refactor(profiling): eager code provenance file-package mapping (#4926)

## Description

This refactor ensures that the file-to-package mapping is created as
early as possible in the parent process, when code provenance is
enabled, to avoid repeating the work in child worker processes.

## Checklist
- [ ] Followed the [library release note
guidelines](https://ddtrace.readthedocs.io/en/stable/contributing.html#Release-Note-Guidelines)
when writing a release note.
- [ ] Add additional sections for `feat` and `fix` pull requests.
- [ ] [Library
documentation](https://github.com/DataDog/dd-trace-py/tree/1.x/docs)
and/or [Datadog's documentation
site](https://github.com/DataDog/documentation/) is updated. Link to doc
PR in description.

## Reviewer Checklist
- [x] Title is accurate.
- [x] Description motivates each change.
- [x] No unnecessary changes were introduced in this PR.
- [x] Avoid breaking
[API](https://ddtrace.readthedocs.io/en/stable/versioning.html#interfaces)
changes unless absolutely necessary.
- [x] Tests provided or description of manual testing performed is
included in the code or PR.
- [x] Release note has been added and follows the [library release note
guidelines](https://ddtrace.readthedocs.io/en/stable/contributing.html#Release-Note-Guidelines),
or else `changelog/no-changelog` label added.
- [x] All relevant GitHub issues are correctly linked.
- [x] Backports are identified and tagged with Mergifyio.

Co-authored-by: Munir Abdinur <[email protected]>

Author: P403n1x87

ddtrace/profiling/exporter/_packages.py

@@ -1,9 +1,10 @@
 # -*- encoding: utf-8 -*-
-import enum
 import logging
 import os
 import sys
 
+from ddtrace.internal.utils.formats import asbool
+
 
 try:
     import pathlib
@@ -90,30 +91,28 @@ def _build_package_file_mapping():
     return mapping
 
 
-class _load_status(enum.Enum):
-    FAILED = "failed"
-
-
-_FILE_PACKAGE_MAPPING = None  # type: typing.Optional[typing.Union[typing.Dict[str, Distribution], _load_status]]
+_FILE_PACKAGE_MAPPING = None  # type: typing.Optional[typing.Dict[str, Distribution]]
+if asbool(os.getenv("DD_PROFILING_ENABLE_CODE_PROVENANCE", False)):
+    # DEV: If code provenance is enabled, create the mapping as soon as this
+    # module is imported. This should happen in the parent process to
+    # guarantee that the work is not repeated in child worker processes.
+    try:
+        _FILE_PACKAGE_MAPPING = _build_package_file_mapping()
+    except Exception:
+        LOG.error(
+            "Unable to build package file mapping, "
+            "please report this to https://github.com/DataDog/dd-trace-py/issues",
+            exc_info=True,
+        )
 
 
 def filename_to_package(
     filename,  # type: str
 ):
     # type: (...) -> typing.Optional[Distribution]
     global _FILE_PACKAGE_MAPPING
+
     if _FILE_PACKAGE_MAPPING is None:
-        try:
-            _FILE_PACKAGE_MAPPING = _build_package_file_mapping()
-        except Exception:
-            _FILE_PACKAGE_MAPPING = _load_status.FAILED
-            LOG.error(
-                "Unable to build package file mapping, "
-                "please report this to https://github.com/DataDog/dd-trace-py/issues",
-                exc_info=True,
-            )
-            return None
-    elif _FILE_PACKAGE_MAPPING is _load_status.FAILED:
         return None
 
     if filename not in _FILE_PACKAGE_MAPPING and filename.endswith(".pyc"):

tests/profiling/exporter/test_packages.py

@@ -42,15 +42,11 @@ def _raise():
 
     # type: (...) -> None
     assert _packages.filename_to_package(_packages.__file__) is None
-    assert len(caplog.records) == 1
-    assert caplog.records[0].message == (
-        "Unable to build package file mapping, please report this to https://github.com/DataDog/dd-trace-py/issues"
-    )
 
 
 def test_filename_to_package():
     # type: (...) -> None
-    _packages._FILE_PACKAGE_MAPPING = None
+    _packages._FILE_PACKAGE_MAPPING = _packages._build_package_file_mapping()
 
     package = _packages.filename_to_package(_packages.__file__)
     assert package.name == "ddtrace"

tests/profiling/exporter/test_pprof.py

@@ -8,6 +8,7 @@
 from ddtrace.profiling.collector import _lock
 from ddtrace.profiling.collector import memalloc
 from ddtrace.profiling.collector import stack_event
+from ddtrace.profiling.exporter import _packages
 from ddtrace.profiling.exporter import pprof
 
 
@@ -709,6 +710,7 @@ def test_pprof_exporter(gan):
 
 @mock.patch("ddtrace.internal.utils.config.get_application_name")
 def test_pprof_exporter_libs(gan):
+    _packages._FILE_PACKAGE_MAPPING = _packages._build_package_file_mapping()
     gan.return_value = "bonjour"
     exp = pprof.PprofExporter()
     TEST_EVENTS = {