fix(benchmarks): correct TPC-H benchmark SQL

[kumarUjjawal]

Which issue does this PR close?

• Closes A few TPCH benchmark queries are incorrect causing issues when scale factor > 1 #21368.

Rationale for this change

TPC-H query 11 was using a fixed 0.0001 threshold in the HAVING clause. Per the TPC-H spec, this value must be 0.0001 / SF.

This means the benchmark query is only correct for scale factor 1. For larger scale factors the filter becomes too
strict, and for smaller scale factors it becomes too loose.

There are also few benchmark queries using fixed end dates where the spec uses date + interval. Those are equivalent but using intervals matches the TPC-H query definitions more closely.

What changes are included in this PR?

• Make TPC-H query 11 use scale-factor substitution.
• Add scale factor support in the benchmark runner.
• Infer scale factor from dataset paths like tpch_sf10.
• Pass the scale factor from bench.sh.
• Keep the old query-loading entry point working with the
  default scale factor of 1.
• Update query 5, 6, 10, 12, and 14 to use interval-based
  date ranges.
• Add regression tests for scale-factor substitution,
  scale-factor parsing, and invalid scale factors.

Are these changes tested?

Yes

Are there any user-facing changes?

TPC-H benchmark query 11 now returns correct results when the scale factor is not 1.

[kumarUjjawal]

cc @Omega359

[Omega359]

Thank you, this looks reasonable to me.

[comphead]

run benchmark tpch

[adriangbot]

🤖 Benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4248112740-1267-dmb6r 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 fix/incorrect_tpch_queries (b232880) to 6db3899 (merge-base) diff using: tpch
Results will be posted here when complete

---

File an issue against this benchmark runner

[Dandandan]

run benchmark tpch10

[adriangbot]

🤖 Benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4249605829-1273-pz4d7 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 fix/incorrect_tpch_queries (b232880) to 6db3899 (merge-base) diff using: tpch10
Results will be posted here when complete

---

File an issue against this benchmark runner

[adriangbot]

🤖 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 fix_incorrect_tpch_queries
--------------------
Benchmark tpch_sf10.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query     ┃                                HEAD ┃         fix_incorrect_tpch_queries ┃        Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 1  │   371.68 / 377.77 ±7.18 / 391.56 ms │  386.96 / 389.77 ±2.31 / 392.92 ms │     no change │
│ QQuery 2  │   138.84 / 140.85 ±2.04 / 144.26 ms │  142.84 / 147.40 ±3.10 / 151.45 ms │     no change │
│ QQuery 3  │   301.42 / 306.17 ±3.86 / 310.39 ms │  303.36 / 316.46 ±7.93 / 327.15 ms │     no change │
│ QQuery 4  │   157.86 / 160.52 ±1.47 / 162.08 ms │  157.04 / 161.06 ±3.80 / 168.18 ms │     no change │
│ QQuery 5  │   437.03 / 441.92 ±4.41 / 449.41 ms │  442.33 / 450.78 ±5.49 / 458.95 ms │     no change │
│ QQuery 6  │   134.35 / 137.83 ±3.20 / 142.91 ms │  133.88 / 135.13 ±1.04 / 136.64 ms │     no change │
│ QQuery 7  │   565.14 / 580.64 ±8.76 / 589.92 ms │  568.20 / 574.77 ±5.98 / 585.58 ms │     no change │
│ QQuery 8  │   485.00 / 490.17 ±4.99 / 496.32 ms │  482.46 / 491.75 ±5.36 / 498.87 ms │     no change │
│ QQuery 9  │  685.40 / 700.85 ±11.48 / 716.52 ms │  754.49 / 756.25 ±1.25 / 757.75 ms │  1.08x slower │
│ QQuery 10 │   359.08 / 373.95 ±9.11 / 384.92 ms │  361.48 / 371.09 ±6.40 / 378.12 ms │     no change │
│ QQuery 11 │   113.63 / 118.22 ±4.45 / 124.86 ms │  111.12 / 116.93 ±5.13 / 124.03 ms │     no change │
│ QQuery 12 │   216.24 / 218.52 ±2.77 / 223.83 ms │  205.37 / 208.31 ±2.91 / 212.23 ms │     no change │
│ QQuery 13 │  327.29 / 344.05 ±13.16 / 362.68 ms │  317.54 / 325.72 ±6.51 / 334.84 ms │ +1.06x faster │
│ QQuery 14 │   186.03 / 187.78 ±1.67 / 190.55 ms │  185.09 / 187.42 ±1.68 / 189.13 ms │     no change │
│ QQuery 15 │   338.21 / 341.11 ±1.83 / 343.50 ms │  335.95 / 340.66 ±3.45 / 346.48 ms │     no change │
│ QQuery 16 │      86.70 / 88.61 ±1.04 / 89.61 ms │     84.72 / 87.02 ±1.55 / 88.88 ms │     no change │
│ QQuery 17 │  772.10 / 795.05 ±38.52 / 871.59 ms │  777.90 / 781.61 ±3.86 / 788.53 ms │     no change │
│ QQuery 18 │ 921.63 / 980.73 ±29.96 / 1001.64 ms │ 856.32 / 880.41 ±14.57 / 900.50 ms │ +1.11x faster │
│ QQuery 19 │   283.44 / 288.08 ±3.69 / 292.62 ms │  276.40 / 287.65 ±6.56 / 294.24 ms │     no change │
│ QQuery 20 │   329.71 / 335.29 ±4.51 / 339.96 ms │  349.71 / 357.44 ±9.31 / 375.19 ms │  1.07x slower │
│ QQuery 21 │   862.94 / 871.83 ±6.96 / 883.46 ms │ 870.66 / 914.81 ±37.40 / 969.33 ms │     no change │
│ QQuery 22 │      85.37 / 87.62 ±1.81 / 90.50 ms │     81.75 / 83.29 ±1.03 / 84.96 ms │     no change │
└───────────┴─────────────────────────────────────┴────────────────────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━┓
┃ Benchmark Summary                         ┃           ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━┩
│ Total Time (HEAD)                         │ 8367.55ms │
│ Total Time (fix_incorrect_tpch_queries)   │ 8365.70ms │
│ Average Time (HEAD)                       │  380.34ms │
│ Average Time (fix_incorrect_tpch_queries) │  380.26ms │
│ Queries Faster                            │         2 │
│ Queries Slower                            │         2 │
│ Queries with No Change                    │        18 │
│ Queries with Failure                      │         0 │
└───────────────────────────────────────────┴───────────┘

Resource Usage

tpch10 — base (merge-base)

Metric	Value
Wall time	42.3s
Peak memory	10.1 GiB
Avg memory	7.7 GiB
CPU user	441.2s
CPU sys	30.8s
Peak spill	0 B

tpch10 — branch

Metric	Value
Wall time	42.2s
Peak memory	10.2 GiB
Avg memory	7.8 GiB
CPU user	440.4s
CPU sys	30.9s
Peak spill	0 B

---

File an issue against this benchmark runner

[comphead]

Thanks @kumarUjjawal it makes sense, thanks for bringing intervals back