gh-108753: Enhance pystats (#108754)

Statistics gathering is now off by default. Use the "-X pystats"
command line option or set the new PYTHONSTATS environment variable
to 1 to turn statistics gathering on at Python startup.

Statistics are no longer dumped at exit if statistics gathering was
off or statistics have been cleared.

Changes:

* Add PYTHONSTATS environment variable.
* sys._stats_dump() now returns False if statistics are not dumped
  because they are all equal to zero.
* Add PyConfig._pystats member.
* Add tests on sys functions and on setting PyConfig._pystats to 1.
* Add Include/cpython/pystats.h and Include/internal/pycore_pystats.h
  header files.
* Rename '_py_stats' variable to '_Py_stats'.
* Exclude Include/cpython/pystats.h from the Py_LIMITED_API.
* Move pystats.h include from object.h to Python.h.
* Add _Py_StatsOn() and _Py_StatsOff() functions. Remove
  '_py_stats_struct' variable from the API: make it static in
  specialize.c.
* Document API in Include/pystats.h and Include/cpython/pystats.h.
* Complete pystats documentation in Doc/using/configure.rst.
* Don't write "all zeros" stats: if _stats_off() and _stats_clear()
  or _stats_dump() were called.
* _PyEval_Fini() now always call _Py_PrintSpecializationStats() which
  does nothing if stats are all zeros.

Co-authored-by: Michael Droettboom <mdboom@gmail.com>

2 files changed, 125 insertions, 0 deletions

diff --git a/Include/cpython/initconfig.h b/Include/cpython/initconfig.h
index 7fb7a98..ee13046 100644
--- a/Include/cpython/initconfig.h
+++ b/Include/cpython/initconfig.h
@@ -215,6 +215,11 @@ typedef struct PyConfig {
 
     // If non-zero, we believe we're running from a source tree.
     int _is_python_build;
+
+#ifdef Py_STATS
+    // If non-zero, turns on statistics gathering.
+    int _pystats;
+#endif
 } PyConfig;
 
 PyAPI_FUNC(void) PyConfig_InitPythonConfig(PyConfig *config);
diff --git a/Include/cpython/pystats.h b/Include/cpython/pystats.h
new file mode 100644
index 0000000..150e16f
--- /dev/null
+++ b/Include/cpython/pystats.h
@@ -0,0 +1,120 @@
+// Statistics on Python performance.
+//
+// API:
+//
+// - _Py_INCREF_STAT_INC() and _Py_DECREF_STAT_INC() used by Py_INCREF()
+//   and Py_DECREF().
+// - _Py_stats variable
+//
+// Functions of the sys module:
+//
+// - sys._stats_on()
+// - sys._stats_off()
+// - sys._stats_clear()
+// - sys._stats_dump()
+//
+// Python must be built with ./configure --enable-pystats to define the
+// Py_STATS macro.
+//
+// Define _PY_INTERPRETER macro to increment interpreter_increfs and
+// interpreter_decrefs. Otherwise, increment increfs and decrefs.
+
+#ifndef Py_CPYTHON_PYSTATS_H
+#  error "this header file must not be included directly"
+#endif
+
+#define SPECIALIZATION_FAILURE_KINDS 36
+
+/* Stats for determining who is calling PyEval_EvalFrame */
+#define EVAL_CALL_TOTAL 0
+#define EVAL_CALL_VECTOR 1
+#define EVAL_CALL_GENERATOR 2
+#define EVAL_CALL_LEGACY 3
+#define EVAL_CALL_FUNCTION_VECTORCALL 4
+#define EVAL_CALL_BUILD_CLASS 5
+#define EVAL_CALL_SLOT 6
+#define EVAL_CALL_FUNCTION_EX 7
+#define EVAL_CALL_API 8
+#define EVAL_CALL_METHOD 9
+
+#define EVAL_CALL_KINDS 10
+
+typedef struct _specialization_stats {
+    uint64_t success;
+    uint64_t failure;
+    uint64_t hit;
+    uint64_t deferred;
+    uint64_t miss;
+    uint64_t deopt;
+    uint64_t failure_kinds[SPECIALIZATION_FAILURE_KINDS];
+} SpecializationStats;
+
+typedef struct _opcode_stats {
+    SpecializationStats specialization;
+    uint64_t execution_count;
+    uint64_t pair_count[256];
+} OpcodeStats;
+
+typedef struct _call_stats {
+    uint64_t inlined_py_calls;
+    uint64_t pyeval_calls;
+    uint64_t frames_pushed;
+    uint64_t frame_objects_created;
+    uint64_t eval_calls[EVAL_CALL_KINDS];
+} CallStats;
+
+typedef struct _object_stats {
+    uint64_t increfs;
+    uint64_t decrefs;
+    uint64_t interpreter_increfs;
+    uint64_t interpreter_decrefs;
+    uint64_t allocations;
+    uint64_t allocations512;
+    uint64_t allocations4k;
+    uint64_t allocations_big;
+    uint64_t frees;
+    uint64_t to_freelist;
+    uint64_t from_freelist;
+    uint64_t new_values;
+    uint64_t dict_materialized_on_request;
+    uint64_t dict_materialized_new_key;
+    uint64_t dict_materialized_too_big;
+    uint64_t dict_materialized_str_subclass;
+    uint64_t dict_dematerialized;
+    uint64_t type_cache_hits;
+    uint64_t type_cache_misses;
+    uint64_t type_cache_dunder_hits;
+    uint64_t type_cache_dunder_misses;
+    uint64_t type_cache_collisions;
+    uint64_t optimization_attempts;
+    uint64_t optimization_traces_created;
+    uint64_t optimization_traces_executed;
+    uint64_t optimization_uops_executed;
+    /* Temporary value used during GC */
+    uint64_t object_visits;
+} ObjectStats;
+
+typedef struct _gc_stats {
+    uint64_t collections;
+    uint64_t object_visits;
+    uint64_t objects_collected;
+} GCStats;
+
+typedef struct _stats {
+    OpcodeStats opcode_stats[256];
+    CallStats call_stats;
+    ObjectStats object_stats;
+    GCStats *gc_stats;
+} PyStats;
+
+
+// Export for shared extensions like 'math'
+PyAPI_DATA(PyStats*) _Py_stats;
+
+#ifdef _PY_INTERPRETER
+#  define _Py_INCREF_STAT_INC() do { if (_Py_stats) _Py_stats->object_stats.interpreter_increfs++; } while (0)
+#  define _Py_DECREF_STAT_INC() do { if (_Py_stats) _Py_stats->object_stats.interpreter_decrefs++; } while (0)
+#else
+#  define _Py_INCREF_STAT_INC() do { if (_Py_stats) _Py_stats->object_stats.increfs++; } while (0)
+#  define _Py_DECREF_STAT_INC() do { if (_Py_stats) _Py_stats->object_stats.decrefs++; } while (0)
+#endif