Add heartbeat to help with detecting hanging agents

Change-Id: I0be9be4384a12551f224fa8b9bfaaa4844efe106
This commit is contained in:
Ilya Shakhat
2015-03-31 19:58:51 +03:00
parent 29f211122e
commit 7788d311bb
2 changed files with 23 additions and 9 deletions

View File

@@ -15,12 +15,14 @@
import copy
import json
import multiprocessing
import os
import uuid
from oslo_config import cfg
from oslo_log import log as logging
from shaker.agent import agent as agent_process
from shaker.engine import config
from shaker.engine import deploy
from shaker.engine import executors as executors_classes
@@ -131,6 +133,14 @@ def main():
else:
message_queue = messaging.MessageQueue(cfg.CONF.server_endpoint)
heartbeat = multiprocessing.Process(
target=agent_process.work,
kwargs=dict(agent_id='heartbeat',
endpoint=cfg.CONF.server_endpoint,
polling_interval=cfg.CONF.polling_interval))
heartbeat.daemon = True
heartbeat.start()
quorum = quorum_pkg.Quorum(
message_queue, cfg.CONF.polling_interval,
cfg.CONF.agent_loss_timeout, cfg.CONF.agent_join_timeout)