Add a method to print the disk profile of an ntuple - #22914
Open
albfsg wants to merge 2 commits into
Open
Conversation
albfsg
force-pushed
the
print_disk_profile
branch
from
July 24, 2026 15:25
e1fd926 to
eb7ab15
Compare
Shows cluster groups, clusters, column ranges and pages. Comes with a test which stress tests the method with an ntuple shuffled on the 3 uppermost layers of the hierarchy: cluster groups, clusters, column ranges (pages are by definition uninterrupted serialized blobs).
Adds the ntuple header, footer and page list to the method. Updates its unit test accordingly.
albfsg
force-pushed
the
print_disk_profile
branch
from
July 24, 2026 15:36
eb7ab15 to
05f0d68
Compare
silverweed
reviewed
Jul 27, 2026
silverweed
left a comment
silverweed
left a comment
Contributor
There was a problem hiding this comment.
Thanks! A few minor comments but otherwise looks good 👍
| std::uint64_t fSize = 0; | ||
| std::string fName; | ||
| std::array<ROOT::DescriptorId_t, 3> fAncestorIds; // clusterGroup, cluster, columnRange | ||
| std::array<std::string, 3> fAncestorNames; // clusterGroup, cluster, columnRange |
Contributor
There was a problem hiding this comment.
You don't really need to store the string names in here, you can reconstruct them from the IDs upon creating the SpeedscopeFrames
Comment on lines
+752
to
+753
| std::vector<ROOT::DescriptorId_t> openIds; | ||
| std::vector<std::size_t> openFrameIndexes; |
Contributor
There was a problem hiding this comment.
Consider collapsing these two vectors in a single one (having elements of a custom type containing both the Id and the index - you can define this type in the function itself.)
|
|
||
| namespace { | ||
|
|
||
| void WriteShuffledNTuple(const std::string &ntupleName, const std::string &path) |
Contributor
There was a problem hiding this comment.
Add a brief description of what this function does
Contributor
There was a problem hiding this comment.
Also use std::string_view instead of const std::string &
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:
Changes or fixes:
Adds
PrintDiskProfilemethod to the experimentalRNTupleInspectorclass.Its brief:
In order to implement it I've added free function
GetAnchorinto theROOT::Internalnamespace, friend to theRPageSourceFileclass. OtherwiseRNTupleInspectorhas no access to it's anchor, which is necessary to visualize an ntuple's header and footer.Comes with a unit test.
Right now only supports Speedscope, with the following results for the test ntuple:
Checklist:
This PR fixes # (nothing, it's a new feature)