Optimize how we track data for persistence #89370
Draft
+403
−604
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
nextjs-bot
added
created-by: Turbopack team
Contributor
Author
This stack of pull requests is managed by Graphite. Learn more about stacking. |
![vercel[bot]](https://avatars.githubusercontent.com/in/8329?s=60&v=4){kind=small}
CodSpeed Performance ReportMerging this PR will improve performance by 3.65%Comparing Summary
Performance Changes
Footnotes
|
Collaborator
Stats from current PR✅ No significant changes detected📊 All Metrics📖 Metrics GlossaryDev Server Metrics:
Build Metrics:
Change Thresholds:
⚡ Dev Server
📦 Dev Server (Webpack) (Legacy)📦 Dev Server (Webpack)
⚡ Production Builds
📦 Production Builds (Webpack) (Legacy)📦 Production Builds (Webpack)
📦 Bundle SizesBundle Sizes⚡ TurbopackClient Main Bundles: **434 kB** → **434 kB** ✅ -2 B81 files with content-based hashes (individual files not comparable between builds) Server Middleware
Build DetailsBuild Manifests
📦 WebpackClient Main Bundles
Polyfills
Pages
Server Edge SSR
Middleware
Build DetailsBuild Manifests
Build Cache
🔄 Shared (bundler-independent)Runtimes
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What?
Optimizes the change tracking mechanism used for persistent cache snapshots in turbo-tasks-backend.
Why?
The previous implementation used a
FxDashMap<TaskId, ModifiedState>to track modified tasks, whereModifiedStatewas an enum withModifiedandSnapshot(Option<Box<TaskStorage>>)variants. This had several inefficiencies:ModifiedStateenum was 16 bytes to account for the rare 'snapshot race' casemodifiedmap was highly sharded leading to large amounts of memory overhead. Most acquisitions were extremely short lived and so this isn't necessary.TaskCacheLogstructure (Sharded<ChunkedVec<...>>), requiring additional synchronization and a separate persistence path.How?
Restructured change tracking into two separate data structures:
modified: Sharded<Vec<TaskId>>- A sharded append-only list for tracking modified task IDs. Since modifications are guarded by a transition in theany_modifiedflag onTaskStorage, each task is only added once, avoiding duplicates without additional synchronization.snapshots: FxDashMap<TaskId, Option<Box<TaskStorage>>>- A small, rarely-used map for the uncommon case where a task is modified during an active snapshot operation. Uses only 16 shards since this is rare (only during dev mode idle-callback persistence races).Unified task cache persistence:
TaskCacheLogandChunkedVecinfrastructuretask_typedirectly in theSnapshotItemstructOther optimizations:
SmallVec::into_boxed_slice()now called directly instead ofinto_vec().into_boxed_slice()(avoids intermediate allocation)swap_retainutility (no longer needed)scope_and_blockwith chunked shards, this reduces the number of 'scratch buffers' allocated to 'one per chunk' instead of 'one per original shard'Results on vercel-site
I ran a sequence of builds on vercel-site comparing canary and this branch
Cold Cache Builds
Warm Cache Builds
The latency deltas are in the noise but there are substantial memory wins from this change