duckdb: flatten runend arrays on export if requested#7951
Open
myrrc wants to merge 1 commit into
Open
Conversation
Signed-off-by: Mikhail Kot <[email protected]>
myrrc
force-pushed
the
myrrc/duckdb-runend-flatten
branch
from
733aaf4 to
edf8146
Compare
myrrc
added
changelog/fix
github-actions
Bot
removed
action/benchmark
Contributor
Polar Signals Profiling ResultsLatest Run
Powered by Polar Signals Cloud |
Contributor
Benchmarks: PolarSignals ProfilingVortex (geomean): 0.987x ➖ datafusion / vortex-file-compressed (0.987x ➖, 0↑ 0↓)
|
Contributor
File Sizes: PolarSignals ProfilingNo file size changes detected. |
Merging this PR will degrade performance by 12.27%
|
| Mode | Benchmark | BASE |
HEAD |
Efficiency | |
|---|---|---|---|---|---|
| ❌ | Simulation | encode_varbin[(1000, 2)] |
148.5 µs | 169.2 µs | -12.27% |
Tip
Investigate this regression by commenting @codspeedbot fix this regression on this PR, or directly use the CodSpeed MCP with your agent.
Comparing myrrc/duckdb-runend-flatten (edf8146) with develop (254f91b)
Contributor
Benchmarks: FineWeb NVMeVerdict: No clear signal (low confidence) datafusion / vortex-file-compressed (0.994x ➖, 0↑ 0↓)
datafusion / vortex-compact (0.990x ➖, 0↑ 0↓)
datafusion / parquet (0.973x ➖, 0↑ 0↓)
duckdb / vortex-file-compressed (0.954x ➖, 1↑ 0↓)
duckdb / vortex-compact (0.955x ➖, 1↑ 0↓)
duckdb / parquet (0.923x ➖, 2↑ 0↓)
Full attributed analysis
|
Contributor
File Sizes: FineWeb NVMeNo file size changes detected. |
Comment on lines
+195
to
+196
| Ok(array) if !flatten => return run_end::new_exporter(array, cache, ctx), | ||
| Ok(array) => array.into_array(), // .into_array() does flattening |
Contributor
There was a problem hiding this comment.
add a new_exporter_with_flatten here?
Contributor
Benchmarks: TPC-H SF=1 on NVMEVerdict: No clear signal (low confidence) datafusion / vortex-file-compressed (0.963x ➖, 1↑ 0↓)
datafusion / vortex-compact (0.968x ➖, 1↑ 0↓)
datafusion / parquet (1.006x ➖, 0↑ 1↓)
datafusion / arrow (0.991x ➖, 0↑ 0↓)
duckdb / vortex-file-compressed (0.961x ➖, 0↑ 0↓)
duckdb / vortex-compact (0.943x ➖, 3↑ 0↓)
duckdb / parquet (0.993x ➖, 0↑ 0↓)
duckdb / duckdb (0.989x ➖, 0↑ 0↓)
Full attributed analysis
|
Contributor
File Sizes: TPC-H SF=1 on NVMENo file size changes detected. |
Contributor
Benchmarks: TPC-DS SF=1 on NVMEVerdict: No clear signal (low confidence) datafusion / vortex-file-compressed (1.083x ➖, 2↑ 39↓)
datafusion / vortex-compact (1.075x ➖, 2↑ 19↓)
datafusion / parquet (1.085x ➖, 0↑ 34↓)
duckdb / vortex-file-compressed (1.039x ➖, 3↑ 16↓)
duckdb / vortex-compact (0.986x ➖, 13↑ 8↓)
duckdb / parquet (1.055x ➖, 1↑ 12↓)
duckdb / duckdb (1.078x ➖, 0↑ 32↓)
Full attributed analysis
|
Contributor
File Sizes: TPC-DS SF=1 on NVMENo file size changes detected. |
Contributor
Benchmarks: FineWeb S3Verdict: No clear signal (low confidence) datafusion / vortex-file-compressed (1.024x ➖, 0↑ 0↓)
datafusion / vortex-compact (1.119x ➖, 0↑ 3↓)
datafusion / parquet (1.157x ➖, 0↑ 1↓)
duckdb / vortex-file-compressed (1.073x ➖, 0↑ 1↓)
duckdb / vortex-compact (1.031x ➖, 0↑ 0↓)
duckdb / parquet (1.078x ➖, 0↑ 0↓)
Full attributed analysis
|
Contributor
Benchmarks: Statistical and Population GeneticsVerdict: Likely improvement (medium confidence) duckdb / vortex-file-compressed (0.775x ✅, 7↑ 1↓)
duckdb / vortex-compact (0.689x ✅, 7↑ 1↓)
duckdb / parquet (1.018x ➖, 0↑ 0↓)
Full attributed analysis
|
Contributor
File Sizes: Statistical and Population GeneticsNo file size changes detected. |
Contributor
Benchmarks: TPC-H SF=10 on NVMEVerdict: No clear signal (low confidence) datafusion / vortex-file-compressed (0.831x ✅, 21↑ 0↓)
datafusion / vortex-compact (0.859x ✅, 20↑ 0↓)
datafusion / parquet (0.900x ➖, 10↑ 0↓)
datafusion / arrow (0.870x ✅, 19↑ 0↓)
duckdb / vortex-file-compressed (0.872x ✅, 17↑ 0↓)
duckdb / vortex-compact (0.872x ✅, 17↑ 0↓)
duckdb / parquet (0.954x ➖, 0↑ 0↓)
duckdb / duckdb (0.930x ➖, 1↑ 0↓)
Full attributed analysis
|
Contributor
File Sizes: TPC-H SF=10 on NVMENo file size changes detected. |
Contributor
Benchmarks: Clickbench on NVMEVerdict: No clear signal (low confidence) datafusion / vortex-file-compressed (0.996x ➖, 0↑ 0↓)
datafusion / parquet (0.992x ➖, 0↑ 0↓)
duckdb / vortex-file-compressed (0.966x ➖, 6↑ 0↓)
duckdb / parquet (0.993x ➖, 1↑ 0↓)
duckdb / duckdb (1.028x ➖, 0↑ 1↓)
Full attributed analysis
|
Contributor
File Sizes: Clickbench on NVMEFile Size Changes (1 files changed, -0.0% overall, 0↑ 1↓)
Totals:
|
Contributor
Benchmarks: TPC-H SF=1 on S3Verdict: No clear signal (environment too noisy confidence) datafusion / vortex-file-compressed (0.957x ➖, 1↑ 0↓)
datafusion / vortex-compact (1.093x ➖, 0↑ 2↓)
datafusion / parquet (1.126x ➖, 0↑ 4↓)
duckdb / vortex-file-compressed (0.984x ➖, 0↑ 0↓)
duckdb / vortex-compact (0.949x ➖, 0↑ 0↓)
duckdb / parquet (0.981x ➖, 0↑ 0↓)
Full attributed analysis
|
Contributor
Benchmarks: TPC-H SF=10 on S3Verdict: No clear signal (environment too noisy confidence) datafusion / vortex-file-compressed (0.980x ➖, 0↑ 0↓)
datafusion / vortex-compact (1.025x ➖, 0↑ 0↓)
datafusion / parquet (1.043x ➖, 1↑ 2↓)
duckdb / vortex-file-compressed (0.939x ➖, 0↑ 0↓)
duckdb / vortex-compact (0.956x ➖, 0↑ 0↓)
duckdb / parquet (0.930x ➖, 0↑ 0↓)
Full attributed analysis
|
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.
There was a bug in runend exporter that didn't flatten the array.
This produced dictionary arrays instead of flat arrays which required duckdb to
re-flatten them which was a regression in statpopgen.