Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
73 changes: 73 additions & 0 deletions Lib/profiling/sampling/__main__.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,73 @@
"""Run the sampling profiler from the command line."""

import sys

MACOS_PERMISSION_ERROR = """\
🔒 Permission Error: Unable to access process memory on macOS

Tachyon needs elevated permissions to profile processes. Try one of these solutions:

1. Try running again with elevated permissions by running 'sudo -E !!'.

2. If targeting system Python processes:
Note: Apple's System Integrity Protection (SIP) may block access to system
Python binaries. Consider using a user-installed Python instead.
"""

LINUX_PERMISSION_ERROR = """
🔒 Tachyon was unable to access process memory. This could be because tachyon
has insufficient privileges (the required capability is CAP_SYS_PTRACE).
Unprivileged processes cannot trace processes that they cannot send signals
to or those running set-user-ID/set-group-ID programs, for security reasons.

If your uid matches the uid of the target process you want to analyze, you
can do one of the following to get 'ptrace' scope permissions:

* If you are running inside a Docker container, you need to make sure you
start the container using the '--cap-add=SYS_PTRACE' or '--privileged'
command line arguments. Notice that this may not be enough if you are not
running as 'root' inside the Docker container as you may need to disable
hardening (see next points).

* Try running again with elevated permissions by running 'sudo -E !!'.

* You can disable kernel hardening for the current session temporarily (until
a reboot happens) by running 'echo 0 | sudo tee /proc/sys/kernel/yama/ptrace_scope'.
"""

WINDOWS_PERMISSION_ERROR = """
🔒 Tachyon requires administrator rights to access process memory on Windows.
Please run your command prompt as Administrator and try again.
"""

GENERIC_PERMISSION_ERROR = """
🔒 Tachyon was unable to access the target process due to operating
system restrictions or missing privileges.
"""

from .cli import main
from .errors import SamplingUnknownProcessError, SamplingModuleNotFoundError, SamplingScriptNotFoundError

def handle_permission_error():
"""Handle PermissionError by displaying appropriate error message."""
if sys.platform == "darwin":
print(MACOS_PERMISSION_ERROR, file=sys.stderr)
elif sys.platform.startswith("linux"):
print(LINUX_PERMISSION_ERROR, file=sys.stderr)
elif sys.platform.startswith("win"):
print(WINDOWS_PERMISSION_ERROR, file=sys.stderr)
else:
print(GENERIC_PERMISSION_ERROR, file=sys.stderr)
sys.exit(1)

if __name__ == '__main__':
try:
main()
except PermissionError:
handle_permission_error()
except SamplingUnknownProcessError as err:
print(f"Tachyon cannot find the process: {err}", file=sys.stderr)
sys.exit(1)
except (SamplingModuleNotFoundError, SamplingScriptNotFoundError) as err:
print(f"Tachyon cannot find the target: {err}", file=sys.stderr)
sys.exit(1)
256 changes: 256 additions & 0 deletions Lib/profiling/sampling/_sync_coordinator.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,256 @@
"""
Internal synchronization coordinator for the sample profiler.

This module is used internally by the sample profiler to coordinate
the startup of target processes. It should not be called directly by users.
"""

import importlib.util
import os
import sys
import socket
import runpy
import time
import types
from typing import List, NoReturn


class CoordinatorError(Exception):
"""Base exception for coordinator errors."""
pass


class ArgumentError(CoordinatorError):
"""Raised when invalid arguments are provided."""
pass


class SyncError(CoordinatorError):
"""Raised when synchronization with profiler fails."""
pass


class TargetError(CoordinatorError):
"""Raised when target execution fails."""
pass


def _validate_arguments(args: List[str]) -> tuple[int, str, List[str]]:
"""
Validate and parse command line arguments.

Args:
args: Command line arguments including script name

Returns:
Tuple of (sync_port, working_directory, target_args)

Raises:
ArgumentError: If arguments are invalid
"""
if len(args) < 4:
raise ArgumentError(
"Insufficient arguments. Expected: <sync_port> <cwd> <target> [args...]"
)

try:
sync_port = int(args[1])
if not (1 <= sync_port <= 65535):
raise ValueError("Port out of range")
except ValueError as e:
raise ArgumentError(f"Invalid sync port '{args[1]}': {e}") from e

cwd = args[2]
if not os.path.isdir(cwd):
raise ArgumentError(f"Working directory does not exist: {cwd}")

target_args = args[3:]
if not target_args:
raise ArgumentError("No target specified")

return sync_port, cwd, target_args


# Constants for socket communication
_MAX_RETRIES = 3
_INITIAL_RETRY_DELAY_SEC = 0.1
_SOCKET_TIMEOUT_SEC = 2.0
_READY_MESSAGE = b"ready"


def _signal_readiness(sync_port: int) -> None:
"""
Signal readiness to the profiler via TCP socket.

Args:
sync_port: Port number where profiler is listening

Raises:
SyncError: If unable to signal readiness
"""
last_error = None

for attempt in range(_MAX_RETRIES):
try:
# Use context manager for automatic cleanup
with socket.create_connection(("127.0.0.1", sync_port), timeout=_SOCKET_TIMEOUT_SEC) as sock:
sock.send(_READY_MESSAGE)
return
except (socket.error, OSError) as e:
last_error = e
if attempt < _MAX_RETRIES - 1:
# Exponential backoff before retry
time.sleep(_INITIAL_RETRY_DELAY_SEC * (2 ** attempt))

# If we get here, all retries failed
raise SyncError(f"Failed to signal readiness after {_MAX_RETRIES} attempts: {last_error}") from last_error


def _setup_environment(cwd: str) -> None:
"""
Set up the execution environment.

Args:
cwd: Working directory to change to

Raises:
TargetError: If unable to set up environment
"""
try:
os.chdir(cwd)
except OSError as e:
raise TargetError(f"Failed to change to directory {cwd}: {e}") from e

# Add current directory to sys.path if not present (for module imports)
if cwd not in sys.path:
sys.path.insert(0, cwd)


def _execute_module(module_name: str, module_args: List[str]) -> None:
"""
Execute a Python module.

Args:
module_name: Name of the module to execute
module_args: Arguments to pass to the module

Raises:
TargetError: If module cannot be found
"""
# Replace sys.argv to match how Python normally runs modules
# When running 'python -m module args', sys.argv is ["__main__.py", "args"]
sys.argv = ["__main__.py"] + module_args

try:
runpy.run_module(module_name, run_name="__main__", alter_sys=True)
except ImportError as e:
raise TargetError(f"Module '{module_name}' not found: {e}") from e
# Let other exceptions (including SystemExit) propagate naturally
# so Python prints the full traceback to stderr


def _execute_script(script_path: str, script_args: List[str], cwd: str) -> None:
"""
Execute a Python script.

Args:
script_path: Path to the script to execute
script_args: Arguments to pass to the script
cwd: Current working directory for path resolution

Raises:
TargetError: If script execution fails
"""
# Make script path absolute if it isn't already
if not os.path.isabs(script_path):
script_path = os.path.join(cwd, script_path)

if not os.path.isfile(script_path):
raise TargetError(f"Script not found: {script_path}")

# Replace sys.argv to match original script call
sys.argv = [script_path] + script_args

try:
with open(script_path, 'rb') as f:
source_code = f.read()

except FileNotFoundError as e:
raise TargetError(f"Script file not found: {script_path}") from e
except PermissionError as e:
raise TargetError(f"Permission denied reading script: {script_path}") from e

main_module = types.ModuleType("__main__")
main_module.__file__ = script_path
main_module.__builtins__ = __builtins__
# gh-140729: Create a __mp_main__ module to allow pickling
sys.modules['__main__'] = sys.modules['__mp_main__'] = main_module

try:
code = compile(source_code, script_path, 'exec', module='__main__')
except SyntaxError as e:
raise TargetError(f"Syntax error in script {script_path}: {e}") from e

# Execute the script - let exceptions propagate naturally so Python
# prints the full traceback to stderr
exec(code, main_module.__dict__)


def main() -> NoReturn:
"""
Main coordinator function.

This function coordinates the startup of a target Python process
with the sample profiler by signaling when the process is ready
to be profiled.
"""
# Phase 1: Parse arguments and set up environment
# Errors here are coordinator errors, not script errors
try:
# Parse and validate arguments
sync_port, cwd, target_args = _validate_arguments(sys.argv)

# Set up execution environment
_setup_environment(cwd)

# Determine execution type and validate target exists
is_module = target_args[0] == "-m"
if is_module:
if len(target_args) < 2:
raise ArgumentError("Module name required after -m")
module_name = target_args[1]
module_args = target_args[2:]

if importlib.util.find_spec(module_name) is None:
raise TargetError(f"Module not found: {module_name}")
else:
script_path = target_args[0]
script_args = target_args[1:]
# Match the path resolution logic in _execute_script
check_path = script_path if os.path.isabs(script_path) else os.path.join(cwd, script_path)
if not os.path.isfile(check_path):
raise TargetError(f"Script not found: {script_path}")

# Signal readiness to profiler
_signal_readiness(sync_port)

except CoordinatorError as e:
print(f"Profiler coordinator error: {e}", file=sys.stderr)
sys.exit(1)
except KeyboardInterrupt:
print("Interrupted", file=sys.stderr)
sys.exit(1)

# Phase 2: Execute the target script/module
# Let exceptions propagate naturally so Python prints full tracebacks
if is_module:
_execute_module(module_name, module_args)
else:
_execute_script(script_path, script_args, cwd)

# Normal exit
sys.exit(0)


if __name__ == "__main__":
main()
Loading
Loading