def _pr_set_pdeathsig() -> None:
"""
Sets PR_SET_PDEATHSIG to ensure a child process is
terminated appropriately.
See http://stackoverflow.com/questions/1884941/ for more information.
For libc.so.6 read http://www.linux-m68k.org/faq/glibcinfo.html
"""
mp._prctl_pr_set_pdeathsig(signal.SIGTERM) # type: ignore[attr-defined]
def _wrap(fn, kwargs, error_queue):
# prctl(2) is a Linux specific system call.
# On other systems the following function call has no effect.
# This is set to ensure that non-daemonic child processes can
# terminate if their parent terminates before they do.
torchmp._prctl_pr_set_pdeathsig(signal.SIGINT)
try:
fn(**kwargs)
except KeyboardInterrupt:
pass # SIGINT; Killed by parent, do nothing
except Exception:
# Propagate exception to parent process, keeping original traceback
import traceback
error_queue.put(traceback.format_exc())
sys.exit(1)
def _start(self):
if self.subprocess_handlers:
raise ValueError(
"The subprocess handlers already initialized. Most likely the start method got called twice."
)
self.subprocess_handlers = {
local_rank: SubprocessHandler(
entrypoint=self.entrypoint, # type: ignore[arg-type] # entrypoint is always a str
args=self.args[local_rank],
env=self.envs[local_rank],
preexec_fn=mp._prctl_pr_set_pdeathsig(signal.SIGTERM), # type: ignore[attr-defined]
stdout=self.stdouts[local_rank],
stderr=self.stderrs[local_rank],
)
for local_rank in range(self.nprocs)
}