Use built-in DF cache for file metadata and fix metrics wiring#6164
Merged
Use built-in DF cache for file metadata and fix metrics wiring#6164
Conversation
github-actions
bot
removed
the
action/benchmark-sql
Contributor
Benchmarks: TPC-H SF=1 on NVMESummary
Detailed Results Table
|
Contributor
Benchmarks: FineWeb NVMeSummary
Detailed Results Table
|
CodSpeed Performance ReportMerging this PR will improve performance by 19.73%Comparing
|
| Mode | Benchmark | BASE |
HEAD |
Efficiency | |
|---|---|---|---|---|---|
| ⚡ | WallTime | u8_FoR[10M] |
7.5 µs | 6.2 µs | +19.73% |
Footnotes
-
1323 benchmarks were skipped, so the baseline results were used instead. If they were deleted from the codebase, click here and archive them to remove them from the performance reports. ↩
Contributor
Benchmarks: TPC-H SF=1 on S3Summary
Detailed Results Table
|
Contributor
Benchmarks: TPC-DS SF=1 on NVMESummary
Detailed Results Table
|
Contributor
Benchmarks: TPC-H SF=10 on NVMESummary
Detailed Results Table
|
Contributor
Benchmarks: FineWeb S3Summary
Detailed Results Table
|
Contributor
Benchmarks: Statistical and Population GeneticsSummary
Detailed Results Table
|
Contributor
Benchmarks: TPC-H SF=10 on S3Summary
Detailed Results Table
|
Contributor
Benchmarks: Clickbench on NVMESummary
Detailed Results Table
|
github-actions
bot
removed
the
action/benchmark-sql
AdamGS
force-pushed
the
adamg/utilize-df-caches
branch
from
49bfc43 to
ecd35ae
Compare
github-actions
bot
removed
the
action/benchmark-sql
AdamGS
force-pushed
the
adamg/utilize-df-caches
branch
from
ecd35ae to
272f664
Compare
github-actions
bot
removed
the
action/benchmark-sql
github-actions
bot
removed
the
action/benchmark-sql
Signed-off-by: Adam Gutglick <adam@spiraldb.com>
Signed-off-by: Adam Gutglick <adam@spiraldb.com>
Signed-off-by: Adam Gutglick <adam@spiraldb.com>
Signed-off-by: Adam Gutglick <adam@spiraldb.com>
Signed-off-by: Adam Gutglick <adam@spiraldb.com>
Signed-off-by: Adam Gutglick <adam@spiraldb.com>
AdamGS
force-pushed
the
adamg/utilize-df-caches
branch
from
d2bc422 to
550803a
Compare
AdamGS
added
action/benchmark-sql
AdamGS
commented
Jan 27, 2026
Comment on lines
+304
to
+308
| let task_ctx = Arc::new(df.task_ctx()); | ||
| let plan = df.create_physical_plan().await?; | ||
| let result = collect(plan.clone(), task_ctx).await?; | ||
|
|
||
| Ok((result, physical_plan)) | ||
| Ok((result, plan)) |
Contributor
Author
There was a problem hiding this comment.
because metrics aren't global anymore, this is the way to get the actual metrics generated during the query.
Signed-off-by: Adam Gutglick <adam@spiraldb.com>
AdamGS
force-pushed
the
adamg/utilize-df-caches
branch
from
1df87dd to
93d54cc
Compare
AdamGS
changed the title
a10y
reviewed
Jan 28, 2026
Comment on lines
170
to
173
| let root_layout = footer.layout(); | ||
| let layout_size = size_of::<DType>() | ||
| let layout_size = size_of_val(footer.dtype()) | ||
| + root_layout.metadata().len() | ||
| + root_layout.segment_ids().len() * size_of::<SegmentId>(); |
Contributor
There was a problem hiding this comment.
i think this might be an under-estimate since it doesn't account for the size of the child layouts? the old code i think always was wrong in this way
Signed-off-by: Andrew Duffy <andrew@a10y.dev>
danking
pushed a commit
that referenced
this pull request
Feb 6, 2026
Instead of using our own custom file cache, we delegate to DataFusion's file metadata cache to stash footers we've already read, allowing users to re-use other existing DF code and extensions while reducing the amount of code we have to care about. It also makes wiring metrics simpler, as we don't cache the layout readers created during `infer_schema` or `infer_stats`, which is desired because `FileFormat` is long living while `FileSource` isn't, so we don't want it to hold a metrics instance. --------- Signed-off-by: Adam Gutglick <adam@spiraldb.com> Signed-off-by: Andrew Duffy <andrew@a10y.dev> Co-authored-by: Andrew Duffy <andrew@a10y.dev>
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.
Instead of using our own custom file cache, we delegate to DataFusion's file metadata cache to stash footers we've already read, allowing users to re-use other existing DF code and extensions while reducing the amount of code we have to care about.
It also makes wiring metrics simpler, as we don't cache the layout readers created during
infer_schemaorinfer_stats, which is desired becauseFileFormatis long living whileFileSourceisn't, so we don't want it to hold a metrics instance.