Consider this working code:
from multiprocessing import Process
from updaters import app1, app2
if __name__ == '__main__':
apps = [ app1, app2]
for app in apps:
instance = app()
p = Process(target=instance.start_listener)
p.start()
p.join()
This works fine until one process fails (lets say some exception) - how Can I programmatically monitor the process and restart it if it fails
Poll the Process.is_alive() and if it returns False delete the process and start a new one, e.g.:
from multiprocessing import Process
from updaters import app1, app2
from time import sleep
if __name__ == '__main__':
apps = [app1, app2]
processes = {}
n = 0
for app in apps:
instance = app()
p = Process(target=instance.start_listener)
p.start()
processes[n] = (p, app) # Keep the process and the app to monitor or restart
n += 1
while len(processes) > 0:
for n in processes.keys():
(p, a) = processes[n]
sleep(0.5)
if p.exitcode is None and not p.is_alive(): # Not finished and not running
# Do your error handling and restarting here assigning the new process to processes[n]
print(a, 'is gone as if never born!')
elif p.exitcode < 0:
print ('Process Ended with an error or a terminate', a)
# Handle this either by restarting or delete the entry so it is removed from list as for else
else:
print (a, 'finished')
p.join() # Allow tidyup
del processes[n] # Removed finished items from the dictionary
# When none are left then loop will end
print ('FINISHED')
for loop needs to increment n after assigning to processes[n]. @alonisser: The running processes are stored in the processes dict. To "poll" it you could nest the last for loop inside a while processes: if you made the p.exitcode < 0: clause delete anything it doesn't/can't restart.
(p, a) = processes[n]