Skip to content

fix: batch insert db by max postgres limit #20

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

Merged
merged 1 commit into from
Feb 18, 2025
Merged

fix: batch insert db by max postgres limit #20

merged 1 commit into from
Feb 18, 2025

Conversation

traviolus
Copy link
Collaborator

@traviolus traviolus commented Feb 18, 2025

Summary by CodeRabbit

  • Refactor
    • Enhanced bulk data insertion by implementing a batching mechanism. Large data operations are now split into manageable chunks, ensuring stable and efficient processing even with high data volumes. This update improves performance and reliability during heavy data operations, reducing potential issues without affecting your overall experience.

@traviolus traviolus requested a review from SeUkKim February 18, 2025 04:47
Copy link

coderabbitai bot commented Feb 18, 2025

Walkthrough

The changes add a constant MaxPostgresParams to represent the PostgreSQL parameter limit and modify the BulkInsert function in the database utility. The function now calculates the maximum rows per batch by dividing this constant by the number of columns. It iterates over the dataset in chunks and executes individual insert queries for each batch instead of a single query. The error handling remains unchanged to ensure that mismatches between columns and values or failed queries are reported appropriately.

Changes

File Change Summary
informative-indexer/db/util.go - Added the constant MaxPostgresParams (set to the maximum unsigned 16-bit integer value).
- Modified BulkInsert to calculate batch sizes based on columns count.
- Introduced a loop to execute batched insert queries, replacing the earlier single query.
- Retained existing error handling logic.

Sequence Diagram(s)

sequenceDiagram
    participant App as Application
    participant Bulk as BulkInsert Function
    participant DB as Database

    App->>Bulk: Call BulkInsert(columns, values)
    activate Bulk
    Bulk->>Bulk: Compute max rows per batch (MaxPostgresParams / numColumns)
    loop For each batch of rows
        Bulk->>DB: Execute batch insert query
        DB-->>Bulk: Return result
    end
    Bulk-->>App: Return success or error
    deactivate Bulk
Loading

Poem

In fields of code, I hop with glee,
Batching queries so nimble and free.
Max parameters guide the way,
Splitting rows in a rhythmic play.
A rabbit cheers our changes today! 🐰🌟

✨ Finishing Touches
  • 📝 Generate Docstrings (Beta)

🪧 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.

Copy link

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

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

Actionable comments posted: 0

🧹 Nitpick comments (1)
informative-indexer/db/util.go (1)

83-83: Add safety checks for the batch size calculation.

The current implementation could benefit from additional safety checks:

  1. Verify that maxRowsPerBatch is at least 1 to prevent infinite loops
  2. Guard against potential integer overflow in the division

Consider applying this improvement:

-maxRowsPerBatch := MaxPostgresParams / len(columns)
+if len(columns) > MaxPostgresParams {
+    return fmt.Errorf("too many columns: %d exceeds maximum allowed parameters", len(columns))
+}
+maxRowsPerBatch := MaxPostgresParams / len(columns)
+if maxRowsPerBatch < 1 {
+    maxRowsPerBatch = 1
+}
📜 Review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between e7e9409 and c043aa5.

📒 Files selected for processing (1)
  • informative-indexer/db/util.go (2 hunks)
🔇 Additional comments (2)
informative-indexer/db/util.go (2)

14-16: LGTM! Well-defined constant for PostgreSQL parameter limit.

Using math.MaxUint16 (65535) as the maximum parameter limit is correct and follows PostgreSQL's specifications.


83-100: LGTM! Effective implementation of batch processing.

The batching logic correctly handles PostgreSQL's parameter limit while maintaining clean error handling and efficient slice operations.

@SeUkKim SeUkKim merged commit 06eb7e0 into main Feb 18, 2025
1 check passed
@SeUkKim SeUkKim deleted the fix/psql-limit branch February 18, 2025 04:57
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants