def my_update_subtask_status(entry_id, current_task_id, new_subtask_status):
"""
Check whether a subtask has been updated before really updating.
Check whether a subtask which has been retried
has had the retry already write its results here before the code
that was invoking the retry had a chance to update this status.
This is the norm in "eager" mode (used by tests) where the retry is called
and run to completion before control is returned to the code that
invoked the retry. If the retries eventually end in failure (e.g. due to
a maximum number of retries being attempted), the "eager" code will return
the error for each retry as it is popped off the stack. We want to just ignore
the later updates that are called as the result of the earlier retries.
This should not be an issue in production, where status is updated before
a task is retried, and is then updated afterwards if the retry fails.
"""
entry = InstructorTask.objects.get(pk=entry_id)
subtask_dict = json.loads(entry.subtasks)
subtask_status_info = subtask_dict['status']
current_subtask_status = SubtaskStatus.from_dict(subtask_status_info[current_task_id])
current_retry_count = current_subtask_status.get_retry_count()
new_retry_count = new_subtask_status.get_retry_count()
if current_retry_count <= new_retry_count:
update_subtask_status(entry_id, current_task_id, new_subtask_status)
def my_update_subtask_status(entry_id, current_task_id, new_subtask_status):
"""
Check whether a subtask has been updated before really updating.
Check whether a subtask which has been retried
has had the retry already write its results here before the code
that was invoking the retry had a chance to update this status.
This is the norm in "eager" mode (used by tests) where the retry is called
and run to completion before control is returned to the code that
invoked the retry. If the retries eventually end in failure (e.g. due to
a maximum number of retries being attempted), the "eager" code will return
the error for each retry as it is popped off the stack. We want to just ignore
the later updates that are called as the result of the earlier retries.
This should not be an issue in production, where status is updated before
a task is retried, and is then updated afterwards if the retry fails.
"""
entry = InstructorTask.objects.get(pk=entry_id)
subtask_dict = json.loads(entry.subtasks)
subtask_status_info = subtask_dict['status']
current_subtask_status = SubtaskStatus.from_dict(
subtask_status_info[current_task_id])
current_retry_count = current_subtask_status.get_retry_count()
new_retry_count = new_subtask_status.get_retry_count()
if current_retry_count <= new_retry_count:
update_subtask_status(entry_id, current_task_id, new_subtask_status)
def check_all_users_email_subtask_is_valid(entry_id, current_task_id,
new_subtask_status):
# Confirm that the InstructorTask actually defines subtasks.
entry = EmailAllUsersTask.objects.get(pk=entry_id)
if len(entry.subtasks) == 0:
format_str = "Unexpected task_id '{}': unable to find subtasks of email for all users task '{}': rejecting task {}"
msg = format_str.format(current_task_id, entry, new_subtask_status)
TASK_LOG.warning(msg)
dog_stats_api.increment('instructor_task.subtask.duplicate.nosubtasks')
raise DuplicateTaskException(msg)
# Confirm that the InstructorTask knows about this particular subtask.
subtask_dict = json.loads(entry.subtasks)
subtask_status_info = subtask_dict['status']
if current_task_id not in subtask_status_info:
format_str = "Unexpected task_id '{}': unable to find status for subtask of email for all users task '{}': rejecting task {}"
msg = format_str.format(current_task_id, entry, new_subtask_status)
TASK_LOG.warning(msg)
dog_stats_api.increment('instructor_task.subtask.duplicate.unknown')
raise DuplicateTaskException(msg)
# Confirm that the InstructorTask doesn't think that this subtask has already been
# performed successfully.
subtask_status = SubtaskStatus.from_dict(
subtask_status_info[current_task_id])
subtask_state = subtask_status.state
if subtask_state in READY_STATES:
format_str = "Unexpected task_id '{}': already completed - status {} for subtask of email for all users task '{}': rejecting task {}"
msg = format_str.format(current_task_id, subtask_status, entry,
new_subtask_status)
TASK_LOG.warning(msg)
dog_stats_api.increment('instructor_task.subtask.duplicate.completed')
raise DuplicateTaskException(msg)
# Confirm that the InstructorTask doesn't think that this subtask is already being
# retried by another task.
if subtask_state == RETRY:
# Check to see if the input number of retries is less than the recorded number.
# If so, then this is an earlier version of the task, and a duplicate.
new_retry_count = new_subtask_status.get_retry_count()
current_retry_count = subtask_status.get_retry_count()
if new_retry_count < current_retry_count:
format_str = "Unexpected task_id '{}': already retried - status {} for subtask of email for all users task '{}': rejecting task {}"
msg = format_str.format(current_task_id, subtask_status, entry,
new_subtask_status)
TASK_LOG.warning(msg)
dog_stats_api.increment(
'instructor_task.subtask.duplicate.retried')
raise DuplicateTaskException(msg)
# Now we are ready to start working on this. Try to lock it.
# If it fails, then it means that another worker is already in the
# middle of working on this.
if not _acquire_subtask_lock(current_task_id):
format_str = "Unexpected task_id '{}': already being executed - for subtask of email for all users task '{}'"
msg = format_str.format(current_task_id, entry)
TASK_LOG.warning(msg)
dog_stats_api.increment('instructor_task.subtask.duplicate.locked')
raise DuplicateTaskException(msg)
def send_all_users_email(entry_id, email_id, to_list, global_email_context,
subtask_status_dict):
subtask_status = SubtaskStatus.from_dict(subtask_status_dict)
current_task_id = subtask_status.task_id
num_to_send = len(to_list)
log.info((u"Preparing to send email %s to %d recipients as subtask %s "
u"for email for all users task %d: context = %s, status=%s"),
email_id, num_to_send, current_task_id, entry_id,
global_email_context, subtask_status)
check_all_users_email_subtask_is_valid(entry_id, current_task_id,
subtask_status)
send_exception = None
new_subtask_status = None
try:
# course_title = global_email_context['course_title']
# ENTENDER LOS PARAMETROS DEL TIMER
with dog_stats_api.timer('course_email.single_task.time.overall'):
new_subtask_status, send_exception = _send_all_users_email(
entry_id,
email_id,
to_list,
global_email_context,
subtask_status,
)
except Exception:
log.exception("Send-email task %s for email %s: failed unexpectedly!",
current_task_id, email_id)
subtask_status.increment(failed=num_to_send, state=FAILURE)
update_subtask_status(entry_id, current_task_id, subtask_status)
raise
if send_exception is None:
log.info("Send-email task %s for email %s: succeeded", current_task_id,
email_id)
update_subtask_status(entry_id, current_task_id, new_subtask_status)
elif isinstance(send_exception, RetryTaskError):
log.warning("Send-email task %s for email %s: being retried",
current_task_id, email_id)
raise send_exception # pylint: disable=raising-bad-type
else:
log.error("Send-email task %s for email %s: failed: %s",
current_task_id, email_id, send_exception)
update_subtask_status(entry_id, current_task_id, new_subtask_status)
raise send_exception # pylint: disable=raising-bad-type
log.info("Send-email task %s for email %s: returning status %s",
current_task_id, email_id, new_subtask_status)
return new_subtask_status.to_dict()
def send_course_email(entry_id, email_id, to_list, global_email_context,
subtask_status_dict):
"""
Sends an email to a list of recipients.
Inputs are:
* `entry_id`: id of the InstructorTask object to which progress should be recorded.
* `email_id`: id of the CourseEmail model that is to be emailed.
* `to_list`: list of recipients. Each is represented as a dict with the following keys:
- 'profile__name': full name of User.
- 'email': email address of User.
- 'pk': primary key of User model.
* `global_email_context`: dict containing values that are unique for this email but the same
for all recipients of this email. This dict is to be used to fill in slots in email
template. It does not include 'name' and 'email', which will be provided by the to_list.
* `subtask_status_dict` : dict containing values representing current status. Keys are:
'task_id' : id of subtask. This is used to pass task information across retries.
'attempted' : number of attempts -- should equal succeeded plus failed
'succeeded' : number that succeeded in processing
'skipped' : number that were not processed.
'failed' : number that failed during processing
'retried_nomax' : number of times the subtask has been retried for conditions that
should not have a maximum count applied
'retried_withmax' : number of times the subtask has been retried for conditions that
should have a maximum count applied
'state' : celery state of the subtask (e.g. QUEUING, PROGRESS, RETRY, FAILURE, SUCCESS)
Most values will be zero on initial call, but may be different when the task is
invoked as part of a retry.
Sends to all addresses contained in to_list that are not also in the Optout table.
Emails are sent multi-part, in both plain text and html. Updates InstructorTask object
with status information (sends, failures, skips) and updates number of subtasks completed.
"""
subtask_status = SubtaskStatus.from_dict(subtask_status_dict)
current_task_id = subtask_status.task_id
num_to_send = len(to_list)
log.info((u"Preparing to send email %s to %d recipients as subtask %s "
u"for instructor task %d: context = %s, status=%s"), email_id,
num_to_send, current_task_id, entry_id, global_email_context,
subtask_status)
# Check that the requested subtask is actually known to the current InstructorTask entry.
# If this fails, it throws an exception, which should fail this subtask immediately.
# This can happen when the parent task has been run twice, and results in duplicate
# subtasks being created for the same InstructorTask entry. This can happen when Celery
# loses its connection to its broker, and any current tasks get requeued.
# We hope to catch this condition in perform_delegate_email_batches() when it's the parent
# task that is resubmitted, but just in case we fail to do so there, we check here as well.
# There is also a possibility that this task will be run twice by Celery, for the same reason.
# To deal with that, we need to confirm that the task has not already been completed.
check_subtask_is_valid(entry_id, current_task_id, subtask_status)
send_exception = None
new_subtask_status = None
try:
course_title = global_email_context['course_title']
with dog_stats_api.timer('course_email.single_task.time.overall',
tags=[_statsd_tag(course_title)]):
new_subtask_status, send_exception = _send_course_email(
entry_id,
email_id,
to_list,
global_email_context,
subtask_status,
)
except Exception:
# Unexpected exception. Try to write out the failure to the entry before failing.
log.exception("Send-email task %s for email %s: failed unexpectedly!",
current_task_id, email_id)
# We got here for really unexpected reasons. Since we don't know how far
# the task got in emailing, we count all recipients as having failed.
# It at least keeps the counts consistent.
subtask_status.increment(failed=num_to_send, state=FAILURE)
update_subtask_status(entry_id, current_task_id, subtask_status)
raise
if send_exception is None:
# Update the InstructorTask object that is storing its progress.
log.info("Send-email task %s for email %s: succeeded", current_task_id,
email_id)
update_subtask_status(entry_id, current_task_id, new_subtask_status)
elif isinstance(send_exception, RetryTaskError):
# If retrying, a RetryTaskError needs to be returned to Celery.
# We assume that the the progress made before the retry condition
# was encountered has already been updated before the retry call was made,
# so we only log here.
log.warning("Send-email task %s for email %s: being retried",
current_task_id, email_id)
raise send_exception # pylint: disable=raising-bad-type
else:
log.error("Send-email task %s for email %s: failed: %s",
current_task_id, email_id, send_exception)
update_subtask_status(entry_id, current_task_id, new_subtask_status)
raise send_exception # pylint: disable=raising-bad-type
# return status in a form that can be serialized by Celery into JSON:
log.info("Send-email task %s for email %s: returning status %s",
current_task_id, email_id, new_subtask_status)
return new_subtask_status.to_dict()
def send_course_email(entry_id, email_id, to_list, global_email_context, subtask_status_dict):
"""
Sends an email to a list of recipients.
Inputs are:
* `entry_id`: id of the InstructorTask object to which progress should be recorded.
* `email_id`: id of the CourseEmail model that is to be emailed.
* `to_list`: list of recipients. Each is represented as a dict with the following keys:
- 'profile__name': full name of User.
- 'email': email address of User.
- 'pk': primary key of User model.
* `global_email_context`: dict containing values that are unique for this email but the same
for all recipients of this email. This dict is to be used to fill in slots in email
template. It does not include 'name' and 'email', which will be provided by the to_list.
* `subtask_status_dict` : dict containing values representing current status. Keys are:
'task_id' : id of subtask. This is used to pass task information across retries.
'attempted' : number of attempts -- should equal succeeded plus failed
'succeeded' : number that succeeded in processing
'skipped' : number that were not processed.
'failed' : number that failed during processing
'retried_nomax' : number of times the subtask has been retried for conditions that
should not have a maximum count applied
'retried_withmax' : number of times the subtask has been retried for conditions that
should have a maximum count applied
'state' : celery state of the subtask (e.g. QUEUING, PROGRESS, RETRY, FAILURE, SUCCESS)
Most values will be zero on initial call, but may be different when the task is
invoked as part of a retry.
Sends to all addresses contained in to_list that are not also in the Optout table.
Emails are sent multi-part, in both plain text and html. Updates InstructorTask object
with status information (sends, failures, skips) and updates number of subtasks completed.
"""
subtask_status = SubtaskStatus.from_dict(subtask_status_dict)
current_task_id = subtask_status.task_id
num_to_send = len(to_list)
log.info((u"Preparing to send email %s to %d recipients as subtask %s "
u"for instructor task %d: context = %s, status=%s"),
email_id, num_to_send, current_task_id, entry_id, global_email_context, subtask_status)
# Check that the requested subtask is actually known to the current InstructorTask entry.
# If this fails, it throws an exception, which should fail this subtask immediately.
# This can happen when the parent task has been run twice, and results in duplicate
# subtasks being created for the same InstructorTask entry. This can happen when Celery
# loses its connection to its broker, and any current tasks get requeued.
# We hope to catch this condition in perform_delegate_email_batches() when it's the parent
# task that is resubmitted, but just in case we fail to do so there, we check here as well.
# There is also a possibility that this task will be run twice by Celery, for the same reason.
# To deal with that, we need to confirm that the task has not already been completed.
check_subtask_is_valid(entry_id, current_task_id, subtask_status)
send_exception = None
new_subtask_status = None
try:
course_title = global_email_context['course_title']
with dog_stats_api.timer('course_email.single_task.time.overall', tags=[_statsd_tag(course_title)]):
new_subtask_status, send_exception = _send_course_email(
entry_id,
email_id,
to_list,
global_email_context,
subtask_status,
)
except Exception:
# Unexpected exception. Try to write out the failure to the entry before failing.
log.exception("Send-email task %s for email %s: failed unexpectedly!", current_task_id, email_id)
# We got here for really unexpected reasons. Since we don't know how far
# the task got in emailing, we count all recipients as having failed.
# It at least keeps the counts consistent.
subtask_status.increment(failed=num_to_send, state=FAILURE)
update_subtask_status(entry_id, current_task_id, subtask_status)
raise
if send_exception is None:
# Update the InstructorTask object that is storing its progress.
log.info("Send-email task %s for email %s: succeeded", current_task_id, email_id)
update_subtask_status(entry_id, current_task_id, new_subtask_status)
elif isinstance(send_exception, RetryTaskError):
# If retrying, a RetryTaskError needs to be returned to Celery.
# We assume that the the progress made before the retry condition
# was encountered has already been updated before the retry call was made,
# so we only log here.
log.warning("Send-email task %s for email %s: being retried", current_task_id, email_id)
raise send_exception # pylint: disable=raising-bad-type
else:
log.error("Send-email task %s for email %s: failed: %s", current_task_id, email_id, send_exception)
update_subtask_status(entry_id, current_task_id, new_subtask_status)
raise send_exception # pylint: disable=raising-bad-type
# return status in a form that can be serialized by Celery into JSON:
log.info("Send-email task %s for email %s: returning status %s", current_task_id, email_id, new_subtask_status)
return new_subtask_status.to_dict()
