def test_get_volume_containing_path_runtime_error(os, list_volumes, path):
"""Test get_volume_containing_path() with no backing volume."""
os.path.isabs.return_value = True
os.path.exists.return_value = True
list_volumes.return_value = _list_volumes_return_value
with pytest.raises(RuntimeError):
podutils.get_volume_containing_path(path)
def get_volume_containing_path(request, path):
"""Get the closest volume mount point to the input absolute path."""
vol = podutils.get_volume_containing_path(path)
return {"name": vol[1].name, "mount_point": vol[0]}
def test_get_volume_containing_path(os, list_volumes, path, ret):
"""Test successful execution of get_volume_containing_path()."""
os.path.exists.return_value = True
list_volumes.return_value = _list_volumes_return_value
assert podutils.get_volume_containing_path(path) == ret
def test_get_volume_containing_path_value_error(path):
"""Test get_volume_containing_path() with bad input."""
with pytest.raises(ValueError):
podutils.get_volume_containing_path(path)
def serve(model: Any,
name: str = None,
wait: bool = True,
predictor: str = None,
preprocessing_fn: Callable = None,
preprocessing_assets: Dict = None) -> KFServer:
"""Main API used to serve models from a notebook or a pipeline step.
This function procedurally deploys a KFServing InferenceService, starting
from a model object. A summary list of actions follows:
* Autogenerate an InferenceService name, if not provided
* Process transformer function (and related assets)
* Dump the model, to a path under a mounted PVC
* Snapshot the PVC
* Hydrate a new PVC from the new snapshot
* Submit an InferenceService CR
* Monitor the CR until it becomes ready
FIXME: Improve documentation. Provide some examples in the docstring and
explain how the preprocessing function parsing works.
Args:
model: Model object to be used as a predictor
name (optional): Name of the predictor. Will be autogenerated if not
provided
wait (optional): Wait for the InferenceService to become ready.
Default: True
predictor (optional): Predictor type to be used for the
InferenceService. If not provided it will be inferred using
the the matching marshalling backends.
preprocessing_fn (optional): A processing function that will be
deployed as a KFServing Transformer
preprocessing_assets (optional): A dictionary with object required by
the preprocessing function. This is needed in case the
preprocessing function references global objects.
Returns: A KFServer instance
"""
log.info("Starting serve procedure for model '%s'", model)
if not name:
name = "%s-%s" % (podutils.get_pod_name(), utils.random_string(5))
# Validate and process transformer
if preprocessing_fn:
_prepare_transformer_assets(preprocessing_fn, preprocessing_assets)
# Detect predictor type
predictor_type = marshal.get_backend(model).predictor_type
if predictor and predictor != predictor_type:
raise RuntimeError("Trying to create an InferenceService with"
" predictor of type '%s' but the model is of type"
" '%s'" % (predictor, predictor_type))
if not predictor_type:
log.error(
"Kale does not yet support serving objects with '%s'"
" backend.\n\nPlease help us improve Kale by opening a new"
" issue at:\n"
"https://github.com/kubeflow-kale/kale/issues",
marshal.get_backend(model).display_name)
utils.graceful_exit(-1)
predictor = predictor_type # in case `predictor` is None
volume = podutils.get_volume_containing_path(PVC_ROOT)
volume_name = volume[1].persistent_volume_claim.claim_name
log.info("Model is contained in volume '%s'", volume_name)
# Dump the model
marshal.set_data_dir(PREDICTOR_MODEL_DIR)
model_filepath = marshal.save(model, "model")
log.info("Model saved successfully at '%s'", model_filepath)
# Take snapshot
task_info = rokutils.snapshot_pvc(volume_name,
bucket=rokutils.SERVING_BUCKET,
wait=True)
task = rokutils.get_task(task_info["task"]["id"],
bucket=rokutils.SERVING_BUCKET)
new_pvc_name = "%s-pvc-%s" % (name, utils.random_string(5))
rokutils.hydrate_pvc_from_snapshot(task["result"]["event"]["object"],
task["result"]["event"]["version"],
new_pvc_name,
bucket=rokutils.SERVING_BUCKET)
# Cleanup: remove dumped model and transformer assets from the current PVC
utils.rm_r(
os.path.join(PREDICTOR_MODEL_DIR, os.path.basename(model_filepath)))
utils.rm_r(TRANSFORMER_ASSETS_DIR, silent=True)
# Need an absolute path from the *root* of the PVC. Add '/' if not exists.
pvc_model_path = "/" + PREDICTOR_MODEL_DIR.lstrip(PVC_ROOT)
# Tensorflow saves the model's files into a directory by itself
if predictor == "tensorflow":
pvc_model_path += "/" + os.path.basename(model_filepath).lstrip("/")
kfserver = create_inference_service(name=name,
predictor=predictor,
pvc_name=new_pvc_name,
model_path=pvc_model_path,
transformer=preprocessing_fn
is not None)
if wait:
monitor_inference_service(kfserver.name)
return kfserver
