Remove caching the array on flat layout reader, rely on the segment cache instead#4459
Merged
Conversation
Signed-off-by: Onur Satici <onur@spiraldb.com>
onursatici
added
the
action/benchmark-sql
github-actions
Bot
removed
the
action/benchmark-sql
Contributor
Benchmarks: TPC-H SF=1 on NVMETable of Results
|
Contributor
Benchmarks: TPC-H SF=1 on S3Table of Results
|
Codecov Report✅ All modified and coverable lines are covered by tests. ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
Contributor
Benchmarks: Statistical and Population GeneticsTable of Results
|
Contributor
Benchmarks: Clickbench on NVMETable of Results
|
Contributor
Benchmarks: TPC-DS SF=1 on NVMETable of Results
|
onursatici
changed the title
Contributor
|
It's great that this is somewhat flat, I would adjust the code of the layout reader since we no longer need a sharedfuture iirc and the comments are no longer correct |
Contributor
|
Mind if we chat through this? Want to double check it fits into 4406. The other reason this existed originally was to avoid parsing the serialized arrays from each segment over and over. Flatbuffers verification was killing us |
gatesn
reviewed
Sep 2, 2025
| .map_err(Arc::new) | ||
| } | ||
| .boxed() | ||
| .shared()) |
Contributor
There was a problem hiding this comment.
Remove shared, then let's do it!
Contributor
Author
|
Unfortunately there is no straightforward way to get rid of shared futures here just yet. Because of the We have to have the Sync bound on both
|
robert3005
approved these changes
Sep 2, 2025
robert3005
left a comment
robert3005
left a comment
Contributor
There was a problem hiding this comment.
One minor thing is that we no longer need the array_future to return VortexResult (that was a case before this pr, just not cleaned up earlier)
Signed-off-by: Onur Satici <onur@spiraldb.com>
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.
With this we don't hold references to arrays in the flat reader, so we can configure the segment cache to have more control on memory held by a layoutref instance. There doesn't seem to be a noticeable regression, other than one query in clickbench datafusion (q23 - 20%).
Another approach could be to have weak references instead.
LayoutRef would still hold cache zone maps and dict values after this change, I did not remove them because they are somewhat bounded