59d41371d85a93a..cbfbd9bb10634093cb13b3f420ca2177a4c30c04 100644 (file)
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1881,7 +1881,7 @@ static int record__synthesize_workload(struct record *rec, bool tail)
                                                 process_synthesized_event,
                                                 &rec->session->machines.host,
                                                 needs_mmap,
-                                                rec->opts.sample_address);
+                                                rec->opts.record_data_mmap);
        perf_thread_map__put(thread_map);
        return err;
 }
@@ -2191,7 +2191,7 @@ static int record__synthesize(struct record *rec, bool tail)
 
                err = __machine__synthesize_threads(machine, tool, &opts->target,
                                                    rec->evlist->core.threads,
-                                                   f, needs_mmap, opts->sample_address,
+                                                   f, needs_mmap, opts->record_data_mmap,
                                                    rec->opts.nr_threads_synthesize);
        }
 
@@ -3006,8 +3006,9 @@ int record_opts__parse_callchain(struct record_opts *record,
        ret = parse_callchain_record_opt(arg, callchain);
        if (!ret) {
                /* Enable data address sampling for DWARF unwind. */
-               if (callchain->record_mode == CALLCHAIN_DWARF)
-                       record->sample_address = true;
+               if (callchain->record_mode == CALLCHAIN_DWARF &&
+                   !record->record_data_mmap_set)
+                       record->record_data_mmap = true;
                callchain_debug(callchain);
        }
 
@@ -3686,6 +3687,9 @@ static struct option __record_options[] = {
        OPT_CALLBACK(0, "off-cpu-thresh", &record.opts, "ms",
                     "Dump off-cpu samples if off-cpu time exceeds this threshold (in milliseconds). (Default: 500ms)",
                     record__parse_off_cpu_thresh),
+       OPT_BOOLEAN_SET(0, "data-mmap", &record.opts.record_data_mmap,
+                       &record.opts.record_data_mmap_set,
+                       "Record mmap events for non-executable mappings"),
        OPT_END()
 };
 
@@ -4249,9 +4253,12 @@ int cmd_record(int argc, const char **argv)
                goto out_opts;
        }
 
-       /* For backward compatibility, -d implies --mem-info */
-       if (rec->opts.sample_address)
+       /* For backward compatibility, -d implies --mem-info and --data-mmap */
+       if (rec->opts.sample_address) {
                rec->opts.sample_data_src = true;
+               if (!rec->opts.record_data_mmap_set)
+                       rec->opts.record_data_mmap = true;
+       }
 
        /*
         * Allow aliases to facilitate the lookup of symbols for address

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 9cd706f6279313c2cc53eba1adbd45f352090f75..ec6552a6f667fec6aee5df3d553cac3572e7fcdf 100644 (file)
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1445,10 +1445,11 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts,
                attr->inherit_stat = 1;
        }
 
-       if (opts->sample_address) {
+       if (opts->sample_address)
                evsel__set_sample_bit(evsel, ADDR);
+
+       if (opts->record_data_mmap)
                attr->mmap_data = track;
-       }
 
        /*
         * We don't allow user space callchains for  function trace

diff --git a/tools/perf/util/record.h b/tools/perf/util/record.h
index ea3a6c4657eefb743dc3d54b0b791ea39117cc10..93627c9a73387ddde8a0120ae0ee0853835620f5 100644 (file)
--- a/tools/perf/util/record.h
+++ b/tools/perf/util/record.h
@@ -40,6 +40,8 @@ struct record_opts {
        bool          record_cgroup;
        bool          record_switch_events;
        bool          record_switch_events_set;
+       bool          record_data_mmap;
+       bool          record_data_mmap_set;
        bool          all_kernel;
        bool          all_user;
        bool          kernel_callchains;