From 9df477c0ce7ac896d75d3bb06c3dd14808cd659a Mon Sep 17 00:00:00 2001
From: Pablo Galindo Salgado <Pablogsal@gmail.com>
Date: Sun, 21 Sep 2025 18:32:03 +0100
Subject: [PATCH] gh-138709: Fix race condition in test_external_inspection
 (#139209)

Fix race condition in test_external_inspection thread status tests

The tests test_thread_status_detection and test_thread_status_gil_detection
had a race condition where the test could sample thread status between when
the sleeper thread sends its "ready" message and when it actually calls
time.sleep(). This caused intermittent test failures where the sleeper
thread would show as running (status=0) instead of idle (status=1 or 2).

The fix moves the thread status collection inside the retry loop and
specifically waits for the expected thread states before proceeding with
assertions. The retry loop now continues until:
- The sleeper thread shows as idle (status=1 for CPU mode, status=2 for GIL mode)
- The busy thread shows as running (status=0)
- Both thread IDs are found in the status collection

This ensures the test waits for threads to settle into their expected states
before making assertions, eliminating the race condition.
---
 Lib/test/test_external_inspection.py | 44 +++++++++++++++-------------
 1 file changed, 24 insertions(+), 20 deletions(-)

diff --git a/Lib/test/test_external_inspection.py b/Lib/test/test_external_inspection.py
index 2f8f5f0e1693..01720457e61f 100644
--- a/Lib/test/test_external_inspection.py
+++ b/Lib/test/test_external_inspection.py
@@ -1751,14 +1751,23 @@ class TestDetectionOfThreadStatus(unittest.TestCase):
                         break
 
                 attempts = 10
+                statuses = {}
                 try:
                     unwinder = RemoteUnwinder(p.pid, all_threads=True, mode=PROFILING_MODE_CPU,
                                                 skip_non_matching_threads=False)
                     for _ in range(attempts):
                         traces = unwinder.get_stack_trace()
-                        # Check if any thread is running
-                        if any(thread_info.status == 0 for interpreter_info in traces
-                               for thread_info in interpreter_info.threads):
+                        # Find threads and their statuses
+                        statuses = {}
+                        for interpreter_info in traces:
+                            for thread_info in interpreter_info.threads:
+                                statuses[thread_info.thread_id] = thread_info.status
+
+                        # Check if sleeper thread is idle and busy thread is running
+                        if (sleeper_tid in statuses and
+                            busy_tid in statuses and
+                            statuses[sleeper_tid] == 1 and
+                            statuses[busy_tid] == 0):
                             break
                         time.sleep(0.5)  # Give a bit of time to let threads settle
                 except PermissionError:
@@ -1766,13 +1775,6 @@ class TestDetectionOfThreadStatus(unittest.TestCase):
                         "Insufficient permissions to read the stack trace"
                     )
 
-
-                # Find threads and their statuses
-                statuses = {}
-                for interpreter_info in traces:
-                    for thread_info in interpreter_info.threads:
-                        statuses[thread_info.thread_id] = thread_info.status
-
                 self.assertIsNotNone(sleeper_tid, "Sleeper thread id not received")
                 self.assertIsNotNone(busy_tid, "Busy thread id not received")
                 self.assertIn(sleeper_tid, statuses, "Sleeper tid not found in sampled threads")
@@ -1861,14 +1863,23 @@ class TestDetectionOfThreadStatus(unittest.TestCase):
                         break
 
                 attempts = 10
+                statuses = {}
                 try:
                     unwinder = RemoteUnwinder(p.pid, all_threads=True, mode=PROFILING_MODE_GIL,
                                                 skip_non_matching_threads=False)
                     for _ in range(attempts):
                         traces = unwinder.get_stack_trace()
-                        # Check if any thread is running
-                        if any(thread_info.status == 0 for interpreter_info in traces
-                               for thread_info in interpreter_info.threads):
+                        # Find threads and their statuses
+                        statuses = {}
+                        for interpreter_info in traces:
+                            for thread_info in interpreter_info.threads:
+                                statuses[thread_info.thread_id] = thread_info.status
+
+                        # Check if sleeper thread is idle (status 2 for GIL mode) and busy thread is running
+                        if (sleeper_tid in statuses and
+                            busy_tid in statuses and
+                            statuses[sleeper_tid] == 2 and
+                            statuses[busy_tid] == 0):
                             break
                         time.sleep(0.5)  # Give a bit of time to let threads settle
                 except PermissionError:
@@ -1876,13 +1887,6 @@ class TestDetectionOfThreadStatus(unittest.TestCase):
                         "Insufficient permissions to read the stack trace"
                     )
 
-
-                # Find threads and their statuses
-                statuses = {}
-                for interpreter_info in traces:
-                    for thread_info in interpreter_info.threads:
-                        statuses[thread_info.thread_id] = thread_info.status
-
                 self.assertIsNotNone(sleeper_tid, "Sleeper thread id not received")
                 self.assertIsNotNone(busy_tid, "Busy thread id not received")
                 self.assertIn(sleeper_tid, statuses, "Sleeper tid not found in sampled threads")
-- 
2.47.3