From f85d120c46e7e31e0516b15a9a11f6721150eb3b Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 23 Aug 2023 21:13:29 -0700
Subject: [PATCH] perf jevents: Sort strings in the big C string to reduce
 faults

Sort the strings within the big C string based on whether they were
for a metric and then by when they were added. This helps group
related strings and reduce minor faults by approximately 10 in 1740,
about 0.57%.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Gaosheng Cui <cuigaosheng1@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230824041330.266337-18-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/pmu-events/jevents.py | 31 +++++++++++++++++++++++--------
 1 file changed, 23 insertions(+), 8 deletions(-)

diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py
index 01335a452e705..e5bce57f56883 100755
--- a/tools/perf/pmu-events/jevents.py
+++ b/tools/perf/pmu-events/jevents.py
@@ -113,13 +113,24 @@ class BigCString:
   strings: Set[str]
   big_string: Sequence[str]
   offsets: Dict[str, int]
+  insert_number: int
+  insert_point: Dict[str, int]
+  metrics: Set[str]
 
   def __init__(self):
     self.strings = set()
+    self.insert_number = 0;
+    self.insert_point = {}
+    self.metrics = set()
 
-  def add(self, s: str) -> None:
+  def add(self, s: str, metric: bool) -> None:
     """Called to add to the big string."""
-    self.strings.add(s)
+    if s not in self.strings:
+      self.strings.add(s)
+      self.insert_point[s] = self.insert_number
+      self.insert_number += 1
+      if metric:
+        self.metrics.add(s)
 
   def compute(self) -> None:
     """Called once all strings are added to compute the string and offsets."""
@@ -160,8 +171,11 @@ class BigCString:
     self.big_string = []
     self.offsets = {}
 
+    def string_cmp_key(s: str) -> Tuple[bool, int, str]:
+      return (s in self.metrics, self.insert_point[s], s)
+
     # Emit all strings that aren't folded in a sorted manner.
-    for s in sorted(self.strings):
+    for s in sorted(self.strings, key=string_cmp_key):
       if s not in folded_strings:
         self.offsets[s] = big_string_offset
         self.big_string.append(f'/* offset={big_string_offset} */ "')
@@ -574,19 +588,20 @@ def preprocess_one_file(parents: Sequence[str], item: os.DirEntry) -> None:
       assert len(mgroup) > 1, parents
       description = f"{metricgroup_descriptions[mgroup]}\\000"
       mgroup = f"{mgroup}\\000"
-      _bcs.add(mgroup)
-      _bcs.add(description)
+      _bcs.add(mgroup, metric=True)
+      _bcs.add(description, metric=True)
       _metricgroups[mgroup] = description
     return
 
   topic = get_topic(item.name)
   for event in read_json_events(item.path, topic):
     pmu_name = f"{event.pmu}\\000"
-    _bcs.add(pmu_name)
     if event.name:
-      _bcs.add(event.build_c_string(metric=False))
+      _bcs.add(pmu_name, metric=False)
+      _bcs.add(event.build_c_string(metric=False), metric=False)
     if event.metric_name:
-      _bcs.add(event.build_c_string(metric=True))
+      _bcs.add(pmu_name, metric=True)
+      _bcs.add(event.build_c_string(metric=True), metric=True)
 
 def process_one_file(parents: Sequence[str], item: os.DirEntry) -> None:
   """Process a JSON file during the main walk."""
-- 
2.30.2