def _flush_batch(self):
# Flush the current batch of mutations to Cloud Datastore.
helper.write_mutations(self._datastore, self._project,
self._mutations)
logging.debug("Successfully wrote %d mutations.",
len(self._mutations))
self._mutations = []
def monitor_migration_status(migration_status, migration_history_obj):
"""
migration_history_obj must be pickled!
Takes a pipeline status result and uses it to update MigrationHistory
status as the migration runs.
Calling forget() on this result will free up the worker to work on
other tasks.
"""
# Set up a datastore client
project = PROJECT or 'meridianedit-staging'
client = apache_helper.get_datastore(project)
throttler = AdaptiveThrottler(window_ms=120000, bucket_ms=1000, overload_ratio=1.25)
if migration_status == 'DONE':
migration_history_obj.properties.get('status').string_value = Status.success
elif migration_status in ['FAILED', 'CANCELLED', 'CANCELLING']:
migration_history_obj.properties.get('status').string_value = Status.failed
elif migration_status in ['STARTING', 'RUNNING', 'UPDATED', 'DRAINING', 'DRAINED']:
migration_history_obj.properties.get('status').string_value = Status.running
elif migration_status in ['PENDING', 'STOPPED'] :
migration_history_obj.properties.get('status').string_value = Status.waiting
elif migration_status == 'UNKNOWN':
migration_history_obj.properties.get('status').string_value = Status.unknown
else:
# Sometimes migration status equals none of these things. Just assume success so
# we can kick off post-migration work. This is based on observation in the wild.
migration_history_obj.properties.get('status').string_value = Status.success
# Write the mutated entity to the datastore
mutations = [Mutation(update=migration_history_obj)]
apache_helper.write_mutations(client, project, mutations, throttler, rpc_stats_callback)
def _flush_batch(self):
# Flush the current batch of mutations to Cloud Datastore.
_, latency_ms = helper.write_mutations(
self._datastore, self._project, self._mutations,
self._update_rpc_stats)
logging.debug("Successfully wrote %d mutations in %dms.",
len(self._mutations), latency_ms)
if not self._fixed_batch_size:
now = time.time()
self._batch_sizer.report_latency(now, latency_ms, len(self._mutations))
self._target_batch_size = self._batch_sizer.get_batch_size(now)
self._mutations = []
self._mutations_size = 0
def _flush_batch(self):
# Flush the current batch of mutations to Cloud Datastore.
_, latency_ms = helper.write_mutations(
self._datastore, self._project, self._mutations,
self._throttler, self._update_rpc_stats,
throttle_delay=_Mutate._WRITE_BATCH_TARGET_LATENCY_MS//1000)
logging.debug("Successfully wrote %d mutations in %dms.",
len(self._mutations), latency_ms)
if not self._fixed_batch_size:
now = time.time()*1000
self._batch_sizer.report_latency(now, latency_ms, len(self._mutations))
self._target_batch_size = self._batch_sizer.get_batch_size(now)
self._mutations = []
self._mutations_size = 0
def _flush_batch(self):
# Flush the current batch of mutations to Cloud Datastore.
_, latency_ms = helper.write_mutations(
self._datastore, self._project, self._mutations,
self._throttler, self._update_rpc_stats,
throttle_delay=util.WRITE_BATCH_TARGET_LATENCY_MS//1000)
_LOGGER.debug("Successfully wrote %d mutations in %dms.",
len(self._mutations), latency_ms)
if not self._fixed_batch_size:
now = time.time()*1000
self._batch_sizer.report_latency(now, latency_ms, len(self._mutations))
self._target_batch_size = self._batch_sizer.get_batch_size(now)
self._mutations = []
self._mutations_size = 0
def _flush_batch(self):
# Flush the current batch of mutations to Cloud Datastore.
helper.write_mutations(self._datastore, self._project, self._mutations)
logging.debug("Successfully wrote %d mutations.", len(self._mutations))
self._mutations = []
def run_data_migration():
request_data = json.loads(request.get_data())
# Required fields
fields = [
'name',
'function_kwargs',
'user'
]
# Some basic validation
for f in fields:
if f not in request_data:
resp_data = json.dumps(
{
'error': 'The ' + f + ' field is required.'
}
)
resp = Response(resp_data, status=400, mimetype='application/json')
return resp
if request_data['name'] not in migration.choices:
resp_data = json.dumps(
{
'error': 'The migration name is not valid.'
}
)
resp = Response(resp_data, status=400, mimetype='application/json')
return resp
migration_name = request_data['name']
function_kwargs = request_data['function_kwargs'] or {}
user = request_data['user']
function_kwargs.update({'name': migration_name})
# Create a MigrationHistory entity to keep track of the migration status
# set the project
project = PROJECT or 'meridianedit-staging'
# Create entity key
partition_id = entity_pb2.PartitionId(project_id=project, namespace_id="")
migration_history_obj_id = datetime.now().strftime("%Y%m%d%H%M%S")
path_element = entity_pb2.Key.PathElement(kind="MigrationHistory", name=migration_history_obj_id)
key = entity_pb2.Key(partition_id=partition_id, path=[path_element])
# Create entity and give it properties
entity = entity_pb2.Entity(key=key)
property_dict = {
'name': migration_name,
'function_kwargs': json.dumps(function_kwargs),
'started_by': user,
'status': 'running',
'created': datetime.now()
}
datastore_helper.add_properties(entity, property_dict)
# Add entity to datastore
mutations = [Mutation(insert=entity)]
client = apache_helper.get_datastore(project)
throttler = AdaptiveThrottler(window_ms=120000, bucket_ms=1000, overload_ratio=1.25)
apache_helper.write_mutations(client, project, mutations, throttler, rpc_stats_callback)
# Call the migration with any given function kwargs
migration_kwargs = {
'migration_history_obj': migration_history_obj_id,
}
migration_kwargs.update(function_kwargs)
# Run the migration in a celery task worker to prevent it timing
# out this connection. Also monitor the task so we can update
# migration status.
run_dataflow_migration.delay(pickle.dumps(entity), **migration_kwargs)
resp_data = {
'migration_history_obj_id': migration_history_obj_id
}
# A default 500 error message is returned if any of this breaks
return Response(json.dumps(resp_data), status=200, mimetype='application/json')
