def chunk_put(req: ray_client_pb2.DataRequest):
"""
Chunks a put request. Doing this lazily is important for large objects,
since taking slices of bytes objects does a copy. This means if we
immediately materialized every chunk of a large object and inserted them
into the result_queue, we would effectively double the memory needed
on the client to handle the put.
"""
total_size = len(req.put.data)
assert total_size > 0, "Cannot chunk object with missing data"
if total_size >= OBJECT_TRANSFER_WARNING_SIZE and log_once(
"client_object_put_size_warning"):
size_gb = total_size / 2**30
warnings.warn(
"Ray Client is attempting to send a "
f"{size_gb:.2f} GiB object over the network, which may "
"be slow. Consider serializing the object and using a remote "
"URI to transfer via S3 or Google Cloud Storage instead. "
"Documentation for doing this can be found here: "
"https://docs.ray.io/en/latest/handling-dependencies.html#remote-uris",
UserWarning,
)
total_chunks = math.ceil(total_size / OBJECT_TRANSFER_CHUNK_SIZE)
for chunk_id in range(0, total_chunks):
start = chunk_id * OBJECT_TRANSFER_CHUNK_SIZE
end = min(total_size, (chunk_id + 1) * OBJECT_TRANSFER_CHUNK_SIZE)
chunk = ray_client_pb2.PutRequest(
client_ref_id=req.put.client_ref_id,
data=req.put.data[start:end],
chunk_id=chunk_id,
total_chunks=total_chunks,
total_size=total_size,
)
yield ray_client_pb2.DataRequest(req_id=req.req_id, put=chunk)
def test_prepare_runtime_init_req_fails():
"""
Check that a connection that is initiated with a non-Init request
raises an error.
"""
put_req = ray_client_pb2.DataRequest(put=ray_client_pb2.PutRequest())
with pytest.raises(AssertionError):
proxier.prepare_runtime_init_req(put_req)
def _put_pickled(self, data, client_ref_id: bytes):
req = ray_client_pb2.PutRequest(data=data)
if client_ref_id is not None:
req.client_ref_id = client_ref_id
resp = self.data_client.PutObject(req)
if not resp.valid:
try:
raise cloudpickle.loads(resp.error)
except (pickle.UnpicklingError, TypeError):
logger.exception("Failed to deserialize {}".format(resp.error))
raise
return ClientObjectRef(resp.id)
def _put(self, val):
if isinstance(val, ClientObjectRef):
raise TypeError(
"Calling 'put' on an ObjectRef is not allowed "
"(similarly, returning an ObjectRef from a remote "
"function is not allowed). If you really want to "
"do this, you can wrap the ObjectRef in a list and "
"call 'put' on it (or return it).")
data = dumps_from_client(val, self._client_id)
req = ray_client_pb2.PutRequest(data=data)
resp = self.data_client.PutObject(req)
return ClientObjectRef(resp.id)
def _put(self, val, *, client_ref_id: bytes = None):
if isinstance(val, ClientObjectRef):
raise TypeError(
"Calling 'put' on an ObjectRef is not allowed "
"(similarly, returning an ObjectRef from a remote "
"function is not allowed). If you really want to "
"do this, you can wrap the ObjectRef in a list and "
"call 'put' on it (or return it).")
data = dumps_from_client(val, self._client_id)
req = ray_client_pb2.PutRequest(data=data)
if client_ref_id is not None:
req.client_ref_id = client_ref_id
resp = self.data_client.PutObject(req)
if not resp.valid:
try:
raise cloudpickle.loads(resp.error)
except pickle.UnpicklingError:
logger.exception("Failed to deserialize {}".format(resp.error))
raise
return ClientObjectRef(resp.id)
def _put(self, val):
data = cloudpickle.dumps(val)
req = ray_client_pb2.PutRequest(data=data)
resp = self.server.PutObject(req)
return ClientObjectRef(resp.id)
def _put(self, val):
data = cloudpickle.dumps(val)
req = ray_client_pb2.PutRequest(data=data)
resp = self.server.PutObject(req, metadata=self.metadata)
return ClientObjectRef.from_remote_ref(resp.ref)
def _put(self, val):
data = dumps_from_client(val, self._client_id)
req = ray_client_pb2.PutRequest(data=data)
resp = self.data_client.PutObject(req)
return ClientObjectRef(resp.id)
