Splitting flaky test: AsyncKVStoreWriter

[nikhil-zlai]

Summary

^^^

Checklist

• Added Unit Tests
• Covered by existing CI
• Integration tested
• Documentation update

Summary by CodeRabbit

• New Features

  • Added a new Async KV Store writer test to the workflow
  • Enhanced test suite with tagging capabilities

• Chores

  • Updated project dependencies in build configuration
  • Refined GitHub Actions workflow configuration

[coderabbitai]

Walkthrough

This pull request introduces a new test for the Async KV Store writer in the Flink project. The changes span across three files: a GitHub workflow configuration, the build configuration file, and a test file. The primary goal is to add a new test for the Async KV Store writer and update the project's dependency management and test execution configuration.

Changes

File	Change Summary
.github/workflows/test_scala_no_spark.yaml	Added new step to run Async KV Store writer test
build.sbt	Updated dependency configuration for flink project to explicitly include online project dependencies
flink/src/test/scala/.../AsyncKVStoreWriterTest.scala	Added TaggedFilterSuite trait and tagName method to test class

Sequence Diagram

sequenceDiagram
    participant Workflow
    participant SBT
    participant TestSuite
    Workflow->>SBT: Trigger test
    SBT->>TestSuite: Run AsyncKVStoreWriterTest
    TestSuite-->>SBT: Test results
    SBT-->>Workflow: Report test outcome

Loading

Possibly related PRs

• Summary upload #50: Similar key-value store functionality
• Tweak spark test setup to tags and run tests appropriately #56: Test tagging and selective test execution
• feat: use log4j2 everywhere in spark consistently #99: Logging practices across codebase

Suggested Reviewers

• piyush-zlai
• varant-zlai

Poem

🚀 Async KV Store, a test takes flight
Workflows dance with code so bright
Dependencies aligned just right
Scala's magic shines tonight
Testing prowess reaches new height! 🧪

Warning

Review ran into problems

🔥 Problems

GitHub Actions: Resource not accessible by integration - https://docs.github.com/rest/actions/workflow-runs#list-workflow-runs-for-a-repository.

Please grant the required permissions to the CodeRabbit GitHub App under the organization or repository settings.

---

🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

• Review comments: Directly reply to a review comment made by CodeRabbit. Example:
  • I pushed a fix in commit <commit_id>, please review it.
  • Generate unit testing code for this file.
  • Open a follow-up GitHub issue for this discussion.
• Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
  • @coderabbitai generate unit testing code for this file.
  • @coderabbitai modularize this function.
• PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
  • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
  • @coderabbitai read src/utils.ts and generate unit testing code.
  • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
  • @coderabbitai help me debug CodeRabbit configuration file.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

• @coderabbitai pause to pause the reviews on a PR.
• @coderabbitai resume to resume the paused reviews.
• @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
• @coderabbitai full review to do a full review from scratch and review all the files again.
• @coderabbitai summary to regenerate the summary of the PR.
• @coderabbitai generate docstrings to generate docstrings for this PR. (Beta)
• @coderabbitai resolve resolve all the CodeRabbit review comments.
• @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
• @coderabbitai help to get help.

Other keywords and placeholders

• Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
• Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
• Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

• You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
• Please see the configuration documentation for more information.
• If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

• Visit our Documentation for detailed information on how to use CodeRabbit.
• Join our Discord Community to get help, request features, and share feedback.
• Follow us on X/Twitter for updates and announcements.

[coderabbitai]

Actionable comments posted: 0

🧹 Nitpick comments (1)

.github/workflows/test_scala_no_spark.yaml (1)

68-68: Remove trailing spaces.

Fix formatting issue.

-          sbt "++ 2.12.18 online/testOnly -- -n catalystUtilHiveUdfTest"      
+          sbt "++ 2.12.18 online/testOnly -- -n catalystUtilHiveUdfTest"

🧰 Tools

🪛 yamllint (1.35.1)

[error] 68-68: trailing spaces

(trailing-spaces)

📜 Review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro (Legacy)

📥 Commits

Reviewing files that changed from the base of the PR and between c35231a and 1996410.

📒 Files selected for processing (3)

• .github/workflows/test_scala_no_spark.yaml (2 hunks)
• build.sbt (1 hunks)
• flink/src/test/scala/ai/chronon/flink/test/AsyncKVStoreWriterTest.scala (2 hunks)

🧰 Additional context used

📓 Learnings (1)

flink/src/test/scala/ai/chronon/flink/test/AsyncKVStoreWriterTest.scala (1)

Learnt from: piyush-zlai
PR: zipline-ai/chronon#33
File: cloud_aws/src/test/scala/ai/chronon/integrations/aws/DynamoDBKVStoreTest.scala:175-175
Timestamp: 2024-11-12T09:38:33.532Z
Learning: Hardcoding future timestamps in tests within `DynamoDBKVStoreTest.scala` is acceptable when data is generated and queried within the same time range, ensuring the tests remain valid over time.

🪛 yamllint (1.35.1)

.github/workflows/test_scala_no_spark.yaml

[error] 68-68: trailing spaces

(trailing-spaces)

⏰ Context from checks skipped due to timeout of 90000ms (7)

• GitHub Check: table_utils_delta_format_spark_tests
• GitHub Check: other_spark_tests
• GitHub Check: mutation_spark_tests
• GitHub Check: join_spark_tests
• GitHub Check: scala_compile_fmt_fix
• GitHub Check: no_spark_scala_tests
• GitHub Check: fetcher_spark_tests

🔇 Additional comments (3)

flink/src/test/scala/ai/chronon/flink/test/AsyncKVStoreWriterTest.scala (1)

7-7: LGTM! Good approach to isolate flaky tests.

The addition of TaggedFilterSuite and tagName enables running these tests in isolation.

Also applies to: 15-15, 64-64

.github/workflows/test_scala_no_spark.yaml (1)

54-56: LGTM! Test isolation step added correctly.

The new step properly executes the tagged test in isolation.

build.sbt (1)

213-213: LGTM! Proper test dependency configuration.

Added test->test scope for online dependency, enabling access to test utilities.