[ntuple] Speed up RNTupleImporter and fix uncompressed Double32_t - #23447
Open
apeters1971 wants to merge 3 commits into
Open
apeters1971 wants to merge 3 commits into
apeters1971 wants to merge 3 commits into
Conversation
Double32_t always forced split encoding, even with compression off. Use kReal32 when there is nothing to encode against.
Add RImportReport so Import() exposes compressed page payload, uncompressed pages, and the destination TFile size after the writer commits.
GetConstSubfields() was allocating a new vector on every TTree entry, which made tree2ntuple and other imports much slower than they should be. Caching the leaf-count layout once removes that bottleneck and makes the conversion run much quicker.
apeters1971
force-pushed
the
rntuple-improvements
branch
from
September 22, 2026 11:45
05ffed2 to
a63f086
Compare
This branch has not been deployed
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This Pull request:
Generic RNTuple write/import improvements.
Changes or fixes:
RNTupleImporter: cache leaf-count field layout (offset, value size, branch index) afterFreeze().GetConstSubfields()was allocating a new vector on every TTree entry and kept import single-threaded. After this, fill can keep pace with IMT page compression.RImportReport/GetLastImportReport()expose compressed page payload, uncompressed pages, and destinationTFilesize after the writer commits.RPageSinkBufchecks that every page is sealed (and has a checksum when same-page merging requires one) beforeCommitCluster, instead of failing later with a null buffer.Double32_t: withSetCompression(0), storekReal32instead of always forcingkSplitReal32. Default compressed writes are unchanged (kSplitReal32). This is an existing column type, not a format version change.Checklist:
This PR fixes #