Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[WIP] handle sigterm gracefully by adding status to metadata #1731

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
38 changes: 38 additions & 0 deletions metaflow/task.py
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,7 @@
import sys
import os
import time
import signal

from types import MethodType, FunctionType

Expand Down Expand Up @@ -39,6 +40,42 @@
MAX_FOREACH_PATH_LENGTH = 256


class SystemSignalHandler:
def __init__(self, run_id, step_name, task_id, metadata_service, metadata_tags):
self.run_id = run_id
self.step_name = (step_name,)
self.task_id = task_id
self.metadata_service = metadata_service
self.metadata_tags = metadata_tags

signal.signal(signal.SIGINT, self.exit_sigint_gracefully)
signal.signal(signal.SIGTERM, self.exit_sigterm_gracefully)
print("SystemSignalHandler initialized...")

def log_exit_signal(self, signal):
metadata_info = [
MetaDatum(
field="signal",
value=signal,
type="signal",
tags=self.metadata_tags,
)
]
self.metadata_service.register_metadata(
self.run_id, self.step_name, self.task_id, metadata_info
)

def exit_sigint_gracefully(self, signum, frame):
print("SIGINT received... ")
self.log_exit_signal("SIGINT")
self.status = signal.SIGINT

def exit_sigterm_gracefully(self, signum, frame):
print("SIGTERM received... ")
self.log_exit_signal("SIGTERM")
self.status = signal.SIGTERM


class MetaflowTask(object):
"""
MetaflowTask prepares a Flow instance for execution of a single step.
Expand Down Expand Up @@ -412,6 +449,7 @@ def run_step(
)

metadata_tags = ["attempt_id:{0}".format(retry_count)]
SystemSignalHandler(run_id, step_name, task_id, self.metadata, metadata_tags)

metadata = [
MetaDatum(
Expand Down