Conversation
- Replaced `fs.readFileSync` with `fs.promises.readFile` in `src/core/sqlite-db.ts`. - Replaced `fs.statSync` with `fs.promises.stat`. - Added `tests/performance/benchmark.ts` to measure event loop blocking. - Verified performance: Event loop ticks increased from ~8 to ~3881 during a 500MB file read, confirming non-blocking behavior. Co-authored-by: zknpr <96851588+zknpr@users.noreply.github.com>
|
👋 Jules, reporting for duty! I'm here to lend a hand with this pull request. When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down. I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job! For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with New to Jules? Learn more at jules.google/docs. For security, I will only act on instructions from the user who triggered this task. |
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Summary of ChangesHello @zknpr, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request addresses a critical performance bottleneck by converting synchronous database file reading operations to asynchronous ones. The change ensures that the application remains responsive and the event loop is not blocked, even when handling large database files. A new performance benchmark script has been added to validate this improvement, confirming that the asynchronous approach successfully prevents event loop blocking. Highlights
🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console. Changelog
Activity
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request correctly addresses a performance issue by replacing synchronous file I/O with asynchronous methods, preventing the event loop from being blocked when reading large database files. The addition of a benchmark script is a great way to validate the improvement. My review includes a suggestion to enhance the benchmark script by making its file operations fully asynchronous and ensuring robust cleanup, which aligns with the overall goal of the PR.
| function createLargeFile() { | ||
| const buffer = Buffer.alloc(FILE_SIZE); | ||
| fs.writeFileSync(TEST_FILE, buffer); | ||
| } | ||
|
|
||
| function deleteLargeFile() { | ||
| if (fs.existsSync(TEST_FILE)) { | ||
| fs.unlinkSync(TEST_FILE); | ||
| } | ||
| } | ||
|
|
||
| async function runBenchmark() { | ||
| deleteLargeFile(); | ||
| console.log('Creating large file...'); | ||
| createLargeFile(); | ||
| console.log(`Created ${FILE_SIZE / 1024 / 1024}MB test file.`); | ||
|
|
||
| const start = performance.now(); | ||
|
|
||
| // Start a timer to check event loop blocking | ||
| let ticks = 0; | ||
| const interval = setInterval(() => { | ||
| ticks++; | ||
| }, 1); // 1ms interval | ||
|
|
||
| try { | ||
| console.log('Starting createDatabaseEngine...'); | ||
| await createDatabaseEngine({ | ||
| content: null, | ||
| filePath: TEST_FILE, | ||
| maxSize: 0, | ||
| }); | ||
| } catch (e: any) { | ||
| // We expect an error because the file is not a valid SQLite database | ||
| // console.log('Expected error (invalid db):', e.message); | ||
| } | ||
|
|
||
| clearInterval(interval); | ||
| const end = performance.now(); | ||
| const duration = end - start; | ||
|
|
||
| console.log(`Time taken: ${duration.toFixed(2)}ms`); | ||
| console.log(`Event loop ticks: ${ticks}`); | ||
|
|
||
| // If ticks are very low relative to duration, it means blocking occurred. | ||
| if (duration > 100 && ticks < (duration / 10)) { | ||
| console.log("RESULT: BLOCKED (Ticks significantly lower than duration)"); | ||
| } else { | ||
| console.log("RESULT: NON-BLOCKING (or fast enough)"); | ||
| } | ||
|
|
||
| deleteLargeFile(); | ||
| } |
There was a problem hiding this comment.
The benchmark script can be improved in two ways:
-
Use asynchronous file operations: The
createLargeFileanddeleteLargeFilefunctions currently use synchronous methods (writeFileSync,existsSync,unlinkSync). While this is for a test script, using their asynchronous counterparts fromfs.promiseswould be more consistent with the non-blocking approach this PR promotes. -
Ensure robust cleanup: The
runBenchmarkfunction should use atry...finallyblock to guarantee thatdeleteLargeFile()is called, even if an unexpected error occurs during the benchmark. This prevents leaving large test files on disk.
The suggested code below implements these improvements.
async function createLargeFile() {
const buffer = Buffer.alloc(FILE_SIZE);
await fs.promises.writeFile(TEST_FILE, buffer);
}
async function deleteLargeFile() {
try {
await fs.promises.unlink(TEST_FILE);
} catch (error: any) {
if (error.code !== 'ENOENT') {
throw error;
}
}
}
async function runBenchmark() {
// Ensure cleanup from any previous runs.
await deleteLargeFile();
console.log('Creating large file...');
await createLargeFile();
console.log(`Created ${FILE_SIZE / 1024 / 1024}MB test file.`);
try {
const start = performance.now();
// Start a timer to check event loop blocking
let ticks = 0;
const interval = setInterval(() => {
ticks++;
}, 1); // 1ms interval
try {
console.log('Starting createDatabaseEngine...');
await createDatabaseEngine({
content: null,
filePath: TEST_FILE,
maxSize: 0,
});
} catch (e: any) {
// We expect an error because the file is not a valid SQLite database
// console.log('Expected error (invalid db):', e.message);
}
clearInterval(interval);
const end = performance.now();
const duration = end - start;
console.log(`Time taken: ${duration.toFixed(2)}ms`);
console.log(`Event loop ticks: ${ticks}`);
// If ticks are very low relative to duration, it means blocking occurred.
if (duration > 100 && ticks < (duration / 10)) {
console.log("RESULT: BLOCKED (Ticks significantly lower than duration)");
} else {
console.log("RESULT: NON-BLOCKING (or fast enough)");
}
} finally {
await deleteLargeFile();
}
}
|
Merged as part of v1.3.0 release in PR #65 |
Acknowledged. Thank you for the update. |
1 participant
This PR addresses a performance issue where reading large database files synchronously in the worker thread was blocking the event loop.
Changes:
fs.statSyncandfs.readFileSyncwith their asynchronous counterparts fromfs.promisesincreateDatabaseEngine.tests/performance/benchmark.tsthat creates a large dummy file and measures the time taken to read it, while also counting event loop ticks to detect blocking.Results:
The change ensures that the extension remains responsive even when loading large database files.
PR created automatically by Jules for task 8887365914515574585 started by @zknpr