bench: run morsel reader in CI benchmarks by joseph-isaacs · Pull Request #9684 · vortex-data/vortex

joseph-isaacs · 2026-08-28T08:05:11Z

Throwaway draft to exercise the morsel-driven layout reader in CI. This branch is not intended to merge.

keeps the existing benchmark labels/result identities
runs Vortex compression and random-access paths through morsels
routes DataFusion and DuckDB ScanBuilder scans through the morsel executor
emits one array per morsel, preserving ordered DataFusion delivery while allowing DuckDB batch reordering
writes SQL benchmark files without dictionary layouts and retains zoned statistics for per-morsel pruning
drops failed or wrong-row-count SQL measurements instead of aborting or reporting a number
rejects unsupported limits and row-index scans; nested and dictionary layouts remain unsupported

Checks:

cargo test -p vortex-morsel
cargo test -p vortex-datafusion persistent::opener::tests -- --nocapture (27 passed, 2 intentionally ignored)
cargo test -p vortex-duckdb (218 passed, 2 pre-existing S3 ignores)
cargo test -p vortex-bench runner::tests
affected-package cargo clippy --all-targets -- -D warnings
TPC-H SF1 Q1 SQL smoke: DataFusion + Vortex and DuckDB + Vortex

Copy the complete morsel prototype onto current develop and route the compression and random-access Vortex benchmark lanes through it. Unsupported measurements are omitted so the throwaway CI run can survey partial coverage. Signed-off-by: Joe Isaacs <joe.isaacs@live.co.uk>

codspeed-hq · 2026-08-28T08:21:51Z

Merging this PR will degrade performance by 3.77%

⚠️

Unknown Walltime execution environment detected

Using the Walltime instrument on standard Hosted Runners will lead to inconsistent data.

For the most accurate results, we recommend using CodSpeed Macro Runners: bare-metal machines fine-tuned for performance measurement consistency.

⚠️

Different runtime environments detected

Some benchmarks with significant performance changes were compared across different runtime environments,
which may affect the accuracy of the results.

Open the report in CodSpeed to investigate

⚡ 1 improved benchmark
❌ 1 regressed benchmark
✅ 2167 untouched benchmarks
⏩ 106 skipped benchmarks¹
🗄️ 4 archived benchmarks run²

Warning

Please fix the performance issues or acknowledge them on CodSpeed.

Performance Changes

	Mode	Benchmark	`BASE`	`HEAD`	Efficiency
❌	WallTime	`arrow_checked_add_u32_avx2[16384]`	17.7 µs	21.3 µs	-16.89%
⚡	WallTime	`mul_u32_nonnull_avx512`	6.3 µs	5.7 µs	+11.43%

Tip

Investigate this regression by commenting @codspeedbot fix this regression on this PR, or directly use the CodSpeed MCP with your agent.

_{Comparing claude/morsel-compress-random-access-ci (681bb3d) with develop (01f147a)}

106 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. ↩
4 benchmarks were run, but are now archived. If they were deleted in another branch, consider rebasing to remove them from the report. Instead if they were added back, click here to restore them. ↩

github-actions · 2026-08-28T08:39:43Z

Polar Signals Profiling Results

Latest Run

Status	Commit	Job	Attempt	Link
🟢 Done	`5b3cb2e`	random-access-bench	1	Explore Profiling Data
🟢 Done	`5b3cb2e`	compress-bench	1	Explore Profiling Data

Powered by Polar Signals Cloud

github-actions · 2026-08-28T09:13:38Z

Benchmarks: Compression 📖

Commits: PR 5b3cb2e4 vs base 68e2aee0

vortex / vortex-file-compressed / ns (0.941x ➖, 4↑ 2↓)

name	ns (PR / base / %diff)
compress time/Arade	1162917746 / 1248805660 / -6.9%
compress time/Bimbo	4920803026 / 5154059542 / -4.5%
compress time/CMSprovider	3936360053 / 4015717164 / -2.0%
compress time/Euro2016	491223179 / 510973997 / -3.9%
compress time/Food	430631539 / 428422301 / +0.5%
compress time/HashTags	918033619 / 923401677 / -0.6%
compress time/TPC-H l_comment canonical	1117248352 / 1180446412 / -5.4%
compress time/TPC-H l_comment chunked	1132820964 / 1239332321 / -8.6%
compress time/taxi	564596059 / 558651509 / +1.1%
compress time/wide table cols=100 chunks=1 rows=1000	8104888 / 8580166 / -5.5%
compress time/wide table cols=100 chunks=50 rows=1000	8323796 / 8281779 / +0.5%
compress time/wide table cols=1000 chunks=1 rows=1000	82391530 / 85342548 / -3.5%
compress time/wide table cols=1000 chunks=50 rows=1000	83573668 / 84887805 / -1.5%
compress time/wide table cols=10000 chunks=1 rows=1000	976944035 / 1010663877 / -3.3%
compress time/wide table cols=10000 chunks=50 rows=1000	982349418 / 992693882 / -1.0%
decompress time/wide table cols=100 chunks=1 rows=1000	4288358 / 2284321 / +87.7% 🔴
decompress time/wide table cols=100 chunks=50 rows=1000	4124677 / 2336887 / +76.5% 🔴
decompress time/wide table cols=1000 chunks=1 rows=1000	17396849 / 22709674 / -23.4% 🟢
decompress time/wide table cols=1000 chunks=50 rows=1000	17282137 / 22881068 / -24.5% 🟢
decompress time/wide table cols=10000 chunks=1 rows=1000	144257462 / 337825788 / -57.3% 🟢
decompress time/wide table cols=10000 chunks=50 rows=1000	143964755 / 269245696 / -46.5% 🟢

vortex / vortex-file-compressed / bytes (1.000x ➖, 0↑ 0↓)

name	bytes (PR / base / %diff)
vortex-file-compressed size/Arade	144460892 / 144460892 / +0.0%
vortex-file-compressed size/Bimbo	461842820 / 461842820 / +0.0%
vortex-file-compressed size/CMSprovider	415192372 / 415192372 / +0.0%
vortex-file-compressed size/Euro2016	157674980 / 157674316 / +0.0%
vortex-file-compressed size/Food	41581536 / 41581536 / +0.0%
vortex-file-compressed size/HashTags	177840236 / 177840236 / +0.0%
vortex-file-compressed size/TPC-H l_comment canonical	163453296 / 163453296 / +0.0%
vortex-file-compressed size/TPC-H l_comment chunked	163453296 / 163453296 / +0.0%
vortex-file-compressed size/taxi	51475084 / 51475084 / +0.0%
vortex-file-compressed size/wide table cols=100 chunks=1 rows=1000	932656 / 932656 / +0.0%
vortex-file-compressed size/wide table cols=100 chunks=50 rows=1000	932656 / 932656 / +0.0%
vortex-file-compressed size/wide table cols=1000 chunks=1 rows=1000	9309856 / 9309856 / +0.0%
vortex-file-compressed size/wide table cols=1000 chunks=50 rows=1000	9309856 / 9309856 / +0.0%
vortex-file-compressed size/wide table cols=10000 chunks=1 rows=1000	93117856 / 93117856 / +0.0%
vortex-file-compressed size/wide table cols=10000 chunks=50 rows=1000	93117856 / 93117856 / +0.0%

vortex / vortex-file-compressed / ratio (0.963x ➖, 4↑ 2↓)

name	ratio (PR / base / %diff)
vortex:parquet-zstd ratio compress time/Arade	0.404820372 / 0.434415258 / -6.8%
vortex:parquet-zstd ratio compress time/Bimbo	0.352929442 / 0.366149024 / -3.6%
vortex:parquet-zstd ratio compress time/CMSprovider	0.509237988 / 0.519872584 / -2.0%
vortex:parquet-zstd ratio compress time/Euro2016	0.322917085 / 0.333026493 / -3.0%
vortex:parquet-zstd ratio compress time/Food	0.47723482 / 0.466446316 / +2.3%
vortex:parquet-zstd ratio compress time/HashTags	0.37630135 / 0.379142051 / -0.7%
vortex:parquet-zstd ratio compress time/TPC-H l_comment canonical	0.303525078 / 0.318224028 / -4.6%
vortex:parquet-zstd ratio compress time/TPC-H l_comment chunked	0.308358304 / 0.334439825 / -7.8%
vortex:parquet-zstd ratio compress time/taxi	0.421178876 / 0.408331698 / +3.1%
vortex:parquet-zstd ratio compress time/wide table cols=100 chunks=1 rows=1000	1.54168416 / 1.66673323 / -7.5%
vortex:parquet-zstd ratio compress time/wide table cols=100 chunks=50 rows=1000	1.62739773 / 1.61061811 / +1.0%
vortex:parquet-zstd ratio compress time/wide table cols=1000 chunks=1 rows=1000	1.27635066 / 1.33328771 / -4.3%
vortex:parquet-zstd ratio compress time/wide table cols=1000 chunks=50 rows=1000	1.28889471 / 1.32063271 / -2.4%
vortex:parquet-zstd ratio compress time/wide table cols=10000 chunks=1 rows=1000	1.31327629 / 1.35825265 / -3.3%
vortex:parquet-zstd ratio compress time/wide table cols=10000 chunks=50 rows=1000	1.32388429 / 1.32583813 / -0.1%
vortex:parquet-zstd ratio decompress time/wide table cols=100 chunks=1 rows=1000	1.76759763 / 0.980065506 / +80.4% 🔴
vortex:parquet-zstd ratio decompress time/wide table cols=100 chunks=50 rows=1000	1.78182337 / 1.00672822 / +77.0% 🔴
vortex:parquet-zstd ratio decompress time/wide table cols=1000 chunks=1 rows=1000	0.629321522 / 0.845889938 / -25.6% 🟢
vortex:parquet-zstd ratio decompress time/wide table cols=1000 chunks=50 rows=1000	0.616894648 / 0.844214964 / -26.9% 🟢
vortex:parquet-zstd ratio decompress time/wide table cols=10000 chunks=1 rows=1000	0.480547854 / 1.14057551 / -57.9% 🟢
vortex:parquet-zstd ratio decompress time/wide table cols=10000 chunks=50 rows=1000	0.474383304 / 0.900801431 / -47.3% 🟢
vortex:parquet-zstd size/Arade	0.559894944 / 0.559894944 / -0.0%
vortex:parquet-zstd size/Bimbo	1.20109766 / 1.20109766 / -0.0%
vortex:parquet-zstd size/CMSprovider	1.10163356 / 1.10163356 / -0.0%
vortex:parquet-zstd size/Euro2016	1.2821288 / 1.2821234 / +0.0%
vortex:parquet-zstd size/Food	1.16476522 / 1.16476522 / -0.0%
vortex:parquet-zstd size/HashTags	1.33216065 / 1.33216065 / -0.0%
vortex:parquet-zstd size/TPC-H l_comment canonical	1.03217425 / 1.03217425 / +0.0%
vortex:parquet-zstd size/TPC-H l_comment chunked	1.03217425 / 1.03217425 / +0.0%
vortex:parquet-zstd size/taxi	0.93110889 / 0.93110889 / -0.0%
vortex:parquet-zstd size/wide table cols=100 chunks=1 rows=1000	1.00027027 / 1.00027027 / -0.0%
vortex:parquet-zstd size/wide table cols=100 chunks=50 rows=1000	1.00027027 / 1.00027027 / -0.0%
vortex:parquet-zstd size/wide table cols=1000 chunks=1 rows=1000	0.998482626 / 0.998482626 / -0.0%
vortex:parquet-zstd size/wide table cols=1000 chunks=50 rows=1000	0.998482626 / 0.998482626 / -0.0%
vortex:parquet-zstd size/wide table cols=10000 chunks=1 rows=1000	0.998689961 / 0.998689961 / +0.0%
vortex:parquet-zstd size/wide table cols=10000 chunks=50 rows=1000	0.998689961 / 0.998689961 / +0.0%

vortex / parquet / ns (1.003x ➖, 0↑ 0↓)

name	ns (PR / base / %diff)
parquet_rs-zstd compress time/Arade	2872675947 / 2874681857 / -0.1%
parquet_rs-zstd compress time/Bimbo	13942738790 / 14076398432 / -0.9%
parquet_rs-zstd compress time/CMSprovider	7729902605 / 7724425733 / +0.1%
parquet_rs-zstd compress time/Euro2016	1521205292 / 1534334380 / -0.9%
parquet_rs-zstd compress time/Food	902347275 / 918481477 / -1.8%
parquet_rs-zstd compress time/HashTags	2439623504 / 2435503196 / +0.2%
parquet_rs-zstd compress time/TPC-H l_comment canonical	3680909533 / 3709482335 / -0.8%
parquet_rs-zstd compress time/TPC-H l_comment chunked	3673716416 / 3705695994 / -0.9%
parquet_rs-zstd compress time/taxi	1340513712 / 1368131625 / -2.0%
parquet_rs-zstd compress time/wide table cols=100 chunks=1 rows=1000	5257165 / 5147894 / +2.1%
parquet_rs-zstd compress time/wide table cols=100 chunks=50 rows=1000	5114789 / 5141988 / -0.5%
parquet_rs-zstd compress time/wide table cols=1000 chunks=1 rows=1000	64552425 / 64009101 / +0.8%
parquet_rs-zstd compress time/wide table cols=1000 chunks=50 rows=1000	64841346 / 64278133 / +0.9%
parquet_rs-zstd compress time/wide table cols=10000 chunks=1 rows=1000	743898327 / 744091223 / -0.0%
parquet_rs-zstd compress time/wide table cols=10000 chunks=50 rows=1000	742020600 / 748729320 / -0.9%
parquet_rs-zstd decompress time/Arade	702563525 / 703679325 / -0.2%
parquet_rs-zstd decompress time/Bimbo	1900991840 / 1902122860 / -0.1%
parquet_rs-zstd decompress time/CMSprovider	1925483902 / 1917797059 / +0.4%
parquet_rs-zstd decompress time/Euro2016	416781639 / 416749217 / +0.0%
parquet_rs-zstd decompress time/Food	219804909 / 220043318 / -0.1%
parquet_rs-zstd decompress time/HashTags	672828541 / 677553721 / -0.7%
parquet_rs-zstd decompress time/TPC-H l_comment canonical	659095307 / 655777109 / +0.5%
parquet_rs-zstd decompress time/TPC-H l_comment chunked	658623563 / 654736182 / +0.6%
parquet_rs-zstd decompress time/taxi	279630496 / 276403994 / +1.2%
parquet_rs-zstd decompress time/wide table cols=100 chunks=1 rows=1000	2426094 / 2330784 / +4.1%
parquet_rs-zstd decompress time/wide table cols=100 chunks=50 rows=1000	2314863 / 2321269 / -0.3%
parquet_rs-zstd decompress time/wide table cols=1000 chunks=1 rows=1000	27643817 / 26847079 / +3.0%
parquet_rs-zstd decompress time/wide table cols=1000 chunks=50 rows=1000	28014730 / 27103367 / +3.4%
parquet_rs-zstd decompress time/wide table cols=10000 chunks=1 rows=1000	300193749 / 296188884 / +1.4%
parquet_rs-zstd decompress time/wide table cols=10000 chunks=50 rows=1000	303477702 / 298895724 / +1.5%

vortex / parquet / bytes (1.000x ➖, 0↑ 0↓)

name	bytes (PR / base / %diff)
parquet size/Arade	258014282 / 258014282 / +0.0%
parquet size/Bimbo	384517292 / 384517292 / +0.0%
parquet size/CMSprovider	376887911 / 376887911 / +0.0%
parquet size/Euro2016	122979049 / 122979049 / +0.0%
parquet size/Food	35699500 / 35699500 / +0.0%
parquet size/HashTags	133497590 / 133497590 / +0.0%
parquet size/TPC-H l_comment canonical	158358238 / 158358238 / +0.0%
parquet size/TPC-H l_comment chunked	158358238 / 158358238 / +0.0%
parquet size/taxi	55283635 / 55283635 / +0.0%
parquet size/wide table cols=100 chunks=1 rows=1000	932404 / 932404 / +0.0%
parquet size/wide table cols=100 chunks=50 rows=1000	932404 / 932404 / +0.0%
parquet size/wide table cols=1000 chunks=1 rows=1000	9324004 / 9324004 / +0.0%
parquet size/wide table cols=1000 chunks=50 rows=1000	9324004 / 9324004 / +0.0%
parquet size/wide table cols=10000 chunks=1 rows=1000	93240004 / 93240004 / +0.0%
parquet size/wide table cols=10000 chunks=50 rows=1000	93240004 / 93240004 / +0.0%

vortex / arrow-ipc / ns (1.026x ➖, 0↑ 2↓)

name	ns (PR / base / %diff)
arrow-ipc compress time/Arade	355919252 / 276483922 / +28.7% 🔴
arrow-ipc compress time/Bimbo	1820500853 / 1749685541 / +4.0%
arrow-ipc compress time/CMSprovider	1460620301 / 1428438748 / +2.3%
arrow-ipc compress time/Euro2016	97216547 / 98094465 / -0.9%
arrow-ipc compress time/Food	73390518 / 72674234 / +1.0%
arrow-ipc compress time/HashTags	294725617 / 284795292 / +3.5%
arrow-ipc compress time/TPC-H l_comment canonical	2101702641 / 2095242362 / +0.3%
arrow-ipc compress time/TPC-H l_comment chunked	2098868363 / 2096632902 / +0.1%
arrow-ipc compress time/taxi	162244000 / 160451707 / +1.1%
arrow-ipc compress time/wide table cols=100 chunks=1 rows=1000	417343 / 405484 / +2.9%
arrow-ipc compress time/wide table cols=100 chunks=50 rows=1000	406868 / 409563 / -0.7%
arrow-ipc compress time/wide table cols=1000 chunks=1 rows=1000	4931356 / 5034700 / -2.1%
arrow-ipc compress time/wide table cols=1000 chunks=50 rows=1000	5214496 / 5198438 / +0.3%
arrow-ipc compress time/wide table cols=10000 chunks=1 rows=1000	55079145 / 54061144 / +1.9%
arrow-ipc compress time/wide table cols=10000 chunks=50 rows=1000	55474100 / 54057043 / +2.6%
arrow-ipc decompress time/Arade	187362278 / 179235408 / +4.5%
arrow-ipc decompress time/Bimbo	596925885 / 589913833 / +1.2%
arrow-ipc decompress time/CMSprovider	713437741 / 683198883 / +4.4%
arrow-ipc decompress time/Euro2016	96262038 / 95977740 / +0.3%
arrow-ipc decompress time/Food	65712180 / 63497527 / +3.5%
arrow-ipc decompress time/HashTags	211375429 / 204369921 / +3.4%
arrow-ipc decompress time/TPC-H l_comment canonical	1032373628 / 1021906286 / +1.0%
arrow-ipc decompress time/TPC-H l_comment chunked	1017692469 / 1013089377 / +0.5%
arrow-ipc decompress time/taxi	72687778 / 73307091 / -0.8%
arrow-ipc decompress time/wide table cols=100 chunks=1 rows=1000	433453 / 386804 / +12.1% 🔴
arrow-ipc decompress time/wide table cols=100 chunks=50 rows=1000	422088 / 418248 / +0.9%
arrow-ipc decompress time/wide table cols=1000 chunks=1 rows=1000	4402641 / 4419977 / -0.4%
arrow-ipc decompress time/wide table cols=1000 chunks=50 rows=1000	4509071 / 4432790 / +1.7%
arrow-ipc decompress time/wide table cols=10000 chunks=1 rows=1000	53344903 / 52449996 / +1.7%
arrow-ipc decompress time/wide table cols=10000 chunks=50 rows=1000	53613457 / 52544240 / +2.0%

vortex / arrow-ipc / bytes (1.000x ➖, 0↑ 0↓)

name	bytes (PR / base / %diff)
arrow-ipc size/Arade	691765162 / 691765162 / +0.0%
arrow-ipc size/Bimbo	3279590114 / 3279590114 / +0.0%
arrow-ipc size/CMSprovider	2422259682 / 2422259682 / +0.0%
arrow-ipc size/Euro2016	360582666 / 360582666 / +0.0%
arrow-ipc size/Food	255782338 / 255782338 / +0.0%
arrow-ipc size/HashTags	704785810 / 704785810 / +0.0%
arrow-ipc size/TPC-H l_comment canonical	4852929378 / 4852929378 / +0.0%
arrow-ipc size/TPC-H l_comment chunked	4852929378 / 4852929378 / +0.0%
arrow-ipc size/taxi	482329690 / 482329690 / +0.0%
arrow-ipc size/wide table cols=100 chunks=1 rows=1000	1257290 / 1257290 / +0.0%
arrow-ipc size/wide table cols=100 chunks=50 rows=1000	1257290 / 1257290 / +0.0%
arrow-ipc size/wide table cols=1000 chunks=1 rows=1000	12568506 / 12568506 / +0.0%
arrow-ipc size/wide table cols=1000 chunks=50 rows=1000	12568506 / 12568506 / +0.0%
arrow-ipc size/wide table cols=10000 chunks=1 rows=1000	125752506 / 125752506 / +0.0%
arrow-ipc size/wide table cols=10000 chunks=50 rows=1000	125752506 / 125752506 / +0.0%

github-actions · 2026-08-28T09:33:18Z

Benchmarks: Random Access 📖

Commits: PR 5b3cb2e4 vs base 68e2aee0
Verdict: Likely regression (high confidence)
Attributed Vortex impact: +819.4%
Engines: random-access Likely regression (+819.4%, high confidence)
Vortex (geomean): hot 9.120x ❌
Parquet (geomean): hot 1.002x ➖
Shifts: Parquet (control) +0.2% · Median polish +189.5%

How to read Verdict and Engines

Verdict: Overall PR-level signal after subtracting baseline drift estimated from Parquet control rows. It can be Likely improvement, Likely regression, or No clear signal.
Engines: Per-engine attribution. DataFusion is compared against DataFusion/Parquet controls; DuckDB is compared against DuckDB/Parquet controls. This answers whether each engine improved or regressed independently.
Confidence: Based on directional consistency, share of rows above the noise floor, and control-run noise.
Hot vs cold: Every measurement is run several times. The first run is reported as the cold run, and the median of the runs after it is reported as the hot run. The verdict and significance use hot runs; each target's geomean reports hot and cold beside each other where the individual runs were recorded and hot alone where they were not, the cold column shows first-run cost per row, and hot/cold is how much of each run the warm path saves. Rows whose results predate per-run reporting show only one value, taken from the value the runner reported.
Table cells: Each cell reads PR / base / %diff. The hot and cold columns mark a change as 🔴 slower or 🟢 faster once it clears this suite's threshold; anything smaller is noise here and is left unmarked, as is hot/cold, because a shift in the warm-up ratio is not a win or a loss by itself.

vortex / arrow-ipc / ns (0.995x ➖, 0↑ 0↓)

name	ns (PR / base / %diff)
random-access/arrow-tokio-local-disk	69508 / 69752 / -0.3%
random-access/arrow-tokio-local-disk-footer	204006 / 202703 / +0.6%
random-access/feature-vectors/correlated/arrow-tokio-local-disk	2947113 / 2775146 / +6.2%
random-access/feature-vectors/correlated/arrow-tokio-local-disk-footer	3002536 / 3226960 / -7.0%
random-access/feature-vectors/uniform/arrow-tokio-local-disk	69647449 / 70336665 / -1.0%
random-access/feature-vectors/uniform/arrow-tokio-local-disk-footer	69732496 / 69510566 / +0.3%
random-access/nested-lists/correlated/arrow-tokio-local-disk	64099 / 68087 / -5.9%
random-access/nested-lists/correlated/arrow-tokio-local-disk-footer	119282 / 121488 / -1.8%
random-access/nested-lists/uniform/arrow-tokio-local-disk	1274097 / 1274431 / -0.0%
random-access/nested-lists/uniform/arrow-tokio-local-disk-footer	1295311 / 1363108 / -5.0%
random-access/nested-structs/correlated/arrow-tokio-local-disk	55077 / 54696 / +0.7%
random-access/nested-structs/correlated/arrow-tokio-local-disk-footer	103627 / 101345 / +2.3%
random-access/nested-structs/uniform/arrow-tokio-local-disk	1019298 / 972486 / +4.8%
random-access/nested-structs/uniform/arrow-tokio-local-disk-footer	1054375 / 1043526 / +1.0%
random-access/taxi/correlated/arrow-tokio-local-disk	120841 / 120546 / +0.2%
random-access/taxi/correlated/arrow-tokio-local-disk-footer	269986 / 271505 / -0.6%
random-access/taxi/uniform/arrow-tokio-local-disk	2674598 / 2743277 / -2.5%
random-access/taxi/uniform/arrow-tokio-local-disk-footer	2866751 / 2859705 / +0.2%

random-access / vortex-file-compressed / ns (9.120x ❌, 0↑ 8↓)

name	ns (PR / base / %diff)
random-access/feature-vectors/correlated/vortex-tokio-local-disk	22091352 / 340670 / +6384.7% 🔴
random-access/feature-vectors/correlated/vortex-tokio-local-disk-footer	26107155 / 1677617 / +1456.2% 🔴
random-access/feature-vectors/uniform/vortex-tokio-local-disk	24546555 / 2635062 / +831.5% 🔴
random-access/feature-vectors/uniform/vortex-tokio-local-disk-footer	28654281 / 4447345 / +544.3% 🔴
random-access/nested-lists/correlated/vortex-tokio-local-disk	3177595 / 288205 / +1002.5% 🔴
random-access/nested-lists/correlated/vortex-tokio-local-disk-footer	3467463 / 454487 / +662.9% 🔴
random-access/nested-lists/uniform/vortex-tokio-local-disk	5233358 / 1620671 / +222.9% 🔴
random-access/nested-lists/uniform/vortex-tokio-local-disk-footer	5596671 / 1923101 / +191.0% 🔴

random-access / parquet / ns (1.002x ➖, 0↑ 0↓)

name	ns (PR / base / %diff)
random-access/feature-vectors/correlated/parquet-tokio-local-disk	350671638018 / 353561221364 / -0.8%
random-access/feature-vectors/correlated/parquet-tokio-local-disk-footer	356943016782 / 355325563893 / +0.5%
random-access/feature-vectors/uniform/parquet-tokio-local-disk	355468325512 / 357201620770 / -0.5%
random-access/feature-vectors/uniform/parquet-tokio-local-disk-footer	352827977944 / 356335518442 / -1.0%
random-access/nested-lists/correlated/parquet-tokio-local-disk	239657171 / 239894885 / -0.1%
random-access/nested-lists/correlated/parquet-tokio-local-disk-footer	242853830 / 244679773 / -0.7%
random-access/nested-lists/uniform/parquet-tokio-local-disk	242941443 / 241854954 / +0.4%
random-access/nested-lists/uniform/parquet-tokio-local-disk-footer	235400900 / 245392376 / -4.1%
random-access/nested-structs/correlated/parquet-tokio-local-disk	19461817 / 19404470 / +0.3%
random-access/nested-structs/correlated/parquet-tokio-local-disk-footer	19888431 / 19214078 / +3.5%
random-access/nested-structs/uniform/parquet-tokio-local-disk	18898317 / 18976389 / -0.4%
random-access/nested-structs/uniform/parquet-tokio-local-disk-footer	19650349 / 19409988 / +1.2%
random-access/parquet-tokio-local-disk	179160840 / 175752061 / +1.9%
random-access/parquet-tokio-local-disk-footer	177707166 / 177589237 / +0.1%
random-access/taxi/correlated/parquet-tokio-local-disk	269523871 / 263563522 / +2.3%
random-access/taxi/correlated/parquet-tokio-local-disk-footer	265945651 / 266348816 / -0.2%
random-access/taxi/uniform/parquet-tokio-local-disk	279729472 / 279171864 / +0.2%
random-access/taxi/uniform/parquet-tokio-local-disk-footer	279042981 / 278040225 / +0.4%

random-access / lance / ns (0.992x ➖, 0↑ 0↓)

name	ns (PR / base / %diff)
random-access/feature-vectors/correlated/lance-tokio-local-disk	346511 / 363344 / -4.6%
random-access/feature-vectors/correlated/lance-tokio-local-disk-footer	1382223 / 1422290 / -2.8%
random-access/feature-vectors/uniform/lance-tokio-local-disk	1101879 / 1094760 / +0.7%
random-access/feature-vectors/uniform/lance-tokio-local-disk-footer	2115187 / 2168503 / -2.5%
random-access/lance-tokio-local-disk	632391 / 626336 / +1.0%
random-access/lance-tokio-local-disk-footer	1637591 / 1687100 / -2.9%
random-access/nested-lists/correlated/lance-tokio-local-disk	186373 / 184309 / +1.1%
random-access/nested-lists/correlated/lance-tokio-local-disk-footer	855419 / 833218 / +2.7%
random-access/nested-lists/uniform/lance-tokio-local-disk	906756 / 901039 / +0.6%
random-access/nested-lists/uniform/lance-tokio-local-disk-footer	1612703 / 1605282 / +0.5%
random-access/nested-structs/correlated/lance-tokio-local-disk	309596 / 318865 / -2.9%
random-access/nested-structs/correlated/lance-tokio-local-disk-footer	699357 / 708367 / -1.3%
random-access/nested-structs/uniform/lance-tokio-local-disk	2410654 / 2415984 / -0.2%
random-access/nested-structs/uniform/lance-tokio-local-disk-footer	2808878 / 2827141 / -0.6%
random-access/taxi/correlated/lance-tokio-local-disk	942128 / 948255 / -0.6%
random-access/taxi/correlated/lance-tokio-local-disk-footer	2197110 / 2207503 / -0.5%
random-access/taxi/uniform/lance-tokio-local-disk	9992308 / 10134555 / -1.4%
random-access/taxi/uniform/lance-tokio-local-disk-footer	10989884 / 11087742 / -0.9%

Signed-off-by: Joe Isaacs <joe.isaacs@live.co.uk>

joseph-isaacs added action/bench-compress Run only the compression benchmark on this PR action/bench-random-access Run only the random-access benchmark on this PR labels Aug 28, 2026 — with ChatGPT Codex Connector

joseph-isaacs removed action/bench-compress Run only the compression benchmark on this PR action/bench-random-access Run only the random-access benchmark on this PR labels Aug 28, 2026

joseph-isaacs added action/bench-compress Run only the compression benchmark on this PR action/bench-random-access Run only the random-access benchmark on this PR labels Aug 28, 2026 — with ChatGPT Codex Connector

joseph-isaacs force-pushed the claude/morsel-compress-random-access-ci branch from 0c19a5a to 78b2246 Compare August 28, 2026 08:09

joseph-isaacs removed action/bench-compress Run only the compression benchmark on this PR action/bench-random-access Run only the random-access benchmark on this PR labels Aug 28, 2026

joseph-isaacs added action/bench-compress Run only the compression benchmark on this PR action/bench-random-access Run only the random-access benchmark on this PR labels Aug 28, 2026 — with ChatGPT Codex Connector

github-actions Bot removed action/bench-compress Run only the compression benchmark on this PR action/bench-random-access Run only the random-access benchmark on this PR labels Aug 28, 2026

joseph-isaacs force-pushed the claude/morsel-compress-random-access-ci branch from 78b2246 to 5b3cb2e Compare August 28, 2026 08:16

joseph-isaacs added action/bench-compress Run only the compression benchmark on this PR action/bench-random-access Run only the random-access benchmark on this PR labels Aug 28, 2026 — with ChatGPT Codex Connector

github-actions Bot removed action/bench-compress Run only the compression benchmark on this PR action/bench-random-access Run only the random-access benchmark on this PR labels Aug 28, 2026

bench: drive SQL scans with morsel executor

5ceeb22

Signed-off-by: Joe Isaacs <joe.isaacs@live.co.uk>

joseph-isaacs changed the title ~~bench: run morsel reader in compression and random access~~ bench: run morsel reader in CI benchmarks Aug 28, 2026

joseph-isaacs added the changelog/skip Do not list PR in the changelog label Aug 28, 2026 — with ChatGPT Codex Connector

joseph-isaacs added 3 commits August 28, 2026 21:26

chore: fix prototype spelling checks

a1f479f

Signed-off-by: Joe Isaacs <joe.isaacs@live.co.uk>

perf: avoid redundant single-thread morsel pools

6131b16

Signed-off-by: Joe Isaacs <joe.isaacs@live.co.uk>

perf: share morsel scans across SQL batches

681bb3d

Signed-off-by: Joe Isaacs <joe.isaacs@live.co.uk>

Navigation Menu

Uh oh!

bench: run morsel reader in CI benchmarks - #9684

bench: run morsel reader in CI benchmarks#9684
joseph-isaacs wants to merge 5 commits into
developfrom
claude/morsel-compress-random-access-ci

joseph-isaacs commented Aug 28, 2026 •

edited

Loading

Uh oh!

codspeed-hq Bot commented Aug 28, 2026 •

edited

Loading

Uh oh!

github-actions Bot commented Aug 28, 2026 •

edited

Loading

Uh oh!

github-actions Bot commented Aug 28, 2026

Uh oh!

github-actions Bot commented Aug 28, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Uh oh!

Conversation

joseph-isaacs commented Aug 28, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

codspeed-hq Bot commented Aug 28, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Merging this PR will degrade performance by 3.77%

Performance Changes

Footnotes

Uh oh!

github-actions Bot commented Aug 28, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Polar Signals Profiling Results

Latest Run

Uh oh!

github-actions Bot commented Aug 28, 2026

Benchmarks: Compression 📖

Uh oh!

github-actions Bot commented Aug 28, 2026

Benchmarks: Random Access 📖

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

joseph-isaacs commented Aug 28, 2026 •

edited

Loading

codspeed-hq Bot commented Aug 28, 2026 •

edited

Loading

github-actions Bot commented Aug 28, 2026 •

edited

Loading