Eliminate redundant pack file decompression during clone operations #16
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Outdated suggestions cannot be applied.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.
Profiling showed 99% of clone time spent in
GeneratePackIndexV2, with 93% inFindCompressedLength. The code was decompressing the entire pack file twice: once to generate the index, then again to extract objects.Changes
New direct parsing path
PackFile.ParseAllObjectsDirectly()that parses objects in a single pass without generating an indexUpdated clone operations
ParsePackFileAndGetCommit()now callsParseAllObjectsDirectly()instead ofGeneratePackIndexV2() → ParsePackIndexV2() → ParseAllObjects()FetchBloblessCloneAsync()uses direct parsingLoadSubdirectoryContentsWithBloblessCloneAsync()uses direct parsingOptimization details
stackallocfor object headersGeneratePackIndexV2()remains unchanged and available when actual .idx/.rev files are neededImpact
Before:
After:
Expected performance: ~50% reduction in pack file parsing time for clone operations.
Original prompt
💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.