Improve distinct compression for index and data blocks#14140
Closed
pdillinger wants to merge 4 commits intofacebook:mainfrom
Closed
Improve distinct compression for index and data blocks#14140pdillinger wants to merge 4 commits intofacebook:mainfrom
pdillinger wants to merge 4 commits intofacebook:mainfrom
Conversation
Summary: This change enables a custom CompressionManager / Compressor to adopt custom handling for data and index blocks. In particular, index blocks for format_version >= 4 use a distinct variant of the block format. Thus, a potentially format-aware compression algorithm such as OpenZL should be told which kind of block we are compressing. (And previously I avoided passing block type in CompressBlock for efficient handling of things like dictionaries but also avoiding checks on every CompressBlock call.) Most of the change is in BlockBasedTableBuilder to call MaybeCloneSpecialized for both kDataBlock and for kIndexBlock. But I also needed some small tweaks/additions to the public API also: * Require a Clone() function from Compressors, to support proper implementations of MaybeCloneSpecialized() in wrapper Compressors. * Assert that the default implementation of CompressorWrapper::MaybeCloneSpecialized() is only used in allowable cases. * Convenience function Compressor::CloneMaybeSpecialized() Test Plan: Greatly expanded DBCompressionTest.CompressionManagerWrapper to make sure the distinction between data blocks and index blocks is properly communicated to a custom CompressionManager/Compressor. The test includes processing the expected structure of data and index blocks, to serve as a tested example for structure-aware compressors.
|
@pdillinger has imported this pull request. If you are a Meta employee, you can view this in D87600019. |
hx235
reviewed
Nov 21, 2025
| verify_decomp = r->data_block_verify_decompressor.get(); | ||
| } else { | ||
| compressor = r->basic_compressor.get(); | ||
| compressor = r->index_block_compressor; |
Contributor
There was a problem hiding this comment.
I'm confused here - when is_data_block=false, is it necessarily index block? If it's not, can you explain more why it's okay to use index_block_compressor? Similarly for "is_data_block ? r->data_block_working_area : r->index_block_working_area,".
Contributor
Author
There was a problem hiding this comment.
Currently only index blocks and data blocks are compressed
hx235
reviewed
Nov 21, 2025
Comment on lines
+1320
to
+1325
| if (data_block_compressor != basic_compressor.get()) { | ||
| delete data_block_compressor; | ||
| } | ||
| if (index_block_compressor != basic_compressor.get()) { | ||
| delete index_block_compressor; | ||
| } |
Contributor
There was a problem hiding this comment.
Is it possible that index_block_compressor == data_block_compressor in custom implementation? Do we have enough API comment to disallow that?
Contributor
Author
There was a problem hiding this comment.
Compressor is managed by unique_ptr. So these raw pointers came from distinct unique_ptrs (if they are not equal to basic_compressor). That's unlikely to change any time soon
hx235
approved these changes
Nov 21, 2025
|
@pdillinger merged this pull request in 35148ac. |
pdillinger
added a commit
to pdillinger/rocksdb
that referenced
this pull request
Nov 24, 2025
Summary: ... from facebook#14140. The assertion in the default implementation of CompressorWrapper::MaybeCloneSpecialized() could fail because this wrapper wasn't overriding it when it should. (See the NOTE on that implementation.) Because this release already has a breaking modification to the Compressor API (adding Clone()), I took this opportunity to add 'const' to MaybeCloneSpecialized(). Also marked some compression classes as 'final' that could be marked as such. Test Plan: unit test expanded to cover this case (verified failing before). Audited the rest of our CompressorWrappers.
meta-codesync bot
pushed a commit
that referenced
this pull request
Nov 24, 2025
Summary: ... from #14140. The assertion in the default implementation of CompressorWrapper::MaybeCloneSpecialized() could fail because this wrapper wasn't overriding it when it should. (See the NOTE on that implementation.) Because this release already has a breaking modification to the Compressor API (adding Clone()), I took this opportunity to add 'const' to MaybeCloneSpecialized(). Also marked some compression classes as 'final' that could be marked as such. Pull Request resolved: #14150 Test Plan: unit test expanded to cover this case (verified failing before). Audited the rest of our CompressorWrappers. Reviewed By: archang19 Differential Revision: D87793987 Pulled By: pdillinger fbshipit-source-id: 61c4469b84e4a47451a9942df09277faeeccfe63
pdillinger
added a commit
that referenced
this pull request
Nov 24, 2025
Summary: ... from #14140. The assertion in the default implementation of CompressorWrapper::MaybeCloneSpecialized() could fail because this wrapper wasn't overriding it when it should. (See the NOTE on that implementation.) Because this release already has a breaking modification to the Compressor API (adding Clone()), I took this opportunity to add 'const' to MaybeCloneSpecialized(). Also marked some compression classes as 'final' that could be marked as such. Pull Request resolved: #14150 Test Plan: unit test expanded to cover this case (verified failing before). Audited the rest of our CompressorWrappers. Reviewed By: archang19 Differential Revision: D87793987 Pulled By: pdillinger fbshipit-source-id: 61c4469b84e4a47451a9942df09277faeeccfe63
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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.
Summary: This change enables a custom CompressionManager / Compressor to adopt custom handling for data and index blocks. In particular, index blocks for format_version >= 4 use a distinct variant of the block format. Thus, a potentially format-aware compression algorithm such as OpenZL should be told which kind of block we are compressing. (And previously I avoided passing block type in CompressBlock for efficient handling of things like dictionaries but also avoiding checks on every CompressBlock call.)
Most of the change is in BlockBasedTableBuilder to call MaybeCloneSpecialized for both kDataBlock and for kIndexBlock. But I also needed some small tweaks/additions to the public API also:
This also fixes a serious bug/oversight in ManagedPtr for (ManagedWorkingArea) that somehow wasn't showing up before. It probably doesn't need a release note because CompressionManager stuff is still considered experimental.
Test Plan: Greatly expanded DBCompressionTest.CompressionManagerWrapper to make sure the distinction between data blocks and index blocks is properly communicated to a custom CompressionManager/Compressor. The test includes processing the expected structure of data and index blocks, to serve as a tested example for structure-aware compressors.