Skip to content

Conversation

@Beaness
Copy link
Contributor

@Beaness Beaness commented Dec 17, 2025

image Should improve chunk rewriting performance

@Beaness Beaness changed the title Optimize 1.7 compression by using velocity-native compressor Optimize 1.7 compression by using velocity-native compressor and reduce memory allocations inside chunk rewriting Dec 17, 2025
@Beaness
Copy link
Contributor Author

Beaness commented Dec 17, 2025

Latest commit has the additional following changes:

  • Dropped ExtendedBlockStorage to prevent having extra memory byte array allocations when it can be written directly to the output byte array
  • Allocate only one byte array in bulk chunk map where all chunks are serialized to

…d on heap byte arrays so native compression has no use
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.

1 participant