bpo-36084: Add native thread ID to threading.Thread objects (pythonGH-11993)

jaketesler · pitrou · commit 4959c33d2555 · 2019-05-12T19:08:24.000+02:00
diff --git a/Doc/library/_thread.rst b/Doc/library/_thread.rst
@@ -85,6 +85,18 @@ This module defines the following constants and functions:
    may be recycled when a thread exits and another thread is created.
 
 
+.. function:: get_native_id()
+
+   Return the native integral Thread ID of the current thread assigned by the kernel.
+   This is a non-negative integer.
+   Its value may be used to uniquely identify this particular thread system-wide
+   (until the thread terminates, after which the value may be recycled by the OS).
+
+   .. availability:: Windows, FreeBSD, Linux, macOS.
+
+   .. versionadded:: 3.8
+
+
 .. function:: stack_size([size])
 
    Return the thread stack size used when creating new threads.  The optional
diff --git a/Doc/library/threading.rst b/Doc/library/threading.rst
@@ -49,6 +49,18 @@ This module defines the following functions:
    .. versionadded:: 3.3
 
 
+.. function:: get_native_id()
+
+   Return the native integral Thread ID of the current thread assigned by the kernel.
+   This is a non-negative integer.
+   Its value may be used to uniquely identify this particular thread system-wide
+   (until the thread terminates, after which the value may be recycled by the OS).
+
+   .. availability:: Windows, FreeBSD, Linux, macOS.
+
+   .. versionadded:: 3.8
+
+
 .. function:: enumerate()
 
    Return a list of all :class:`Thread` objects currently alive.  The list
@@ -297,6 +309,25 @@ since it is impossible to detect the termination of alien threads.
       another thread is created.  The identifier is available even after the
       thread has exited.
 
+   .. attribute:: native_id
+
+      The native integral thread ID of this thread or ``0`` if the thread has not
+      been started.  This is a non-negative integer.  See the
+      :func:`get_native_id` function.
+      This represents the Thread ID (``TID``) as assigned to the
+      thread by the OS (kernel).  Its value may be used to uniquely identify
+      this particular thread system-wide.
+
+      .. note::
+
+         Similar to Process IDs, Thread IDs are only valid (guaranteed unique
+         system-wide) from the time the thread is created until the thread
+         has been terminated.
+
+      .. availability:: Windows, FreeBSD, Linux, macOS.
+
+      .. versionadded:: 3.8
+
    .. method:: is_alive()
 
       Return whether the thread is alive.
diff --git a/Include/pythread.h b/Include/pythread.h
@@ -25,6 +25,7 @@ PyAPI_FUNC(void) PyThread_init_thread(void);
 PyAPI_FUNC(unsigned long) PyThread_start_new_thread(void (*)(void *), void *);
 PyAPI_FUNC(void) _Py_NO_RETURN PyThread_exit_thread(void);
 PyAPI_FUNC(unsigned long) PyThread_get_thread_ident(void);
+PyAPI_FUNC(unsigned long) PyThread_get_thread_native_id(void);
 
 PyAPI_FUNC(PyThread_type_lock) PyThread_allocate_lock(void);
 PyAPI_FUNC(void) PyThread_free_lock(PyThread_type_lock);
diff --git a/Lib/_dummy_thread.py b/Lib/_dummy_thread.py
@@ -71,6 +71,10 @@ def get_ident():
     """
     return 1
 
+def get_native_id():
+    """Dummy implementation of _thread.get_native_id()."""
+    return 0
+
 def allocate_lock():
     """Dummy implementation of _thread.allocate_lock()."""
     return LockType()
diff --git a/Lib/test/test_threading.py b/Lib/test/test_threading.py
@@ -104,6 +104,10 @@ def test_various_ops(self):
             self.assertRegex(repr(t), r'^<TestThread\(.*, initial\)>$')
             t.start()
 
+        native_ids = set(t.native_id for t in threads) | {threading.get_native_id()}
+        self.assertNotIn(None, native_ids)
+        self.assertEqual(len(native_ids), NUMTASKS + 1)
+
         if verbose:
             print('waiting for all tasks to complete')
         for t in threads:
diff --git a/Lib/threading.py b/Lib/threading.py
@@ -23,8 +23,8 @@
 # with the multiprocessing module, which doesn't provide the old
 # Java inspired names.
 
-__all__ = ['get_ident', 'active_count', 'Condition', 'current_thread',
-           'enumerate', 'main_thread', 'TIMEOUT_MAX',
+__all__ = ['get_ident', 'get_native_id', 'active_count', 'Condition',
+           'current_thread', 'enumerate', 'main_thread', 'TIMEOUT_MAX',
            'Event', 'Lock', 'RLock', 'Semaphore', 'BoundedSemaphore', 'Thread',
            'Barrier', 'BrokenBarrierError', 'Timer', 'ThreadError',
            'setprofile', 'settrace', 'local', 'stack_size']
@@ -34,6 +34,7 @@
 _allocate_lock = _thread.allocate_lock
 _set_sentinel = _thread._set_sentinel
 get_ident = _thread.get_ident
+get_native_id = _thread.get_native_id
 ThreadError = _thread.error
 try:
     _CRLock = _thread.RLock
@@ -790,6 +791,7 @@ class is implemented.
         else:
             self._daemonic = current_thread().daemon
         self._ident = None
+        self._native_id = 0
         self._tstate_lock = None
         self._started = Event()
         self._is_stopped = False
@@ -891,6 +893,9 @@ def _bootstrap(self):
     def _set_ident(self):
         self._ident = get_ident()
 
+    def _set_native_id(self):
+        self._native_id = get_native_id()
+
     def _set_tstate_lock(self):
         """
         Set a lock object which will be released by the interpreter when
@@ -903,6 +908,7 @@ def _bootstrap_inner(self):
         try:
             self._set_ident()
             self._set_tstate_lock()
+            self._set_native_id()
             self._started.set()
             with _active_limbo_lock:
                 _active[self._ident] = self
@@ -1077,6 +1083,17 @@ def ident(self):
         assert self._initialized, "Thread.__init__() not called"
         return self._ident
 
+    @property
+    def native_id(self):
+        """Native integral thread ID of this thread or 0 if it has not been started.
+
+        This is a non-negative integer. See the get_native_id() function.
+        This represents the Thread ID as reported by the kernel.
+
+        """
+        assert self._initialized, "Thread.__init__() not called"
+        return self._native_id
+
     def is_alive(self):
         """Return whether the thread is alive.
 
@@ -1176,6 +1193,7 @@ def __init__(self):
         self._set_tstate_lock()
         self._started.set()
         self._set_ident()
+        self._set_native_id()
         with _active_limbo_lock:
             _active[self._ident] = self
 
@@ -1195,6 +1213,7 @@ def __init__(self):
 
         self._started.set()
         self._set_ident()
+        self._set_native_id()
         with _active_limbo_lock:
             _active[self._ident] = self
 
diff --git a/Misc/NEWS.d/next/Core and Builtins/2019-02-22-23-03-20.bpo-36084.86Eh4X.rst b/Misc/NEWS.d/next/Core and Builtins/2019-02-22-23-03-20.bpo-36084.86Eh4X.rst
@@ -0,0 +1 @@
+Add native thread ID (TID) to threading.Thread objects
diff --git a/Modules/_threadmodule.c b/Modules/_threadmodule.c
@@ -1159,6 +1159,20 @@ allocated consecutive numbers starting at 1, this behavior should not\n\
 be relied upon, and the number should be seen purely as a magic cookie.\n\
 A thread's identity may be reused for another thread after it exits.");
 
+static PyObject *
+thread_get_native_id(PyObject *self, PyObject *Py_UNUSED(ignored))
+{
+    unsigned long native_id = PyThread_get_thread_native_id();
+    return PyLong_FromUnsignedLong(native_id);
+}
+
+PyDoc_STRVAR(get_native_id_doc,
+"get_native_id() -> integer\n\
+\n\
+Return a non-negative integer identifying the thread as reported\n\
+by the OS (kernel). This may be used to uniquely identify a\n\
+particular thread within a system.");
+
 static PyObject *
 thread__count(PyObject *self, PyObject *Py_UNUSED(ignored))
 {
@@ -1310,6 +1324,8 @@ static PyMethodDef thread_methods[] = {
      METH_NOARGS, interrupt_doc},
     {"get_ident",               thread_get_ident,
      METH_NOARGS, get_ident_doc},
+    {"get_native_id",           thread_get_native_id,
+     METH_NOARGS, get_native_id_doc},
     {"_count",                  thread__count,
      METH_NOARGS, _count_doc},
     {"stack_size",              (PyCFunction)thread_stack_size,
diff --git a/Python/thread_nt.h b/Python/thread_nt.h
@@ -143,6 +143,8 @@ LeaveNonRecursiveMutex(PNRMUTEX mutex)
 
 unsigned long PyThread_get_thread_ident(void);
 
+unsigned long PyThread_get_thread_native_id(void);
+
 /*
  * Initialization of the C package, should not be needed.
  */
@@ -227,6 +229,20 @@ PyThread_get_thread_ident(void)
     return GetCurrentThreadId();
 }
 
+/*
+ * Return the native Thread ID (TID) of the calling thread.
+ * The native ID of a thread is valid and guaranteed to be unique system-wide
+ * from the time the thread is created until the thread has been terminated.
+ */
+unsigned long
+PyThread_get_thread_native_id(void)
+{
+    if (!initialized)
+        PyThread_init_thread();
+
+    return GetCurrentThreadId();
+}
+
 void _Py_NO_RETURN
 PyThread_exit_thread(void)
 {
diff --git a/Python/thread_pthread.h b/Python/thread_pthread.h
@@ -12,6 +12,12 @@
 #endif
 #include <signal.h>
 
+#if defined(__linux__)
+#include <sys/syscall.h>
+#elif defined(__FreeBSD__)
+#include <pthread_np.h>
+#endif
+
 /* The POSIX spec requires that use of pthread_attr_setstacksize
    be conditional on _POSIX_THREAD_ATTR_STACKSIZE being defined. */
 #ifdef _POSIX_THREAD_ATTR_STACKSIZE
@@ -302,6 +308,27 @@ PyThread_get_thread_ident(void)
     return (unsigned long) threadid;
 }
 
+unsigned long
+PyThread_get_thread_native_id(void)
+{
+    if (!initialized)
+        PyThread_init_thread();
+#ifdef __APPLE__
+    uint64_t native_id;
+    pthread_threadid_np(NULL, &native_id);
+#elif defined(__linux__)
+    pid_t native_id;
+    native_id = syscall(__NR_gettid);
+#elif defined(__FreeBSD__)
+    pid_t native_id;
+    native_id = pthread_getthreadid_np();
+#else
+    unsigned long native_id;
+    native_id = 0;
+#endif
+    return (unsigned long) native_id;
+}
+
 void _Py_NO_RETURN
 PyThread_exit_thread(void)
 {

Original file line number	Diff line number	Diff line change
`@@ -0,0 +1 @@`
	`1`	`+Add native thread ID (TID) to threading.Thread objects`