Group pprof samples by threadpool comm

This is a heuristic, that many threads often live in threadpools
labelled with numbers and a common string. By grouping these
threadpools, we're able to see common work.

Often these threadpools are created with a format string like "DefaultPool%d",
and my heuristic "unmaps" that, kind-of. Hopefully it's clear to the reader of
these labels what is meant.

Here's an example of running it on a Google Maps build, which nicely shows the
difference between the `thread` and new `threadpool` tags:

```
$ pprof pprof.profile
Entering interactive mode (type "help" for commands, "o" for options)
(pprof) tags

 thread: Total 103383248686.0
         22118435629.0 (21.39%): DefaultPool8
         13358985234.0 (12.92%): DefaultPool1
          7386956769.0 ( 7.15%): GoogleApiHandle
          5410867464.0 ( 5.23%): Primes-1
          5307503967.0 ( 5.13%): Binder:14330_3
          5151798743.0 ( 4.98%): com.google.android.apps.maps
          4790949129.0 ( 4.63%): queued-work-loo
          3147004739.0 ( 3.04%): RenderThread
          2885251486.0 ( 2.79%): ChromiumNet
          2629960939.0 ( 2.54%): GLViewThreadImp
          2614501772.0 ( 2.53%): Labeling
          2317391011.0 ( 2.24%): LocFreshPool1
          2268259602.0 ( 2.19%): MemoryMon
          2129146149.0 ( 2.06%): weak-identity-m
          1870032894.0 ( 1.81%): Binder:14330_1
          1814053100.0 ( 1.75%): Primes-2
          1804141068.0 ( 1.75%): DefaultPool6
          1724206320.0 ( 1.67%): TilePrepPool2
          1611002144.0 ( 1.56%): DefaultPool7
          1579754376.0 ( 1.53%): Jit thread pool
          1518972491.0 ( 1.47%): TilePrepPool3
          1356331492.0 ( 1.31%): DefaultPool3
          1210458509.0 ( 1.17%): DefaultPool5
          1198135693.0 ( 1.16%): NavState
          1126259329.0 ( 1.09%): Location
          1008315579.0 ( 0.98%): DefaultPool4
           983120929.0 ( 0.95%): TilePrepPool1
           814214874.0 ( 0.79%): Timer-0
           793766954.0 ( 0.77%): ThreadPoolForeg
           344686545.0 ( 0.33%): HeapTaskDaemon
           244979090.0 ( 0.24%): DefaultPool2
           146047936.0 ( 0.14%): NetworkPool1
           126920534.0 ( 0.12%): NetworkPool2
            82417870.0 ( 0.08%): OfflineManage
            70649177.0 (0.068%): Sensors
            68850631.0 (0.067%): NavInternal
            66499899.0 (0.064%): NetworkPool4
            59950214.0 (0.058%): Primes-nativecr
            51125581.0 (0.049%): NetworkPool3
            39731570.0 (0.038%): NetworkPool5
            29167450.0 (0.028%): ReferenceQueueD
            27231566.0 (0.026%): pool-6-thread-1
            23984844.0 (0.023%): CronetInit
            18201927.0 (0.018%): Binder:14330_4
            12020989.0 (0.012%): ClassLoader
            11934322.0 (0.012%): SharedPreferenc
            8960622.0 (0.0087%): Primes-Jank
            5272917.0 (0.0051%): FinalizerDaemon
             5145625.0 (0.005%): GAC_Executor[1]
             3079896.0 (0.003%): NativeLibLoader
            1476511.0 (0.0014%): pool-6-thread-2
            1342552.0 (0.0013%): network
            1224843.0 (0.0012%): OfflineDynamic
            1112971.0 (0.0011%): Binder:14330_2
            568698.0 (0.00055%): ThreadPoolServi
            264167.0 (0.00026%): pool-6-thread-3
            199062.0 (0.00019%): LocFreshPool2
            183646.0 (0.00018%): Network File Th
            144583.0 (0.00014%): OneGoogle #0
             59323.0 (5.7e-05%): glide-active-re
             34740.0 (3.4e-05%): Traffic auto-re

threadpool: Total 103383248686.0
             42712648745.0 (41.31%): DefaultPool%d
              7386956769.0 ( 7.15%): GoogleApiHandle
              7224920564.0 ( 6.99%): Primes-%d
              7196851759.0 ( 6.96%): Binder:%d_%d
              5151798743.0 ( 4.98%): com.google.android.apps.maps
              4790949129.0 ( 4.63%): queued-work-loo
              4226299740.0 ( 4.09%): TilePrepPool%d
              3147004739.0 ( 3.04%): RenderThread
              2885251486.0 ( 2.79%): ChromiumNet
              2629960939.0 ( 2.54%): GLViewThreadImp
              2614501772.0 ( 2.53%): Labeling
              2317590073.0 ( 2.24%): LocFreshPool%d
              2268259602.0 ( 2.19%): MemoryMon
              2129146149.0 ( 2.06%): weak-identity-m
              1579754376.0 ( 1.53%): Jit thread pool
              1198135693.0 ( 1.16%): NavState
              1126259329.0 ( 1.09%): Location
               814214874.0 ( 0.79%): Timer-%d
               793766954.0 ( 0.77%): ThreadPoolForeg
               430325520.0 ( 0.42%): NetworkPool%d
               344686545.0 ( 0.33%): HeapTaskDaemon
                82417870.0 ( 0.08%): OfflineManage
                70649177.0 (0.068%): Sensors
                68850631.0 (0.067%): NavInternal
                59950214.0 (0.058%): Primes-nativecr
                29167450.0 (0.028%): ReferenceQueueD
                28972244.0 (0.028%): pool-%d-thread-%d
                23984844.0 (0.023%): CronetInit
                12020989.0 (0.012%): ClassLoader
                11934322.0 (0.012%): SharedPreferenc
                8960622.0 (0.0087%): Primes-Jank
                5272917.0 (0.0051%): FinalizerDaemon
                 5145625.0 (0.005%): GAC_Executor[%d]
                 3079896.0 (0.003%): NativeLibLoader
                1342552.0 (0.0013%): network
                1224843.0 (0.0012%): OfflineDynamic
                568698.0 (0.00055%): ThreadPoolServi
                183646.0 (0.00018%): Network File Th
                144583.0 (0.00014%): OneGoogle #%d
                 59323.0 (5.7e-05%): glide-active-re
                 34740.0 (3.4e-05%): Traffic auto-re
```

BUG=200992206
Test: ran test/test.py -p TestPprofProtoGenerator.\*

Change-Id: I249aed58f753f58215c9bd0e7e2e5b9253baf610

2 files changed, 20 insertions, 3 deletions

diff --git a/simpleperf/scripts/pprof_proto_generator.py b/simpleperf/scripts/pprof_proto_generator.py
index 20f61987..b29634da 100755
--- a/simpleperf/scripts/pprof_proto_generator.py
+++ b/simpleperf/scripts/pprof_proto_generator.py
@@ -27,6 +27,7 @@
 import logging
 import os
 import os.path
+import re
 
 from simpleperf_report_lib import ReportLib
 from simpleperf_utils import (Addr2Nearestline, BaseArgumentParser, BinaryFinder, extant_dir,
@@ -301,6 +302,7 @@ class PprofProfileGenerator(object):
             self.lib.ShowArtFrames()
         for file_path in self.config['proguard_mapping_file'] or []:
             self.lib.AddProguardMappingFile(file_path)
+        numbers_re = re.compile(r"\d+")
 
         # Process all samples in perf.data, aggregate samples.
         while True:
@@ -320,9 +322,16 @@ class PprofProfileGenerator(object):
             sample = Sample()
             sample.add_value(sample_type_id, 1)
             sample.add_value(sample_type_id + 1, report_sample.period)
-            label = Label(self.get_string_id("thread"),
-                          self.get_string_id(report_sample.thread_comm))
-            sample.labels.append(label)
+            sample.labels.append(Label(
+                self.get_string_id("thread"),
+                self.get_string_id(report_sample.thread_comm)))
+            # Heuristic: threadpools doing similar work are often named as
+            # name-1, name-2, name-3. Combine threadpools into one label
+            # "name-%d" if they only differ by a number.
+            sample.labels.append(Label(
+                self.get_string_id("threadpool"),
+                self.get_string_id(
+                    numbers_re.sub("%d", report_sample.thread_comm))))
             if self._filter_symbol(symbol):
                 location_id = self.get_location_id(report_sample.ip, symbol)
                 sample.add_location_id(location_id)
diff --git a/simpleperf/scripts/test/pprof_proto_generator_test.py b/simpleperf/scripts/test/pprof_proto_generator_test.py
index 72089f71..4a8de00b 100644
--- a/simpleperf/scripts/test/pprof_proto_generator_test.py
+++ b/simpleperf/scripts/test/pprof_proto_generator_test.py
@@ -50,6 +50,14 @@ class TestPprofProtoGenerator(TestBase):
         self.assertIn(key, self.run_generator(['--pid', '10419', '10416']))
         self.assertNotIn(key, self.run_generator(['--pid', '10416']))
 
+    def test_thread_labels(self):
+        output = self.run_generator()
+        self.assertIn('label[0] = thread:Binder:10419_1', output)
+        self.assertIn('label[0] = thread:Binder:10419_2', output)
+        self.assertIn('label[0] = thread:Binder:10419_3', output)
+        self.assertIn('label[0] = thread:Binder:10419_4', output)
+        self.assertIn('label[1] = threadpool:Binder:%d_%d', output)
+
     def test_tid_filter(self):
         key1 = 'art::ProfileSaver::Run()'  # function in thread 10459
         key2 = 'PlayScene::DoFrame()'  # function in thread 10463