Skip to content

perf: do not build parquet pruning predicates if no page index - #21556

Closed
alamb wants to merge 3 commits into
apache:mainfrom
alamb:alamb/less_page_predicates
Closed

perf: do not build parquet pruning predicates if no page index#21556
alamb wants to merge 3 commits into
apache:mainfrom
alamb:alamb/less_page_predicates

Conversation

@alamb

@alambalamb commented Apr 11, 2026

Copy link
Copy Markdown
Contributor

Which issue does this PR close?

Rationale for this change

@Dandandan suggested #21480 (comment)

Maybe better is to delay it so they are only created after we loaded the page index, this avoids doing it as well for files without page index (and avoids it in short-circuit scenarios / query cancellation).

Which is a good idea to further optimize low latency queries

This also applies to the clickbench_partitioned dataset which has no page indexes

What changes are included in this PR?

  1. Delay page pruning until after we have loaded the page index (if it exists)
  2. Tests

Are these changes tested?

Yes

Are there any user-facing changes?

Faster performance (though I am not sure we will be able to measure it)

@alamb
alamb marked this pull request as draft April 11, 2026 14:20
@alamb

alamb commented Apr 11, 2026

Copy link
Copy Markdown
ContributorAuthor

run benchmark clickbench_partitioned

@github-actionsgithub-actionsBot added the datasource Changes to the datasource crate label Apr 11, 2026
@adriangbot

adriangbot commented Apr 11, 2026

Copy link
Copy Markdown

🤖 Benchmark running (GKE) | trigger
Instance:c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4229575297-1086-h28h4 6.12.55+ #1 SMP Sun Feb 1 08:59:41 UTC 2026 aarch64 GNU/Linux

CPU Details (lscpu)
Architecture: aarch64
CPU op-mode(s): 64-bit
Byte Order: Little Endian
CPU(s): 16
On-line CPU(s) list: 0-15
Vendor ID: ARM
Model name: Neoverse-V2
Model: 1
Thread(s) per core: 1
Core(s) per cluster: 16
Socket(s): -
Cluster(s): 1
Stepping: r0p1
BogoMIPS: 2000.00
Flags: fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache: 1 MiB (16 instances)
L1i cache: 1 MiB (16 instances)
L2 cache: 32 MiB (16 instances)
L3 cache: 80 MiB (1 instance)
NUMA node(s): 1
NUMA node0 CPU(s): 0-15
Vulnerability Gather data sampling: Not affected
Vulnerability Indirect target selection: Not affected
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Mmio stale data: Not affected
Vulnerability Reg file data sampling: Not affected
Vulnerability Retbleed: Not affected
Vulnerability Spec rstack overflow: Not affected
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1: Mitigation; __user pointer sanitization
Vulnerability Spectre v2: Mitigation; CSV2, BHB
Vulnerability Srbds: Not affected
Vulnerability Tsa: Not affected
Vulnerability Tsx async abort: Not affected
Vulnerability Vmscape: Not affected

Comparing alamb/less_page_predicates (3017761) to ec00112 (merge-base) diff using: clickbench_partitioned
Results will be posted here when complete

File an issue against this benchmark runner

@alambalamb mentioned this pull request Apr 11, 2026
Merged
@adriangbot

adriangbot commented Apr 11, 2026

Copy link
Copy Markdown

🤖 Benchmark completed (GKE) | trigger

Instance:c4a-highmem-16 (12 vCPU / 65 GiB)

CPU Details (lscpu)
Architecture: aarch64
CPU op-mode(s): 64-bit
Byte Order: Little Endian
CPU(s): 16
On-line CPU(s) list: 0-15
Vendor ID: ARM
Model name: Neoverse-V2
Model: 1
Thread(s) per core: 1
Core(s) per cluster: 16
Socket(s): -
Cluster(s): 1
Stepping: r0p1
BogoMIPS: 2000.00
Flags: fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache: 1 MiB (16 instances)
L1i cache: 1 MiB (16 instances)
L2 cache: 32 MiB (16 instances)
L3 cache: 80 MiB (1 instance)
NUMA node(s): 1
NUMA node0 CPU(s): 0-15
Vulnerability Gather data sampling: Not affected
Vulnerability Indirect target selection: Not affected
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Mmio stale data: Not affected
Vulnerability Reg file data sampling: Not affected
Vulnerability Retbleed: Not affected
Vulnerability Spec rstack overflow: Not affected
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1: Mitigation; __user pointer sanitization
Vulnerability Spectre v2: Mitigation; CSV2, BHB
Vulnerability Srbds: Not affected
Vulnerability Tsa: Not affected
Vulnerability Tsx async abort: Not affected
Vulnerability Vmscape: Not affected
Details

Comparing HEAD and alamb_less_page_predicates
--------------------
Benchmark clickbench_partitioned.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query ┃ HEAD ┃ alamb_less_page_predicates ┃ Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 0 │ 1.25 / 4.60 ±6.52 / 17.63 ms │ 1.18 / 4.43 ±6.33 / 17.09 ms │ no change │
│ QQuery 1 │ 14.32 / 15.05 ±0.47 / 15.76 ms │ 14.12 / 14.56 ±0.24 / 14.77 ms │ no change │
│ QQuery 2 │ 44.21 / 44.50 ±0.21 / 44.86 ms │ 45.21 / 45.54 ±0.17 / 45.70 ms │ no change │
│ QQuery 3 │ 43.73 / 45.67 ±1.68 / 47.73 ms │ 43.50 / 46.01 ±1.36 / 47.36 ms │ no change │
│ QQuery 4 │ 292.05 / 299.73 ±5.26 / 305.44 ms │ 284.91 / 292.12 ±7.01 / 303.08 ms │ no change │
│ QQuery 5 │ 348.14 / 352.74 ±3.02 / 356.55 ms │ 341.28 / 348.77 ±4.09 / 352.45 ms │ no change │
│ QQuery 6 │ 5.56 / 6.12 ±0.50 / 7.05 ms │ 5.78 / 10.78 ±8.09 / 26.87 ms │ 1.76x slower │
│ QQuery 7 │ 16.79 / 17.44 ±0.67 / 18.52 ms │ 17.02 / 17.50 ±0.40 / 17.98 ms │ no change │
│ QQuery 8 │ 421.25 / 429.65 ±9.86 / 447.26 ms │ 428.16 / 434.06 ±5.34 / 443.14 ms │ no change │
│ QQuery 9 │ 662.89 / 669.75 ±4.59 / 675.21 ms │ 641.00 / 657.84 ±11.20 / 674.00 ms │ no change │
│ QQuery 10 │ 91.49 / 96.57 ±5.25 / 105.81 ms │ 91.87 / 96.37 ±3.16 / 101.32 ms │ no change │
│ QQuery 11 │ 105.85 / 106.67 ±0.82 / 108.10 ms │ 104.90 / 106.76 ±1.84 / 109.75 ms │ no change │
│ QQuery 12 │ 342.63 / 349.79 ±6.53 / 358.46 ms │ 341.97 / 348.53 ±7.80 / 362.73 ms │ no change │
│ QQuery 13 │ 451.69 / 474.10 ±12.96 / 485.95 ms │ 459.17 / 477.70 ±11.85 / 492.73 ms │ no change │
│ QQuery 14 │ 351.10 / 355.43 ±4.70 / 361.55 ms │ 347.93 / 355.20 ±6.21 / 364.35 ms │ no change │
│ QQuery 15 │ 353.72 / 366.95 ±10.64 / 385.93 ms │ 363.47 / 381.51 ±15.48 / 408.28 ms │ no change │
│ QQuery 16 │ 709.78 / 724.42 ±12.20 / 744.41 ms │ 721.42 / 735.03 ±17.11 / 766.03 ms │ no change │
│ QQuery 17 │ 711.02 / 717.64 ±8.60 / 733.53 ms │ 725.16 / 728.35 ±1.65 / 729.61 ms │ no change │
│ QQuery 18 │ 1474.75 / 1497.12 ±29.35 / 1554.29 ms │ 1414.00 / 1485.70 ±39.36 / 1533.49 ms │ no change │
│ QQuery 19 │ 37.19 / 47.46 ±18.83 / 85.05 ms │ 36.12 / 39.16 ±3.47 / 45.73 ms │ +1.21x faster │
│ QQuery 20 │ 724.08 / 742.56 ±20.53 / 776.24 ms │ 721.32 / 732.85 ±14.04 / 759.82 ms │ no change │
│ QQuery 21 │ 770.95 / 774.33 ±1.89 / 776.53 ms │ 763.03 / 769.12 ±6.09 / 779.01 ms │ no change │
│ QQuery 22 │ 1142.42 / 1149.80 ±5.53 / 1155.07 ms │ 1128.28 / 1134.82 ±3.52 / 1138.84 ms │ no change │
│ QQuery 23 │ 3108.86 / 3130.03 ±13.90 / 3146.42 ms │ 3078.63 / 3118.68 ±27.77 / 3164.65 ms │ no change │
│ QQuery 24 │ 100.21 / 102.94 ±2.00 / 106.40 ms │ 104.33 / 107.11 ±1.94 / 110.22 ms │ no change │
│ QQuery 25 │ 137.71 / 140.06 ±1.54 / 142.04 ms │ 140.20 / 142.17 ±1.81 / 144.96 ms │ no change │
│ QQuery 26 │ 99.11 / 102.66 ±2.35 / 106.41 ms │ 100.43 / 104.37 ±3.36 / 108.56 ms │ no change │
│ QQuery 27 │ 856.41 / 864.91 ±4.34 / 868.41 ms │ 860.41 / 865.82 ±5.02 / 873.22 ms │ no change │
│ QQuery 28 │ 3279.26 / 3307.43 ±16.57 / 3327.93 ms │ 3290.46 / 3326.77 ±24.14 / 3362.59 ms │ no change │
│ QQuery 29 │ 51.01 / 55.57 ±5.13 / 65.51 ms │ 51.41 / 54.92 ±4.64 / 64.02 ms │ no change │
│ QQuery 30 │ 362.91 / 372.89 ±6.11 / 381.68 ms │ 360.33 / 369.52 ±10.69 / 389.54 ms │ no change │
│ QQuery 31 │ 366.72 / 384.86 ±17.44 / 417.69 ms │ 378.64 / 385.87 ±6.17 / 396.71 ms │ no change │
│ QQuery 32 │ 1235.86 / 1263.32 ±18.32 / 1280.21 ms │ 1203.98 / 1260.26 ±42.80 / 1334.63 ms │ no change │
│ QQuery 33 │ 1553.43 / 1604.98 ±46.55 / 1685.03 ms │ 1598.19 / 1628.63 ±25.07 / 1666.55 ms │ no change │
│ QQuery 34 │ 1490.33 / 1531.89 ±50.69 / 1629.39 ms │ 1504.88 / 1575.29 ±78.69 / 1722.54 ms │ no change │
│ QQuery 35 │ 380.52 / 383.58 ±3.21 / 388.25 ms │ 394.46 / 398.79 ±4.90 / 407.61 ms │ no change │
│ QQuery 36 │ 117.12 / 119.93 ±1.82 / 121.86 ms │ 116.76 / 125.24 ±6.68 / 137.02 ms │ no change │
│ QQuery 37 │ 48.81 / 50.34 ±1.43 / 52.69 ms │ 48.28 / 49.52 ±0.93 / 50.47 ms │ no change │
│ QQuery 38 │ 75.70 / 77.81 ±1.31 / 79.67 ms │ 75.15 / 76.18 ±0.87 / 77.19 ms │ no change │
│ QQuery 39 │ 202.82 / 215.68 ±8.99 / 229.83 ms │ 208.24 / 216.43 ±8.90 / 231.23 ms │ no change │
│ QQuery 40 │ 24.33 / 26.09 ±1.88 / 29.49 ms │ 23.26 / 24.31 ±0.73 / 25.52 ms │ +1.07x faster │
│ QQuery 41 │ 19.48 / 20.70 ±1.05 / 22.34 ms │ 20.69 / 21.33 ±0.66 / 22.56 ms │ no change │
│ QQuery 42 │ 19.09 / 19.84 ±0.43 / 20.42 ms │ 19.52 / 19.98 ±0.41 / 20.65 ms │ no change │
└───────────┴───────────────────────────────────────┴───────────────────────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Benchmark Summary ┃ ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Total Time (HEAD) │ 23063.60ms │
│ Total Time (alamb_less_page_predicates) │ 23133.90ms │
│ Average Time (HEAD) │ 536.36ms │
│ Average Time (alamb_less_page_predicates) │ 538.00ms │
│ Queries Faster │ 2 │
│ Queries Slower │ 1 │
│ Queries with No Change │ 40 │
│ Queries with Failure │ 0 │
└───────────────────────────────────────────┴────────────┘

Resource Usage

clickbench_partitioned — base (merge-base)

MetricValue
Wall time116.5s
Peak memory37.3 GiB
Avg memory28.3 GiB
CPU user1078.0s
CPU sys105.4s
Peak spill0 B

clickbench_partitioned — branch

MetricValue
Wall time116.8s
Peak memory38.5 GiB
Avg memory28.8 GiB
CPU user1080.9s
CPU sys106.0s
Peak spill0 B

File an issue against this benchmark runner

@alambalamb mentioned this pull request Apr 11, 2026
Closed
@alamb

alamb commented Apr 11, 2026

Copy link
Copy Markdown
ContributorAuthor

run benchmark clickbench_partitioned

@adriangbot

adriangbot commented Apr 11, 2026

Copy link
Copy Markdown

🤖 Benchmark running (GKE) | trigger
Instance:c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4229653435-1087-ghckj 6.12.55+ #1 SMP Sun Feb 1 08:59:41 UTC 2026 aarch64 GNU/Linux

CPU Details (lscpu)
Architecture: aarch64
CPU op-mode(s): 64-bit
Byte Order: Little Endian
CPU(s): 16
On-line CPU(s) list: 0-15
Vendor ID: ARM
Model name: Neoverse-V2
Model: 1
Thread(s) per core: 1
Core(s) per cluster: 16
Socket(s): -
Cluster(s): 1
Stepping: r0p1
BogoMIPS: 2000.00
Flags: fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache: 1 MiB (16 instances)
L1i cache: 1 MiB (16 instances)
L2 cache: 32 MiB (16 instances)
L3 cache: 80 MiB (1 instance)
NUMA node(s): 1
NUMA node0 CPU(s): 0-15
Vulnerability Gather data sampling: Not affected
Vulnerability Indirect target selection: Not affected
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Mmio stale data: Not affected
Vulnerability Reg file data sampling: Not affected
Vulnerability Retbleed: Not affected
Vulnerability Spec rstack overflow: Not affected
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1: Mitigation; __user pointer sanitization
Vulnerability Spectre v2: Mitigation; CSV2, BHB
Vulnerability Srbds: Not affected
Vulnerability Tsa: Not affected
Vulnerability Tsx async abort: Not affected
Vulnerability Vmscape: Not affected

Comparing alamb/less_page_predicates (56c95dc) to ec00112 (merge-base) diff using: clickbench_partitioned
Results will be posted here when complete

File an issue against this benchmark runner

@adriangbot

adriangbot commented Apr 11, 2026

Copy link
Copy Markdown

🤖 Benchmark completed (GKE) | trigger

Instance:c4a-highmem-16 (12 vCPU / 65 GiB)

CPU Details (lscpu)
Architecture: aarch64
CPU op-mode(s): 64-bit
Byte Order: Little Endian
CPU(s): 16
On-line CPU(s) list: 0-15
Vendor ID: ARM
Model name: Neoverse-V2
Model: 1
Thread(s) per core: 1
Core(s) per cluster: 16
Socket(s): -
Cluster(s): 1
Stepping: r0p1
BogoMIPS: 2000.00
Flags: fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache: 1 MiB (16 instances)
L1i cache: 1 MiB (16 instances)
L2 cache: 32 MiB (16 instances)
L3 cache: 80 MiB (1 instance)
NUMA node(s): 1
NUMA node0 CPU(s): 0-15
Vulnerability Gather data sampling: Not affected
Vulnerability Indirect target selection: Not affected
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Mmio stale data: Not affected
Vulnerability Reg file data sampling: Not affected
Vulnerability Retbleed: Not affected
Vulnerability Spec rstack overflow: Not affected
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1: Mitigation; __user pointer sanitization
Vulnerability Spectre v2: Mitigation; CSV2, BHB
Vulnerability Srbds: Not affected
Vulnerability Tsa: Not affected
Vulnerability Tsx async abort: Not affected
Vulnerability Vmscape: Not affected
Details

Comparing HEAD and alamb_less_page_predicates
--------------------
Benchmark clickbench_partitioned.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query ┃ HEAD ┃ alamb_less_page_predicates ┃ Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 0 │ 1.19 / 4.48 ±6.42 / 17.31 ms │ 1.19 / 4.43 ±6.36 / 17.15 ms │ no change │
│ QQuery 1 │ 13.97 / 14.70 ±0.41 / 15.22 ms │ 13.52 / 14.09 ±0.30 / 14.33 ms │ no change │
│ QQuery 2 │ 43.57 / 43.75 ±0.13 / 43.95 ms │ 43.98 / 44.38 ±0.47 / 45.29 ms │ no change │
│ QQuery 3 │ 42.36 / 44.75 ±2.51 / 49.11 ms │ 42.21 / 44.86 ±2.66 / 48.64 ms │ no change │
│ QQuery 4 │ 289.83 / 303.99 ±9.11 / 314.49 ms │ 291.67 / 298.23 ±5.39 / 305.09 ms │ no change │
│ QQuery 5 │ 345.55 / 352.16 ±5.12 / 360.90 ms │ 341.48 / 346.18 ±3.14 / 350.89 ms │ no change │
│ QQuery 6 │ 6.07 / 8.54 ±3.82 / 16.08 ms │ 5.80 / 6.44 ±0.59 / 7.34 ms │ +1.33x faster │
│ QQuery 7 │ 16.74 / 17.63 ±1.24 / 20.08 ms │ 15.98 / 16.08 ±0.08 / 16.16 ms │ +1.10x faster │
│ QQuery 8 │ 421.43 / 433.73 ±17.34 / 467.48 ms │ 419.06 / 428.97 ±5.34 / 433.97 ms │ no change │
│ QQuery 9 │ 641.81 / 653.14 ±11.56 / 675.39 ms │ 657.26 / 667.13 ±7.51 / 674.24 ms │ no change │
│ QQuery 10 │ 92.86 / 96.18 ±3.89 / 103.76 ms │ 91.96 / 93.49 ±2.30 / 98.08 ms │ no change │
│ QQuery 11 │ 104.73 / 106.81 ±1.85 / 110.16 ms │ 104.61 / 105.52 ±0.95 / 106.99 ms │ no change │
│ QQuery 12 │ 351.26 / 355.16 ±2.33 / 358.29 ms │ 337.97 / 341.77 ±3.85 / 348.98 ms │ no change │
│ QQuery 13 │ 467.35 / 479.96 ±9.48 / 493.52 ms │ 451.51 / 467.84 ±12.46 / 481.69 ms │ no change │
│ QQuery 14 │ 354.03 / 358.39 ±4.82 / 367.69 ms │ 346.42 / 351.09 ±3.92 / 357.30 ms │ no change │
│ QQuery 15 │ 365.34 / 398.66 ±25.73 / 433.55 ms │ 366.56 / 393.38 ±19.52 / 419.83 ms │ no change │
│ QQuery 16 │ 735.26 / 749.41 ±13.29 / 773.98 ms │ 716.07 / 773.78 ±36.67 / 825.30 ms │ no change │
│ QQuery 17 │ 712.01 / 716.03 ±3.56 / 722.52 ms │ 710.54 / 722.02 ±13.26 / 747.40 ms │ no change │
│ QQuery 18 │ 1468.84 / 1487.92 ±13.29 / 1508.49 ms │ 1440.16 / 1488.51 ±35.21 / 1540.10 ms │ no change │
│ QQuery 19 │ 36.24 / 48.97 ±24.82 / 98.62 ms │ 36.33 / 50.71 ±27.11 / 104.90 ms │ no change │
│ QQuery 20 │ 722.45 / 740.77 ±18.95 / 766.42 ms │ 724.24 / 737.76 ±13.57 / 756.66 ms │ no change │
│ QQuery 21 │ 765.29 / 774.36 ±8.55 / 790.00 ms │ 765.23 / 770.14 ±3.92 / 774.51 ms │ no change │
│ QQuery 22 │ 1137.09 / 1143.36 ±4.54 / 1148.42 ms │ 1133.41 / 1139.77 ±4.82 / 1147.76 ms │ no change │
│ QQuery 23 │ 3066.52 / 3102.92 ±21.60 / 3133.68 ms │ 3094.01 / 3102.31 ±6.68 / 3113.55 ms │ no change │
│ QQuery 24 │ 99.13 / 101.77 ±2.23 / 105.32 ms │ 98.82 / 102.96 ±2.10 / 104.57 ms │ no change │
│ QQuery 25 │ 139.35 / 142.09 ±2.78 / 145.69 ms │ 139.45 / 140.65 ±0.99 / 142.06 ms │ no change │
│ QQuery 26 │ 98.44 / 102.12 ±2.04 / 104.30 ms │ 99.64 / 101.75 ±1.72 / 104.50 ms │ no change │
│ QQuery 27 │ 856.66 / 864.50 ±5.43 / 871.79 ms │ 848.47 / 852.98 ±2.84 / 856.22 ms │ no change │
│ QQuery 28 │ 3274.83 / 3302.95 ±14.91 / 3318.89 ms │ 3291.38 / 3319.87 ±15.39 / 3334.36 ms │ no change │
│ QQuery 29 │ 50.31 / 56.61 ±6.69 / 68.57 ms │ 50.55 / 54.29 ±5.11 / 64.35 ms │ no change │
│ QQuery 30 │ 365.69 / 369.51 ±2.16 / 372.34 ms │ 359.72 / 365.37 ±4.19 / 369.10 ms │ no change │
│ QQuery 31 │ 368.37 / 382.93 ±9.70 / 398.25 ms │ 371.52 / 382.23 ±8.97 / 394.42 ms │ no change │
│ QQuery 32 │ 1032.24 / 1077.90 ±44.72 / 1156.29 ms │ 1233.88 / 1266.15 ±44.21 / 1350.67 ms │ 1.17x slower │
│ QQuery 33 │ 1476.27 / 1484.23 ±5.43 / 1492.50 ms │ 1487.57 / 1572.43 ±46.92 / 1625.87 ms │ 1.06x slower │
│ QQuery 34 │ 1488.73 / 1498.92 ±9.96 / 1513.01 ms │ 1503.16 / 1556.34 ±38.40 / 1604.54 ms │ no change │
│ QQuery 35 │ 385.97 / 395.99 ±8.44 / 408.78 ms │ 383.68 / 394.56 ±6.43 / 402.66 ms │ no change │
│ QQuery 36 │ 113.67 / 120.71 ±3.65 / 124.21 ms │ 113.37 / 121.29 ±4.15 / 124.47 ms │ no change │
│ QQuery 37 │ 47.86 / 50.08 ±1.24 / 51.62 ms │ 48.97 / 50.61 ±1.69 / 53.58 ms │ no change │
│ QQuery 38 │ 75.90 / 78.21 ±1.29 / 79.63 ms │ 77.10 / 79.06 ±1.65 / 82.01 ms │ no change │
│ QQuery 39 │ 208.35 / 220.66 ±9.09 / 231.54 ms │ 210.09 / 215.02 ±3.50 / 218.84 ms │ no change │
│ QQuery 40 │ 23.18 / 24.84 ±2.01 / 28.75 ms │ 23.96 / 25.19 ±1.20 / 27.02 ms │ no change │
│ QQuery 41 │ 19.35 / 21.40 ±1.46 / 23.76 ms │ 20.14 / 22.34 ±1.73 / 24.83 ms │ no change │
│ QQuery 42 │ 19.96 / 20.41 ±0.36 / 21.01 ms │ 19.67 / 20.17 ±0.36 / 20.59 ms │ no change │
└───────────┴───────────────────────────────────────┴───────────────────────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Benchmark Summary ┃ ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Total Time (HEAD) │ 22751.58ms │
│ Total Time (alamb_less_page_predicates) │ 23052.17ms │
│ Average Time (HEAD) │ 529.11ms │
│ Average Time (alamb_less_page_predicates) │ 536.10ms │
│ Queries Faster │ 2 │
│ Queries Slower │ 2 │
│ Queries with No Change │ 39 │
│ Queries with Failure │ 0 │
└───────────────────────────────────────────┴────────────┘

Resource Usage

clickbench_partitioned — base (merge-base)

MetricValue
Wall time114.9s
Peak memory40.8 GiB
Avg memory28.6 GiB
CPU user1080.2s
CPU sys88.4s
Peak spill0 B

clickbench_partitioned — branch

MetricValue
Wall time116.4s
Peak memory38.0 GiB
Avg memory27.8 GiB
CPU user1081.0s
CPU sys99.9s
Peak spill0 B

File an issue against this benchmark runner

@github-actions

github-actionsBot commented Jun 11, 2026

Copy link
Copy Markdown

Thank you for your contribution. Unfortunately, this pull request is stale because it has been open 60 days with no activity. Please remove the stale label or comment or this will be closed in 7 days.

@github-actionsgithub-actionsBot added the Stale PR has not had any activity for some time label Jun 11, 2026
Sign up for freeto join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

datasourceChanges to the datasource crateStalePR has not had any activity for some time

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@alamb@adriangbot