[3.13] gh-142183: Cache one datachunk per tstate to prevent alloc/dealloc thrashing (GH-145789) (#146123)

* gh-142183: Cache one datachunk per tstate to prevent alloc/dealloc thrashing (GH-145789) (#145828)

Cache one datachunk per tstate to prevent alloc/dealloc thrashing when repeatedly hitting the same call depth at exactly the wrong boundary.

Move new _ts member to the end to not mess up remote debuggers' ideas of the
struct's layout. (The struct is only created by the runtime, and the new
field only used by the runtime, so it should be safe.)

(cherry picked from commit 706fd4ec08)
(cherry picked from commit 19cbcc0f85)
Co-authored-by: blurb-it[bot] <43283697+blurb-it[bot]@users.noreply.github.com>
Co-authored-by: Miss Islington (bot) <31488909+miss-islington@users.noreply.github.com>

Include/cpython/pystate.h

@@ -200,6 +200,8 @@ struct _ts {
        The PyThreadObject must hold the only reference to this value.
     */
     PyObject *threading_local_sentinel;
+
+    _PyStackChunk *datastack_cached_chunk;
 };
 
 #ifdef Py_DEBUG

Misc/NEWS.d/next/Core_and_Builtins/2026-03-11-00-13-59.gh-issue-142183.2iVhJH.rst

@@ -0,0 +1 @@
+Avoid a pathological case where repeated calls at a specific stack depth could be significantly slower.

Python/pystate.c

@@ -1521,6 +1521,7 @@ init_threadstate(_PyThreadStateImpl *_tstate,
     tstate->datastack_chunk = NULL;
     tstate->datastack_top = NULL;
     tstate->datastack_limit = NULL;
+    tstate->datastack_cached_chunk = NULL;
     tstate->what_event = -1;
     tstate->previous_executor = NULL;
     tstate->dict_global_version = 0;
@@ -1655,6 +1656,11 @@ clear_datastack(PyThreadState *tstate)
         _PyObject_VirtualFree(chunk, chunk->size);
         chunk = prev;
     }
+    if (tstate->datastack_cached_chunk != NULL) {
+        _PyObject_VirtualFree(tstate->datastack_cached_chunk,
+                              tstate->datastack_cached_chunk->size);
+        tstate->datastack_cached_chunk = NULL;
+    }
 }
 
 void
@@ -2934,9 +2940,20 @@ push_chunk(PyThreadState *tstate, int size)
     while (allocate_size < (int)sizeof(PyObject*)*(size + MINIMUM_OVERHEAD)) {
         allocate_size *= 2;
     }
-    _PyStackChunk *new = allocate_chunk(allocate_size, tstate->datastack_chunk);
-    if (new == NULL) {
-        return NULL;
+    _PyStackChunk *new;
+    if (tstate->datastack_cached_chunk != NULL
+        && (size_t)allocate_size <= tstate->datastack_cached_chunk->size)
+    {
+        new = tstate->datastack_cached_chunk;
+        tstate->datastack_cached_chunk = NULL;
+        new->previous = tstate->datastack_chunk;
+        new->top = 0;
+    }
+    else {
+        new = allocate_chunk(allocate_size, tstate->datastack_chunk);
+        if (new == NULL) {
+            return NULL;
+        }
     }
     if (tstate->datastack_chunk) {
         tstate->datastack_chunk->top = tstate->datastack_top -
@@ -2972,12 +2989,17 @@ _PyThreadState_PopFrame(PyThreadState *tstate, _PyInterpreterFrame * frame)
     if (base == &tstate->datastack_chunk->data[0]) {
         _PyStackChunk *chunk = tstate->datastack_chunk;
         _PyStackChunk *previous = chunk->previous;
+        _PyStackChunk *cached = tstate->datastack_cached_chunk;
         // push_chunk ensures that the root chunk is never popped:
         assert(previous);
         tstate->datastack_top = &previous->data[previous->top];
         tstate->datastack_chunk = previous;
-        _PyObject_VirtualFree(chunk, chunk->size);
         tstate->datastack_limit = (PyObject **)(((char *)previous) + previous->size);
+        chunk->previous = NULL;
+        if (cached != NULL) {
+            _PyObject_VirtualFree(cached, cached->size);
+        }
+        tstate->datastack_cached_chunk = chunk;
     }
     else {
         assert(tstate->datastack_top);