Conversation
Signed-off-by: Connor Tsui <connor.tsui20@gmail.com>
Polar Signals Profiling ResultsLatest Run
Previous Runs (3)
Powered by Polar Signals Cloud |
Benchmarks: PolarSignals ProfilingVortex (geomean): 0.976x ➖ datafusion / vortex-file-compressed (0.976x ➖, 1↑ 0↓)
|
File Sizes: PolarSignals ProfilingFile Size Changes (1 files changed, +0.0% overall, 1↑ 0↓)
Totals:
|
Benchmarks: TPC-H SF=1 on NVMEVerdict: No clear signal (low confidence) datafusion / vortex-file-compressed (0.952x ➖, 0↑ 0↓)
datafusion / vortex-compact (0.961x ➖, 0↑ 0↓)
datafusion / parquet (0.963x ➖, 3↑ 1↓)
datafusion / arrow (0.977x ➖, 1↑ 0↓)
duckdb / vortex-file-compressed (0.986x ➖, 0↑ 0↓)
duckdb / vortex-compact (0.980x ➖, 0↑ 0↓)
duckdb / parquet (0.934x ➖, 6↑ 1↓)
duckdb / duckdb (0.984x ➖, 0↑ 0↓)
Full attributed analysis
|
File Sizes: TPC-H SF=1 on NVMEFile Size Changes (6 files changed, -0.0% overall, 0↑ 6↓)
Totals:
|
Benchmarks: FineWeb NVMeVerdict: No clear signal (low confidence) datafusion / vortex-file-compressed (1.036x ➖, 2↑ 2↓)
datafusion / vortex-compact (1.191x ❌, 0↑ 7↓)
datafusion / parquet (0.981x ➖, 0↑ 0↓)
duckdb / vortex-file-compressed (1.058x ➖, 0↑ 2↓)
duckdb / vortex-compact (1.123x ❌, 0↑ 5↓)
duckdb / parquet (1.005x ➖, 0↑ 1↓)
Full attributed analysis
|
File Sizes: FineWeb NVMeFile Size Changes (2 files changed, +0.1% overall, 2↑ 0↓)
Totals:
|
Benchmarks: TPC-DS SF=1 on NVMEVerdict: No clear signal (low confidence) datafusion / vortex-file-compressed (0.879x ✅, 56↑ 0↓)
datafusion / vortex-compact (0.898x ✅, 40↑ 0↓)
datafusion / parquet (0.909x ➖, 31↑ 0↓)
duckdb / vortex-file-compressed (0.955x ➖, 11↑ 1↓)
duckdb / vortex-compact (0.964x ➖, 5↑ 0↓)
duckdb / parquet (0.976x ➖, 5↑ 0↓)
duckdb / duckdb (0.974x ➖, 4↑ 0↓)
Full attributed analysis
|
File Sizes: TPC-DS SF=1 on NVMEFile Size Changes (25 files changed, +0.1% overall, 13↑ 12↓)
Totals:
|
Benchmarks: FineWeb S3Verdict: No clear signal (environment too noisy confidence) datafusion / vortex-file-compressed (0.951x ➖, 1↑ 1↓)
datafusion / vortex-compact (0.921x ➖, 1↑ 0↓)
datafusion / parquet (0.970x ➖, 1↑ 1↓)
duckdb / vortex-file-compressed (1.060x ➖, 0↑ 1↓)
duckdb / vortex-compact (0.984x ➖, 0↑ 0↓)
duckdb / parquet (0.947x ➖, 0↑ 0↓)
Full attributed analysis
|
Benchmarks: TPC-H SF=10 on NVMEVerdict: No clear signal (medium confidence) datafusion / vortex-file-compressed (1.083x ➖, 2↑ 13↓)
datafusion / vortex-compact (1.209x ❌, 0↑ 22↓)
datafusion / parquet (0.983x ➖, 0↑ 0↓)
datafusion / arrow (0.957x ➖, 3↑ 0↓)
duckdb / vortex-file-compressed (1.172x ❌, 0↑ 21↓)
duckdb / vortex-compact (1.122x ❌, 0↑ 16↓)
duckdb / parquet (1.112x ❌, 0↑ 15↓)
duckdb / duckdb (1.064x ➖, 0↑ 2↓)
Full attributed analysis
|
File Sizes: TPC-H SF=10 on NVMEFile Size Changes (19 files changed, -0.0% overall, 0↑ 19↓)
Totals:
|
Benchmarks: Statistical and Population GeneticsVerdict: No clear signal (low confidence) duckdb / vortex-file-compressed (1.104x ❌, 0↑ 5↓)
duckdb / vortex-compact (1.094x ➖, 0↑ 3↓)
duckdb / parquet (1.082x ➖, 0↑ 1↓)
Full attributed analysis
|
File Sizes: Statistical and Population GeneticsFile Size Changes (2 files changed, +0.0% overall, 1↑ 1↓)
Totals:
|
Benchmarks: Random AccessVortex (geomean): 0.810x ✅ unknown / unknown (0.847x ✅, 28↑ 0↓)
|
Benchmarks: Clickbench on NVMEVerdict: No clear signal (low confidence) datafusion / vortex-file-compressed (0.989x ➖, 0↑ 1↓)
datafusion / parquet (0.995x ➖, 0↑ 0↓)
duckdb / vortex-file-compressed (0.984x ➖, 2↑ 1↓)
duckdb / parquet (1.008x ➖, 0↑ 0↓)
duckdb / duckdb (1.011x ➖, 1↑ 1↓)
Full attributed analysis
|
File Sizes: Clickbench on NVMEFile Size Changes (110 files changed, -0.0% overall, 0↑ 110↓)
Totals:
|
Benchmarks: TPC-H SF=1 on S3Verdict: No clear signal (environment too noisy confidence) datafusion / vortex-file-compressed (0.914x ➖, 2↑ 0↓)
datafusion / vortex-compact (0.869x ➖, 3↑ 0↓)
datafusion / parquet (1.138x ➖, 0↑ 5↓)
duckdb / vortex-file-compressed (0.953x ➖, 0↑ 1↓)
duckdb / vortex-compact (0.990x ➖, 0↑ 0↓)
duckdb / parquet (0.970x ➖, 0↑ 0↓)
Full attributed analysis
|
Benchmarks: CompressionVortex (geomean): 1.010x ➖ unknown / unknown (1.000x ➖, 5↑ 6↓)
|
Benchmarks: TPC-H SF=10 on S3Verdict: No clear signal (environment too noisy confidence) datafusion / vortex-file-compressed (0.796x ➖, 5↑ 0↓)
datafusion / vortex-compact (0.960x ➖, 0↑ 0↓)
datafusion / parquet (0.917x ➖, 2↑ 1↓)
duckdb / vortex-file-compressed (0.954x ➖, 0↑ 0↓)
duckdb / vortex-compact (0.949x ➖, 0↑ 0↓)
duckdb / parquet (0.921x ➖, 0↑ 0↓)
Full attributed analysis
|
|
so compress time definitely improved, but there are regressions in file size. I think I know why (chooses FSST instead of Dict), and I can fix that |
Signed-off-by: Connor Tsui <connor.tsui20@gmail.com>
d9a6ec5 to
9823b45
Compare
Signed-off-by: Connor Tsui <connor.tsui20@gmail.com>
Summary
Tracking issue: #7216
API Changes
TODO maybe?
Testing
Benchmarks run.