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

chore!: docker log to stdout and minor logging tweaks #951

Open
wants to merge 3 commits into
base: v1.3-dev
Choose a base branch
from

Conversation

lklimek
Copy link
Collaborator

@lklimek lklimek commented Oct 10, 2024

Issue being fixed or feature implemented

We must redirect stderr to stdout before grepping output of docker logs command.
It's quite hard to use.

What was done?

  1. Updated entrypoint.sh to redirect stderr to stdout
  2. tuned one log

How Has This Been Tested?

Locally

Breaking Changes

logs captured from docker logs must now be read from stdout instead of stderr.

Checklist:

  • I have performed a self-review of my own code
  • I have commented my code, particularly in hard-to-understand areas
  • I have added or updated relevant unit/integration/functional/e2e tests
  • I have made corresponding changes to the documentation

For repository code-owners and collaborators only

  • I have assigned this pull request to a milestone

Summary by CodeRabbit

  • Bug Fixes

    • Improved error handling and logging in the catchup replay process, adjusting log severity for better clarity.
  • Chores

    • Enhanced script consistency by removing leading spaces in the entrypoint script.

@lklimek lklimek added this to the v1.3 milestone Oct 10, 2024
Copy link
Contributor

coderabbitai bot commented Oct 10, 2024

Walkthrough

The changes involve formatting adjustments in the docker-entrypoint.sh script, specifically removing leading spaces for improved indentation consistency. The functionality of the script remains unchanged. In internal/consensus/state.go, the modifications focus on error handling in the OnStart method, where the log level for an error during the catchup replay process has been adjusted from Error to Warn. No new logic has been introduced, and the overall structure remains intact.

Changes

File Path Change Summary
DOCKER/docker-entrypoint.sh Removed leading spaces for consistent indentation.
internal/consensus/state.go Changed log level from Error to Warn in OnStart method.

Sequence Diagram(s)

sequenceDiagram
    participant User
    participant DockerEntryPoint
    participant State

    User->>DockerEntryPoint: Start container
    DockerEntryPoint->>DockerEntryPoint: Initialize configuration
    DockerEntryPoint->>State: Call OnStart
    State->>State: Execute catchup replay
    State-->>State: Log warning if error occurs
    State-->>DockerEntryPoint: Complete process
    DockerEntryPoint-->>User: Container running
Loading

🐰 In the script, a tidy hop,
Spaces removed, no need to stop.
In the state, a warning's now clear,
Catchup replay, we have no fear!
With logs that softly chime,
All is well, it's rabbit time! 🐇


📜 Recent review details

Configuration used: CodeRabbit UI
Review profile: CHILL

📥 Commits

Files that changed from the base of the PR and between 8468fc6 and 9dda3b6.

📒 Files selected for processing (2)
  • DOCKER/docker-entrypoint.sh (2 hunks)
  • internal/consensus/state.go (1 hunks)
✅ Files skipped from review due to trivial changes (1)
  • DOCKER/docker-entrypoint.sh
🧰 Additional context used
🔇 Additional comments (1)
internal/consensus/state.go (1)

449-449: Consider the implications of changing the log level from Error to Warn

The log level for catchup replay errors has been changed from Error to Warn. While this change doesn't affect the actual error handling logic, it does impact how these issues are perceived and potentially responded to.

  1. Reduced visibility: Warnings are typically considered less severe than errors, which might lead to these issues being overlooked.
  2. Monitoring impact: If there are any monitoring or alerting systems in place that rely on error-level logs, they may need to be updated.
  3. Operational changes: This change might require updates to operational procedures or documentation related to log monitoring and issue response.

Please ensure that this change aligns with the intended severity of catchup replay issues and that all relevant systems and procedures are updated accordingly.

To verify the impact of this change, we can check for any other occurrences of catchup replay error logging and any log-based alerting configurations:

✅ Verification successful

Log level change from Error to Warn verified

The change in log level for catchup replay errors from Error to Warn has been verified.

  • No other catchup replay error logs found in the codebase.
  • No log-based alerting configurations dependent on error-level logs detected.

This change should not negatively impact monitoring or alerting systems.

🏁 Scripts executed

The following scripts were executed for the analysis:

Script:

#!/bin/bash
# Check for other occurrences of catchup replay error logging
echo "Checking for other catchup replay error logs:"
rg --type go 'catchup replay' -C 3

# Check for any log-based alerting configurations
echo "Checking for log-based alerting configurations:"
rg --type yaml 'alert.*error'

Length of output: 656


Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media?

❤️ Share
🪧 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 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.

@lklimek lklimek enabled auto-merge (squash) October 10, 2024 13:14
@lklimek lklimek removed the request for review from QuantumExplorer October 11, 2024 05:50
@@ -52,14 +51,14 @@ if [ ! -d "$TMHOME/config" ]; then
fi

# Start tenderdash in the background
tenderdash "$@" &
tenderdash "$@" 2>&1 &
Copy link
Member

Choose a reason for hiding this comment

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

Are you sure you want to send all stderr from Tenderdash? We should probably let Tenderdash control output and adjust the logger to use stdout instead of stderr. There might be some confusion in the future when you do some stderr output from Tenderdash and do not see it when you run a docker container.

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

My AI junior says:

For server software running on Linux, it is generally recommended to send logs to `stderr`. This is because `stdout` is typically used for regular output, while `stderr` is used for logging errors and diagnostic information. Sending logs to `stderr` helps to separate log messages from the normal output of the program, making it easier to manage and analyze logs.

Here's a summary of the best practices:

- **stdout**: Use for regular program output, such as the results of a command or data that the program is designed to produce.
- **stderr**: Use for logging errors, warnings, and diagnostic information.

By following this convention, you can ensure that logs are properly handled and can be redirected or processed separately from the main output of your server software.

So, Tenderdash behavior to send logs to stderr is correct. For a particular use case of Docker, I decided to join these streams for usability.

@lklimek lklimek requested a review from shumkov October 11, 2024 08:15
Copy link

This pull request has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.

@github-actions github-actions bot added the Stale label Oct 22, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants