Merge branch 'main' into fix-get-process-name-on-wsl

Author: rwgk

ci/tools/setup-sanitizer

@@ -1,6 +1,6 @@
 #!/usr/bin/env bash
 
-# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 #
 # SPDX-License-Identifier: Apache-2.0
 
@@ -12,7 +12,15 @@ set -euo pipefail
 if [[ "${SETUP_SANITIZER}" == 1 ]]; then
   COMPUTE_SANITIZER="${CUDA_HOME}/bin/compute-sanitizer"
   COMPUTE_SANITIZER_VERSION=$(${COMPUTE_SANITIZER} --version | grep -Eo "[0-9]{4}\.[0-9]\.[0-9]" | sed -e 's/\.//g')
-  SANITIZER_CMD="${COMPUTE_SANITIZER} --target-processes=all --launch-timeout=0 --tool=memcheck --error-exitcode=1 --report-api-errors=no"
+  # --target-processes=application-only: attach the sanitizer to the parent
+  # pytest process only. Spawned multiprocessing.Process children run without
+  # the sanitizer. This aims to mitigate a class of CI hangs where child
+  # processes take an extreme amount of time to spawn (>30 seconds). Test bugs
+  # triggered by that specific condition are typically uncovered only in CI,
+  # where they become emergencies and are difficult to debug. The parent
+  # process is still fully sanitized, which is where most of the interesting
+  # host-side IPC plumbing runs anyway.
+  SANITIZER_CMD="${COMPUTE_SANITIZER} --target-processes=application-only --launch-timeout=0 --tool=memcheck --error-exitcode=1 --report-api-errors=no"
   if [[ "$COMPUTE_SANITIZER_VERSION" -ge 202111 ]]; then
     SANITIZER_CMD="${SANITIZER_CMD} --padding=32"
   fi

cuda_core/AGENTS.md

@@ -125,12 +125,15 @@ Python or Cython type annotations should be included for all public APIs.  Avoid
 the use of `Any` unless absolutely necessary.  The argument and return types as
 defined in the docstrings should match the type annotations.
 
+Python imports should generally be outside of an if typing.TYPE_CHECK: block, even if the imported object is only used in type annotations. Use if typing.TYPE_CHECK: only to avoid creating import cycles. (This guidance maximizes compatibility with the cross-reference mechanisms in Sphinx.)
+
 ### Semantics
 
-Designs involving manual resource management should be avoided.  Where
-appropriate, provide context managers (implemented with `__enter__` and
-`__exit__`, not `contextlib.contextmanager`) or RAII using a `__del__` or
-`__dealloc__` method.
+APIs should exist for both manual resource management (such as `close()`) and
+automatic resource management, using context managers or destructors where
+appropriate.  Context managers should be implemented with `__enter__` and
+`__exit__`, not `contextlib.contextmanager`.  For destructors use `__dealloc__`
+where possible, otherwise `__del__`.
 
 ### Documentation
 

cuda_core/pyproject.toml

@@ -58,7 +58,7 @@ cu12 = ["cuda-bindings[all]==12.*"]
 cu13 = ["cuda-bindings[all]==13.*"]
 
 [dependency-groups]
-test = ["cython>=3.2,<3.3", "setuptools", "pytest>=6.2.4", "pytest-benchmark", "pytest-randomly", "pytest-repeat", "pytest-rerunfailures", "cloudpickle", "psutil", "cffi"]
+test = ["cython>=3.2,<3.3", "setuptools", "pytest>=6.2.4", "pytest-benchmark", "pytest-randomly", "pytest-repeat", "pytest-rerunfailures", "pytest-timeout", "cloudpickle", "psutil", "cffi"]
 ml-dtypes = ["ml-dtypes>=0.5.4,<0.6.0"]
 test-cu12 = [ {include-group = "ml-dtypes" }, {include-group = "test" }, "cupy-cuda12x; python_version < '3.14'", "cuda-toolkit[cudart]==12.*"]  # runtime headers needed by CuPy
 test-cu13 = [ {include-group = "ml-dtypes" }, {include-group = "test" }, "cupy-cuda13x; python_version < '3.14'", "cuda-toolkit[cudart]==13.*"]  # runtime headers needed by CuPy

cuda_core/tests/conftest.py

@@ -213,14 +213,24 @@ def pop_all_contexts():
 
 @pytest.fixture
 def ipc_device():
-    """Obtains a device suitable for IPC-enabled mempool tests, or skips."""
+    """Obtains a device suitable for IPC-enabled mempool tests, or skips.
+
+    The fixture also tracks every ``multiprocessing.Process`` spawned during
+    the test and kills any survivors at teardown. This prevents a stuck child
+    (e.g., compute-sanitizer wedged during IPC teardown -- see issue #2004)
+    from blocking ``ipc_memory_resource``'s ``mr.close()`` for hours.
+    """
+    from helpers.child_processes import track_child_processes
+
     device = Device(0)
     device.set_current()
 
     if not device.properties.memory_pools_supported:
         pytest.skip("Device does not support mempool operations")
 
-    return _require_ipc_mempool_devices((device,))[0]
+    device = _require_ipc_mempool_devices((device,))[0]
+    with track_child_processes():
+        yield device
 
 
 @pytest.fixture(
@@ -291,8 +301,16 @@ def mempool_device_x3():
 
 @pytest.fixture
 def ipc_mempool_device_x2(mempool_device_x2):
-    """Fixture that provides two IPC-capable mempool devices, or skips."""
-    return _require_ipc_mempool_devices(mempool_device_x2)
+    """Fixture that provides two IPC-capable mempool devices, or skips.
+
+    Also tracks/kills any leftover ``multiprocessing.Process`` children at
+    teardown for the same reasons documented on :func:`ipc_device`.
+    """
+    from helpers.child_processes import track_child_processes
+
+    devices = _require_ipc_mempool_devices(mempool_device_x2)
+    with track_child_processes():
+        yield devices
 
 
 @pytest.fixture(

cuda_core/tests/helpers/child_processes.py

@@ -0,0 +1,103 @@
+# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+
+"""Helpers for tests that spawn ``multiprocessing.Process`` children.
+
+These exist primarily to defend IPC tests against a class of CI hang where a
+child process spawns too slowly and the parent does not implement proper guards
+for that (see issue #2004). Without intervention, a zombie child holds an IPC
+memory handle and blocks the parent's ``mr.close()`` in fixture teardown,
+leading to deadlock and wedging the test runner for hours.
+"""
+
+import contextlib
+import multiprocessing.process
+import weakref
+
+from cuda_python_test_helpers import under_compute_sanitizer
+
+CHILD_TIMEOUT_SEC_DEFAULT = 30
+CHILD_TIMEOUT_SEC_SANITIZER = 120
+
+
+def child_timeout_sec() -> int:
+    """Return the per-process join/wait timeout for IPC-style tests.
+
+    Compute-sanitizer significantly slows process startup and CUDA context
+    teardown, so we use a larger budget when it is active.
+    """
+    return CHILD_TIMEOUT_SEC_SANITIZER if under_compute_sanitizer() else CHILD_TIMEOUT_SEC_DEFAULT
+
+
+def kill_subprocesses(*processes):
+    """Kill any of the given Process objects that are still alive.
+
+    Returns the list of processes that were killed (i.e. that were still alive
+    when the call was made). Callers should ``assert not survivors`` to convert
+    a non-empty return value into a clean test failure, e.g.::
+
+        proc_a.join(timeout=CHILD_TIMEOUT_SEC)
+        proc_b.join(timeout=CHILD_TIMEOUT_SEC)
+        survivors = kill_subprocesses(proc_a, proc_b)
+        assert not survivors, f"timed out waiting on: {[p.name for p in survivors]}"
+        assert proc_a.exitcode == 0
+        assert proc_b.exitcode == 0
+
+    Killing survivors before the subsequent asserts prevents a zombie child
+    from holding IPC handles past the test body and blocking fixture
+    teardown.
+    """
+    killed = []
+    for proc in processes:
+        try:
+            alive = proc.is_alive()
+        except (ValueError, AssertionError):
+            # is_alive() raises if the Process was never started or has
+            # already been closed; nothing to clean up.
+            continue
+        if not alive:
+            continue
+        with contextlib.suppress(ValueError, AssertionError):
+            proc.kill()
+            proc.join()
+        killed.append(proc)
+    return killed
+
+
+@contextlib.contextmanager
+def track_child_processes():
+    """Context manager that kills any ``multiprocessing.Process`` children still
+    alive at exit.
+
+    Patches ``multiprocessing.process.BaseProcess.__init__`` to record every
+    ``Process`` instance constructed inside the ``with`` block. This covers
+    the delegating ``mp.Process`` class as well as direct ``SpawnProcess`` /
+    ``ForkProcess`` instances (including those created by ``mp.Pool``), since
+    all of them inherit from ``BaseProcess``. On exit, any tracked process
+    that is still alive is killed and joined.
+
+    This protects fixture teardown (e.g. ``ipc_memory_resource``'s
+    ``mr.close()``) from blocking on IPC handles held by a stuck child --
+    see issue #2004.
+    """
+    tracked = weakref.WeakSet()
+    base = multiprocessing.process.BaseProcess
+    original_init = base.__init__
+
+    def tracking_init(self, *args, **kwargs):
+        original_init(self, *args, **kwargs)
+        tracked.add(self)
+
+    base.__init__ = tracking_init
+    try:
+        yield
+    finally:
+        base.__init__ = original_init
+        for proc in list(tracked):
+            # is_alive() / kill() raise ValueError if the Process was never
+            # started or has already been closed; nothing to clean up in that
+            # case.
+            with contextlib.suppress(ValueError):
+                if proc.is_alive():
+                    proc.kill()
+                    proc.join()

cuda_core/tests/memory_ipc/__init__.py

@@ -0,0 +1,3 @@
+# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+#
+# SPDX-License-Identifier: Apache-2.0

cuda_core/tests/memory_ipc/conftest.py

@@ -0,0 +1,41 @@
+# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+
+"""Per-directory conftest for memory IPC tests.
+
+Applies an outer-guard ``pytest.mark.timeout`` to every test in this directory.
+Individual tests still drive their own per-process waits using
+``child_timeout_sec()`` from ``helpers.child_processes``; this marker is the
+final fallback so that no IPC test can wedge the CI runner for hours if
+deadlock occurs.
+"""
+
+import pathlib
+
+import pytest
+from helpers.child_processes import child_timeout_sec
+
+_HERE = pathlib.Path(__file__).parent.resolve()
+
+
+def _outer_timeout_sec() -> int:
+    # IPC tests spawn children that run concurrently, so expected wall-clock
+    # is ~CHILD_TIMEOUT_SEC regardless of how many subsequent join/wait
+    # timeouts the test chains together (each subsequent join returns
+    # immediately once its child is already done). Exceeding that already
+    # means something is genuinely stuck, at which point the outer guard
+    # firing is the right outcome -- the per-test asserts wouldn't add
+    # useful diagnostic value over "test exceeded its budget", and the
+    # autouse track_child_processes() context manager still cleans up.
+    return child_timeout_sec() + 30
+
+
+def pytest_collection_modifyitems(config, items):
+    marker = pytest.mark.timeout(_outer_timeout_sec())
+    for item in items:
+        try:
+            item_path = pathlib.Path(str(item.fspath)).resolve()
+        except OSError:
+            continue
+        if _HERE in item_path.parents:
+            item.add_marker(marker)

cuda_core/tests/memory_ipc/test_errors.py

@@ -6,15 +6,31 @@
 import re
 
 import pytest
+from helpers.child_processes import child_timeout_sec, kill_subprocesses
 
 from cuda.core import Buffer, Device, DeviceMemoryResource, DeviceMemoryResourceOptions
 from cuda.core._utils.cuda_utils import CUDAError
 
-CHILD_TIMEOUT_SEC = 30
+CHILD_TIMEOUT_SEC = child_timeout_sec()
 NBYTES = 64
 POOL_SIZE = 2097152
 
 
+def test_outer_timeout_marker_is_applied(request):
+    """Verify that memory_ipc/conftest.py applies the outer pytest-timeout marker.
+
+    If this test fails, the per-directory conftest is not being loaded, or its
+    pytest_collection_modifyitems hook is not adding the marker. Without this
+    marker, the only thing protecting the GHA runner from a wedged IPC test is
+    the in-test cleanup -- which we want to keep as defense in depth, not as
+    the sole guard.
+    """
+    expected = child_timeout_sec() + 30
+    marker = request.node.get_closest_marker("timeout")
+    assert marker is not None, "memory_ipc/conftest.py did not apply a timeout marker"
+    assert marker.args == (expected,), f"unexpected timeout value: {marker.args!r}"
+
+
 class ChildErrorHarness:
     """Test harness for checking errors in child processes. Subclasses override
     PARENT_ACTION, CHILD_ACTION, and ASSERT (see below for examples)."""
@@ -43,6 +59,8 @@ def test_main(self, ipc_device, ipc_memory_resource):
 
             # Wait for the child process.
             process.join(timeout=CHILD_TIMEOUT_SEC)
+            survivors = kill_subprocesses(process)
+            assert not survivors, "child did not exit within timeout"
             assert process.exitcode == 0
         finally:
             for mr in self._extra_mrs:

cuda_core/tests/memory_ipc/test_event_ipc.py

@@ -5,13 +5,14 @@
 
 import pytest
 from helpers.buffers import compare_equal_buffers, make_scratch_buffer
+from helpers.child_processes import child_timeout_sec, kill_subprocesses
 from helpers.latch import LatchKernel
 from helpers.logging import TimestampedLogger
 
 from cuda.core import Device, EventOptions
 
 ENABLE_LOGGING = False  # Set True for test debugging and development
-CHILD_TIMEOUT_SEC = 30
+CHILD_TIMEOUT_SEC = child_timeout_sec()
 NBYTES = 64
 
 
@@ -67,6 +68,8 @@ def test_main(self, ipc_device, ipc_memory_resource):
         log("releasing stream1")
         latch.release()
         process.join(timeout=CHILD_TIMEOUT_SEC)
+        survivors = kill_subprocesses(process)
+        assert not survivors, "child did not exit within timeout"
         assert process.exitcode == 0
         log("done")
 
@@ -162,6 +165,8 @@ def test_main(self, ipc_device, blocking_sync, use_options_cls, use_option_kw):
         assert props[5] is None
 
         process.join(timeout=CHILD_TIMEOUT_SEC)
+        survivors = kill_subprocesses(process)
+        assert not survivors, "child did not exit within timeout"
         assert process.exitcode == 0
 
     def child_main(self, q_in, q_out):

cuda_core/tests/memory_ipc/test_ipc_duplicate_import.py

@@ -13,11 +13,12 @@
 import multiprocessing as mp
 
 import pytest
+from helpers.child_processes import child_timeout_sec, kill_subprocesses
 from helpers.logging import TimestampedLogger
 
 from cuda.core import Buffer, Device
 
-CHILD_TIMEOUT_SEC = 30
+CHILD_TIMEOUT_SEC = child_timeout_sec()
 NBYTES = 64
 POOL_SIZE = 2097152
 
@@ -84,6 +85,8 @@ def test_main(self, ipc_device, ipc_memory_resource):
 
         log("waiting for child")
         process.join(timeout=CHILD_TIMEOUT_SEC)
+        survivors = kill_subprocesses(process)
         log(f"child exit code: {process.exitcode}")
+        assert not survivors, "child did not exit within timeout"
         assert process.exitcode == 0, f"Child process failed with exit code {process.exitcode}"
         log("done")