Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Added E2E test to run Python wheels on interactive cluster created in bundle #1864

Merged
merged 1 commit into from
Nov 1, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
@@ -0,0 +1,25 @@
{
"properties": {
"project_name": {
"type": "string",
"default": "my_test_code",
"description": "Unique name for this project"
},
"spark_version": {
"type": "string",
"description": "Spark version used for job cluster"
},
"node_type_id": {
"type": "string",
"description": "Node type id for job cluster"
},
"unique_id": {
"type": "string",
"description": "Unique ID for job name"
},
"instance_pool_id": {
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is not being used in the test, should we use it in the cluster specification to reduce the time this test takes to run?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We create an interactive cluster as part of this test, so instance_pool_id needs to be removed

"type": "string",
"description": "Instance pool id for job cluster"
}
}
}
Original file line number Diff line number Diff line change
@@ -0,0 +1,29 @@
bundle:
name: wheel-task

workspace:
root_path: "~/.bundle/{{.unique_id}}"

resources:
clusters:
test_cluster:
cluster_name: "test-cluster-{{.unique_id}}"
spark_version: "{{.spark_version}}"
node_type_id: "{{.node_type_id}}"
num_workers: 1
data_security_mode: USER_ISOLATION

jobs:
some_other_job:
name: "[${bundle.target}] Test Wheel Job {{.unique_id}}"
tasks:
- task_key: TestTask
existing_cluster_id: "${resources.clusters.test_cluster.cluster_id}"
python_wheel_task:
package_name: my_test_code
entry_point: run
parameters:
- "one"
- "two"
libraries:
- whl: ./dist/*.whl
Original file line number Diff line number Diff line change
@@ -0,0 +1,15 @@
from setuptools import setup, find_packages

import {{.project_name}}

setup(
name="{{.project_name}}",
version={{.project_name}}.__version__,
author={{.project_name}}.__author__,
url="https://databricks.com",
author_email="john.doe@databricks.com",
description="my example wheel",
packages=find_packages(include=["{{.project_name}}"]),
entry_points={"group1": "run={{.project_name}}.__main__:main"},
install_requires=["setuptools"],
)
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
__version__ = "0.0.1"
__author__ = "Databricks"
Original file line number Diff line number Diff line change
@@ -0,0 +1,16 @@
"""
The entry point of the Python Wheel
"""

import sys


def main():
# This method will print the provided arguments
print("Hello from my func")
print("Got arguments:")
print(sys.argv)


if __name__ == "__main__":
main()
19 changes: 15 additions & 4 deletions internal/bundle/python_wheel_test.go
Original file line number Diff line number Diff line change
Expand Up @@ -5,17 +5,18 @@ import (

"github.com/databricks/cli/internal"
"github.com/databricks/cli/internal/acc"
"github.com/databricks/cli/internal/testutil"
"github.com/databricks/cli/libs/env"
"github.com/google/uuid"
"github.com/stretchr/testify/require"
)

func runPythonWheelTest(t *testing.T, sparkVersion string, pythonWheelWrapper bool) {
func runPythonWheelTest(t *testing.T, templateName string, sparkVersion string, pythonWheelWrapper bool) {
ctx, _ := acc.WorkspaceTest(t)

nodeTypeId := internal.GetNodeTypeId(env.Get(ctx, "CLOUD_ENV"))
instancePoolId := env.Get(ctx, "TEST_INSTANCE_POOL_ID")
bundleRoot, err := initTestTemplate(t, ctx, "python_wheel_task", map[string]any{
bundleRoot, err := initTestTemplate(t, ctx, templateName, map[string]any{
"node_type_id": nodeTypeId,
"unique_id": uuid.New().String(),
"spark_version": sparkVersion,
Expand Down Expand Up @@ -45,9 +46,19 @@ func runPythonWheelTest(t *testing.T, sparkVersion string, pythonWheelWrapper bo
}

func TestAccPythonWheelTaskDeployAndRunWithoutWrapper(t *testing.T) {
runPythonWheelTest(t, "13.3.x-snapshot-scala2.12", false)
runPythonWheelTest(t, "python_wheel_task", "13.3.x-snapshot-scala2.12", false)
}

func TestAccPythonWheelTaskDeployAndRunWithWrapper(t *testing.T) {
runPythonWheelTest(t, "12.2.x-scala2.12", true)
runPythonWheelTest(t, "python_wheel_task", "12.2.x-scala2.12", true)
}

func TestAccPythonWheelTaskDeployAndRunOnInteractiveCluster(t *testing.T) {
_, wt := acc.WorkspaceTest(t)

if testutil.IsAWSCloud(wt.T) {
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

You can create clusters on AWS right? Does the test runner not have enough permissions?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

it's a permission issue, yes

t.Skip("Skipping test for AWS cloud because it is not permitted to create clusters")
}

runPythonWheelTest(t, "python_wheel_task_with_cluster", defaultSparkVersion, false)
}
Loading