def __init__(self, local_config):
self.log_level = os.getenv('CLOUDBUTTON_LOGLEVEL')
self.config = local_config
self.name = 'local'
self.alive = True
self.queue = Queue()
self.logs_dir = os.path.join(STORAGE_FOLDER, LOGS_PREFIX)
self.num_workers = self.config['workers']
self.workers = []
if not is_unix_system():
for worker_id in range(self.num_workers):
p = Thread(target=self._process_runner, args=(worker_id, ))
self.workers.append(p)
p.daemon = True
p.start()
else:
for worker_id in range(self.num_workers):
p = Process(target=self._process_runner, args=(worker_id, ))
self.workers.append(p)
p.daemon = True
p.start()
log_msg = 'PyWren v{} init for Localhost - Total workers: {}'.format(
__version__, self.num_workers)
logger.info(log_msg)
if not self.log_level:
print(log_msg)
def _start_invoker_process(self):
"""
Starts the invoker process responsible to spawn pending calls in background
"""
if self.is_cloudbutton_function or not is_unix_system():
for inv_id in range(INVOKER_PROCESSES):
p = Thread(target=self._run_invoker_process, args=(inv_id, ))
self.invokers.append(p)
p.daemon = True
p.start()
else:
for inv_id in range(INVOKER_PROCESSES):
p = Process(target=self._run_invoker_process, args=(inv_id, ))
self.invokers.append(p)
p.daemon = True
p.start()
def get_memory_usage(formatted=True):
"""
Gets the current memory usage of the runtime.
To be used only in the action code.
"""
if not is_unix_system():
return
split_args = False
pids_to_show = None
discriminate_by_pid = False
ps_mem.verify_environment(pids_to_show)
sorted_cmds, shareds, count, total, swaps, total_swap = \
ps_mem.get_memory_usage(pids_to_show, split_args, discriminate_by_pid,
include_self=True, only_self=False)
if formatted:
return sizeof_fmt(int(ps_mem.human(total, units=1)))
else:
return int(ps_mem.human(total, units=1))
def wait(self,
fs=None,
throw_except=True,
return_when=ALL_COMPLETED,
download_results=False,
timeout=None,
THREADPOOL_SIZE=128,
WAIT_DUR_SEC=1):
"""
Wait for the Future instances (possibly created by different Executor instances)
given by fs to complete. Returns a named 2-tuple of sets. The first set, named done,
contains the futures that completed (finished or cancelled futures) before the wait
completed. The second set, named not_done, contains the futures that did not complete
(pending or running futures). timeout can be used to control the maximum number of
seconds to wait before returning.
:param fs: Futures list. Default None
:param throw_except: Re-raise exception if call raised. Default True.
:param return_when: One of `ALL_COMPLETED`, `ANY_COMPLETED`, `ALWAYS`
:param download_results: Download results. Default false (Only get statuses)
:param timeout: Timeout of waiting for results.
:param THREADPOOL_SIZE: Number of threads to use. Default 64
:param WAIT_DUR_SEC: Time interval between each check.
:return: `(fs_done, fs_notdone)`
where `fs_done` is a list of futures that have completed
and `fs_notdone` is a list of futures that have not completed.
:rtype: 2-tuple of list
"""
futures = fs or self.futures
if type(futures) != list:
futures = [futures]
if not futures:
raise Exception(
'You must run the call_async(), map() or map_reduce(), or provide'
' a list of futures before calling the wait()/get_result() method'
)
if download_results:
msg = 'ExecutorID {} - Getting results...'.format(self.executor_id)
fs_done = [f for f in futures if f.done]
fs_not_done = [f for f in futures if not f.done]
else:
msg = 'ExecutorID {} - Waiting for functions to complete...'.format(
self.executor_id)
fs_done = [f for f in futures if f.ready or f.done]
fs_not_done = [f for f in futures if not f.ready and not f.done]
if not fs_not_done:
return fs_done, fs_not_done
print(msg) if not self.log_level else logger.info(msg)
if is_unix_system() and timeout is not None:
logger.debug(
'Setting waiting timeout to {} seconds'.format(timeout))
error_msg = 'Timeout of {} seconds exceeded waiting for function activations to finish'.format(
timeout)
signal.signal(signal.SIGALRM, partial(timeout_handler, error_msg))
signal.alarm(timeout)
pbar = None
error = False
if not self.is_cloudbutton_function and not self.log_level:
from tqdm.auto import tqdm
if is_notebook():
pbar = tqdm(bar_format='{n}/|/ {n_fmt}/{total_fmt}',
total=len(fs_not_done)) # ncols=800
else:
print()
pbar = tqdm(bar_format=' {l_bar}{bar}| {n_fmt}/{total_fmt} ',
total=len(fs_not_done),
disable=False)
try:
if self.rabbitmq_monitor:
logger.info('Using RabbitMQ to monitor function activations')
wait_rabbitmq(futures,
self.internal_storage,
rabbit_amqp_url=self.rabbit_amqp_url,
download_results=download_results,
throw_except=throw_except,
pbar=pbar,
return_when=return_when,
THREADPOOL_SIZE=THREADPOOL_SIZE)
else:
wait_storage(futures,
self.internal_storage,
download_results=download_results,
throw_except=throw_except,
return_when=return_when,
pbar=pbar,
THREADPOOL_SIZE=THREADPOOL_SIZE,
WAIT_DUR_SEC=WAIT_DUR_SEC)
except KeyboardInterrupt:
if download_results:
not_dones_call_ids = [(f.job_id, f.call_id) for f in futures
if not f.done]
else:
not_dones_call_ids = [(f.job_id, f.call_id) for f in futures
if not f.ready and not f.done]
msg = ('ExecutorID {} - Cancelled - Total Activations not done: {}'
.format(self.executor_id, len(not_dones_call_ids)))
if pbar:
pbar.close()
print()
print(msg) if not self.log_level else logger.info(msg)
error = True
except Exception as e:
error = True
raise e
finally:
self.invoker.stop()
if is_unix_system():
signal.alarm(0)
if pbar and not pbar.disable:
pbar.close()
if not is_notebook():
print()
if self.data_cleaner and not self.is_cloudbutton_function:
self.clean(cloudobjects=False, force=False, log=False)
if not fs and error and is_notebook():
del self.futures[len(self.futures) - len(futures):]
if download_results:
fs_done = [f for f in futures if f.done]
fs_notdone = [f for f in futures if not f.done]
else:
fs_done = [f for f in futures if f.ready or f.done]
fs_notdone = [f for f in futures if not f.ready and not f.done]
return fs_done, fs_notdone
def _init_runtime(self, docker_image_name):
name = self._format_runtime_name(docker_image_name)
if self._is_localhost:
if is_unix_system():
uid_cmd = "id -u $USER"
uid = subprocess.check_output(uid_cmd,
shell=True).decode().strip()
if self.docker_client:
running_containers = self.docker_client.containers.list(
filters={'name': 'pywren'})
running_runtimes = [c.name for c in running_containers]
if name not in running_runtimes:
self.docker_client.containers.run(
docker_image_name,
entrypoint='python',
command='/tmp/{}/__main__.py'.format(
DOCKER_BASE_FOLDER),
volumes=['{}:/tmp'.format(TEMP)],
detach=True,
auto_remove=True,
user=uid,
name=name,
ports={'8080/tcp': docker_config.PYWREN_SERVER_PORT})
time.sleep(5)
else:
running_runtimes_cmd = "docker ps --format '{{.Names}}' -f name=pywren"
running_runtimes = subprocess.run(
running_runtimes_cmd, shell=True,
stdout=subprocess.PIPE).stdout.decode()
if name not in running_runtimes:
if is_unix_system():
cmd = (
'docker run -d --name {} --user {} -v {}:/tmp -p 8080:{}'
' --entrypoint "python" {} /tmp/{}/__main__.py'.
format(name, uid, TEMP,
docker_config.PYWREN_SERVER_PORT,
docker_image_name, DOCKER_BASE_FOLDER))
else:
cmd = ('docker run -d --name {} -v {}:/tmp -p 8080:{}'
' --entrypoint "python" {} /tmp/{}/__main__.py'.
format(name, TEMP,
docker_config.PYWREN_SERVER_PORT,
docker_image_name, DOCKER_BASE_FOLDER))
if not self.log_level:
cmd = cmd + " >{} 2>&1".format(os.devnull)
res = os.system(cmd)
if res != 0:
raise Exception(
'There was an error starting the runtime')
time.sleep(5)
else:
running_runtimes_cmd = "docker ps --format '{{.Names}}' -f name=pywren"
running_runtimes = self._ssh_run_remote_command(
running_runtimes_cmd)
cmd = ('docker run -d --name {} -v /tmp:/tmp -p 8080:{}'
' --entrypoint "python" {} /tmp/{}/__main__.py'.format(
name, docker_config.PYWREN_SERVER_PORT,
docker_image_name, DOCKER_BASE_FOLDER))
if name not in running_runtimes:
self._ssh_run_remote_command(cmd)
time.sleep(5)